lemonhat commited on
Commit
d36c542
·
verified ·
1 Parent(s): fb725ad

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: t1_5k_v1_tag5
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # t1_5k_v1_tag5
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the t1_5k_v1_tag5 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.3876
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 8
46
+ - total_train_batch_size: 8
47
+ - total_eval_batch_size: 8
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.344 | 0.4082 | 100 | 0.4118 |
57
+ | 0.315 | 0.8163 | 200 | 0.3878 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.6.0+cu124
64
+ - Datasets 3.1.0
65
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.38757580518722534,
4
+ "eval_runtime": 0.4512,
5
+ "eval_samples_per_second": 4.433,
6
+ "eval_steps_per_second": 2.216,
7
+ "total_flos": 24710676480000.0,
8
+ "train_loss": 0.39906880940709794,
9
+ "train_runtime": 467.2882,
10
+ "train_samples_per_second": 4.182,
11
+ "train_steps_per_second": 0.524
12
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.46.1",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.38757580518722534,
4
+ "eval_runtime": 0.4512,
5
+ "eval_samples_per_second": 4.433,
6
+ "eval_steps_per_second": 2.216
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.1"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3ae7bfdcd70312535d0c556fbbdf73c531c4ae08fe8b83f7dad99acafe7561
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3c4eccdbe7166a04e0fe20fd7332b5a3c55c59618448bd9cb440b7bff9a8c3
3
+ size 1459729952
model.safetensors.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6425499648
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.norm.weight": "model-00002-of-00002.safetensors"
260
+ }
261
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 24710676480000.0,
4
+ "train_loss": 0.39906880940709794,
5
+ "train_runtime": 467.2882,
6
+ "train_samples_per_second": 4.182,
7
+ "train_steps_per_second": 0.524
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 245, "loss": 1.0703, "lr": 4.9997944716957985e-06, "epoch": 0.004081632653061225, "percentage": 0.41, "elapsed_time": "0:00:03", "remaining_time": "0:12:17"}
2
+ {"current_steps": 2, "total_steps": 245, "loss": 0.9497, "lr": 4.9991779205767e-06, "epoch": 0.00816326530612245, "percentage": 0.82, "elapsed_time": "0:00:07", "remaining_time": "0:15:10"}
3
+ {"current_steps": 3, "total_steps": 245, "loss": 0.9212, "lr": 4.99815044801767e-06, "epoch": 0.012244897959183673, "percentage": 1.22, "elapsed_time": "0:00:09", "remaining_time": "0:12:31"}
4
+ {"current_steps": 4, "total_steps": 245, "loss": 0.831, "lr": 4.9967122229584614e-06, "epoch": 0.0163265306122449, "percentage": 1.63, "elapsed_time": "0:00:11", "remaining_time": "0:11:08"}
5
+ {"current_steps": 5, "total_steps": 245, "loss": 0.7045, "lr": 4.994863481875842e-06, "epoch": 0.02040816326530612, "percentage": 2.04, "elapsed_time": "0:00:12", "remaining_time": "0:10:20"}
6
+ {"current_steps": 6, "total_steps": 245, "loss": 0.7605, "lr": 4.992604528744705e-06, "epoch": 0.024489795918367346, "percentage": 2.45, "elapsed_time": "0:00:14", "remaining_time": "0:09:46"}
7
+ {"current_steps": 7, "total_steps": 245, "loss": 0.6814, "lr": 4.989935734988098e-06, "epoch": 0.02857142857142857, "percentage": 2.86, "elapsed_time": "0:00:16", "remaining_time": "0:09:25"}
8
+ {"current_steps": 8, "total_steps": 245, "loss": 0.685, "lr": 4.986857539416144e-06, "epoch": 0.0326530612244898, "percentage": 3.27, "elapsed_time": "0:00:18", "remaining_time": "0:09:06"}
9
+ {"current_steps": 9, "total_steps": 245, "loss": 0.644, "lr": 4.983370448153896e-06, "epoch": 0.036734693877551024, "percentage": 3.67, "elapsed_time": "0:00:20", "remaining_time": "0:08:50"}
10
+ {"current_steps": 10, "total_steps": 245, "loss": 0.5987, "lr": 4.979475034558115e-06, "epoch": 0.04081632653061224, "percentage": 4.08, "elapsed_time": "0:00:22", "remaining_time": "0:08:38"}
11
+ {"current_steps": 11, "total_steps": 245, "loss": 0.5733, "lr": 4.9751719391230055e-06, "epoch": 0.044897959183673466, "percentage": 4.49, "elapsed_time": "0:00:23", "remaining_time": "0:08:27"}
12
+ {"current_steps": 12, "total_steps": 245, "loss": 0.5448, "lr": 4.97046186937489e-06, "epoch": 0.04897959183673469, "percentage": 4.9, "elapsed_time": "0:00:25", "remaining_time": "0:08:18"}
13
+ {"current_steps": 13, "total_steps": 245, "loss": 0.5215, "lr": 4.965345599755888e-06, "epoch": 0.053061224489795916, "percentage": 5.31, "elapsed_time": "0:00:27", "remaining_time": "0:08:11"}
14
+ {"current_steps": 14, "total_steps": 245, "loss": 0.5634, "lr": 4.959823971496575e-06, "epoch": 0.05714285714285714, "percentage": 5.71, "elapsed_time": "0:00:29", "remaining_time": "0:08:04"}
15
+ {"current_steps": 15, "total_steps": 245, "loss": 0.5725, "lr": 4.953897892477664e-06, "epoch": 0.061224489795918366, "percentage": 6.12, "elapsed_time": "0:00:31", "remaining_time": "0:07:58"}
16
+ {"current_steps": 16, "total_steps": 245, "loss": 0.5581, "lr": 4.947568337080733e-06, "epoch": 0.0653061224489796, "percentage": 6.53, "elapsed_time": "0:00:33", "remaining_time": "0:07:53"}
17
+ {"current_steps": 17, "total_steps": 245, "loss": 0.5833, "lr": 4.940836346028011e-06, "epoch": 0.06938775510204082, "percentage": 6.94, "elapsed_time": "0:00:34", "remaining_time": "0:07:47"}
18
+ {"current_steps": 18, "total_steps": 245, "loss": 0.4874, "lr": 4.933703026211262e-06, "epoch": 0.07346938775510205, "percentage": 7.35, "elapsed_time": "0:00:36", "remaining_time": "0:07:43"}
19
+ {"current_steps": 19, "total_steps": 245, "loss": 0.5475, "lr": 4.926169550509787e-06, "epoch": 0.07755102040816327, "percentage": 7.76, "elapsed_time": "0:00:38", "remaining_time": "0:07:38"}
20
+ {"current_steps": 20, "total_steps": 245, "loss": 0.4306, "lr": 4.918237157597574e-06, "epoch": 0.08163265306122448, "percentage": 8.16, "elapsed_time": "0:00:40", "remaining_time": "0:07:35"}
21
+ {"current_steps": 21, "total_steps": 245, "loss": 0.5024, "lr": 4.909907151739634e-06, "epoch": 0.08571428571428572, "percentage": 8.57, "elapsed_time": "0:00:42", "remaining_time": "0:07:31"}
22
+ {"current_steps": 22, "total_steps": 245, "loss": 0.4308, "lr": 4.901180902577549e-06, "epoch": 0.08979591836734693, "percentage": 8.98, "elapsed_time": "0:00:44", "remaining_time": "0:07:26"}
23
+ {"current_steps": 23, "total_steps": 245, "loss": 0.4731, "lr": 4.892059844904273e-06, "epoch": 0.09387755102040816, "percentage": 9.39, "elapsed_time": "0:00:45", "remaining_time": "0:07:22"}
24
+ {"current_steps": 24, "total_steps": 245, "loss": 0.4177, "lr": 4.882545478428219e-06, "epoch": 0.09795918367346938, "percentage": 9.8, "elapsed_time": "0:00:47", "remaining_time": "0:07:18"}
25
+ {"current_steps": 25, "total_steps": 245, "loss": 0.4993, "lr": 4.872639367526672e-06, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:00:49", "remaining_time": "0:07:16"}
26
+ {"current_steps": 26, "total_steps": 245, "loss": 0.3984, "lr": 4.862343140988573e-06, "epoch": 0.10612244897959183, "percentage": 10.61, "elapsed_time": "0:00:51", "remaining_time": "0:07:12"}
27
+ {"current_steps": 27, "total_steps": 245, "loss": 0.4885, "lr": 4.851658491746707e-06, "epoch": 0.11020408163265306, "percentage": 11.02, "elapsed_time": "0:00:53", "remaining_time": "0:07:09"}
28
+ {"current_steps": 28, "total_steps": 245, "loss": 0.4676, "lr": 4.8405871765993435e-06, "epoch": 0.11428571428571428, "percentage": 11.43, "elapsed_time": "0:00:54", "remaining_time": "0:07:06"}
29
+ {"current_steps": 29, "total_steps": 245, "loss": 0.4346, "lr": 4.829131015921386e-06, "epoch": 0.11836734693877551, "percentage": 11.84, "elapsed_time": "0:00:56", "remaining_time": "0:07:03"}
30
+ {"current_steps": 30, "total_steps": 245, "loss": 0.3914, "lr": 4.817291893365055e-06, "epoch": 0.12244897959183673, "percentage": 12.24, "elapsed_time": "0:00:58", "remaining_time": "0:07:00"}
31
+ {"current_steps": 31, "total_steps": 245, "loss": 0.4998, "lr": 4.805071755550177e-06, "epoch": 0.12653061224489795, "percentage": 12.65, "elapsed_time": "0:01:00", "remaining_time": "0:06:57"}
32
+ {"current_steps": 32, "total_steps": 245, "loss": 0.4586, "lr": 4.7924726117441135e-06, "epoch": 0.1306122448979592, "percentage": 13.06, "elapsed_time": "0:01:02", "remaining_time": "0:06:54"}
33
+ {"current_steps": 33, "total_steps": 245, "loss": 0.4406, "lr": 4.779496533531393e-06, "epoch": 0.1346938775510204, "percentage": 13.47, "elapsed_time": "0:01:04", "remaining_time": "0:06:51"}
34
+ {"current_steps": 34, "total_steps": 245, "loss": 0.4112, "lr": 4.766145654473096e-06, "epoch": 0.13877551020408163, "percentage": 13.88, "elapsed_time": "0:01:05", "remaining_time": "0:06:48"}
35
+ {"current_steps": 35, "total_steps": 245, "loss": 0.3947, "lr": 4.752422169756048e-06, "epoch": 0.14285714285714285, "percentage": 14.29, "elapsed_time": "0:01:07", "remaining_time": "0:06:46"}
36
+ {"current_steps": 36, "total_steps": 245, "loss": 0.4523, "lr": 4.738328335831883e-06, "epoch": 0.1469387755102041, "percentage": 14.69, "elapsed_time": "0:01:09", "remaining_time": "0:06:44"}
37
+ {"current_steps": 37, "total_steps": 245, "loss": 0.3953, "lr": 4.72386647004603e-06, "epoch": 0.1510204081632653, "percentage": 15.1, "elapsed_time": "0:01:11", "remaining_time": "0:06:41"}
38
+ {"current_steps": 38, "total_steps": 245, "loss": 0.4683, "lr": 4.7090389502566884e-06, "epoch": 0.15510204081632653, "percentage": 15.51, "elapsed_time": "0:01:13", "remaining_time": "0:06:38"}
39
+ {"current_steps": 39, "total_steps": 245, "loss": 0.4271, "lr": 4.693848214443858e-06, "epoch": 0.15918367346938775, "percentage": 15.92, "elapsed_time": "0:01:15", "remaining_time": "0:06:36"}
40
+ {"current_steps": 40, "total_steps": 245, "loss": 0.4562, "lr": 4.678296760308474e-06, "epoch": 0.16326530612244897, "percentage": 16.33, "elapsed_time": "0:01:16", "remaining_time": "0:06:34"}
41
+ {"current_steps": 41, "total_steps": 245, "loss": 0.4527, "lr": 4.6623871448617345e-06, "epoch": 0.1673469387755102, "percentage": 16.73, "elapsed_time": "0:01:18", "remaining_time": "0:06:31"}
42
+ {"current_steps": 42, "total_steps": 245, "loss": 0.4218, "lr": 4.646121984004666e-06, "epoch": 0.17142857142857143, "percentage": 17.14, "elapsed_time": "0:01:20", "remaining_time": "0:06:29"}
43
+ {"current_steps": 43, "total_steps": 245, "loss": 0.3863, "lr": 4.629503952098011e-06, "epoch": 0.17551020408163265, "percentage": 17.55, "elapsed_time": "0:01:22", "remaining_time": "0:06:26"}
44
+ {"current_steps": 44, "total_steps": 245, "loss": 0.4849, "lr": 4.612535781522504e-06, "epoch": 0.17959183673469387, "percentage": 17.96, "elapsed_time": "0:01:24", "remaining_time": "0:06:24"}
45
+ {"current_steps": 45, "total_steps": 245, "loss": 0.4309, "lr": 4.5952202622296015e-06, "epoch": 0.1836734693877551, "percentage": 18.37, "elapsed_time": "0:01:25", "remaining_time": "0:06:21"}
46
+ {"current_steps": 46, "total_steps": 245, "loss": 0.3827, "lr": 4.57756024128276e-06, "epoch": 0.18775510204081633, "percentage": 18.78, "elapsed_time": "0:01:27", "remaining_time": "0:06:19"}
47
+ {"current_steps": 47, "total_steps": 245, "loss": 0.4364, "lr": 4.559558622389304e-06, "epoch": 0.19183673469387755, "percentage": 19.18, "elapsed_time": "0:01:29", "remaining_time": "0:06:17"}
48
+ {"current_steps": 48, "total_steps": 245, "loss": 0.4761, "lr": 4.541218365422997e-06, "epoch": 0.19591836734693877, "percentage": 19.59, "elapsed_time": "0:01:31", "remaining_time": "0:06:15"}
49
+ {"current_steps": 49, "total_steps": 245, "loss": 0.3942, "lr": 4.522542485937369e-06, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:33", "remaining_time": "0:06:13"}
50
+ {"current_steps": 50, "total_steps": 245, "loss": 0.4418, "lr": 4.5035340546698915e-06, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:01:35", "remaining_time": "0:06:11"}
51
+ {"current_steps": 51, "total_steps": 245, "loss": 0.3799, "lr": 4.484196197037082e-06, "epoch": 0.20816326530612245, "percentage": 20.82, "elapsed_time": "0:01:37", "remaining_time": "0:06:09"}
52
