dabrown commited on
Commit
1e9bbcf
·
verified ·
1 Parent(s): b2c501a

Training in progress, step 275, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2-7B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Qwen2-7B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "up_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": true
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afb1944bf70c5ec62765c53ba94193d278cbc67aa12247c843dd35f68f3b9bd
3
+ size 80792096
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c396a09a82bf2ffec74f1d3f49d45310298ab311e6559c563317f0f31c98bbe
3
+ size 41460084
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9673839065b58d76bc3b02d183cf197c172d16da9dabd5f8c5d915fe61be07
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5be8b274530ed5517e32e7b23ab26f34602144201990badc0a09d01cd9796b2
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 131072,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "left",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1974 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2503128911138924,
5
+ "eval_steps": 275,
6
+ "global_step": 275,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0009102286949596086,
13
+ "grad_norm": 0.3924100995063782,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.8811,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0009102286949596086,
20
+ "eval_loss": 2.6547484397888184,
21
+ "eval_runtime": 202.3055,
22
+ "eval_samples_per_second": 9.15,
23
+ "eval_steps_per_second": 4.577,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0018204573899192173,
28
+ "grad_norm": 0.4433031976222992,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.8541,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0027306860848788257,
35
+ "grad_norm": 0.4557134211063385,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.6364,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0036409147798384346,
42
+ "grad_norm": 0.3975633978843689,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.6666,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.004551143474798043,
49
+ "grad_norm": 0.36896416544914246,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.745,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.0054613721697576514,
56
+ "grad_norm": 0.30803996324539185,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.7417,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.00637160086471726,
63
+ "grad_norm": 0.40208426117897034,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.7006,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.007281829559676869,
70
+ "grad_norm": 0.5293606519699097,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.6852,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.008192058254636477,
77
+ "grad_norm": 0.4535931646823883,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.6472,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.009102286949596085,
84
+ "grad_norm": 0.32121461629867554,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.6648,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.010012515644555695,
91
+ "grad_norm": 0.3374486565589905,
92
+ "learning_rate": 0.00019999958388469571,
93
+ "loss": 2.5696,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.010922744339515303,
98
+ "grad_norm": 0.3663835823535919,
99
+ "learning_rate": 0.00019999833554224577,
100
+ "loss": 2.4938,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.011832973034474913,
105
+ "grad_norm": 0.32625913619995117,
106
+ "learning_rate": 0.00019999625498303932,
107
+ "loss": 2.5661,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.01274320172943452,
112
+ "grad_norm": 0.382977157831192,
113
+ "learning_rate": 0.00019999334222439147,
114
+ "loss": 2.5544,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.013653430424394129,
119
+ "grad_norm": 0.3954707384109497,
120
+ "learning_rate": 0.00019998959729054295,
121
+ "loss": 2.5744,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.014563659119353738,
126
+ "grad_norm": 0.30874142050743103,
127
+ "learning_rate": 0.0001999850202126604,
128
+ "loss": 2.5242,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.015473887814313346,
133
+ "grad_norm": 0.30474328994750977,
134
+ "learning_rate": 0.00019997961102883552,
135
+ "loss": 2.4201,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.016384116509272954,
140
+ "grad_norm": 0.32679283618927,
141
+ "learning_rate": 0.00019997336978408531,
142
+ "loss": 2.5165,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.017294345204232564,
147
+ "grad_norm": 0.3267504572868347,
148
+ "learning_rate": 0.00019996629653035126,
149
+ "loss": 2.2016,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.01820457389919217,
154
+ "grad_norm": 0.33519116044044495,
155
+ "learning_rate": 0.00019995839132649917,
156
+ "loss": 2.4004,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.01911480259415178,
161
+ "grad_norm": 0.36370110511779785,
162
+ "learning_rate": 0.00019994965423831854,
163
+ "loss": 2.4736,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.02002503128911139,
168
+ "grad_norm": 0.36940237879753113,
169
+ "learning_rate": 0.0001999400853385221,
170
+ "loss": 2.4726,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.020935259984071,
175
+ "grad_norm": 0.3428037762641907,
176
+ "learning_rate": 0.0001999296847067452,
177
+ "loss": 2.4291,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.021845488679030606,
182
+ "grad_norm": 0.3404378294944763,
183
+ "learning_rate": 0.00019991845242954505,
184
+ "loss": 2.0424,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.022755717373990215,
189
+ "grad_norm": 0.3714047074317932,
190
+ "learning_rate": 0.00019990638860040006,
191
+ "loss": 2.2809,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.023665946068949825,
196
+ "grad_norm": 0.37741491198539734,
197
+ "learning_rate": 0.00019989349331970923,
198
+ "loss": 2.2841,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.02457617476390943,
203
+ "grad_norm": 0.38504019379615784,
204
