yihanwang617 commited on
Commit
67f1575
·
verified ·
1 Parent(s): 9791755

Model save

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B
3
+ library_name: peft
4
+ license: llama3
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: llama-3-qlora-wizard-processed-indicator-0.6
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
+ # llama-3-qlora-wizard-processed-indicator-0.6
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6736
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: 0.0002
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 64
48
+ - total_eval_batch_size: 16
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 0.7109 | 0.1842 | 200 | 0.7065 |
59
+ | 0.7185 | 0.3683 | 400 | 0.6904 |
60
+ | 0.7062 | 0.5525 | 600 | 0.6819 |
61
+ | 0.6629 | 0.7366 | 800 | 0.6758 |
62
+ | 0.6769 | 0.9208 | 1000 | 0.6736 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - PEFT 0.12.0
68
+ - Transformers 4.40.1
69
+ - Pytorch 2.4.0+cu121
70
+ - Datasets 2.20.0
71
+ - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "v_proj",
24
  "up_proj",
 
25
  "k_proj",
26
- "q_proj",
27
- "gate_proj",
28
- "o_proj",
29
- "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
+ "gate_proj",
25
  "v_proj",
26
  "up_proj",
27
+ "down_proj",
28
  "k_proj",
29
+ "q_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1cf4958d339f59c1120f280357f65ecbcdc429e01b4cf5acb0c3ae80abef42
3
  size 2185327392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ef0ef57c66cafbf3d3bbb9f4265f64086c0766e426ceebc67d58d57c0cdb44
3
  size 2185327392
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 4801486812086272.0,
4
+ "train_loss": 0.7253576234998405,
5
+ "train_runtime": 22925.9932,
6
+ "train_samples": 69499,
7
+ "train_samples_per_second": 3.031,
8
+ "train_steps_per_second": 0.047
9
+ }
runs/Sep06_16-22-59_nova.cs.ucla.edu/events.out.tfevents.1725665178.nova.cs.ucla.edu.2404961.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a0cb46bdbdc313b989fca457196996ffb1ab7bacb558a8b0e3d924ebd50b44e
3
- size 50931
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95cc654421c3f691d75dd2b1d1b43e3cbf202519a6b242553335230d0094b69
3
+ size 52551
runs/Sep06_22-01-38_nova.cs.ucla.edu/events.out.tfevents.1725685482.nova.cs.ucla.edu.2653377.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:308264da904ae39f967ed1f9eeddbc3c71f9fa44649a9af761707566a9ff59f1
3
- size 9439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9489445a0dcffaa6507d796c0bf4e9cc05b28bb98c668c470850fb348e7fde6
3
+ size 10494
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 4801486812086272.0,
4
+ "train_loss": 0.7253576234998405,
5
+ "train_runtime": 22925.9932,
6
+ "train_samples": 69499,
7
+ "train_samples_per_second": 3.031,
8
+ "train_steps_per_second": 0.047
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1596 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 200,
6
+ "global_step": 1086,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0009208103130755065,
13
+ "grad_norm": 0.7104283979721944,
14
+ "learning_rate": 1.8348623853211011e-06,
15
+ "loss": 1.2184,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004604051565377533,
20
+ "grad_norm": 0.8484084058142851,
21
+ "learning_rate": 9.174311926605506e-06,
22
+ "loss": 1.2345,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.009208103130755065,
27
+ "grad_norm": 0.8895650483641482,
28
+ "learning_rate": 1.834862385321101e-05,
29
+ "loss": 1.2996,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.013812154696132596,
34
+ "grad_norm": 0.6693826221356033,
35
+ "learning_rate": 2.7522935779816515e-05,
36
+ "loss": 1.2409,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.01841620626151013,
41
+ "grad_norm": 0.9775039809987707,
42
+ "learning_rate": 3.669724770642202e-05,
43
+ "loss": 1.078,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.02302025782688766,
48
+ "grad_norm": 0.42561125364219876,
49
+ "learning_rate": 4.587155963302753e-05,
50
+ "loss": 0.9796,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.027624309392265192,
55
+ "grad_norm": 0.20515777384298603,
56
+ "learning_rate": 5.504587155963303e-05,
57
+ "loss": 0.8728,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.03222836095764273,
62
+ "grad_norm": 0.21277732125436763,
63
+ "learning_rate": 6.422018348623854e-05,
64
+ "loss": 0.8742,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.03683241252302026,
69
+ "grad_norm": 0.2807596133606811,
70
+ "learning_rate": 7.339449541284404e-05,
71
+ "loss": 0.8226,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.04143646408839779,
76
+ "grad_norm": 0.2462315157718494,
77
+ "learning_rate": 8.256880733944955e-05,
78
+ "loss": 0.8238,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.04604051565377532,
83
+ "grad_norm": 0.1796423907240695,
84
+ "learning_rate": 9.174311926605506e-05,
85
+ "loss": 0.8043,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05064456721915286,
90
+ "grad_norm": 0.16102348645765954,
91
+ "learning_rate": 0.00010091743119266055,
92
+ "loss": 0.7908,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.055248618784530384,
97
+ "grad_norm": 0.1468812473488326,
98
+ "learning_rate": 0.00011009174311926606,
99
+ "loss": 0.7798,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.05985267034990792,
104
+ "grad_norm": 0.15243943821399936,
105
+ "learning_rate": 0.00011926605504587157,
106
+ "loss": 0.7939,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.06445672191528545,
111
+ "grad_norm": 0.16911773454140264,
112
+ "learning_rate": 0.00012844036697247707,