+ {"current_steps": 52, "total_steps": 245, "loss": 0.3691, "lr": 4.464532092620607e-06, "epoch": 0.21224489795918366, "percentage": 21.22, "elapsed_time": "0:01:38", "remaining_time": "0:06:07"}
53
+ {"current_steps": 53, "total_steps": 245, "loss": 0.4283, "lr": 4.444544974644493e-06, "epoch": 0.2163265306122449, "percentage": 21.63, "elapsed_time": "0:01:40", "remaining_time": "0:06:04"}
54
+ {"current_steps": 54, "total_steps": 245, "loss": 0.4729, "lr": 4.424238129443515e-06, "epoch": 0.22040816326530613, "percentage": 22.04, "elapsed_time": "0:01:42", "remaining_time": "0:06:03"}
55
+ {"current_steps": 55, "total_steps": 245, "loss": 0.4193, "lr": 4.4036148959228365e-06, "epoch": 0.22448979591836735, "percentage": 22.45, "elapsed_time": "0:01:44", "remaining_time": "0:06:00"}
56
+ {"current_steps": 56, "total_steps": 245, "loss": 0.3448, "lr": 4.382678665009028e-06, "epoch": 0.22857142857142856, "percentage": 22.86, "elapsed_time": "0:01:46", "remaining_time": "0:05:58"}
57
+ {"current_steps": 57, "total_steps": 245, "loss": 0.3713, "lr": 4.361432879092518e-06, "epoch": 0.23265306122448978, "percentage": 23.27, "elapsed_time": "0:01:48", "remaining_time": "0:05:56"}
58
+ {"current_steps": 58, "total_steps": 245, "loss": 0.4023, "lr": 4.339881031461588e-06, "epoch": 0.23673469387755103, "percentage": 23.67, "elapsed_time": "0:01:50", "remaining_time": "0:05:54"}
59
+ {"current_steps": 59, "total_steps": 245, "loss": 0.4063, "lr": 4.318026665727993e-06, "epoch": 0.24081632653061225, "percentage": 24.08, "elapsed_time": "0:01:51", "remaining_time": "0:05:52"}
60
+ {"current_steps": 60, "total_steps": 245, "loss": 0.4078, "lr": 4.295873375244319e-06, "epoch": 0.24489795918367346, "percentage": 24.49, "elapsed_time": "0:01:53", "remaining_time": "0:05:50"}
61
+ {"current_steps": 61, "total_steps": 245, "loss": 0.4126, "lr": 4.273424802513145e-06, "epoch": 0.24897959183673468, "percentage": 24.9, "elapsed_time": "0:01:55", "remaining_time": "0:05:48"}
62
+ {"current_steps": 62, "total_steps": 245, "loss": 0.4224, "lr": 4.2506846385881375e-06, "epoch": 0.2530612244897959, "percentage": 25.31, "elapsed_time": "0:01:57", "remaining_time": "0:05:46"}
63
+ {"current_steps": 63, "total_steps": 245, "loss": 0.4787, "lr": 4.227656622467162e-06, "epoch": 0.2571428571428571, "percentage": 25.71, "elapsed_time": "0:01:59", "remaining_time": "0:05:44"}
64
+ {"current_steps": 64, "total_steps": 245, "loss": 0.3748, "lr": 4.204344540477499e-06, "epoch": 0.2612244897959184, "percentage": 26.12, "elapsed_time": "0:02:01", "remaining_time": "0:05:42"}
65
+ {"current_steps": 65, "total_steps": 245, "loss": 0.446, "lr": 4.1807522256532925e-06, "epoch": 0.2653061224489796, "percentage": 26.53, "elapsed_time": "0:02:02", "remaining_time": "0:05:40"}
66
+ {"current_steps": 66, "total_steps": 245, "loss": 0.3762, "lr": 4.156883557105308e-06, "epoch": 0.2693877551020408, "percentage": 26.94, "elapsed_time": "0:02:04", "remaining_time": "0:05:38"}
67
+ {"current_steps": 67, "total_steps": 245, "loss": 0.4028, "lr": 4.132742459383122e-06, "epoch": 0.27346938775510204, "percentage": 27.35, "elapsed_time": "0:02:06", "remaining_time": "0:05:36"}
68
+ {"current_steps": 68, "total_steps": 245, "loss": 0.4166, "lr": 4.1083329018298356e-06, "epoch": 0.27755102040816326, "percentage": 27.76, "elapsed_time": "0:02:08", "remaining_time": "0:05:34"}
69
+ {"current_steps": 69, "total_steps": 245, "loss": 0.404, "lr": 4.083658897929425e-06, "epoch": 0.2816326530612245, "percentage": 28.16, "elapsed_time": "0:02:10", "remaining_time": "0:05:32"}
70
+ {"current_steps": 70, "total_steps": 245, "loss": 0.4047, "lr": 4.058724504646834e-06, "epoch": 0.2857142857142857, "percentage": 28.57, "elapsed_time": "0:02:12", "remaining_time": "0:05:30"}
71
+ {"current_steps": 71, "total_steps": 245, "loss": 0.3509, "lr": 4.033533821760917e-06, "epoch": 0.2897959183673469, "percentage": 28.98, "elapsed_time": "0:02:14", "remaining_time": "0:05:28"}
72
+ {"current_steps": 72, "total_steps": 245, "loss": 0.3597, "lr": 4.008090991190341e-06, "epoch": 0.2938775510204082, "percentage": 29.39, "elapsed_time": "0:02:15", "remaining_time": "0:05:26"}
73
+ {"current_steps": 73, "total_steps": 245, "loss": 0.4371, "lr": 3.982400196312565e-06, "epoch": 0.2979591836734694, "percentage": 29.8, "elapsed_time": "0:02:17", "remaining_time": "0:05:24"}
74
+ {"current_steps": 74, "total_steps": 245, "loss": 0.39, "lr": 3.9564656612759904e-06, "epoch": 0.3020408163265306, "percentage": 30.2, "elapsed_time": "0:02:19", "remaining_time": "0:05:22"}
75
+ {"current_steps": 75, "total_steps": 245, "loss": 0.4004, "lr": 3.930291650305424e-06, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:02:21", "remaining_time": "0:05:20"}
76
+ {"current_steps": 76, "total_steps": 245, "loss": 0.3959, "lr": 3.903882467000938e-06, "epoch": 0.31020408163265306, "percentage": 31.02, "elapsed_time": "0:02:23", "remaining_time": "0:05:18"}
77
+ {"current_steps": 77, "total_steps": 245, "loss": 0.3981, "lr": 3.8772424536302565e-06, "epoch": 0.3142857142857143, "percentage": 31.43, "elapsed_time": "0:02:25", "remaining_time": "0:05:16"}
78
+ {"current_steps": 78, "total_steps": 245, "loss": 0.3972, "lr": 3.8503759904148005e-06, "epoch": 0.3183673469387755, "percentage": 31.84, "elapsed_time": "0:02:27", "remaining_time": "0:05:14"}
79
+ {"current_steps": 79, "total_steps": 245, "loss": 0.3377, "lr": 3.823287494809469e-06, "epoch": 0.3224489795918367, "percentage": 32.24, "elapsed_time": "0:02:28", "remaining_time": "0:05:12"}
80
+ {"current_steps": 80, "total_steps": 245, "loss": 0.4188, "lr": 3.7959814207763134e-06, "epoch": 0.32653061224489793, "percentage": 32.65, "elapsed_time": "0:02:30", "remaining_time": "0:05:11"}
81
+ {"current_steps": 81, "total_steps": 245, "loss": 0.3721, "lr": 3.7684622580522057e-06, "epoch": 0.3306122448979592, "percentage": 33.06, "elapsed_time": "0:02:32", "remaining_time": "0:05:09"}
82
+ {"current_steps": 82, "total_steps": 245, "loss": 0.4187, "lr": 3.740734531410626e-06, "epoch": 0.3346938775510204, "percentage": 33.47, "elapsed_time": "0:02:34", "remaining_time": "0:05:07"}
83
+ {"current_steps": 83, "total_steps": 245, "loss": 0.3896, "lr": 3.71280279991768e-06, "epoch": 0.33877551020408164, "percentage": 33.88, "elapsed_time": "0:02:36", "remaining_time": "0:05:05"}
84
+ {"current_steps": 84, "total_steps": 245, "loss": 0.3715, "lr": 3.684671656182497e-06, "epoch": 0.34285714285714286, "percentage": 34.29, "elapsed_time": "0:02:38", "remaining_time": "0:05:03"}
85
+ {"current_steps": 85, "total_steps": 245, "loss": 0.3963, "lr": 3.656345725602089e-06, "epoch": 0.3469387755102041, "percentage": 34.69, "elapsed_time": "0:02:40", "remaining_time": "0:05:01"}
86
+ {"current_steps": 86, "total_steps": 245, "loss": 0.3551, "lr": 3.6278296656008366e-06, "epoch": 0.3510204081632653, "percentage": 35.1, "elapsed_time": "0:02:41", "remaining_time": "0:04:59"}
87
+ {"current_steps": 87, "total_steps": 245, "loss": 0.3788, "lr": 3.599128164864706e-06, "epoch": 0.3551020408163265, "percentage": 35.51, "elapsed_time": "0:02:43", "remaining_time": "0:04:57"}
88
+ {"current_steps": 88, "total_steps": 245, "loss": 0.4037, "lr": 3.5702459425703146e-06, "epoch": 0.35918367346938773, "percentage": 35.92, "elapsed_time": "0:02:45", "remaining_time": "0:04:55"}
89
+ {"current_steps": 89, "total_steps": 245, "loss": 0.4119, "lr": 3.541187747608998e-06, "epoch": 0.363265306122449, "percentage": 36.33, "elapsed_time": "0:02:47", "remaining_time": "0:04:53"}
90
+ {"current_steps": 90, "total_steps": 245, "loss": 0.3638, "lr": 3.5119583578059845e-06, "epoch": 0.3673469387755102, "percentage": 36.73, "elapsed_time": "0:02:49", "remaining_time": "0:04:51"}
91
+ {"current_steps": 91, "total_steps": 245, "loss": 0.3841, "lr": 3.4825625791348093e-06, "epoch": 0.37142857142857144, "percentage": 37.14, "elapsed_time": "0:02:51", "remaining_time": "0:04:49"}
92
+ {"current_steps": 92, "total_steps": 245, "loss": 0.4185, "lr": 3.4530052449271044e-06, "epoch": 0.37551020408163266, "percentage": 37.55, "elapsed_time": "0:02:52", "remaining_time": "0:04:47"}
93
+ {"current_steps": 93, "total_steps": 245, "loss": 0.3622, "lr": 3.4232912150778914e-06, "epoch": 0.3795918367346939, "percentage": 37.96, "elapsed_time": "0:02:54", "remaining_time": "0:04:45"}
94
+ {"current_steps": 94, "total_steps": 245, "loss": 0.4191, "lr": 3.393425375246503e-06, "epoch": 0.3836734693877551, "percentage": 38.37, "elapsed_time": "0:02:56", "remaining_time": "0:04:43"}
95
+ {"current_steps": 95, "total_steps": 245, "loss": 0.3611, "lr": 3.3634126360532694e-06, "epoch": 0.3877551020408163, "percentage": 38.78, "elapsed_time": "0:02:58", "remaining_time": "0:04:41"}
96
+ {"current_steps": 96, "total_steps": 245, "loss": 0.3779, "lr": 3.333257932272105e-06, "epoch": 0.39183673469387753, "percentage": 39.18, "elapsed_time": "0:03:00", "remaining_time": "0:04:39"}
97
+ {"current_steps": 97, "total_steps": 245, "loss": 0.3692, "lr": 3.3029662220191146e-06, "epoch": 0.39591836734693875, "percentage": 39.59, "elapsed_time": "0:03:02", "remaining_time": "0:04:37"}
98
+ {"current_steps": 98, "total_steps": 245, "loss": 0.4198, "lr": 3.272542485937369e-06, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:03:04", "remaining_time": "0:04:36"}
99
+ {"current_steps": 99, "total_steps": 245, "loss": 0.3304, "lr": 3.2419917263779765e-06, "epoch": 0.40408163265306124, "percentage": 40.41, "elapsed_time": "0:03:05", "remaining_time": "0:04:34"}
100
+ {"current_steps": 100, "total_steps": 245, "loss": 0.344, "lr": 3.2113189665775812e-06, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:03:07", "remaining_time": "0:04:32"}
101
+ {"current_steps": 100, "total_steps": 245, "eval_loss": 0.41177019476890564, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:03:08", "remaining_time": "0:04:32"}
102
+ {"current_steps": 101, "total_steps": 245, "loss": 0.3527, "lr": 3.180529249832428e-06, "epoch": 0.4122448979591837, "percentage": 41.22, "elapsed_time": "0:03:09", "remaining_time": "0:04:30"}
103
+ {"current_steps": 102, "total_steps": 245, "loss": 0.345, "lr": 3.1496276386691327e-06, "epoch": 0.4163265306122449, "percentage": 41.63, "elapsed_time": "0:03:11", "remaining_time": "0:04:28"}
104
+ {"current_steps": 103, "total_steps": 245, "loss": 0.3598, "lr": 3.1186192140122863e-06, "epoch": 0.4204081632653061, "percentage": 42.04, "elapsed_time": "0:03:13", "remaining_time": "0:04:26"}
105
+ {"current_steps": 104, "total_steps": 245, "loss": 0.3834, "lr": 3.0875090743490383e-06, "epoch": 0.42448979591836733, "percentage": 42.45, "elapsed_time": "0:03:15", "remaining_time": "0:04:24"}
106
+ {"current_steps": 105, "total_steps": 245, "loss": 0.3542, "lr": 3.056302334890786e-06, "epoch": 0.42857142857142855, "percentage": 42.86, "elapsed_time": "0:03:17", "remaining_time": "0:04:22"}
107
+ {"current_steps": 106, "total_steps": 245, "loss": 0.3905, "lr": 3.0250041267321234e-06, "epoch": 0.4326530612244898, "percentage": 43.27, "elapsed_time": "0:03:19", "remaining_time": "0:04:21"}
108
+ {"current_steps": 107, "total_steps": 245, "loss": 0.3681, "lr": 2.993619596007168e-06, "epoch": 0.43673469387755104, "percentage": 43.67, "elapsed_time": "0:03:20", "remaining_time": "0:04:19"}
109
+ {"current_steps": 108, "total_steps": 245, "loss": 0.3817, "lr": 2.9621539030434223e-06, "epoch": 0.44081632653061226, "percentage": 44.08, "elapsed_time": "0:03:22", "remaining_time": "0:04:17"}
110
+ {"current_steps": 109, "total_steps": 245, "loss": 0.4041, "lr": 2.9306122215132974e-06, "epoch": 0.4448979591836735, "percentage": 44.49, "elapsed_time": "0:03:24", "remaining_time": "0:04:15"}
111
+ {"current_steps": 110, "total_steps": 245, "loss": 0.3409, "lr": 2.8989997375834485e-06, "epoch": 0.4489795918367347, "percentage": 44.9, "elapsed_time": "0:03:26", "remaining_time": "0:04:13"}
112
+ {"current_steps": 111, "total_steps": 245, "loss": 0.3872, "lr": 2.8673216490620453e-06, "epoch": 0.4530612244897959, "percentage": 45.31, "elapsed_time": "0:03:28", "remaining_time": "0:04:11"}
113
+ {"current_steps": 112, "total_steps": 245, "loss": 0.3729, "lr": 2.835583164544139e-06, "epoch": 0.45714285714285713, "percentage": 45.71, "elapsed_time": "0:03:30", "remaining_time": "0:04:09"}
114
+ {"current_steps": 113, "total_steps": 245, "loss": 0.3785, "lr": 2.8037895025552513e-06, "epoch": 0.46122448979591835, "percentage": 46.12, "elapsed_time": "0:03:31", "remaining_time": "0:04:07"}
115
+ {"current_steps": 114, "total_steps": 245, "loss": 0.4038, "lr": 2.7719458906933277e-06, "epoch": 0.46530612244897956, "percentage": 46.53, "elapsed_time": "0:03:33", "remaining_time": "0:04:05"}
116
+ {"current_steps": 115, "total_steps": 245, "loss": 0.3886, "lr": 2.7400575647692046e-06, "epoch": 0.46938775510204084, "percentage": 46.94, "elapsed_time": "0:03:35", "remaining_time": "0:04:03"}
117
+ {"current_steps": 116, "total_steps": 245, "loss": 0.3655, "lr": 2.7081297679457238e-06, "epoch": 0.47346938775510206, "percentage": 47.35, "elapsed_time": "0:03:37", "remaining_time": "0:04:01"}
118
+ {"current_steps": 117, "total_steps": 245, "loss": 0.3158, "lr": 2.676167749875635e-06, "epoch": 0.4775510204081633, "percentage": 47.76, "elapsed_time": "0:03:39", "remaining_time": "0:03:59"}
119
+ {"current_steps": 118, "total_steps": 245, "loss": 0.3759, "lr": 2.6441767658384363e-06, "epoch": 0.4816326530612245, "percentage": 48.16, "elapsed_time": "0:03:41", "remaining_time": "0:03:57"}
120
+ {"current_steps": 119, "total_steps": 245, "loss": 0.3441, "lr": 2.6121620758762877e-06, "epoch": 0.4857142857142857, "percentage": 48.57, "elapsed_time": "0:03:42", "remaining_time": "0:03:56"}
121
+ {"current_steps": 120, "total_steps": 245, "loss": 0.3535, "lr": 2.580128943929139e-06, "epoch": 0.4897959183673469, "percentage": 48.98, "elapsed_time": "0:03:44", "remaining_time": "0:03:54"}
122
+ {"current_steps": 121, "total_steps": 245, "loss": 0.4291, "lr": 2.5480826369692178e-06, "epoch": 0.49387755102040815, "percentage": 49.39, "elapsed_time": "0:03:46", "remaining_time": "0:03:52"}
123
+ {"current_steps": 122, "total_steps": 245, "loss": 0.3604, "lr": 2.516028424135028e-06, "epoch": 0.49795918367346936, "percentage": 49.8, "elapsed_time": "0:03:48", "remaining_time": "0:03:50"}
124
+ {"current_steps": 123, "total_steps": 245, "loss": 0.4383, "lr": 2.4839715758649724e-06, "epoch": 0.5020408163265306, "percentage": 50.2, "elapsed_time": "0:03:50", "remaining_time": "0:03:48"}
125
+ {"current_steps": 124, "total_steps": 245, "loss": 0.3736, "lr": 2.4519173630307826e-06, "epoch": 0.5061224489795918, "percentage": 50.61, "elapsed_time": "0:03:52", "remaining_time": "0:03:46"}
126
+ {"current_steps": 125, "total_steps": 245, "loss": 0.3888, "lr": 2.4198710560708623e-06, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:03:54", "remaining_time": "0:03:44"}
127
+ {"current_steps": 126, "total_steps": 245, "loss": 0.4691, "lr": 2.3878379241237136e-06, "epoch": 0.5142857142857142, "percentage": 51.43, "elapsed_time": "0:03:55", "remaining_time": "0:03:42"}
128
+ {"current_steps": 127, "total_steps": 245, "loss": 0.3468, "lr": 2.3558232341615645e-06, "epoch": 0.5183673469387755, "percentage": 51.84, "elapsed_time": "0:03:57", "remaining_time": "0:03:40"}
129
+ {"current_steps": 128, "total_steps": 245, "loss": 0.363, "lr": 2.323832250124365e-06, "epoch": 0.5224489795918368, "percentage": 52.24, "elapsed_time": "0:03:59", "remaining_time": "0:03:39"}
130
+ {"current_steps": 129, "total_steps": 245, "loss": 0.4216, "lr": 2.291870232054277e-06, "epoch": 0.5265306122448979, "percentage": 52.65, "elapsed_time": "0:04:01", "remaining_time": "0:03:37"}
131
+ {"current_steps": 130, "total_steps": 245, "loss": 0.3625, "lr": 2.2599424352307958e-06, "epoch": 0.5306122448979592, "percentage": 53.06, "elapsed_time": "0:04:03", "remaining_time": "0:03:35"}
132
+ {"current_steps": 131, "total_steps": 245, "loss": 0.3443, "lr": 2.228054109306673e-06, "epoch": 0.5346938775510204, "percentage": 53.47, "elapsed_time": "0:04:05", "remaining_time": "0:03:33"}
133
+ {"current_steps": 132, "total_steps": 245, "loss": 0.3434, "lr": 2.196210497444749e-06, "epoch": 0.5387755102040817, "percentage": 53.88, "elapsed_time": "0:04:07", "remaining_time": "0:03:31"}
134
+ {"current_steps": 133, "total_steps": 245, "loss": 0.3636, "lr": 2.1644168354558623e-06, "epoch": 0.5428571428571428, "percentage": 54.29, "elapsed_time": "0:04:08", "remaining_time": "0:03:29"}
135
+ {"current_steps": 134, "total_steps": 245, "loss": 0.3202, "lr": 2.1326783509379555e-06, "epoch": 0.5469387755102041, "percentage": 54.69, "elapsed_time": "0:04:10", "remaining_time": "0:03:27"}
136
+ {"current_steps": 135, "total_steps": 245, "loss": 0.3714, "lr": 2.1010002624165528e-06, "epoch": 0.5510204081632653, "percentage": 55.1, "elapsed_time": "0:04:12", "remaining_time": "0:03:25"}
137
+ {"current_steps": 136, "total_steps": 245, "loss": 0.3404, "lr": 2.069387778486703e-06, "epoch": 0.5551020408163265, "percentage": 55.51, "elapsed_time": "0:04:14", "remaining_time": "0:03:23"}
138
+ {"current_steps": 137, "total_steps": 245, "loss": 0.3986, "lr": 2.037846096956578e-06, "epoch": 0.5591836734693878, "percentage": 55.92, "elapsed_time": "0:04:16", "remaining_time": "0:03:21"}
139
+ {"current_steps": 138, "total_steps": 245, "loss": 0.3611, "lr": 2.0063804039928324e-06, "epoch": 0.563265306122449, "percentage": 56.33, "elapsed_time": "0:04:18", "remaining_time": "0:03:20"}
140
+ {"current_steps": 139, "total_steps": 245, "loss": 0.3646, "lr": 1.9749958732678766e-06, "epoch": 0.5673469387755102, "percentage": 56.73, "elapsed_time": "0:04:19", "remaining_time": "0:03:18"}
141
+ {"current_steps": 140, "total_steps": 245, "loss": 0.4041, "lr": 1.9436976651092143e-06, "epoch": 0.5714285714285714, "percentage": 57.14, "elapsed_time": "0:04:21", "remaining_time": "0:03:16"}
142
+ {"current_steps": 141, "total_steps": 245, "loss": 0.4063, "lr": 1.912490925650962e-06, "epoch": 0.5755102040816327, "percentage": 57.55, "elapsed_time": "0:04:23", "remaining_time": "0:03:14"}
143
+ {"current_steps": 142, "total_steps": 245, "loss": 0.3309, "lr": 1.8813807859877147e-06, "epoch": 0.5795918367346938, "percentage": 57.96, "elapsed_time": "0:04:25", "remaining_time": "0:03:12"}
144
+ {"current_steps": 143, "total_steps": 245, "loss": 0.3503, "lr": 1.8503723613308683e-06, "epoch": 0.5836734693877551, "percentage": 58.37, "elapsed_time": "0:04:27", "remaining_time": "0:03:10"}
145
+ {"current_steps": 144, "total_steps": 245, "loss": 0.4039, "lr": 1.8194707501675724e-06, "epoch": 0.5877551020408164, "percentage": 58.78, "elapsed_time": "0:04:29", "remaining_time": "0:03:08"}
146
+ {"current_steps": 145, "total_steps": 245, "loss": 0.3243, "lr": 1.7886810334224192e-06, "epoch": 0.5918367346938775, "percentage": 59.18, "elapsed_time": "0:04:31", "remaining_time": "0:03:06"}
147
+ {"current_steps": 146, "total_steps": 245, "loss": 0.3556, "lr": 1.7580082736220235e-06, "epoch": 0.5959183673469388, "percentage": 59.59, "elapsed_time": "0:04:32", "remaining_time": "0:03:05"}
148
+ {"current_steps": 147, "total_steps": 245, "loss": 0.3709, "lr": 1.7274575140626318e-06, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:04:34", "remaining_time": "0:03:03"}
149
+ {"current_steps": 148, "total_steps": 245, "loss": 0.3823, "lr": 1.6970337779808862e-06, "epoch": 0.6040816326530613, "percentage": 60.41, "elapsed_time": "0:04:36", "remaining_time": "0:03:01"}
150
+ {"current_steps": 149, "total_steps": 245, "loss": 0.3361, "lr": 1.6667420677278962e-06, "epoch": 0.6081632653061224, "percentage": 60.82, "elapsed_time": "0:04:38", "remaining_time": "0:02:59"}
151
+ {"current_steps": 150, "total_steps": 245, "loss": 0.3898, "lr": 1.6365873639467314e-06, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:04:40", "remaining_time": "0:02:57"}
152
+ {"current_steps": 151, "total_steps": 245, "loss": 0.3587, "lr": 1.6065746247534986e-06, "epoch": 0.6163265306122448, "percentage": 61.63, "elapsed_time": "0:04:42", "remaining_time": "0:02:55"}
153
+ {"current_steps": 152, "total_steps": 245, "loss": 0.3503, "lr": 1.5767087849221097e-06, "epoch": 0.6204081632653061, "percentage": 62.04, "elapsed_time": "0:04:43", "remaining_time": "0:02:53"}
154
+ {"current_steps": 153, "total_steps": 245, "loss": 0.3321, "lr": 1.546994755072896e-06, "epoch": 0.6244897959183674, "percentage": 62.45, "elapsed_time": "0:04:45", "remaining_time": "0:02:51"}
155
+ {"current_steps": 154, "total_steps": 245, "loss": 0.3473, "lr": 1.5174374208651913e-06, "epoch": 0.6285714285714286, "percentage": 62.86, "elapsed_time": "0:04:47", "remaining_time": "0:02:49"}
156
+ {"current_steps": 155, "total_steps": 245, "loss": 0.3272, "lr": 1.4880416421940155e-06, "epoch": 0.6326530612244898, "percentage": 63.27, "elapsed_time": "0:04:49", "remaining_time": "0:02:48"}
157
+ {"current_steps": 156, "total_steps": 245, "loss": 0.3195, "lr": 1.4588122523910032e-06, "epoch": 0.636734693877551, "percentage": 63.67, "elapsed_time": "0:04:51", "remaining_time": "0:02:46"}
158
+ {"current_steps": 157, "total_steps": 245, "loss": 0.3838, "lr": 1.429754057429687e-06, "epoch": 0.6408163265306123, "percentage": 64.08, "elapsed_time": "0:04:53", "remaining_time": "0:02:44"}
159
+ {"current_steps": 158, "total_steps": 245, "loss": 0.3484, "lr": 1.400871835135295e-06, "epoch": 0.6448979591836734, "percentage": 64.49, "elapsed_time": "0:04:54", "remaining_time": "0:02:42"}
160
+ {"current_steps": 159, "total_steps": 245, "loss": 0.3591, "lr": 1.3721703343991634e-06, "epoch": 0.6489795918367347, "percentage": 64.9, "elapsed_time": "0:04:56", "remaining_time": "0:02:40"}
161
+ {"current_steps": 160, "total_steps": 245, "loss": 0.3773, "lr": 1.3436542743979125e-06, "epoch": 0.6530612244897959, "percentage": 65.31, "elapsed_time": "0:04:58", "remaining_time": "0:02:38"}
162
+ {"current_steps": 161, "total_steps": 245, "loss": 0.3886, "lr": 1.3153283438175036e-06, "epoch": 0.6571428571428571, "percentage": 65.71, "elapsed_time": "0:05:00", "remaining_time": "0:02:36"}
163
+ {"current_steps": 162, "total_steps": 245, "loss": 0.3387, "lr": 1.2871972000823197e-06, "epoch": 0.6612244897959184, "percentage": 66.12, "elapsed_time": "0:05:02", "remaining_time": "0:02:34"}
164
+ {"current_steps": 163, "total_steps": 245, "loss": 0.3483, "lr": 1.2592654685893757e-06, "epoch": 0.6653061224489796, "percentage": 66.53, "elapsed_time": "0:05:03", "remaining_time": "0:02:32"}
165
+ {"current_steps": 164, "total_steps": 245, "loss": 0.3409, "lr": 1.231537741947795e-06, "epoch": 0.6693877551020408, "percentage": 66.94, "elapsed_time": "0:05:05", "remaining_time": "0:02:30"}
166
+ {"current_steps": 165, "total_steps": 245, "loss": 0.3353, "lr": 1.2040185792236874e-06, "epoch": 0.673469387755102, "percentage": 67.35, "elapsed_time": "0:05:07", "remaining_time": "0:02:29"}
167
+ {"current_steps": 166, "total_steps": 245, "loss": 0.3724, "lr": 1.1767125051905314e-06, "epoch": 0.6775510204081633, "percentage": 67.76, "elapsed_time": "0:05:09", "remaining_time": "0:02:27"}
168
+ {"current_steps": 167, "total_steps": 245, "loss": 0.3725, "lr": 1.1496240095852002e-06, "epoch": 0.6816326530612244, "percentage": 68.16, "elapsed_time": "0:05:11", "remaining_time": "0:02:25"}
169
+ {"current_steps": 168, "total_steps": 245, "loss": 0.3621, "lr": 1.122757546369744e-06, "epoch": 0.6857142857142857, "percentage": 68.57, "elapsed_time": "0:05:13", "remaining_time": "0:02:23"}
170
+ {"current_steps": 169, "total_steps": 245, "loss": 0.3666, "lr": 1.0961175329990631e-06, "epoch": 0.689795918367347, "percentage": 68.98, "elapsed_time": "0:05:14", "remaining_time": "0:02:21"}
171
+ {"current_steps": 170, "total_steps": 245, "loss": 0.3692, "lr": 1.0697083496945766e-06, "epoch": 0.6938775510204082, "percentage": 69.39, "elapsed_time": "0:05:16", "remaining_time": "0:02:19"}
172
+ {"current_steps": 171, "total_steps": 245, "loss": 0.3458, "lr": 1.04353433872401e-06, "epoch": 0.6979591836734694, "percentage": 69.8, "elapsed_time": "0:05:18", "remaining_time": "0:02:17"}
173