113
+ "loss": 0.7692,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.06906077348066299,
118
+ "grad_norm": 0.14029887618581424,
119
+ "learning_rate": 0.00013761467889908258,
120
+ "loss": 0.7702,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.07366482504604052,
125
+ "grad_norm": 0.15991589862519767,
126
+ "learning_rate": 0.0001467889908256881,
127
+ "loss": 0.7801,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.07826887661141804,
132
+ "grad_norm": 0.16836933389270248,
133
+ "learning_rate": 0.0001559633027522936,
134
+ "loss": 0.7493,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.08287292817679558,
139
+ "grad_norm": 0.17161343155107908,
140
+ "learning_rate": 0.0001651376146788991,
141
+ "loss": 0.752,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.08747697974217311,
146
+ "grad_norm": 0.17139003055306476,
147
+ "learning_rate": 0.00017431192660550458,
148
+ "loss": 0.7504,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.09208103130755065,
153
+ "grad_norm": 0.14118381221233112,
154
+ "learning_rate": 0.00018348623853211012,
155
+ "loss": 0.7474,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.09668508287292818,
160
+ "grad_norm": 0.15274245520687557,
161
+ "learning_rate": 0.0001926605504587156,
162
+ "loss": 0.7153,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.10128913443830571,
167
+ "grad_norm": 0.17243376201491117,
168
+ "learning_rate": 0.00019999948301225543,
169
+ "loss": 0.7418,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.10589318600368323,
174
+ "grad_norm": 0.15501917072069255,
175
+ "learning_rate": 0.00019998138900246913,
176
+ "loss": 0.7471,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.11049723756906077,
181
+ "grad_norm": 0.1721566405839237,
182
+ "learning_rate": 0.00019993745095073183,
183
+ "loss": 0.7453,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.1151012891344383,
188
+ "grad_norm": 0.13679964856454155,
189
+ "learning_rate": 0.00019986768021452574,
190
+ "loss": 0.7228,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.11970534069981584,
195
+ "grad_norm": 0.14703324544205662,
196
+ "learning_rate": 0.00019977209482878574,
197
+ "loss": 0.7124,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.12430939226519337,
202
+ "grad_norm": 0.18865400963921064,
203
+ "learning_rate": 0.00019965071950123732,
204
+ "loss": 0.7536,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1289134438305709,
209
+ "grad_norm": 0.1474544520231936,
210
+ "learning_rate": 0.00019950358560601013,
211
+ "loss": 0.7429,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.13351749539594843,
216
+ "grad_norm": 0.13523126598394036,
217
+ "learning_rate": 0.00019933073117552795,
218
+ "loss": 0.7267,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.13812154696132597,
223
+ "grad_norm": 0.146238565087472,
224
+ "learning_rate": 0.00019913220089067793,
225
+ "loss": 0.7749,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.1427255985267035,
230
+ "grad_norm": 0.1550423764417148,
231
+ "learning_rate": 0.00019890804606926087,
232
+ "loss": 0.7329,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.14732965009208104,
237
+ "grad_norm": 0.1591980721619053,
238
+ "learning_rate": 0.00019865832465272635,
239
+ "loss": 0.7534,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.15193370165745856,
244
+ "grad_norm": 0.1531186776106742,
245
+ "learning_rate": 0.00019838310119119545,
246
+ "loss": 0.756,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.15653775322283608,
251
+ "grad_norm": 0.1476816081597602,
252
+ "learning_rate": 0.0001980824468267753,
253
+ "loss": 0.7489,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.16114180478821363,
258
+ "grad_norm": 0.14795132619266863,
259
+ "learning_rate": 0.00019775643927516954,
260
+ "loss": 0.7209,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.16574585635359115,
265
+ "grad_norm": 0.14679273124596579,
266
+ "learning_rate": 0.00019740516280559005,
267
+ "loss": 0.7296,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.1703499079189687,
272
+ "grad_norm": 0.14120244970365975,
273
+ "learning_rate": 0.00019702870821897386,
274
+ "loss": 0.7512,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.17495395948434622,
279
+ "grad_norm": 0.1399532146516525,
280
+ "learning_rate": 0.00019662717282451249,
281
+ "loss": 0.7091,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.17955801104972377,
286
+ "grad_norm": 0.1472244949078579,
287
+ "learning_rate": 0.00019620066041449853,
288
+ "loss": 0.7235,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.1841620626151013,
293
+ "grad_norm": 0.13348485928094997,
294
+ "learning_rate": 0.0001957492812374965,
295
+ "loss": 0.7109,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.1841620626151013,
300
+ "eval_loss": 0.7064515352249146,
301
+ "eval_runtime": 48.9511,
302
+ "eval_samples_per_second": 10.214,
303
+ "eval_steps_per_second": 0.654,
304
+ "step": 200
305
+ },
306
+ {
307
+ "epoch": 0.1887661141804788,
308
+ "grad_norm": 0.12975499369978807,
309
+ "learning_rate": 0.00019527315196984487,
310
+ "loss": 0.7103,
311
+ "step": 205
312
+ },
313
+ {
314
+ "epoch": 0.19337016574585636,
315
+ "grad_norm": 0.1309790778507949,
316
+ "learning_rate": 0.00019477239568549667,
317
+ "loss": 0.7166,
318
+ "step": 210
319
+ },
320
+ {
321
+ "epoch": 0.19797421731123388,
322
+ "grad_norm": 0.13709065108741178,
323
+ "learning_rate": 0.00019424714182420604,
324
+ "loss": 0.7043,
325
+ "step": 215
326
+ },
327
+ {
328
+ "epoch": 0.20257826887661143,