+ {"current_steps": 172, "total_steps": 245, "loss": 0.3446, "lr": 1.0175998036874357e-06, "epoch": 0.7020408163265306, "percentage": 70.2, "elapsed_time": "0:05:20", "remaining_time": "0:02:16"}
174
+ {"current_steps": 173, "total_steps": 245, "loss": 0.2927, "lr": 9.91909008809659e-07, "epoch": 0.7061224489795919, "percentage": 70.61, "elapsed_time": "0:05:22", "remaining_time": "0:02:14"}
175
+ {"current_steps": 174, "total_steps": 245, "loss": 0.365, "lr": 9.66466178239084e-07, "epoch": 0.710204081632653, "percentage": 71.02, "elapsed_time": "0:05:24", "remaining_time": "0:02:12"}
176
+ {"current_steps": 175, "total_steps": 245, "loss": 0.37, "lr": 9.412754953531664e-07, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:05:26", "remaining_time": "0:02:10"}
177
+ {"current_steps": 176, "total_steps": 245, "loss": 0.3765, "lr": 9.163411020705762e-07, "epoch": 0.7183673469387755, "percentage": 71.84, "elapsed_time": "0:05:27", "remaining_time": "0:02:08"}
178
+ {"current_steps": 177, "total_steps": 245, "loss": 0.3311, "lr": 8.916670981701656e-07, "epoch": 0.7224489795918367, "percentage": 72.24, "elapsed_time": "0:05:29", "remaining_time": "0:02:06"}
179
+ {"current_steps": 178, "total_steps": 245, "loss": 0.3377, "lr": 8.672575406168782e-07, "epoch": 0.726530612244898, "percentage": 72.65, "elapsed_time": "0:05:31", "remaining_time": "0:02:04"}
180
+ {"current_steps": 179, "total_steps": 245, "loss": 0.3043, "lr": 8.431164428946928e-07, "epoch": 0.7306122448979592, "percentage": 73.06, "elapsed_time": "0:05:33", "remaining_time": "0:02:02"}
181
+ {"current_steps": 180, "total_steps": 245, "loss": 0.3309, "lr": 8.192477743467078e-07, "epoch": 0.7346938775510204, "percentage": 73.47, "elapsed_time": "0:05:35", "remaining_time": "0:02:01"}
182
+ {"current_steps": 181, "total_steps": 245, "loss": 0.326, "lr": 7.956554595225017e-07, "epoch": 0.7387755102040816, "percentage": 73.88, "elapsed_time": "0:05:37", "remaining_time": "0:01:59"}
183
+ {"current_steps": 182, "total_steps": 245, "loss": 0.3185, "lr": 7.723433775328385e-07, "epoch": 0.7428571428571429, "percentage": 74.29, "elapsed_time": "0:05:38", "remaining_time": "0:01:57"}
184
+ {"current_steps": 183, "total_steps": 245, "loss": 0.4109, "lr": 7.493153614118634e-07, "epoch": 0.746938775510204, "percentage": 74.69, "elapsed_time": "0:05:40", "remaining_time": "0:01:55"}
185
+ {"current_steps": 184, "total_steps": 245, "loss": 0.4135, "lr": 7.265751974868554e-07, "epoch": 0.7510204081632653, "percentage": 75.1, "elapsed_time": "0:05:42", "remaining_time": "0:01:53"}
186
+ {"current_steps": 185, "total_steps": 245, "loss": 0.4066, "lr": 7.041266247556814e-07, "epoch": 0.7551020408163265, "percentage": 75.51, "elapsed_time": "0:05:44", "remaining_time": "0:01:51"}
187
+ {"current_steps": 186, "total_steps": 245, "loss": 0.3616, "lr": 6.819733342720067e-07, "epoch": 0.7591836734693878, "percentage": 75.92, "elapsed_time": "0:05:46", "remaining_time": "0:01:49"}
188
+ {"current_steps": 187, "total_steps": 245, "loss": 0.4512, "lr": 6.601189685384127e-07, "epoch": 0.763265306122449, "percentage": 76.33, "elapsed_time": "0:05:48", "remaining_time": "0:01:48"}
189
+ {"current_steps": 188, "total_steps": 245, "loss": 0.347, "lr": 6.385671209074829e-07, "epoch": 0.7673469387755102, "percentage": 76.73, "elapsed_time": "0:05:50", "remaining_time": "0:01:46"}
190
+ {"current_steps": 189, "total_steps": 245, "loss": 0.3564, "lr": 6.17321334990973e-07, "epoch": 0.7714285714285715, "percentage": 77.14, "elapsed_time": "0:05:51", "remaining_time": "0:01:44"}
191
+ {"current_steps": 190, "total_steps": 245, "loss": 0.3215, "lr": 5.963851040771639e-07, "epoch": 0.7755102040816326, "percentage": 77.55, "elapsed_time": "0:05:53", "remaining_time": "0:01:42"}
192
+ {"current_steps": 191, "total_steps": 245, "loss": 0.3391, "lr": 5.757618705564849e-07, "epoch": 0.7795918367346939, "percentage": 77.96, "elapsed_time": "0:05:55", "remaining_time": "0:01:40"}
193
+ {"current_steps": 192, "total_steps": 245, "loss": 0.3166, "lr": 5.554550253555066e-07, "epoch": 0.7836734693877551, "percentage": 78.37, "elapsed_time": "0:05:57", "remaining_time": "0:01:38"}
194
+ {"current_steps": 193, "total_steps": 245, "loss": 0.3432, "lr": 5.354679073793942e-07, "epoch": 0.7877551020408163, "percentage": 78.78, "elapsed_time": "0:05:59", "remaining_time": "0:01:36"}
195
+ {"current_steps": 194, "total_steps": 245, "loss": 0.3786, "lr": 5.158038029629195e-07, "epoch": 0.7918367346938775, "percentage": 79.18, "elapsed_time": "0:06:01", "remaining_time": "0:01:34"}
196
+ {"current_steps": 195, "total_steps": 245, "loss": 0.3456, "lr": 4.964659453301088e-07, "epoch": 0.7959183673469388, "percentage": 79.59, "elapsed_time": "0:06:03", "remaining_time": "0:01:33"}
197
+ {"current_steps": 196, "total_steps": 245, "loss": 0.2893, "lr": 4.774575140626317e-07, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:06:04", "remaining_time": "0:01:31"}
198
+ {"current_steps": 197, "total_steps": 245, "loss": 0.3202, "lr": 4.5878163457700327e-07, "epoch": 0.8040816326530612, "percentage": 80.41, "elapsed_time": "0:06:06", "remaining_time": "0:01:29"}
199
+ {"current_steps": 198, "total_steps": 245, "loss": 0.3558, "lr": 4.4044137761069584e-07, "epoch": 0.8081632653061225, "percentage": 80.82, "elapsed_time": "0:06:08", "remaining_time": "0:01:27"}
200
+ {"current_steps": 199, "total_steps": 245, "loss": 0.3797, "lr": 4.2243975871724017e-07, "epoch": 0.8122448979591836, "percentage": 81.22, "elapsed_time": "0:06:10", "remaining_time": "0:01:25"}
201
+ {"current_steps": 200, "total_steps": 245, "loss": 0.315, "lr": 4.0477973777039854e-07, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:06:12", "remaining_time": "0:01:23"}
202
+ {"current_steps": 200, "total_steps": 245, "eval_loss": 0.3877667188644409, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:06:12", "remaining_time": "0:01:23"}
203
+ {"current_steps": 201, "total_steps": 245, "loss": 0.3517, "lr": 3.874642184774977e-07, "epoch": 0.8204081632653061, "percentage": 82.04, "elapsed_time": "0:06:14", "remaining_time": "0:01:22"}
204
+ {"current_steps": 202, "total_steps": 245, "loss": 0.33, "lr": 3.7049604790198976e-07, "epoch": 0.8244897959183674, "percentage": 82.45, "elapsed_time": "0:06:16", "remaining_time": "0:01:20"}
205
+ {"current_steps": 203, "total_steps": 245, "loss": 0.3047, "lr": 3.538780159953348e-07, "epoch": 0.8285714285714286, "percentage": 82.86, "elapsed_time": "0:06:18", "remaining_time": "0:01:18"}
206
+ {"current_steps": 204, "total_steps": 245, "loss": 0.3118, "lr": 3.3761285513826627e-07, "epoch": 0.8326530612244898, "percentage": 83.27, "elapsed_time": "0:06:20", "remaining_time": "0:01:16"}
207
+ {"current_steps": 205, "total_steps": 245, "loss": 0.3093, "lr": 3.217032396915265e-07, "epoch": 0.8367346938775511, "percentage": 83.67, "elapsed_time": "0:06:22", "remaining_time": "0:01:14"}
208
+ {"current_steps": 206, "total_steps": 245, "loss": 0.3706, "lr": 3.06151785556143e-07, "epoch": 0.8408163265306122, "percentage": 84.08, "elapsed_time": "0:06:24", "remaining_time": "0:01:12"}
209
+ {"current_steps": 207, "total_steps": 245, "loss": 0.327, "lr": 2.9096104974331186e-07, "epoch": 0.8448979591836735, "percentage": 84.49, "elapsed_time": "0:06:25", "remaining_time": "0:01:10"}
210
+ {"current_steps": 208, "total_steps": 245, "loss": 0.3858, "lr": 2.761335299539708e-07, "epoch": 0.8489795918367347, "percentage": 84.9, "elapsed_time": "0:06:27", "remaining_time": "0:01:08"}
211
+ {"current_steps": 209, "total_steps": 245, "loss": 0.3489, "lr": 2.6167166416811745e-07, "epoch": 0.8530612244897959, "percentage": 85.31, "elapsed_time": "0:06:29", "remaining_time": "0:01:07"}
212
+ {"current_steps": 210, "total_steps": 245, "loss": 0.2961, "lr": 2.4757783024395244e-07, "epoch": 0.8571428571428571, "percentage": 85.71, "elapsed_time": "0:06:31", "remaining_time": "0:01:05"}
213
+ {"current_steps": 211, "total_steps": 245, "loss": 0.3677, "lr": 2.338543455269046e-07, "epoch": 0.8612244897959184, "percentage": 86.12, "elapsed_time": "0:06:33", "remaining_time": "0:01:03"}
214
+ {"current_steps": 212, "total_steps": 245, "loss": 0.3543, "lr": 2.205034664686076e-07, "epoch": 0.8653061224489796, "percentage": 86.53, "elapsed_time": "0:06:35", "remaining_time": "0:01:01"}
215
+ {"current_steps": 213, "total_steps": 245, "loss": 0.3204, "lr": 2.075273882558873e-07, "epoch": 0.8693877551020408, "percentage": 86.94, "elapsed_time": "0:06:37", "remaining_time": "0:00:59"}
216
+ {"current_steps": 214, "total_steps": 245, "loss": 0.3593, "lr": 1.9492824444982378e-07, "epoch": 0.8734693877551021, "percentage": 87.35, "elapsed_time": "0:06:38", "remaining_time": "0:00:57"}
217
+ {"current_steps": 215, "total_steps": 245, "loss": 0.3516, "lr": 1.8270810663494591e-07, "epoch": 0.8775510204081632, "percentage": 87.76, "elapsed_time": "0:06:40", "remaining_time": "0:00:55"}
218
+ {"current_steps": 216, "total_steps": 245, "loss": 0.3111, "lr": 1.7086898407861486e-07, "epoch": 0.8816326530612245, "percentage": 88.16, "elapsed_time": "0:06:42", "remaining_time": "0:00:54"}
219
+ {"current_steps": 217, "total_steps": 245, "loss": 0.3241, "lr": 1.59412823400657e-07, "epoch": 0.8857142857142857, "percentage": 88.57, "elapsed_time": "0:06:44", "remaining_time": "0:00:52"}
220
+ {"current_steps": 218, "total_steps": 245, "loss": 0.3015, "lr": 1.483415082532938e-07, "epoch": 0.889795918367347, "percentage": 88.98, "elapsed_time": "0:06:46", "remaining_time": "0:00:50"}
221
+ {"current_steps": 219, "total_steps": 245, "loss": 0.3429, "lr": 1.3765685901142718e-07, "epoch": 0.8938775510204081, "percentage": 89.39, "elapsed_time": "0:06:48", "remaining_time": "0:00:48"}
222
+ {"current_steps": 220, "total_steps": 245, "loss": 0.3424, "lr": 1.273606324733284e-07, "epoch": 0.8979591836734694, "percentage": 89.8, "elapsed_time": "0:06:50", "remaining_time": "0:00:46"}
223
+ {"current_steps": 221, "total_steps": 245, "loss": 0.3288, "lr": 1.1745452157178206e-07, "epoch": 0.9020408163265307, "percentage": 90.2, "elapsed_time": "0:06:51", "remaining_time": "0:00:44"}
224
+ {"current_steps": 222, "total_steps": 245, "loss": 0.3053, "lr": 1.0794015509572819e-07, "epoch": 0.9061224489795918, "percentage": 90.61, "elapsed_time": "0:06:53", "remaining_time": "0:00:42"}
225
+ {"current_steps": 223, "total_steps": 245, "loss": 0.4205, "lr": 9.881909742245177e-08, "epoch": 0.9102040816326531, "percentage": 91.02, "elapsed_time": "0:06:55", "remaining_time": "0:00:41"}
226
+ {"current_steps": 224, "total_steps": 245, "loss": 0.3369, "lr": 9.00928482603669e-08, "epoch": 0.9142857142857143, "percentage": 91.43, "elapsed_time": "0:06:57", "remaining_time": "0:00:39"}
227
+ {"current_steps": 225, "total_steps": 245, "loss": 0.3323, "lr": 8.176284240242638e-08, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:06:59", "remaining_time": "0:00:37"}
228
+ {"current_steps": 226, "total_steps": 245, "loss": 0.4046, "lr": 7.383044949021339e-08, "epoch": 0.9224489795918367, "percentage": 92.24, "elapsed_time": "0:07:01", "remaining_time": "0:00:35"}
229
+ {"current_steps": 227, "total_steps": 245, "loss": 0.3286, "lr": 6.629697378873839e-08, "epoch": 0.926530612244898, "percentage": 92.65, "elapsed_time": "0:07:02", "remaining_time": "0:00:33"}
230
+ {"current_steps": 228, "total_steps": 245, "loss": 0.3781, "lr": 5.9163653971989754e-08, "epoch": 0.9306122448979591, "percentage": 93.06, "elapsed_time": "0:07:04", "remaining_time": "0:00:31"}
231
+ {"current_steps": 229, "total_steps": 245, "loss": 0.3199, "lr": 5.2431662919267825e-08, "epoch": 0.9346938775510204, "percentage": 93.47, "elapsed_time": "0:07:06", "remaining_time": "0:00:29"}
232
+ {"current_steps": 230, "total_steps": 245, "loss": 0.2983, "lr": 4.61021075223364e-08, "epoch": 0.9387755102040817, "percentage": 93.88, "elapsed_time": "0:07:08", "remaining_time": "0:00:27"}
233
+ {"current_steps": 231, "total_steps": 245, "loss": 0.4382, "lr": 4.017602850342584e-08, "epoch": 0.9428571428571428, "percentage": 94.29, "elapsed_time": "0:07:10", "remaining_time": "0:00:26"}
234