329
+ "grad_norm": 0.13342648155684383,
330
+ "learning_rate": 0.00019369752615806988,
331
+ "loss": 0.7136,
332
+ "step": 220
333
+ },
334
+ {
335
+ "epoch": 0.20718232044198895,
336
+ "grad_norm": 0.13844474906898738,
337
+ "learning_rate": 0.00019312369075643194,
338
+ "loss": 0.7207,
339
+ "step": 225
340
+ },
341
+ {
342
+ "epoch": 0.21178637200736647,
343
+ "grad_norm": 0.14186684102196156,
344
+ "learning_rate": 0.00019252578394915988,
345
+ "loss": 0.7255,
346
+ "step": 230
347
+ },
348
+ {
349
+ "epoch": 0.21639042357274402,
350
+ "grad_norm": 0.15866211011849904,
351
+ "learning_rate": 0.0001919039602883035,
352
+ "loss": 0.7223,
353
+ "step": 235
354
+ },
355
+ {
356
+ "epoch": 0.22099447513812154,
357
+ "grad_norm": 0.1314674917628441,
358
+ "learning_rate": 0.00019125838050814472,
359
+ "loss": 0.7228,
360
+ "step": 240
361
+ },
362
+ {
363
+ "epoch": 0.22559852670349909,
364
+ "grad_norm": 0.14491106611651047,
365
+ "learning_rate": 0.00019058921148364994,
366
+ "loss": 0.7261,
367
+ "step": 245
368
+ },
369
+ {
370
+ "epoch": 0.2302025782688766,
371
+ "grad_norm": 0.12821922589500195,
372
+ "learning_rate": 0.00018989662618733446,
373
+ "loss": 0.7071,
374
+ "step": 250
375
+ },
376
+ {
377
+ "epoch": 0.23480662983425415,
378
+ "grad_norm": 0.14571212342587975,
379
+ "learning_rate": 0.00018918080364455122,
380
+ "loss": 0.7016,
381
+ "step": 255
382
+ },
383
+ {
384
+ "epoch": 0.23941068139963168,
385
+ "grad_norm": 0.13772160137757872,
386
+ "learning_rate": 0.0001884419288872147,
387
+ "loss": 0.7069,
388
+ "step": 260
389
+ },
390
+ {
391
+ "epoch": 0.2440147329650092,
392
+ "grad_norm": 0.1423677034382106,
393
+ "learning_rate": 0.00018768019290597252,
394
+ "loss": 0.7294,
395
+ "step": 265
396
+ },
397
+ {
398
+ "epoch": 0.24861878453038674,
399
+ "grad_norm": 0.12203724600652281,
400
+ "learning_rate": 0.0001868957926008362,
401
+ "loss": 0.7168,
402
+ "step": 270
403
+ },
404
+ {
405
+ "epoch": 0.2532228360957643,
406
+ "grad_norm": 0.1329347877570805,
407
+ "learning_rate": 0.00018608893073028505,
408
+ "loss": 0.7026,
409
+ "step": 275
410
+ },
411
+ {
412
+ "epoch": 0.2578268876611418,
413
+ "grad_norm": 0.13186384109645674,
414
+ "learning_rate": 0.00018525981585885536,
415
+ "loss": 0.7082,
416
+ "step": 280
417
+ },
418
+ {
419
+ "epoch": 0.26243093922651933,
420
+ "grad_norm": 0.14256872075438773,
421
+ "learning_rate": 0.00018440866230322878,
422
+ "loss": 0.6917,
423
+ "step": 285
424
+ },
425
+ {
426
+ "epoch": 0.26703499079189685,
427
+ "grad_norm": 0.14428503648361754,
428
+ "learning_rate": 0.00018353569007683394,
429
+ "loss": 0.719,
430
+ "step": 290
431
+ },
432
+ {
433
+ "epoch": 0.2716390423572744,
434
+ "grad_norm": 0.1820352962113873,
435
+ "learning_rate": 0.00018264112483297565,
436
+ "loss": 0.7264,
437
+ "step": 295
438
+ },
439
+ {
440
+ "epoch": 0.27624309392265195,
441
+ "grad_norm": 0.15797994447204652,
442
+ "learning_rate": 0.00018172519780650594,
443
+ "loss": 0.7195,
444
+ "step": 300
445
+ },
446
+ {
447
+ "epoch": 0.28084714548802947,
448
+ "grad_norm": 0.13313017408023753,
449
+ "learning_rate": 0.00018078814575405244,
450
+ "loss": 0.7425,
451
+ "step": 305
452
+ },
453
+ {
454
+ "epoch": 0.285451197053407,
455
+ "grad_norm": 0.13520681133489493,
456
+ "learning_rate": 0.00017983021089281983,
457
+ "loss": 0.707,
458
+ "step": 310
459
+ },
460
+ {
461
+ "epoch": 0.2900552486187845,
462
+ "grad_norm": 0.12245549217896762,
463
+ "learning_rate": 0.0001788516408379791,
464
+ "loss": 0.7154,
465
+ "step": 315
466
+ },
467
+ {
468
+ "epoch": 0.2946593001841621,
469
+ "grad_norm": 0.12748362531526,
470
+ "learning_rate": 0.0001778526885386621,
471
+ "loss": 0.7197,
472
+ "step": 320
473
+ },
474
+ {
475
+ "epoch": 0.2992633517495396,
476
+ "grad_norm": 0.11117223964124032,
477
+ "learning_rate": 0.00017683361221257707,
478
+ "loss": 0.6973,
479
+ "step": 325
480
+ },
481
+ {
482
+ "epoch": 0.30386740331491713,
483
+ "grad_norm": 0.1289936719815313,
484
+ "learning_rate": 0.0001757946752792622,
485
+ "loss": 0.7247,
486
+ "step": 330
487
+ },
488
+ {
489
+ "epoch": 0.30847145488029465,
490
+ "grad_norm": 0.16488859196213657,
491
+ "learning_rate": 0.00017473614629199486,
492
+ "loss": 0.7286,
493
+ "step": 335
494
+ },
495
+ {
496
+ "epoch": 0.31307550644567217,
497
+ "grad_norm": 0.14470083977942239,
498
+ "learning_rate": 0.00017365829886837353,
499
+ "loss": 0.7343,
500
+ "step": 340
501
+ },
502
+ {
503
+ "epoch": 0.31767955801104975,
504
+ "grad_norm": 0.13447366414444684,
505
+ "learning_rate": 0.00017256141161959085,
506
+ "loss": 0.7255,
507
+ "step": 345
508
+ },
509
+ {
510
+ "epoch": 0.32228360957642727,
511
+ "grad_norm": 0.1217662376207493,
512
+ "learning_rate": 0.00017144576807841583,
513
+ "loss": 0.724,
514
+ "step": 350
515
+ },
516
+ {
517
+ "epoch": 0.3268876611418048,
518
+ "grad_norm": 0.15300308488915879,
519
+ "learning_rate": 0.00017031165662590388,
520
+ "loss": 0.7267,
521
+ "step": 355
522
+ },
523
+ {
524
+ "epoch": 0.3314917127071823,
525
+ "grad_norm": 0.13907462570860107,
526
+ "learning_rate": 0.0001691593704168536,
527
+ "loss": 0.748,
528
+ "step": 360
529
+ },
530
+ {
531
+ "epoch": 0.3360957642725598,
532
+ "grad_norm": 0.13780875633005546,
533
+ "learning_rate": 0.0001679892073040296,
534
+ "loss": 0.7262,
535
+ "step": 365
536
+ },
537
+ {
538
+ "epoch": 0.3406998158379374,
539
+ "grad_norm": 0.1305755908910725,
540
+ "learning_rate": 0.00016680146976117105,
541
+ "loss": 0.7155,
542
+ "step": 370
543
+ },
544
+ {
545
+ "epoch": 0.3453038674033149,
546
+ "grad_norm": 0.14568215090440456,
547
+ "learning_rate": 0.00016559646480480562,
548
+ "loss": 0.7223,
549
+ "step": 375
550
+ },
551
+ {
552
+ "epoch": 0.34990791896869244,
553
+ "grad_norm": 0.12857349185078817,
554
+ "learning_rate": 0.00016437450391488926,
555
+ "loss": 0.7336,
556
+ "step": 380
557
+ },
558
+ {
559
+ "epoch": 0.35451197053406996,
560
+ "grad_norm": 0.11784320830005238,
561
+ "learning_rate": 0.00016313590295429224,
562
+ "loss": 0.6889,
563
+ "step": 385
564
+ },
565
+ {
566
+ "epoch": 0.35911602209944754,
567
+ "grad_norm": 0.13646526167574166,
568
+ "learning_rate": 0.00016188098208715218,
569
+ "loss": 0.7192,
570
+ "step": 390
571
+ },
572
+ {
573
+ "epoch": 0.36372007366482506,
574
+ "grad_norm": 0.12175101806984481,
575
+ "learning_rate": 0.00016061006569611524,
576
+ "loss": 0.6836,
577
+ "step": 395
578
+ },
579
+ {
580
+ "epoch": 0.3683241252302026,
581
+ "grad_norm": 0.13758905451063172,
582
+ "learning_rate": 0.00015932348229848702,
583
+ "loss": 0.7185,
584
+ "step": 400
585
+ },
586
+ {
587
+ "epoch": 0.3683241252302026,
588
+ "eval_loss": 0.6904310584068298,
589
+ "eval_runtime": 47.8076,
590
+ "eval_samples_per_second": 10.459,
591
+ "eval_steps_per_second": 0.669,
592
+ "step": 400
593
+ },
594
+ {
595
+ "epoch": 0.3729281767955801,
596
+ "grad_norm": 0.11922226680398379,
597
+ "learning_rate": 0.00015802156446131463,
598
+ "loss": 0.7108,
599
+ "step": 405
600
+ },
601
+ {
602
+ "epoch": 0.3775322283609576,
603
+ "grad_norm": 0.12914369421847746,
604
+ "learning_rate": 0.0001567046487154218,
605
+ "loss": 0.7297,
606
+ "step": 410
607
+ },
608
+ {
609
+ "epoch": 0.3821362799263352,
610
+ "grad_norm": 0.163588935842005,
611
+ "learning_rate": 0.0001553730754684196,
612
+ "loss": 0.7286,
613
+ "step": 415
614
+ },
615
+ {
616
+ "epoch": 0.3867403314917127,
617
+ "grad_norm": 0.1305481480361055,
618
+ "learning_rate": 0.000154027188916715,
619
+ "loss": 0.7083,
620
+ "step": 420
621
+ },
622
+ {
623
+ "epoch": 0.39134438305709024,
624
+ "grad_norm": 0.13075746937102734,
625
+ "learning_rate": 0.00015266733695653998,
626
+ "loss": 0.7022,
627
+ "step": 425
628
+ },
629
+ {
630
+ "epoch": 0.39594843462246776,
631
+ "grad_norm": 0.13867395016440975,
632
+ "learning_rate": 0.0001512938710940244,
633
+ "loss": 0.6883,
634
+ "step": 430
635
+ },
636
+ {
637
+ "epoch": 0.4005524861878453,
638
+ "grad_norm": 0.1468540519744832,
639
+ "learning_rate": 0.00014990714635433567,
640
+ "loss": 0.724,
641
+ "step": 435
642
+ },
643
+ {
644
+ "epoch": 0.40515653775322286,
645
+ "grad_norm": 0.1306098517144093,
646
+ "learning_rate": 0.00014850752118990884,
647
+ "loss": 0.7063,
648
+ "step": 440
649
+ },
650
+ {
651
+ "epoch": 0.4097605893186004,
652
+ "grad_norm": 0.1424067979705426,
653
+ "learning_rate": 0.00014709535738779075,
654
+ "loss": 0.7402,
655
+ "step": 445
656
+ },
657
+ {
658
+ "epoch": 0.4143646408839779,
659
+ "grad_norm": 0.1407997721241163,
660
+ "learning_rate": 0.00014567101997612215,
661
+ "loss": 0.7006,
662
+ "step": 450
663
+ },
664
+ {
665
+ "epoch": 0.4189686924493554,
666
+ "grad_norm": 0.14729031365921527,
667
+ "learning_rate": 0.00014423487712978238,
668
+ "loss": 0.7024,
669
+ "step": 455
670
+ },
671
+ {
672
+ "epoch": 0.42357274401473294,
673
+ "grad_norm": 0.13260028024156117,
674
+ "learning_rate": 0.00014278730007521998,
675
+ "loss": 0.7173,
676
+ "step": 460
677
+ },
678
+ {
679
+ "epoch": 0.4281767955801105,
680
+ "grad_norm": 0.1335675383386336,
681
+ "learning_rate": 0.00014132866299449524,
682
+ "loss": 0.7289,
683
+ "step": 465
684
+ },
685
+ {
686
+ "epoch": 0.43278084714548803,
687
+ "grad_norm": 0.14637775224173455,
688
+ "learning_rate": 0.00013985934292855826,
689
+ "loss": 0.7005,
690
+ "step": 470
691
+ },
692
+ {
693
+ "epoch": 0.43738489871086556,
694
+ "grad_norm": 0.1502047175694278,
695
+ "learning_rate": 0.00013837971967978836,
696
+ "loss": 0.7004,
697
+ "step": 475
698
+ },
699
+ {
700
+ "epoch": 0.4419889502762431,
701
+ "grad_norm": 0.14633484532534424,
702
+ "learning_rate": 0.00013689017571381928,
703
+ "loss": 0.7288,
704
+ "step": 480
705
+ },
706
+ {
707
+ "epoch": 0.44659300184162065,
708
+ "grad_norm": 0.13826365436143537,
709
+ "learning_rate": 0.00013539109606067643,
710
+ "loss": 0.7085,
711
+ "step": 485
712
+ },
713
+ {
714
+ "epoch": 0.45119705340699817,
715
+ "grad_norm": 0.14385098441490782,
716
+ "learning_rate": 0.00013388286821525085,
717
+ "loss": 0.6974,
718
+ "step": 490
719
+ },
720
+ {
721
+ "epoch": 0.4558011049723757,
722
+ "grad_norm": 0.13011880817111474,
723
+ "learning_rate": 0.00013236588203713646,
724
+ "loss": 0.7041,
725
+ "step": 495
726
+ },
727
+ {
728
+ "epoch": 0.4604051565377532,
729
+ "grad_norm": 0.12462262006306969,
730
+ "learning_rate": 0.0001308405296498556,
731
+ "loss": 0.6962,
732
+ "step": 500
733
+ },
734
+ {
735
+ "epoch": 0.46500920810313073,
736
+ "grad_norm": 0.12244444903136163,
737
+ "learning_rate": 0.00012930720533949966,
738
+ "loss": 0.6999,
739
+ "step": 505
740
+ },
741
+ {
742
+ "epoch": 0.4696132596685083,
743
+ "grad_norm": 0.1339305914859919,
744
+ "learning_rate": 0.00012776630545281088,
745
+ "loss": 0.6806,
746
+ "step": 510
747
+ },
748
+ {
749
+ "epoch": 0.47421731123388583,
750
+ "grad_norm": 0.13980664973687393,
751
+ "learning_rate": 0.00012621822829473074,
752
+ "loss": 0.7394,
753
+ "step": 515
754
+ },
755
+ {
756
+ "epoch": 0.47882136279926335,
757
+ "grad_norm": 0.16365863143826853,
758
+ "learning_rate": 0.00012466337402544333,
759
+ "loss": 0.7279,
760