+ {"current_steps": 232, "total_steps": 245, "loss": 0.3189, "lr": 3.4654400244112654e-08, "epoch": 0.9469387755102041, "percentage": 94.69, "elapsed_time": "0:07:12", "remaining_time": "0:00:24"}
235
+ {"current_steps": 233, "total_steps": 245, "loss": 0.3415, "lr": 2.9538130625110796e-08, "epoch": 0.9510204081632653, "percentage": 95.1, "elapsed_time": "0:07:13", "remaining_time": "0:00:22"}
236
+ {"current_steps": 234, "total_steps": 245, "loss": 0.3002, "lr": 2.4828060876995462e-08, "epoch": 0.9551020408163265, "percentage": 95.51, "elapsed_time": "0:07:15", "remaining_time": "0:00:20"}
237
+ {"current_steps": 235, "total_steps": 245, "loss": 0.3414, "lr": 2.052496544188487e-08, "epoch": 0.9591836734693877, "percentage": 95.92, "elapsed_time": "0:07:17", "remaining_time": "0:00:18"}
238
+ {"current_steps": 236, "total_steps": 245, "loss": 0.3561, "lr": 1.6629551846104874e-08, "epoch": 0.963265306122449, "percentage": 96.33, "elapsed_time": "0:07:19", "remaining_time": "0:00:16"}
239
+ {"current_steps": 237, "total_steps": 245, "loss": 0.3677, "lr": 1.3142460583856487e-08, "epoch": 0.9673469387755103, "percentage": 96.73, "elapsed_time": "0:07:21", "remaining_time": "0:00:14"}
240
+ {"current_steps": 238, "total_steps": 245, "loss": 0.3691, "lr": 1.006426501190233e-08, "epoch": 0.9714285714285714, "percentage": 97.14, "elapsed_time": "0:07:22", "remaining_time": "0:00:13"}
241
+ {"current_steps": 239, "total_steps": 245, "loss": 0.3313, "lr": 7.3954712552953835e-09, "epoch": 0.9755102040816327, "percentage": 97.55, "elapsed_time": "0:07:24", "remaining_time": "0:00:11"}
242
+ {"current_steps": 240, "total_steps": 245, "loss": 0.3224, "lr": 5.136518124159162e-09, "epoch": 0.9795918367346939, "percentage": 97.96, "elapsed_time": "0:07:26", "remaining_time": "0:00:09"}
243
+ {"current_steps": 241, "total_steps": 245, "loss": 0.3561, "lr": 3.287777041539042e-09, "epoch": 0.9836734693877551, "percentage": 98.37, "elapsed_time": "0:07:28", "remaining_time": "0:00:07"}
244
+ {"current_steps": 242, "total_steps": 245, "loss": 0.3371, "lr": 1.8495519823308329e-09, "epoch": 0.9877551020408163, "percentage": 98.78, "elapsed_time": "0:07:30", "remaining_time": "0:00:05"}
245
+ {"current_steps": 243, "total_steps": 245, "loss": 0.3295, "lr": 8.220794233004814e-10, "epoch": 0.9918367346938776, "percentage": 99.18, "elapsed_time": "0:07:32", "remaining_time": "0:00:03"}
246
+ {"current_steps": 244, "total_steps": 245, "loss": 0.4688, "lr": 2.0552830420184077e-10, "epoch": 0.9959183673469387, "percentage": 99.59, "elapsed_time": "0:07:33", "remaining_time": "0:00:01"}
247
+ {"current_steps": 245, "total_steps": 245, "loss": 0.3356, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:35", "remaining_time": "0:00:00"}
248
+ {"current_steps": 245, "total_steps": 245, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:47", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1773 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 100,
6
+ "global_step": 245,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004081632653061225,
13
+ "grad_norm": 16.657059580490245,
14
+ "learning_rate": 4.9997944716957985e-06,
15
+ "loss": 1.0703,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00816326530612245,
20
+ "grad_norm": 10.223923753279664,
21
+ "learning_rate": 4.9991779205767e-06,
22
+ "loss": 0.9497,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.012244897959183673,
27
+ "grad_norm": 6.756338491219137,
28
+ "learning_rate": 4.99815044801767e-06,
29
+ "loss": 0.9212,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0163265306122449,
34
+ "grad_norm": 5.334225089715787,
35
+ "learning_rate": 4.9967122229584614e-06,
36
+ "loss": 0.831,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.02040816326530612,
41
+ "grad_norm": 3.6725701262385275,
42
+ "learning_rate": 4.994863481875842e-06,
43
+ "loss": 0.7045,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.024489795918367346,
48
+ "grad_norm": 3.196343759801356,
49
+ "learning_rate": 4.992604528744705e-06,
50
+ "loss": 0.7605,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.02857142857142857,
55
+ "grad_norm": 2.5582923515292584,
56
+ "learning_rate": 4.989935734988098e-06,
57
+ "loss": 0.6814,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0326530612244898,
62
+ "grad_norm": 3.1074056214851806,
63
+ "learning_rate": 4.986857539416144e-06,
64
+ "loss": 0.685,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.036734693877551024,
69
+ "grad_norm": 2.6678827844341266,
70
+ "learning_rate": 4.983370448153896e-06,
71
+ "loss": 0.644,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04081632653061224,
76
+ "grad_norm": 2.3389817721495647,
77
+ "learning_rate": 4.979475034558115e-06,
78
+ "loss": 0.5987,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.044897959183673466,
83
+ "grad_norm": 2.240291389592008,
84
+ "learning_rate": 4.9751719391230055e-06,
85
+ "loss": 0.5733,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04897959183673469,
90
+ "grad_norm": 1.9550893105524885,
91
+ "learning_rate": 4.97046186937489e-06,
92
+ "loss": 0.5448,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.053061224489795916,
97
+ "grad_norm": 2.1074419250096112,
98
+ "learning_rate": 4.965345599755888e-06,
99
+ "loss": 0.5215,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.05714285714285714,
104
+ "grad_norm": 1.9911800695176722,
105
+ "learning_rate": 4.959823971496575e-06,
106
+ "loss": 0.5634,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.061224489795918366,
111
+ "grad_norm": 2.4691727896363984,
112
+ "learning_rate": 4.953897892477664e-06,
113
+ "loss": 0.5725,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0653061224489796,
118
+ "grad_norm": 1.7034586399546563,
119
+ "learning_rate": 4.947568337080733e-06,
120
+ "loss": 0.5581,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.06938775510204082,
125
+ "grad_norm": 1.751174045795546,
126
+ "learning_rate": 4.940836346028011e-06,
127
+ "loss": 0.5833,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07346938775510205,
132
+ "grad_norm": 1.7287270444097231,
133
+ "learning_rate": 4.933703026211262e-06,
134
+ "loss": 0.4874,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.07755102040816327,
139
+ "grad_norm": 1.706097001851992,
140
+ "learning_rate": 4.926169550509787e-06,
141
+ "loss": 0.5475,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08163265306122448,
146
+ "grad_norm": 1.7205594962434398,
147
+ "learning_rate": 4.918237157597574e-06,
148
+ "loss": 0.4306,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.08571428571428572,
153
+ "grad_norm": 1.6526245840797151,
154
+ "learning_rate": 4.909907151739634e-06,
155
+ "loss": 0.5024,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.08979591836734693,
160
+ "grad_norm": 1.6935402955194163,
161
+ "learning_rate": 4.901180902577549e-06,
162
+ "loss": 0.4308,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.09387755102040816,
167
+ "grad_norm": 1.8770755848085463,
168
+ "learning_rate": 4.892059844904273e-06,
169
+ "loss": 0.4731,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.09795918367346938,
174
+ "grad_norm": 1.6724213881702623,
175
+ "learning_rate": 4.882545478428219e-06,
176
+ "loss": 0.4177,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.10204081632653061,
181
+ "grad_norm": 1.5576260021825532,
182
+ "learning_rate": 4.872639367526672e-06,
183
+ "loss": 0.4993,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.10612244897959183,
188
+ "grad_norm": 1.5571083161599073,
189
+ "learning_rate": 4.862343140988573e-06,
190
+ "loss": 0.3984,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11020408163265306,
195
+ "grad_norm": 1.9103895770083137,
196
+ "learning_rate": 4.851658491746707e-06,
197
+ "loss": 0.4885,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11428571428571428,
202
+ "grad_norm": 1.6615524691055585,
203
+ "learning_rate": 4.8405871765993435e-06,
204
+ "loss": 0.4676,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.11836734693877551,
209
+ "grad_norm": 1.751651840765487,
210
+ "learning_rate": 4.829131015921386e-06,
211
+ "loss": 0.4346,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.12244897959183673,
216
+ "grad_norm": 1.5419774221484523,
217
+ "learning_rate": 4.817291893365055e-06,
218
+ "loss": 0.3914,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.12653061224489795,
223
+ "grad_norm": 1.9967361324982256,
224
+ "learning_rate": 4.805071755550177e-06,
225
+ "loss": 0.4998,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.1306122448979592,
230
+ "grad_norm": 1.8511902583112827,
231
+ "learning_rate": 4.7924726117441135e-06,
232
+ "loss": 0.4586,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.1346938775510204,
237
+ "grad_norm": 1.570331088172573,
238
+ "learning_rate": 4.779496533531393e-06,
239
+ "loss": 0.4406,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.13877551020408163,
244
+ "grad_norm": 1.7199660299735156,
245
+ "learning_rate": 4.766145654473096e-06,
246
+ "loss": 0.4112,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.14285714285714285,
251
+ "grad_norm": 1.5226188572995256,
252
+ "learning_rate": 4.752422169756048e-06,
253
+ "loss": 0.3947,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1469387755102041,
258
+ "grad_norm": 1.4537387756760975,
259
+ "learning_rate": 4.738328335831883e-06,
260
+ "loss": 0.4523,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.1510204081632653,
265
+ "grad_norm": 1.524546763388935,
266
+ "learning_rate": 4.72386647004603e-06,
267
+ "loss": 0.3953,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.15510204081632653,
272
+ "grad_norm": 1.9875545246550548,
273
+ "learning_rate": 4.7090389502566884e-06,
274
+ "loss": 0.4683,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.15918367346938775,
279
+ "grad_norm": 1.4948971873705341,
280
+ "learning_rate": 4.693848214443858e-06,
281
+ "loss": 0.4271,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.16326530612244897,
286
+ "grad_norm": 1.493585982894778,
287
+ "learning_rate": 4.678296760308474e-06,
288
+ "loss": 0.4562,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1673469387755102,
293
+ "grad_norm": 1.6315018115367141,
294
+ "learning_rate": 4.6623871448617345e-06,
295
+ "loss": 0.4527,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.17142857142857143,
300
+ "grad_norm": 1.589087540215102,
301
+ "learning_rate": 4.646121984004666e-06,
302
+ "loss": 0.4218,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.17551020408163265,
307
+ "grad_norm": 1.406556899154804,
308
+ "learning_rate": 4.629503952098011e-06,
309
+ "loss": 0.3863,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.17959183673469387,
314
+ "grad_norm": 1.7430824923060468,
315
+ "learning_rate": 4.612535781522504e-06,
316
+ "loss": 0.4849,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.1836734693877551,
321
+ "grad_norm": 1.6564623948734394,
322
+ "learning_rate": 4.5952202622296015e-06,
323
+ "loss": 0.4309,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.18775510204081633,
328
+ "grad_norm": 1.5474967119229082,
329
+ "learning_rate": 4.57756024128276e-06,
330
+ "loss": 0.3827,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.19183673469387755,
335
+ "grad_norm": 1.5270474645139251,
336
+ "learning_rate": 4.559558622389304e-06,
337
+ "loss": 0.4364,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.19591836734693877,
342
+ "grad_norm": 1.6187844894346521,
343
+ "learning_rate": 4.541218365422997e-06,
344
+ "loss": 0.4761,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.2,
349
+ "grad_norm": 1.4818331791681476,
350
+ "learning_rate": 4.522542485937369e-06,
351
+ "loss": 0.3942,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.20408163265306123,
356
+ "grad_norm": 1.490776241319931,
357
+ "learning_rate": 4.5035340546698915e-06,
358
+ "loss": 0.4418,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.20816326530612245,
363
+ "grad_norm": 1.538930163385909,
364
+ "learning_rate": 4.484196197037082e-06,
365
+ "loss": 0.3799,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.21224489795918366,
370