+ "step": 520
761
+ },
762
+ {
763
+ "epoch": 0.48342541436464087,
764
+ "grad_norm": 0.1335430922734083,
765
+ "learning_rate": 0.00012310214455693808,
766
+ "loss": 0.7034,
767
+ "step": 525
768
+ },
769
+ {
770
+ "epoch": 0.4880294659300184,
771
+ "grad_norm": 0.14433559304424956,
772
+ "learning_rate": 0.0001215349434491203,
773
+ "loss": 0.6937,
774
+ "step": 530
775
+ },
776
+ {
777
+ "epoch": 0.49263351749539597,
778
+ "grad_norm": 0.132024243038777,
779
+ "learning_rate": 0.00011996217580549556,
780
+ "loss": 0.6986,
781
+ "step": 535
782
+ },
783
+ {
784
+ "epoch": 0.4972375690607735,
785
+ "grad_norm": 0.13633158247507002,
786
+ "learning_rate": 0.00011838424816845506,
787
+ "loss": 0.7044,
788
+ "step": 540
789
+ },
790
+ {
791
+ "epoch": 0.501841620626151,
792
+ "grad_norm": 0.12135498656651347,
793
+ "learning_rate": 0.0001168015684141891,
794
+ "loss": 0.7231,
795
+ "step": 545
796
+ },
797
+ {
798
+ "epoch": 0.5064456721915286,
799
+ "grad_norm": 0.1381176811216971,
800
+ "learning_rate": 0.0001152145456472558,
801
+ "loss": 0.6942,
802
+ "step": 550
803
+ },
804
+ {
805
+ "epoch": 0.511049723756906,
806
+ "grad_norm": 0.14462125066523807,
807
+ "learning_rate": 0.00011362359009483212,
808
+ "loss": 0.7,
809
+ "step": 555
810
+ },
811
+ {
812
+ "epoch": 0.5156537753222836,
813
+ "grad_norm": 0.1401876774896849,
814
+ "learning_rate": 0.00011202911300067507,
815
+ "loss": 0.6917,
816
+ "step": 560
817
+ },
818
+ {
819
+ "epoch": 0.5202578268876611,
820
+ "grad_norm": 0.12761995189511605,
821
+ "learning_rate": 0.00011043152651881971,
822
+ "loss": 0.6913,
823
+ "step": 565
824
+ },
825
+ {
826
+ "epoch": 0.5248618784530387,
827
+ "grad_norm": 0.1309083720987428,
828
+ "learning_rate": 0.0001088312436070422,
829
+ "loss": 0.7039,
830
+ "step": 570
831
+ },
832
+ {
833
+ "epoch": 0.5294659300184162,
834
+ "grad_norm": 0.13969770628383765,
835
+ "learning_rate": 0.00010722867792011486,
836
+ "loss": 0.7138,
837
+ "step": 575
838
+ },
839
+ {
840
+ "epoch": 0.5340699815837937,
841
+ "grad_norm": 0.12065461537026531,
842
+ "learning_rate": 0.0001056242437028812,
843
+ "loss": 0.7012,
844
+ "step": 580
845
+ },
846
+ {
847
+ "epoch": 0.5386740331491713,
848
+ "grad_norm": 0.1403328333527622,
849
+ "learning_rate": 0.00010401835568317842,
850
+ "loss": 0.7107,
851
+ "step": 585
852
+ },
853
+ {
854
+ "epoch": 0.5432780847145487,
855
+ "grad_norm": 0.1524065503450793,
856
+ "learning_rate": 0.00010241142896463491,
857
+ "loss": 0.7253,
858
+ "step": 590
859
+ },
860
+ {
861
+ "epoch": 0.5478821362799263,
862
+ "grad_norm": 0.1459506865219953,
863
+ "learning_rate": 0.00010080387891937084,
864
+ "loss": 0.7164,
865
+ "step": 595
866
+ },
867
+ {
868
+ "epoch": 0.5524861878453039,
869
+ "grad_norm": 0.13249474415125184,
870
+ "learning_rate": 9.91961210806292e-05,
871
+ "loss": 0.7062,
872
+ "step": 600
873
+ },
874
+ {
875
+ "epoch": 0.5524861878453039,
876
+ "eval_loss": 0.681869387626648,
877
+ "eval_runtime": 47.8405,
878
+ "eval_samples_per_second": 10.451,
879
+ "eval_steps_per_second": 0.669,
880
+ "step": 600
881
+ },
882
+ {
883
+ "epoch": 0.5570902394106814,
884
+ "grad_norm": 0.12788937438752834,
885
+ "learning_rate": 9.758857103536513e-05,
886
+ "loss": 0.7099,
887
+ "step": 605
888
+ },
889
+ {
890
+ "epoch": 0.5616942909760589,
891
+ "grad_norm": 0.14086950862534534,
892
+ "learning_rate": 9.59816443168216e-05,
893
+ "loss": 0.6991,
894
+ "step": 610
895
+ },
896
+ {
897
+ "epoch": 0.5662983425414365,
898
+ "grad_norm": 0.12626280805151868,
899
+ "learning_rate": 9.437575629711882e-05,
900
+ "loss": 0.7099,
901
+ "step": 615
902
+ },
903
+ {
904
+ "epoch": 0.570902394106814,
905
+ "grad_norm": 0.14750922735308492,
906
+ "learning_rate": 9.277132207988517e-05,
907
+ "loss": 0.7116,
908
+ "step": 620
909
+ },
910
+ {
911
+ "epoch": 0.5755064456721916,
912
+ "grad_norm": 0.12947957016862066,
913
+ "learning_rate": 9.116875639295782e-05,
914
+ "loss": 0.7173,
915
+ "step": 625
916
+ },
917
+ {
918
+ "epoch": 0.580110497237569,
919
+ "grad_norm": 0.1217085102913984,
920
+ "learning_rate": 8.95684734811803e-05,
921
+ "loss": 0.6782,
922
+ "step": 630
923
+ },
924
+ {
925
+ "epoch": 0.5847145488029466,
926
+ "grad_norm": 0.12805246153113478,
927
+ "learning_rate": 8.797088699932494e-05,
928
+ "loss": 0.6981,
929
+ "step": 635
930
+ },
931
+ {
932
+ "epoch": 0.5893186003683242,
933
+ "grad_norm": 0.13677967208339983,
934
+ "learning_rate": 8.637640990516792e-05,
935
+ "loss": 0.725,
936
+ "step": 640
937
+ },
938
+ {
939
+ "epoch": 0.5939226519337016,
940
+ "grad_norm": 0.1348897795554575,
941
+ "learning_rate": 8.478545435274423e-05,
942
+ "loss": 0.7403,
943
+ "step": 645
944
+ },
945
+ {
946
+ "epoch": 0.5985267034990792,
947
+ "grad_norm": 0.1425142278541099,
948
+ "learning_rate": 8.319843158581092e-05,
949
+ "loss": 0.7524,
950
+ "step": 650
951
+ },
952
+ {
953
+ "epoch": 0.6031307550644567,
954
+ "grad_norm": 0.1371048777547919,
955
+ "learning_rate": 8.161575183154495e-05,
956
+ "loss": 0.7075,
957
+ "step": 655
958
+ },
959
+ {
960
+ "epoch": 0.6077348066298343,
961
+ "grad_norm": 0.1445081769660327,
962
+ "learning_rate": 8.003782419450447e-05,
963
+ "loss": 0.6835,
964
+ "step": 660
965
+ },
966
+ {
967
+ "epoch": 0.6123388581952118,
968
+ "grad_norm": 0.11760848785277568,
969
+ "learning_rate": 7.846505655087972e-05,
970
+ "loss": 0.7081,
971
+ "step": 665
972
+ },
973
+ {
974
+ "epoch": 0.6169429097605893,
975
+ "grad_norm": 0.1438799054992206,
976
+ "learning_rate": 7.689785544306193e-05,
977
+ "loss": 0.7187,
978
+ "step": 670
979
+ },
980
+ {
981
+ "epoch": 0.6215469613259669,
982
+ "grad_norm": 0.14002441000957835,
983
+ "learning_rate": 7.533662597455667e-05,
984
+ "loss": 0.7009,
985
+ "step": 675
986
+ },
987
+ {
988
+ "epoch": 0.6261510128913443,
989
+ "grad_norm": 0.14656402716158887,
990
+ "learning_rate": 7.378177170526927e-05,
991
+ "loss": 0.6918,
992
+ "step": 680
993
+ },
994
+ {
995
+ "epoch": 0.6307550644567219,
996
+ "grad_norm": 0.15779771059270742,
997
+ "learning_rate": 7.223369454718918e-05,
998
+ "loss": 0.7186,
999
+ "step": 685
1000
+ },
1001
+ {
1002
+ "epoch": 0.6353591160220995,
1003
+ "grad_norm": 0.11794313696285232,
1004
+ "learning_rate": 7.069279466050035e-05,
1005
+ "loss": 0.6843,
1006
+ "step": 690
1007
+ },
1008
+ {
1009
+ "epoch": 0.639963167587477,
1010
+ "grad_norm": 0.13595292601440173,
1011
+ "learning_rate": 6.915947035014443e-05,
1012
+ "loss": 0.7168,
1013
+ "step": 695
1014
+ },
1015
+ {
1016
+ "epoch": 0.6445672191528545,
1017
+ "grad_norm": 0.1344328444601024,
1018
+ "learning_rate": 6.763411796286357e-05,
1019
+ "loss": 0.6965,
1020
+ "step": 700
1021
+ },
1022
+ {
1023
+ "epoch": 0.649171270718232,
1024
+ "grad_norm": 0.1231670701178996,
1025
+ "learning_rate": 6.611713178474916e-05,
1026
+ "loss": 0.7244,
1027
+ "step": 705
1028
+ },
1029
+ {
1030
+ "epoch": 0.6537753222836096,
1031
+ "grad_norm": 0.1437978280644596,
1032
+ "learning_rate": 6.460890393932362e-05,
1033
+ "loss": 0.6734,
1034
+ "step": 710
1035
+ },
1036
+ {
1037
+ "epoch": 0.6583793738489871,
1038
+ "grad_norm": 0.13712514064241163,
1039
+ "learning_rate": 6.310982428618077e-05,
1040
+ "loss": 0.7112,
1041
+ "step": 715
1042
+ },
1043
+ {
1044
+ "epoch": 0.6629834254143646,
1045
+ "grad_norm": 0.12729820444217552,
1046
+ "learning_rate": 6.162028032021167e-05,
1047
+ "loss": 0.677,
1048
+ "step": 720
1049
+ },
1050
+ {
1051
+ "epoch": 0.6675874769797422,
1052
+ "grad_norm": 0.12007586806931402,
1053
+ "learning_rate": 6.014065707144176e-05,
1054
+ "loss": 0.6761,
1055
+ "step": 725
1056
+ },
1057
+ {
1058
+ "epoch": 0.6721915285451197,
1059
+ "grad_norm": 0.11950710825018164,
1060
+ "learning_rate": 5.867133700550479e-05,
1061
+ "loss": 0.7132,
1062
+ "step": 730
1063
+ },
1064
+ {
1065
+ "epoch": 0.6767955801104972,
1066
+ "grad_norm": 0.12219449475526536,
1067
+ "learning_rate": 5.721269992478002e-05,
1068
+ "loss": 0.6891,
1069
+ "step": 735
1070
+ },
1071
+ {
1072
+ "epoch": 0.6813996316758748,
1073
+ "grad_norm": 0.13820553666745064,
1074
+ "learning_rate": 5.576512287021765e-05,
1075
+ "loss": 0.7032,
1076
+ "step": 740
1077
+ },
1078
+ {
1079
+ "epoch": 0.6860036832412523,
1080
+ "grad_norm": 0.12575435617713188,
1081
+ "learning_rate": 5.432898002387783e-05,
1082
+ "loss": 0.685,
1083
+ "step": 745
1084
+ },
1085
+ {
1086
+ "epoch": 0.6906077348066298,
1087
+ "grad_norm": 0.12305743189245932,
1088
+ "learning_rate": 5.290464261220927e-05,
1089
+ "loss": 0.6874,
1090
+ "step": 750
1091
+ },
1092
+ {
1093
+ "epoch": 0.6952117863720073,
1094
+ "grad_norm": 0.1602899973447253,
1095
+ "learning_rate": 5.149247881009118e-05,
1096
+ "loss": 0.7074,
1097
+ "step": 755
1098
+ },
1099
+ {
1100
+ "epoch": 0.6998158379373849,
1101
+ "grad_norm": 0.11125288181618329,
1102
+ "learning_rate": 5.009285364566435e-05,
1103
+ "loss": 0.6646,
1104
+ "step": 760
1105
+ },
1106
+ {
1107
+ "epoch": 0.7044198895027625,
1108
+ "grad_norm": 0.12864820726453974,
1109
+ "learning_rate": 4.870612890597565e-05,
1110
+ "loss": 0.6976,
1111
+ "step": 765
1112
+ },
1113
+ {
1114
+ "epoch": 0.7090239410681399,
1115
+ "grad_norm": 0.12633554254462218,
1116
+ "learning_rate": 4.733266304346005e-05,
1117
+ "loss": 0.6886,
1118
+ "step": 770
1119
+ },
1120
+ {
1121
+ "epoch": 0.7136279926335175,
1122
+ "grad_norm": 0.13645165523957492,
1123
+ "learning_rate": 4.5972811083285014e-05,
1124
+ "loss": 0.7263,
1125
+ "step": 775
1126
+ },
1127
+ {
1128
+ "epoch": 0.7182320441988951,
1129
+ "grad_norm": 0.14653256629663075,
1130
+ "learning_rate": 4.462692453158039e-05,
1131
+ "loss": 0.7078,
1132
+ "step": 780
1133
+ },
1134
+ {
1135
+ "epoch": 0.7228360957642725,
1136
+ "grad_norm": 0.13327438185784568,
1137
+ "learning_rate": 4.329535128457822e-05,
1138
+ "loss": 0.7057,
1139
+ "step": 785
1140
+ },
1141
+ {
1142
+ "epoch": 0.7274401473296501,
1143
+ "grad_norm": 0.1383815308770519,
1144
+ "learning_rate": 4.197843553868538e-05,
1145
+ "loss": 0.6894,
1146
+ "step": 790
1147
+ },
1148
+ {
1149
+ "epoch": 0.7320441988950276,
1150
+ "grad_norm": 0.12797224319884995,
1151
+ "learning_rate": 4.0676517701513015e-05,
1152
+ "loss": 0.685,
1153
+ "step": 795
1154
+ },
1155
+ {
1156
+ "epoch": 0.7366482504604052,
1157
+ "grad_norm": 0.13203365820667615,
1158
+ "learning_rate": 3.93899343038848e-05,
1159
+ "loss": 0.6629,
1160
+ "step": 800
1161
+ },
1162
+ {
1163
+ "epoch": 0.7366482504604052,
1164
+ "eval_loss": 0.6758299469947815,
1165
+ "eval_runtime": 47.789,
1166
+ "eval_samples_per_second": 10.463,
1167
+ "eval_steps_per_second": 0.67,
1168
+ "step": 800
1169
+ },
1170
+ {
1171
+ "epoch": 0.7412523020257827,
1172
+ "grad_norm": 0.14945609861259754,
1173
+ "learning_rate": 3.8119017912847873e-05,
1174
+ "loss": 0.7157,
1175
+ "step": 805
1176
+ },
1177
+ {
1178
+ "epoch": 0.7458563535911602,
1179
+ "grad_norm": 0.14064204226125424,
1180
+ "learning_rate": 3.686409704570778e-05,
1181
+ "loss": 0.7077,
1182
+ "step": 810
1183
+ },
1184
+ {
1185
+ "epoch": 0.7504604051565378,
1186
+ "grad_norm": 0.15174343823382735,
1187
+ "learning_rate": 3.5625496085110754e-05,