+ "grad_norm": 1.436438929338258,
371
+ "learning_rate": 4.464532092620607e-06,
372
+ "loss": 0.3691,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.2163265306122449,
377
+ "grad_norm": 1.6612946834452833,
378
+ "learning_rate": 4.444544974644493e-06,
379
+ "loss": 0.4283,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.22040816326530613,
384
+ "grad_norm": 1.5312924886442771,
385
+ "learning_rate": 4.424238129443515e-06,
386
+ "loss": 0.4729,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.22448979591836735,
391
+ "grad_norm": 1.4909966058428838,
392
+ "learning_rate": 4.4036148959228365e-06,
393
+ "loss": 0.4193,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.22857142857142856,
398
+ "grad_norm": 1.3058558034203949,
399
+ "learning_rate": 4.382678665009028e-06,
400
+ "loss": 0.3448,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.23265306122448978,
405
+ "grad_norm": 1.3643801310823822,
406
+ "learning_rate": 4.361432879092518e-06,
407
+ "loss": 0.3713,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.23673469387755103,
412
+ "grad_norm": 1.4735837478488467,
413
+ "learning_rate": 4.339881031461588e-06,
414
+ "loss": 0.4023,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.24081632653061225,
419
+ "grad_norm": 1.461965775217398,
420
+ "learning_rate": 4.318026665727993e-06,
421
+ "loss": 0.4063,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.24489795918367346,
426
+ "grad_norm": 1.4414341841068916,
427
+ "learning_rate": 4.295873375244319e-06,
428
+ "loss": 0.4078,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.24897959183673468,
433
+ "grad_norm": 2.0424079146130207,
434
+ "learning_rate": 4.273424802513145e-06,
435
+ "loss": 0.4126,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2530612244897959,
440
+ "grad_norm": 1.5257226836465727,
441
+ "learning_rate": 4.2506846385881375e-06,
442
+ "loss": 0.4224,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.2571428571428571,
447
+ "grad_norm": 1.6083684879243871,
448
+ "learning_rate": 4.227656622467162e-06,
449
+ "loss": 0.4787,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.2612244897959184,
454
+ "grad_norm": 1.631419187892748,
455
+ "learning_rate": 4.204344540477499e-06,
456
+ "loss": 0.3748,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.2653061224489796,
461
+ "grad_norm": 1.4959375993694664,
462
+ "learning_rate": 4.1807522256532925e-06,
463
+ "loss": 0.446,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2693877551020408,
468
+ "grad_norm": 1.46127746032636,
469
+ "learning_rate": 4.156883557105308e-06,
470
+ "loss": 0.3762,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.27346938775510204,
475
+ "grad_norm": 1.5174152808057437,
476
+ "learning_rate": 4.132742459383122e-06,
477
+ "loss": 0.4028,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.27755102040816326,
482
+ "grad_norm": 1.3944762699063917,
483
+ "learning_rate": 4.1083329018298356e-06,
484
+ "loss": 0.4166,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.2816326530612245,
489
+ "grad_norm": 1.5677848638242116,
490
+ "learning_rate": 4.083658897929425e-06,
491
+ "loss": 0.404,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.2857142857142857,
496
+ "grad_norm": 1.546308544470418,
497
+ "learning_rate": 4.058724504646834e-06,
498
+ "loss": 0.4047,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.2897959183673469,
503
+ "grad_norm": 1.4252180266498895,
504
+ "learning_rate": 4.033533821760917e-06,
505
+ "loss": 0.3509,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.2938775510204082,
510
+ "grad_norm": 1.4580496774793081,
511
+ "learning_rate": 4.008090991190341e-06,
512
+ "loss": 0.3597,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.2979591836734694,
517
+ "grad_norm": 1.513514165749645,
518
+ "learning_rate": 3.982400196312565e-06,
519
+ "loss": 0.4371,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3020408163265306,
524
+ "grad_norm": 1.455676495634296,
525
+ "learning_rate": 3.9564656612759904e-06,
526
+ "loss": 0.39,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.30612244897959184,
531
+ "grad_norm": 1.4320340845401187,
532
+ "learning_rate": 3.930291650305424e-06,
533
+ "loss": 0.4004,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.31020408163265306,
538
+ "grad_norm": 1.2753680724356664,
539
+ "learning_rate": 3.903882467000938e-06,
540
+ "loss": 0.3959,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3142857142857143,
545
+ "grad_norm": 1.4477121232798214,
546
+ "learning_rate": 3.8772424536302565e-06,
547
+ "loss": 0.3981,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3183673469387755,
552
+ "grad_norm": 1.4954518344954142,
553
+ "learning_rate": 3.8503759904148005e-06,
554
+ "loss": 0.3972,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.3224489795918367,
559
+ "grad_norm": 1.32597628544497,
560
+ "learning_rate": 3.823287494809469e-06,
561
+ "loss": 0.3377,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.32653061224489793,
566
+ "grad_norm": 1.4135975079699707,
567
+ "learning_rate": 3.7959814207763134e-06,
568
+ "loss": 0.4188,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3306122448979592,
573
+ "grad_norm": 1.3618948630181382,
574
+ "learning_rate": 3.7684622580522057e-06,
575
+ "loss": 0.3721,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3346938775510204,
580
+ "grad_norm": 1.5727248385550423,
581
+ "learning_rate": 3.740734531410626e-06,
582
+ "loss": 0.4187,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.33877551020408164,
587
+ "grad_norm": 1.533706052203793,
588
+ "learning_rate": 3.71280279991768e-06,
589
+ "loss": 0.3896,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.34285714285714286,
594
+ "grad_norm": 1.4609689388296134,
595
+ "learning_rate": 3.684671656182497e-06,
596
+ "loss": 0.3715,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3469387755102041,
601
+ "grad_norm": 1.484149379972334,
602
+ "learning_rate": 3.656345725602089e-06,
603
+ "loss": 0.3963,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3510204081632653,
608
+ "grad_norm": 1.5335318537802856,
609
+ "learning_rate": 3.6278296656008366e-06,
610
+ "loss": 0.3551,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3551020408163265,
615
+ "grad_norm": 1.4229118588935876,
616
+ "learning_rate": 3.599128164864706e-06,
617
+ "loss": 0.3788,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.35918367346938773,
622
+ "grad_norm": 1.4322012901825225,
623
+ "learning_rate": 3.5702459425703146e-06,
624
+ "loss": 0.4037,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.363265306122449,
629
+ "grad_norm": 1.753089905366805,
630
+ "learning_rate": 3.541187747608998e-06,
631
+ "loss": 0.4119,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.3673469387755102,
636
+ "grad_norm": 1.4217045424807102,
637
+ "learning_rate": 3.5119583578059845e-06,
638
+ "loss": 0.3638,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.37142857142857144,
643
+ "grad_norm": 1.4023023935901349,
644
+ "learning_rate": 3.4825625791348093e-06,
645
+ "loss": 0.3841,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.37551020408163266,
650
+ "grad_norm": 1.6135129367692993,
651
+ "learning_rate": 3.4530052449271044e-06,
652
+ "loss": 0.4185,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.3795918367346939,
657
+ "grad_norm": 1.2994504163579816,
658
+ "learning_rate": 3.4232912150778914e-06,
659
+ "loss": 0.3622,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3836734693877551,
664
+ "grad_norm": 1.4662560026306155,
665
+ "learning_rate": 3.393425375246503e-06,
666
+ "loss": 0.4191,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.3877551020408163,
671
+ "grad_norm": 1.3245886999634378,
672
+ "learning_rate": 3.3634126360532694e-06,
673
+ "loss": 0.3611,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.39183673469387753,
678
+ "grad_norm": 1.3386741947693677,
679
+ "learning_rate": 3.333257932272105e-06,
680
+ "loss": 0.3779,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.39591836734693875,
685
+ "grad_norm": 1.7128220876393268,
686
+ "learning_rate": 3.3029662220191146e-06,
687
+ "loss": 0.3692,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.4,
692
+ "grad_norm": 1.4859041012272738,
693
+ "learning_rate": 3.272542485937369e-06,
694
+ "loss": 0.4198,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.40408163265306124,
699
+ "grad_norm": 1.2811105825201938,
700
+ "learning_rate": 3.2419917263779765e-06,
701
+ "loss": 0.3304,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.40816326530612246,
706
+ "grad_norm": 1.4161047862011562,
707
+ "learning_rate": 3.2113189665775812e-06,
708
+ "loss": 0.344,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.40816326530612246,
713
+ "eval_loss": 0.41177019476890564,
714
+ "eval_runtime": 0.4548,
715
+ "eval_samples_per_second": 4.398,
716
+ "eval_steps_per_second": 2.199,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.4122448979591837,
721
+ "grad_norm": 1.424552124833777,
722
+ "learning_rate": 3.180529249832428e-06,
723
+ "loss": 0.3527,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.4163265306122449,
728
+ "grad_norm": 1.5106809102542953,
729
+ "learning_rate": 3.1496276386691327e-06,
730
+ "loss": 0.345,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.4204081632653061,
735
+ "grad_norm": 1.3988080783758308,
736
+ "learning_rate": 3.1186192140122863e-06,
737
+ "loss": 0.3598,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.42448979591836733,
742
+ "grad_norm": 1.4137005251193302,
743
+ "learning_rate": 3.0875090743490383e-06,
744
+ "loss": 0.3834,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.42857142857142855,
749
+ "grad_norm": 1.5342454614867198,
750
+ "learning_rate": 3.056302334890786e-06,
751
+ "loss": 0.3542,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.4326530612244898,
756
+ "grad_norm": 1.429903716817647,
757
+ "learning_rate": 3.0250041267321234e-06,
758
+ "loss": 0.3905,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.43673469387755104,
763
+ "grad_norm": 1.274745603536459,
764
+ "learning_rate": 2.993619596007168e-06,
765
+ "loss": 0.3681,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.44081632653061226,
770
+ "grad_norm": 1.5223751366926457,
771
+ "learning_rate": 2.9621539030434223e-06,
772
+ "loss": 0.3817,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.4448979591836735,
777
+ "grad_norm": 1.4209664338670696,
778
+ "learning_rate": 2.9306122215132974e-06,
779
+ "loss": 0.4041,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.4489795918367347,
784
+ "grad_norm": 1.3653848159519357,
785
+ "learning_rate": 2.8989997375834485e-06,
786
+ "loss": 0.3409,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.4530612244897959,
791
+ "grad_norm": 1.520617956903416,
792
+ "learning_rate": 2.8673216490620453e-06,
793
+ "loss": 0.3872,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.45714285714285713,
798
+ "grad_norm": 1.3968209308120578,
799
+ "learning_rate": 2.835583164544139e-06,
800
+ "loss": 0.3729,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.46122448979591835,
805
+ "grad_norm": 1.636047150882859,
806
+ "learning_rate": 2.8037895025552513e-06,
807
+ "loss": 0.3785,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.46530612244897956,
812
+ "grad_norm": 1.5584753808243215,
813
+ "learning_rate": 2.7719458906933277e-06,
814
+ "loss": 0.4038,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.46938775510204084,
819
+ "grad_norm": 1.88935387106703,
820
+ "learning_rate": 2.7400575647692046e-06,
821
+ "loss": 0.3886,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.47346938775510206,
826
+ "grad_norm": 1.2954431127488966,
827
+ "learning_rate": 2.7081297679457238e-06,
828
+ "loss": 0.3655,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.4775510204081633,
833
+ "grad_norm": 1.2894994461977476,
834
+ "learning_rate": 2.676167749875635e-06,
835
+ "loss": 0.3158,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.4816326530612245,
840
+ "grad_norm": 1.4753492843573608,
841
+ "learning_rate": 2.6441767658384363e-06,
842