1188
+ "loss": 0.714,
1189
+ "step": 815
1190
+ },
1191
+ {
1192
+ "epoch": 0.7550644567219152,
1193
+ "grad_norm": 0.13218371839998455,
1194
+ "learning_rate": 3.440353519519439e-05,
1195
+ "loss": 0.7095,
1196
+ "step": 820
1197
+ },
1198
+ {
1199
+ "epoch": 0.7596685082872928,
1200
+ "grad_norm": 0.1323028538168689,
1201
+ "learning_rate": 3.3198530238828976e-05,
1202
+ "loss": 0.6971,
1203
+ "step": 825
1204
+ },
1205
+ {
1206
+ "epoch": 0.7642725598526704,
1207
+ "grad_norm": 0.14745827705981765,
1208
+ "learning_rate": 3.20107926959704e-05,
1209
+ "loss": 0.7041,
1210
+ "step": 830
1211
+ },
1212
+ {
1213
+ "epoch": 0.7688766114180479,
1214
+ "grad_norm": 0.1442754442357172,
1215
+ "learning_rate": 3.0840629583146416e-05,
1216
+ "loss": 0.6814,
1217
+ "step": 835
1218
+ },
1219
+ {
1220
+ "epoch": 0.7734806629834254,
1221
+ "grad_norm": 0.13106050495634988,
1222
+ "learning_rate": 2.9688343374096115e-05,
1223
+ "loss": 0.6823,
1224
+ "step": 840
1225
+ },
1226
+ {
1227
+ "epoch": 0.7780847145488029,
1228
+ "grad_norm": 0.1644775188382007,
1229
+ "learning_rate": 2.8554231921584162e-05,
1230
+ "loss": 0.7221,
1231
+ "step": 845
1232
+ },
1233
+ {
1234
+ "epoch": 0.7826887661141805,
1235
+ "grad_norm": 0.13022155447713443,
1236
+ "learning_rate": 2.743858838040918e-05,
1237
+ "loss": 0.7135,
1238
+ "step": 850
1239
+ },
1240
+ {
1241
+ "epoch": 0.787292817679558,
1242
+ "grad_norm": 0.13264345669070807,
1243
+ "learning_rate": 2.6341701131626486e-05,
1244
+ "loss": 0.6979,
1245
+ "step": 855
1246
+ },
1247
+ {
1248
+ "epoch": 0.7918968692449355,
1249
+ "grad_norm": 0.14323695673993403,
1250
+ "learning_rate": 2.526385370800515e-05,
1251
+ "loss": 0.6969,
1252
+ "step": 860
1253
+ },
1254
+ {
1255
+ "epoch": 0.7965009208103131,
1256
+ "grad_norm": 0.1542994659104081,
1257
+ "learning_rate": 2.4205324720737786e-05,
1258
+ "loss": 0.7042,
1259
+ "step": 865
1260
+ },
1261
+ {
1262
+ "epoch": 0.8011049723756906,
1263
+ "grad_norm": 0.1449879659078434,
1264
+ "learning_rate": 2.316638778742295e-05,
1265
+ "loss": 0.6899,
1266
+ "step": 870
1267
+ },
1268
+ {
1269
+ "epoch": 0.8057090239410681,
1270
+ "grad_norm": 0.13076802781423985,
1271
+ "learning_rate": 2.214731146133793e-05,
1272
+ "loss": 0.7111,
1273
+ "step": 875
1274
+ },
1275
+ {
1276
+ "epoch": 0.8103130755064457,
1277
+ "grad_norm": 0.13291253398347233,
1278
+ "learning_rate": 2.1148359162020937e-05,
1279
+ "loss": 0.6914,
1280
+ "step": 880
1281
+ },
1282
+ {
1283
+ "epoch": 0.8149171270718232,
1284
+ "grad_norm": 0.13550181071065082,
1285
+ "learning_rate": 2.0169789107180193e-05,
1286
+ "loss": 0.6866,
1287
+ "step": 885
1288
+ },
1289
+ {
1290
+ "epoch": 0.8195211786372008,
1291
+ "grad_norm": 0.1210302923733577,
1292
+ "learning_rate": 1.921185424594758e-05,
1293
+ "loss": 0.6879,
1294
+ "step": 890
1295
+ },
1296
+ {
1297
+ "epoch": 0.8241252302025782,
1298
+ "grad_norm": 0.14037576745574026,
1299
+ "learning_rate": 1.827480219349409e-05,
1300
+ "loss": 0.7038,
1301
+ "step": 895
1302
+ },
1303
+ {
1304
+ "epoch": 0.8287292817679558,
1305
+ "grad_norm": 0.14791019025478577,
1306
+ "learning_rate": 1.7358875167024335e-05,
1307
+ "loss": 0.6604,
1308
+ "step": 900
1309
+ },
1310
+ {
1311
+ "epoch": 0.8333333333333334,
1312
+ "grad_norm": 0.11954867056661006,
1313
+ "learning_rate": 1.6464309923166033e-05,
1314
+ "loss": 0.7045,
1315
+ "step": 905
1316
+ },
1317
+ {
1318
+ "epoch": 0.8379373848987108,
1319
+ "grad_norm": 0.13365725863804348,
1320
+ "learning_rate": 1.5591337696771246e-05,
1321
+ "loss": 0.7313,
1322
+ "step": 910
1323
+ },
1324
+ {
1325
+ "epoch": 0.8425414364640884,
1326
+ "grad_norm": 0.13259625682339735,
1327
+ "learning_rate": 1.4740184141144664e-05,
1328
+ "loss": 0.7099,
1329
+ "step": 915
1330
+ },
1331
+ {
1332
+ "epoch": 0.8471454880294659,
1333
+ "grad_norm": 0.14145923503935914,
1334
+ "learning_rate": 1.391106926971496e-05,
1335
+ "loss": 0.6952,
1336
+ "step": 920
1337
+ },
1338
+ {
1339
+ "epoch": 0.8517495395948435,
1340
+ "grad_norm": 0.14338379016355754,
1341
+ "learning_rate": 1.3104207399163815e-05,
1342
+ "loss": 0.6856,
1343
+ "step": 925
1344
+ },
1345
+ {
1346
+ "epoch": 0.856353591160221,
1347
+ "grad_norm": 0.14829983664793228,
1348
+ "learning_rate": 1.2319807094027492e-05,
1349
+ "loss": 0.7156,
1350
+ "step": 930
1351
+ },
1352
+ {
1353
+ "epoch": 0.8609576427255985,
1354
+ "grad_norm": 0.12075075754668071,
1355
+ "learning_rate": 1.1558071112785296e-05,
1356
+ "loss": 0.6929,
1357
+ "step": 935
1358
+ },
1359
+ {
1360
+ "epoch": 0.8655616942909761,
1361
+ "grad_norm": 0.12950812269617865,
1362
+ "learning_rate": 1.0819196355448801e-05,
1363
+ "loss": 0.7045,
1364
+ "step": 940
1365
+ },
1366
+ {
1367
+ "epoch": 0.8701657458563536,
1368
+ "grad_norm": 0.1348184333941541,
1369
+ "learning_rate": 1.0103373812665551e-05,
1370
+ "loss": 0.6891,
1371
+ "step": 945
1372
+ },
1373
+ {
1374
+ "epoch": 0.8747697974217311,
1375
+ "grad_norm": 0.12025879421103704,
1376
+ "learning_rate": 9.410788516350077e-06,
1377
+ "loss": 0.6829,
1378
+ "step": 950
1379
+ },
1380
+ {
1381
+ "epoch": 0.8793738489871087,
1382
+ "grad_norm": 0.1332253794557465,
1383
+ "learning_rate": 8.741619491855291e-06,
1384
+ "loss": 0.7057,
1385
+ "step": 955
1386
+ },
1387
+ {
1388
+ "epoch": 0.8839779005524862,
1389
+ "grad_norm": 0.1219486531845245,
1390
+ "learning_rate": 8.096039711696545e-06,
1391
+ "loss": 0.701,
1392
+ "step": 960
1393
+ },
1394
+ {
1395
+ "epoch": 0.8885819521178637,
1396
+ "grad_norm": 0.13660210114125856,
1397