+ "loss": 0.3759,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.4857142857142857,
847
+ "grad_norm": 1.391691332136167,
848
+ "learning_rate": 2.6121620758762877e-06,
849
+ "loss": 0.3441,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.4897959183673469,
854
+ "grad_norm": 1.3532045632878618,
855
+ "learning_rate": 2.580128943929139e-06,
856
+ "loss": 0.3535,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.49387755102040815,
861
+ "grad_norm": 1.4356805788676563,
862
+ "learning_rate": 2.5480826369692178e-06,
863
+ "loss": 0.4291,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.49795918367346936,
868
+ "grad_norm": 1.3687857610653356,
869
+ "learning_rate": 2.516028424135028e-06,
870
+ "loss": 0.3604,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.5020408163265306,
875
+ "grad_norm": 1.8119273751395244,
876
+ "learning_rate": 2.4839715758649724e-06,
877
+ "loss": 0.4383,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.5061224489795918,
882
+ "grad_norm": 1.3462773894259714,
883
+ "learning_rate": 2.4519173630307826e-06,
884
+ "loss": 0.3736,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.5102040816326531,
889
+ "grad_norm": 1.4422701747154922,
890
+ "learning_rate": 2.4198710560708623e-06,
891
+ "loss": 0.3888,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.5142857142857142,
896
+ "grad_norm": 1.495287660532892,
897
+ "learning_rate": 2.3878379241237136e-06,
898
+ "loss": 0.4691,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.5183673469387755,
903
+ "grad_norm": 1.3283445734401957,
904
+ "learning_rate": 2.3558232341615645e-06,
905
+ "loss": 0.3468,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.5224489795918368,
910
+ "grad_norm": 1.3027240411363075,
911
+ "learning_rate": 2.323832250124365e-06,
912
+ "loss": 0.363,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.5265306122448979,
917
+ "grad_norm": 1.7568860790417562,
918
+ "learning_rate": 2.291870232054277e-06,
919
+ "loss": 0.4216,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.5306122448979592,
924
+ "grad_norm": 1.2906387015660221,
925
+ "learning_rate": 2.2599424352307958e-06,
926
+ "loss": 0.3625,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.5346938775510204,
931
+ "grad_norm": 1.3218624129799028,
932
+ "learning_rate": 2.228054109306673e-06,
933
+ "loss": 0.3443,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.5387755102040817,
938
+ "grad_norm": 1.3331826819132822,
939
+ "learning_rate": 2.196210497444749e-06,
940
+ "loss": 0.3434,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.5428571428571428,
945
+ "grad_norm": 1.4078471278275901,
946
+ "learning_rate": 2.1644168354558623e-06,
947
+ "loss": 0.3636,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.5469387755102041,
952
+ "grad_norm": 1.2800407658738853,
953
+ "learning_rate": 2.1326783509379555e-06,
954
+ "loss": 0.3202,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.5510204081632653,
959
+ "grad_norm": 1.4573670571072839,
960
+ "learning_rate": 2.1010002624165528e-06,
961
+ "loss": 0.3714,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.5551020408163265,
966
+ "grad_norm": 1.305405643622936,
967
+ "learning_rate": 2.069387778486703e-06,
968
+ "loss": 0.3404,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.5591836734693878,
973
+ "grad_norm": 1.3927062948866884,
974
+ "learning_rate": 2.037846096956578e-06,
975
+ "loss": 0.3986,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.563265306122449,
980
+ "grad_norm": 1.3678544360331244,
981
+ "learning_rate": 2.0063804039928324e-06,
982
+ "loss": 0.3611,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.5673469387755102,
987
+ "grad_norm": 1.4218382332395751,
988
+ "learning_rate": 1.9749958732678766e-06,
989
+ "loss": 0.3646,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.5714285714285714,
994
+ "grad_norm": 1.5559621424858547,
995
+ "learning_rate": 1.9436976651092143e-06,
996
+ "loss": 0.4041,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.5755102040816327,
1001
+ "grad_norm": 1.6870513054072005,
1002
+ "learning_rate": 1.912490925650962e-06,
1003
+ "loss": 0.4063,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.5795918367346938,
1008
+ "grad_norm": 1.2890623635335983,
1009
+ "learning_rate": 1.8813807859877147e-06,
1010
+ "loss": 0.3309,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.5836734693877551,
1015
+ "grad_norm": 1.4378926200378859,
1016
+ "learning_rate": 1.8503723613308683e-06,
1017
+ "loss": 0.3503,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.5877551020408164,
1022
+ "grad_norm": 1.558487239296629,
1023
+ "learning_rate": 1.8194707501675724e-06,
1024
+ "loss": 0.4039,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.5918367346938775,
1029
+ "grad_norm": 1.4373515362917595,
1030
+ "learning_rate": 1.7886810334224192e-06,
1031
+ "loss": 0.3243,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.5959183673469388,
1036
+ "grad_norm": 1.3695805878840897,
1037
+ "learning_rate": 1.7580082736220235e-06,
1038
+ "loss": 0.3556,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.6,
1043
+ "grad_norm": 1.3489323850388346,
1044
+ "learning_rate": 1.7274575140626318e-06,
1045
+ "loss": 0.3709,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.6040816326530613,
1050
+ "grad_norm": 1.3220370595287076,
1051
+ "learning_rate": 1.6970337779808862e-06,
1052
+ "loss": 0.3823,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.6081632653061224,
1057
+ "grad_norm": 1.3850874208932904,
1058
+ "learning_rate": 1.6667420677278962e-06,
1059
+ "loss": 0.3361,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.6122448979591837,
1064
+ "grad_norm": 1.618591496639687,
1065
+ "learning_rate": 1.6365873639467314e-06,
1066
+ "loss": 0.3898,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.6163265306122448,
1071
+ "grad_norm": 1.3082113355281526,
1072
+ "learning_rate": 1.6065746247534986e-06,
1073
+ "loss": 0.3587,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.6204081632653061,
1078
+ "grad_norm": 1.3600721985573652,
1079
+ "learning_rate": 1.5767087849221097e-06,
1080
+ "loss": 0.3503,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.6244897959183674,
1085
+ "grad_norm": 1.278780667709555,
1086
+ "learning_rate": 1.546994755072896e-06,
1087
+ "loss": 0.3321,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.6285714285714286,
1092
+ "grad_norm": 1.4249582307563469,
1093
+ "learning_rate": 1.5174374208651913e-06,
1094
+ "loss": 0.3473,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.6326530612244898,
1099
+ "grad_norm": 2.037827254313745,
1100
+ "learning_rate": 1.4880416421940155e-06,
1101
+ "loss": 0.3272,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.636734693877551,
1106
+ "grad_norm": 1.4171071671671724,
1107
+ "learning_rate": 1.4588122523910032e-06,
1108
+ "loss": 0.3195,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.6408163265306123,
1113
+ "grad_norm": 1.384302959320626,
1114
+ "learning_rate": 1.429754057429687e-06,
1115
+ "loss": 0.3838,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.6448979591836734,
1120
+ "grad_norm": 1.3101889387438383,
1121
+ "learning_rate": 1.400871835135295e-06,
1122
+ "loss": 0.3484,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.6489795918367347,
1127
+ "grad_norm": 1.3823309455100632,
1128
+ "learning_rate": 1.3721703343991634e-06,
1129
+ "loss": 0.3591,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.6530612244897959,
1134
+ "grad_norm": 1.4879774725691692,
1135
+ "learning_rate": 1.3436542743979125e-06,
1136
+ "loss": 0.3773,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.6571428571428571,
1141
+ "grad_norm": 1.4832807282548983,
1142
+ "learning_rate": 1.3153283438175036e-06,
1143
+ "loss": 0.3886,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.6612244897959184,
1148
+ "grad_norm": 1.358795698297107,
1149
+ "learning_rate": 1.2871972000823197e-06,
1150
+ "loss": 0.3387,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.6653061224489796,
1155
+ "grad_norm": 1.3581391000760228,
1156
+ "learning_rate": 1.2592654685893757e-06,
1157
+ "loss": 0.3483,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.6693877551020408,
1162
+ "grad_norm": 1.2982289131641926,
1163
+ "learning_rate": 1.231537741947795e-06,
1164
+ "loss": 0.3409,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.673469387755102,
1169
+ "grad_norm": 1.3848873461457987,
1170
+ "learning_rate": 1.2040185792236874e-06,
1171
+ "loss": 0.3353,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.6775510204081633,
1176
+ "grad_norm": 1.5912787786186957,
1177
+ "learning_rate": 1.1767125051905314e-06,
1178
+ "loss": 0.3724,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.6816326530612244,
1183
+ "grad_norm": 1.4308183750378232,
1184
+ "learning_rate": 1.1496240095852002e-06,
1185
+ "loss": 0.3725,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.6857142857142857,
1190
+ "grad_norm": 1.3570563385910772,
1191
+ "learning_rate": 1.122757546369744e-06,
1192
+ "loss": 0.3621,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.689795918367347,
1197
+ "grad_norm": 1.8417844358559656,
1198
+ "learning_rate": 1.0961175329990631e-06,
1199
+ "loss": 0.3666,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.6938775510204082,
1204
+ "grad_norm": 1.3499410996420529,
1205
+ "learning_rate": 1.0697083496945766e-06,
1206
+ "loss": 0.3692,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.6979591836734694,
1211
+ "grad_norm": 1.420569947454573,
1212
+ "learning_rate": 1.04353433872401e-06,
1213
+ "loss": 0.3458,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.7020408163265306,
1218
+ "grad_norm": 1.2402887891941334,
1219
+ "learning_rate": 1.0175998036874357e-06,
1220
+ "loss": 0.3446,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.7061224489795919,
1225
+ "grad_norm": 1.2606147384874788,
1226
+ "learning_rate": 9.91909008809659e-07,
1227
+ "loss": 0.2927,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.710204081632653,
1232
+ "grad_norm": 1.334457218668563,
1233
+ "learning_rate": 9.66466178239084e-07,
1234
+ "loss": 0.365,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.7142857142857143,
1239
+ "grad_norm": 1.4595428944665638,
1240
+ "learning_rate": 9.412754953531664e-07,
1241
+ "loss": 0.37,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.7183673469387755,
1246
+ "grad_norm": 1.5970216416171357,
1247
+ "learning_rate": 9.163411020705762e-07,
1248
+ "loss": 0.3765,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.7224489795918367,
1253
+ "grad_norm": 1.3077995038570127,
1254
+ "learning_rate": 8.916670981701656e-07,
1255
+ "loss": 0.3311,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.726530612244898,
1260
+ "grad_norm": 1.4473730293727218,
1261
+ "learning_rate": 8.672575406168782e-07,
1262
+ "loss": 0.3377,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.7306122448979592,
1267
+ "grad_norm": 1.2670538072222066,
1268
+ "learning_rate": 8.431164428946928e-07,
1269
+ "loss": 0.3043,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.7346938775510204,
1274
+ "grad_norm": 1.4947021551322752,
1275
+ "learning_rate": 8.192477743467078e-07,
1276
+ "loss": 0.3309,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.7387755102040816,
1281
+ "grad_norm": 1.340308412011245,
1282
+ "learning_rate": 7.956554595225017e-07,
1283
+ "loss": 0.326,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.7428571428571429,
1288
+ "grad_norm": 1.3313240918755387,
1289
+ "learning_rate": 7.723433775328385e-07,
1290
+ "loss": 0.3185,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.746938775510204,
1295
+ "grad_norm": 1.5258069598372948,
1296
+ "learning_rate": 7.493153614118634e-07,
1297
+ "loss": 0.4109,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.7510204081632653,
1302
+ "grad_norm": 1.6060529294344565,
1303
+ "learning_rate": 7.265751974868554e-07,
1304
+ "loss": 0.4135,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.7551020408163265,
1309
+ "grad_norm": 1.4452541973628832,
1310
+ "learning_rate": 7.041266247556814e-07,
1311