+ "learning_rate": 7.474216050840122e-06,
1398
+ "loss": 0.7016,
1399
+ "step": 965
1400
+ },
1401
+ {
1402
+ "epoch": 0.8931860036832413,
1403
+ "grad_norm": 0.11517510371236951,
1404
+ "learning_rate": 6.876309243568058e-06,
1405
+ "loss": 0.6961,
1406
+ "step": 970
1407
+ },
1408
+ {
1409
+ "epoch": 0.8977900552486188,
1410
+ "grad_norm": 0.14163517493869995,
1411
+ "learning_rate": 6.302473841930134e-06,
1412
+ "loss": 0.7082,
1413
+ "step": 975
1414
+ },
1415
+ {
1416
+ "epoch": 0.9023941068139963,
1417
+ "grad_norm": 0.14904472118298337,
1418
+ "learning_rate": 5.752858175793951e-06,
1419
+ "loss": 0.7017,
1420
+ "step": 980
1421
+ },
1422
+ {
1423
+ "epoch": 0.9069981583793738,
1424
+ "grad_norm": 0.13222086336141328,
1425
+ "learning_rate": 5.2276043145033425e-06,
1426
+ "loss": 0.6951,
1427
+ "step": 985
1428
+ },
1429
+ {
1430
+ "epoch": 0.9116022099447514,
1431
+ "grad_norm": 0.12747716652913677,
1432
+ "learning_rate": 4.726848030155129e-06,
1433
+ "loss": 0.727,
1434
+ "step": 990
1435
+ },
1436
+ {
1437
+ "epoch": 0.916206261510129,
1438
+ "grad_norm": 0.142369192844187,
1439
+ "learning_rate": 4.2507187625035135e-06,
1440
+ "loss": 0.7112,
1441
+ "step": 995
1442
+ },
1443
+ {
1444
+ "epoch": 0.9208103130755064,
1445
+ "grad_norm": 0.12916678602655413,
1446
+ "learning_rate": 3.7993395855014936e-06,
1447
+ "loss": 0.6769,
1448
+ "step": 1000
1449
+ },
1450
+ {
1451
+ "epoch": 0.9208103130755064,
1452
+ "eval_loss": 0.6735966205596924,
1453
+ "eval_runtime": 47.6678,
1454
+ "eval_samples_per_second": 10.489,
1455
+ "eval_steps_per_second": 0.671,
1456
+ "step": 1000
1457
+ },
1458
+ {
1459
+ "epoch": 0.925414364640884,
1460
+ "grad_norm": 0.1315541461105031,
1461
+ "learning_rate": 3.372827175487536e-06,
1462
+ "loss": 0.7239,
1463
+ "step": 1005
1464
+ },
1465
+ {
1466
+ "epoch": 0.9300184162062615,
1467
+ "grad_norm": 0.12551668481359965,
1468
+ "learning_rate": 2.9712917810261644e-06,
1469
+ "loss": 0.707,
1470
+ "step": 1010
1471
+ },
1472
+ {
1473
+ "epoch": 0.934622467771639,
1474
+ "grad_norm": 0.13010659142747308,
1475
+ "learning_rate": 2.5948371944099713e-06,
1476
+ "loss": 0.7066,
1477
+ "step": 1015
1478
+ },
1479
+ {
1480
+ "epoch": 0.9392265193370166,
1481
+ "grad_norm": 0.1374733909690572,
1482
+ "learning_rate": 2.2435607248304623e-06,
1483
+ "loss": 0.6981,
1484
+ "step": 1020
1485
+ },
1486
+ {
1487
+ "epoch": 0.9438305709023941,
1488
+ "grad_norm": 0.1557801553309302,
1489
+ "learning_rate": 1.91755317322474e-06,
1490
+ "loss": 0.6994,
1491
+ "step": 1025
1492
+ },
1493
+ {
1494
+ "epoch": 0.9484346224677717,
1495
+ "grad_norm": 0.1264138943615379,
1496
+ "learning_rate": 1.6168988088045678e-06,
1497
+ "loss": 0.704,
1498
+ "step": 1030
1499
+ },
1500
+ {
1501
+ "epoch": 0.9530386740331491,
1502
+ "grad_norm": 0.10632950484964579,
1503
+ "learning_rate": 1.341675347273652e-06,
1504
+ "loss": 0.677,
1505
+ "step": 1035
1506
+ },
1507
+ {
1508
+ "epoch": 0.9576427255985267,
1509
+ "grad_norm": 0.1230994587161385,
1510
+ "learning_rate": 1.0919539307391314e-06,
1511
+ "loss": 0.6891,
1512
+ "step": 1040
1513
+ },
1514
+ {
1515
+ "epoch": 0.9622467771639043,
1516
+ "grad_norm": 0.1356286737876717,
1517
+ "learning_rate": 8.67799109322076e-07,
1518
+ "loss": 0.6993,
1519
+ "step": 1045
1520
+ },
1521
+ {
1522
+ "epoch": 0.9668508287292817,
1523
+ "grad_norm": 0.1544804686351126,
1524
+ "learning_rate": 6.692688244720358e-07,
1525
+ "loss": 0.6888,
1526
+ "step": 1050
1527
+ },
1528
+ {
1529
+ "epoch": 0.9714548802946593,
1530
+ "grad_norm": 0.1409581730070821,
1531
+ "learning_rate": 4.964143939898746e-07,
1532
+ "loss": 0.7092,
1533
+ "step": 1055
1534
+ },
1535
+ {
1536
+ "epoch": 0.9760589318600368,
1537
+ "grad_norm": 0.13126265245760058,
1538
+ "learning_rate": 3.49280498762683e-07,
1539
+ "loss": 0.7008,
1540
+ "step": 1060
1541
+ },
1542
+ {
1543
+ "epoch": 0.9806629834254144,
1544
+ "grad_norm": 0.13981476492383843,
1545
+ "learning_rate": 2.2790517121428212e-07,
1546
+ "loss": 0.682,
1547
+ "step": 1065
1548
+ },
1549
+ {
1550
+ "epoch": 0.9852670349907919,
1551
+ "grad_norm": 0.11466302388077335,
1552
+ "learning_rate": 1.323197854742775e-07,
1553
+ "loss": 0.7008,
1554
+ "step": 1070
1555
+ },
1556
+ {
1557
+ "epoch": 0.9898710865561694,
1558
+ "grad_norm": 0.14514253246885966,
1559
+ "learning_rate": 6.254904926820126e-08,
1560
+ "loss": 0.7039,
1561
+ "step": 1075
1562
+ },
1563
+ {
1564
+ "epoch": 0.994475138121547,
1565
+ "grad_norm": 0.12201481168818025,
1566
+ "learning_rate": 1.8610997530876807e-08,
1567
+ "loss": 0.696,
1568
+ "step": 1080
1569
+ },
1570
+ {
1571
+ "epoch": 0.9990791896869244,
1572
+ "grad_norm": 0.13117233881672566,
1573
+ "learning_rate": 5.169877445809767e-10,
1574
+ "loss": 0.6881,
1575
+ "step": 1085
1576
+ },
1577
+ {
1578
+ "epoch": 1.0,
1579
+ "step": 1086,
1580
+ "total_flos": 4801486812086272.0,
1581
+ "train_loss": 0.7253576234998405,
1582
+ "train_runtime": 22925.9932,
1583
+ "train_samples_per_second": 3.031,
1584
+ "train_steps_per_second": 0.047
1585
+ }
1586
+ ],
1587
+ "logging_steps": 5,
1588
+ "max_steps": 1086,
1589
+ "num_input_tokens_seen": 0,
1590
+ "num_train_epochs": 1,
1591
+ "save_steps": 100,
1592
+ "total_flos": 4801486812086272.0,
1593
+ "train_batch_size": 2,
1594
+ "trial_name": null,
1595
+ "trial_params": null
1596
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93a6d77b15cdab40383c2c71260711ab5f45cf3565e453e53feaa05ead76cfde
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c4324397610646e7d89fea3bf80e3f8b93fba81bf42de58f0a36c7c120e72d
3
  size 6264