+ "loss": 0.4066,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.7591836734693878,
1316
+ "grad_norm": 1.3988724988261894,
1317
+ "learning_rate": 6.819733342720067e-07,
1318
+ "loss": 0.3616,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.763265306122449,
1323
+ "grad_norm": 1.964791421746527,
1324
+ "learning_rate": 6.601189685384127e-07,
1325
+ "loss": 0.4512,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.7673469387755102,
1330
+ "grad_norm": 1.4076718637049928,
1331
+ "learning_rate": 6.385671209074829e-07,
1332
+ "loss": 0.347,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.7714285714285715,
1337
+ "grad_norm": 1.3960439547754258,
1338
+ "learning_rate": 6.17321334990973e-07,
1339
+ "loss": 0.3564,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.7755102040816326,
1344
+ "grad_norm": 1.302654212495319,
1345
+ "learning_rate": 5.963851040771639e-07,
1346
+ "loss": 0.3215,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.7795918367346939,
1351
+ "grad_norm": 1.2530416793186747,
1352
+ "learning_rate": 5.757618705564849e-07,
1353
+ "loss": 0.3391,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.7836734693877551,
1358
+ "grad_norm": 1.2903245054104984,
1359
+ "learning_rate": 5.554550253555066e-07,
1360
+ "loss": 0.3166,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.7877551020408163,
1365
+ "grad_norm": 1.4320441334828347,
1366
+ "learning_rate": 5.354679073793942e-07,
1367
+ "loss": 0.3432,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.7918367346938775,
1372
+ "grad_norm": 1.525304275310309,
1373
+ "learning_rate": 5.158038029629195e-07,
1374
+ "loss": 0.3786,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.7959183673469388,
1379
+ "grad_norm": 1.388536933961604,
1380
+ "learning_rate": 4.964659453301088e-07,
1381
+ "loss": 0.3456,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.8,
1386
+ "grad_norm": 1.2189775989393807,
1387
+ "learning_rate": 4.774575140626317e-07,
1388
+ "loss": 0.2893,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.8040816326530612,
1393
+ "grad_norm": 1.4248638107242801,
1394
+ "learning_rate": 4.5878163457700327e-07,
1395
+ "loss": 0.3202,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.8081632653061225,
1400
+ "grad_norm": 1.4065663255244416,
1401
+ "learning_rate": 4.4044137761069584e-07,
1402
+ "loss": 0.3558,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.8122448979591836,
1407
+ "grad_norm": 1.3826876539403885,
1408
+ "learning_rate": 4.2243975871724017e-07,
1409
+ "loss": 0.3797,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.8163265306122449,
1414
+ "grad_norm": 1.2853876259186308,
1415
+ "learning_rate": 4.0477973777039854e-07,
1416
+ "loss": 0.315,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.8163265306122449,
1421
+ "eval_loss": 0.3877667188644409,
1422
+ "eval_runtime": 0.464,
1423
+ "eval_samples_per_second": 4.31,
1424
+ "eval_steps_per_second": 2.155,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.8204081632653061,
1429
+ "grad_norm": 1.3096896464876782,
1430
+ "learning_rate": 3.874642184774977e-07,
1431
+ "loss": 0.3517,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.8244897959183674,
1436
+ "grad_norm": 1.2945736981864886,
1437
+ "learning_rate": 3.7049604790198976e-07,
1438
+ "loss": 0.33,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.8285714285714286,
1443
+ "grad_norm": 1.2479126233725772,
1444
+ "learning_rate": 3.538780159953348e-07,
1445
+ "loss": 0.3047,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.8326530612244898,
1450
+ "grad_norm": 1.2923098663751,
1451
+ "learning_rate": 3.3761285513826627e-07,
1452
+ "loss": 0.3118,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.8367346938775511,
1457
+ "grad_norm": 1.2582959146052648,
1458
+ "learning_rate": 3.217032396915265e-07,
1459
+ "loss": 0.3093,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.8408163265306122,
1464
+ "grad_norm": 1.3965103540897894,
1465
+ "learning_rate": 3.06151785556143e-07,
1466
+ "loss": 0.3706,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.8448979591836735,
1471
+ "grad_norm": 1.329693099048807,
1472
+ "learning_rate": 2.9096104974331186e-07,
1473
+ "loss": 0.327,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.8489795918367347,
1478
+ "grad_norm": 1.4160123782021836,
1479
+ "learning_rate": 2.761335299539708e-07,
1480
+ "loss": 0.3858,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.8530612244897959,
1485
+ "grad_norm": 1.2862938015428163,
1486
+ "learning_rate": 2.6167166416811745e-07,
1487
+ "loss": 0.3489,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.8571428571428571,
1492
+ "grad_norm": 1.341158848028325,
1493
+ "learning_rate": 2.4757783024395244e-07,
1494
+ "loss": 0.2961,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.8612244897959184,
1499
+ "grad_norm": 1.3700377406970665,
1500
+ "learning_rate": 2.338543455269046e-07,
1501
+ "loss": 0.3677,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.8653061224489796,
1506
+ "grad_norm": 1.3204836939089972,
1507
+ "learning_rate": 2.205034664686076e-07,
1508
+ "loss": 0.3543,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.8693877551020408,
1513
+ "grad_norm": 1.3430262112006996,
1514
+ "learning_rate": 2.075273882558873e-07,
1515
+ "loss": 0.3204,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.8734693877551021,
1520
+ "grad_norm": 1.4629848680903754,
1521
+ "learning_rate": 1.9492824444982378e-07,
1522
+ "loss": 0.3593,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.8775510204081632,
1527
+ "grad_norm": 1.288148515205458,
1528
+ "learning_rate": 1.8270810663494591e-07,
1529
+ "loss": 0.3516,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.8816326530612245,
1534
+ "grad_norm": 1.3663652142091813,
1535
+ "learning_rate": 1.7086898407861486e-07,
1536
+ "loss": 0.3111,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.8857142857142857,
1541
+ "grad_norm": 1.408021272996467,
1542
+ "learning_rate": 1.59412823400657e-07,
1543
+ "loss": 0.3241,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.889795918367347,
1548
+ "grad_norm": 1.2795188625943397,
1549
+ "learning_rate": 1.483415082532938e-07,
1550
+ "loss": 0.3015,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.8938775510204081,
1555
+ "grad_norm": 1.4676037274571763,
1556
+ "learning_rate": 1.3765685901142718e-07,
1557
+ "loss": 0.3429,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.8979591836734694,
1562
+ "grad_norm": 1.4122359436677794,
1563
+ "learning_rate": 1.273606324733284e-07,
1564
+ "loss": 0.3424,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.9020408163265307,
1569
+ "grad_norm": 1.2842306768214384,
1570
+ "learning_rate": 1.1745452157178206e-07,
1571
+ "loss": 0.3288,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.9061224489795918,
1576
+ "grad_norm": 1.276465045159128,
1577
+ "learning_rate": 1.0794015509572819e-07,
1578
+ "loss": 0.3053,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.9102040816326531,
1583
+ "grad_norm": 1.5016119854373835,
1584
+ "learning_rate": 9.881909742245177e-08,
1585
+ "loss": 0.4205,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.9142857142857143,
1590
+ "grad_norm": 1.39579236750675,
1591
+ "learning_rate": 9.00928482603669e-08,
1592
+ "loss": 0.3369,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.9183673469387755,
1597
+ "grad_norm": 1.4912653601304233,
1598
+ "learning_rate": 8.176284240242638e-08,
1599
+ "loss": 0.3323,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.9224489795918367,
1604
+ "grad_norm": 1.5085011636238668,
1605
+ "learning_rate": 7.383044949021339e-08,
1606
+ "loss": 0.4046,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.926530612244898,
1611
+ "grad_norm": 1.292053843498188,
1612
+ "learning_rate": 6.629697378873839e-08,
1613
+ "loss": 0.3286,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.9306122448979591,
1618
+ "grad_norm": 1.4201829741178236,
1619
+ "learning_rate": 5.9163653971989754e-08,
1620
+ "loss": 0.3781,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.9346938775510204,
1625
+ "grad_norm": 1.313299474014384,
1626
+ "learning_rate": 5.2431662919267825e-08,
1627
+ "loss": 0.3199,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.9387755102040817,
1632
+ "grad_norm": 1.2119999609455956,
1633
+ "learning_rate": 4.61021075223364e-08,
1634
+ "loss": 0.2983,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.9428571428571428,
1639
+ "grad_norm": 1.4645880609031143,
1640
+ "learning_rate": 4.017602850342584e-08,
1641
+ "loss": 0.4382,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.9469387755102041,
1646
+ "grad_norm": 1.193649605180574,
1647
+ "learning_rate": 3.4654400244112654e-08,
1648
+ "loss": 0.3189,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.9510204081632653,
1653
+ "grad_norm": 1.3181152826792921,
1654
+ "learning_rate": 2.9538130625110796e-08,
1655
+ "loss": 0.3415,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.9551020408163265,
1660
+ "grad_norm": 1.3237217153988747,
1661
+ "learning_rate": 2.4828060876995462e-08,
1662
+ "loss": 0.3002,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.9591836734693877,
1667
+ "grad_norm": 1.3729661179078707,
1668
+ "learning_rate": 2.052496544188487e-08,
1669
+ "loss": 0.3414,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.963265306122449,
1674
+ "grad_norm": 1.4065518187997124,
1675
+ "learning_rate": 1.6629551846104874e-08,
1676
+ "loss": 0.3561,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.9673469387755103,
1681
+ "grad_norm": 1.4398595664847205,
1682
+ "learning_rate": 1.3142460583856487e-08,
1683
+ "loss": 0.3677,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.9714285714285714,
1688
+ "grad_norm": 1.3477155899078384,
1689
+ "learning_rate": 1.006426501190233e-08,
1690
+ "loss": 0.3691,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.9755102040816327,
1695
+ "grad_norm": 1.2858812368804982,
1696
+ "learning_rate": 7.3954712552953835e-09,
1697
+ "loss": 0.3313,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.9795918367346939,
1702
+ "grad_norm": 1.302679939937873,
1703
+ "learning_rate": 5.136518124159162e-09,
1704
+ "loss": 0.3224,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.9836734693877551,
1709
+ "grad_norm": 1.347071089177764,
1710
+ "learning_rate": 3.287777041539042e-09,
1711
+ "loss": 0.3561,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.9877551020408163,
1716
+ "grad_norm": 1.3736530877098208,
1717
+ "learning_rate": 1.8495519823308329e-09,
1718
+ "loss": 0.3371,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.9918367346938776,
1723
+ "grad_norm": 1.302883849222916,
1724
+ "learning_rate": 8.220794233004814e-10,
1725
+ "loss": 0.3295,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.9959183673469387,
1730
+ "grad_norm": 1.5676128450479734,
1731
+ "learning_rate": 2.0552830420184077e-10,
1732
+ "loss": 0.4688,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 1.0,
1737
+ "grad_norm": 1.4943203596503118,
1738
+ "learning_rate": 0.0,
1739
+ "loss": 0.3356,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 1.0,
1744
+ "step": 245,
1745
+ "total_flos": 24710676480000.0,
1746
+ "train_loss": 0.39906880940709794,
1747
+ "train_runtime": 467.2882,
1748
+ "train_samples_per_second": 4.182,
1749
+ "train_steps_per_second": 0.524
1750
+ }
1751
+ ],
1752
+ "logging_steps": 1,
1753
+ "max_steps": 245,
1754
+ "num_input_tokens_seen": 0,
1755
+ "num_train_epochs": 1,
1756
+ "save_steps": 2000000,
1757
+ "stateful_callbacks": {
1758
+ "TrainerControl": {
1759
+ "args": {
1760
+ "should_epoch_stop": false,
1761
+ "should_evaluate": false,
1762
+ "should_log": false,
1763
+ "should_save": true,
1764
+ "should_training_stop": true
1765
+ },
1766
+ "attributes": {}
1767
+ }
1768
+ },
1769
+ "total_flos": 24710676480000.0,
1770
+ "train_batch_size": 1,
1771
+ "trial_name": null,
1772
+ "trial_params": null
1773
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d401357d9009d0e0b340c1ac090a85f1b98e8d4bf62239df5e8254ad155c5b7a
3
+ size 7160
training_eval_loss.png ADDED
training_loss.png ADDED