+ "learning_rate": 0.00019987976669479088,
205
+ "loss": 2.2056,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.02548640345886904,
210
+ "grad_norm": 0.4182392954826355,
211
+ "learning_rate": 0.00019986520883988232,
212
+ "loss": 2.3747,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.02639663215382865,
217
+ "grad_norm": 0.4266968369483948,
218
+ "learning_rate": 0.0001998498198761384,
219
+ "loss": 2.3608,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.027306860848788257,
224
+ "grad_norm": 0.3748364746570587,
225
+ "learning_rate": 0.00019983359993163078,
226
+ "loss": 2.0789,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.028217089543747867,
231
+ "grad_norm": 0.4157109558582306,
232
+ "learning_rate": 0.00019981654914134686,
233
+ "loss": 2.3174,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.029127318238707477,
238
+ "grad_norm": 0.4328743517398834,
239
+ "learning_rate": 0.00019979866764718843,
240
+ "loss": 2.3304,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.030037546933667083,
245
+ "grad_norm": 0.4545007050037384,
246
+ "learning_rate": 0.0001997799555979709,
247
+ "loss": 2.3578,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.030947775628626693,
252
+ "grad_norm": 0.4287387430667877,
253
+ "learning_rate": 0.00019976041314942155,
254
+ "loss": 2.1072,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.0318580043235863,
259
+ "grad_norm": 0.4378172755241394,
260
+ "learning_rate": 0.0001997400404641787,
261
+ "loss": 2.2507,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.03276823301854591,
266
+ "grad_norm": 0.42525431513786316,
267
+ "learning_rate": 0.00019971883771179003,
268
+ "loss": 2.1549,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.03367846171350552,
273
+ "grad_norm": 0.4390096068382263,
274
+ "learning_rate": 0.00019969680506871137,
275
+ "loss": 2.3869,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.03458869040846513,
280
+ "grad_norm": 0.4858846068382263,
281
+ "learning_rate": 0.00019967394271830504,
282
+ "loss": 2.5711,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.03549891910342474,
287
+ "grad_norm": 0.46703851222991943,
288
+ "learning_rate": 0.00019965025085083858,
289
+ "loss": 2.3567,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.03640914779838434,
294
+ "grad_norm": 0.4408855438232422,
295
+ "learning_rate": 0.000199625729663483,
296
+ "loss": 2.1646,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.03731937649334395,
301
+ "grad_norm": 0.49953216314315796,
302
+ "learning_rate": 0.00019960037936031104,
303
+ "loss": 2.3658,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.03822960518830356,
308
+ "grad_norm": 0.48640862107276917,
309
+ "learning_rate": 0.00019957420015229572,
310
+ "loss": 2.4125,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.03913983388326317,
315
+ "grad_norm": 0.5187159776687622,
316
+ "learning_rate": 0.00019954719225730847,
317
+ "loss": 2.3655,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.04005006257822278,
322
+ "grad_norm": 0.48923739790916443,
323
+ "learning_rate": 0.00019951935590011718,
324
+ "loss": 2.257,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.04096029127318239,
329
+ "grad_norm": 0.4975845515727997,
330
+ "learning_rate": 0.0001994906913123846,
331
+ "loss": 2.185,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.041870519968142,
336
+ "grad_norm": 0.5635886788368225,
337
+ "learning_rate": 0.00019946119873266613,
338
+ "loss": 2.6952,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.0427807486631016,
343
+ "grad_norm": 0.5890567898750305,
344
+ "learning_rate": 0.00019943087840640814,
345
+ "loss": 2.5154,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.04369097735806121,
350
+ "grad_norm": 0.6770642995834351,
351
+ "learning_rate": 0.0001993997305859456,
352
+ "loss": 2.7011,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.04460120605302082,
357
+ "grad_norm": 0.7621054649353027,
358
+ "learning_rate": 0.0001993677555305002,
359
+ "loss": 2.5097,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.04551143474798043,
364
+ "grad_norm": 1.2259888648986816,
365
+ "learning_rate": 0.00019933495350617813,
366
+ "loss": 2.516,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.04642166344294004,
371
+ "grad_norm": 1.261356234550476,
372
+ "learning_rate": 0.00019930132478596796,
373
+ "loss": 2.7173,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.04733189213789965,
378
+ "grad_norm": 0.5333342552185059,
379
+ "learning_rate": 0.00019926686964973813,
380
+ "loss": 2.7659,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.04824212083285925,
385
+ "grad_norm": 0.43384629487991333,
386
+ "learning_rate": 0.00019923158838423482,
387
+ "loss": 2.4593,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.04915234952781886,
392
+ "grad_norm": 0.506197452545166,
393
+ "learning_rate": 0.00019919548128307954,
394
+ "loss": 2.6135,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.05006257822277847,
399
+ "grad_norm": 0.4372877776622772,
400
+ "learning_rate": 0.00019915854864676664,
401
+ "loss": 2.4952,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.05097280691773808,
406
+ "grad_norm": 0.4044889509677887,
407
+ "learning_rate": 0.00019912079078266085,
408
+ "loss": 2.6152,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.05188303561269769,
413
+ "grad_norm": 0.4284885823726654,
414
+ "learning_rate": 0.0001990822080049946,
415
+ "loss": 2.508,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.0527932643076573,
420
+ "grad_norm": 0.4030478298664093,
421
+ "learning_rate": 0.0001990428006348656,
422
+ "loss": 2.4545,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.053703493002616905,
427
+ "grad_norm": 0.37658700346946716,
428
+ "learning_rate": 0.00019900256900023413,
429
+ "loss": 2.3762,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.054613721697576514,
434
+ "grad_norm": 0.3478519022464752,
435
+ "learning_rate": 0.00019896151343592008,
436
+ "loss": 2.2991,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.055523950392536124,
441
+ "grad_norm": 0.38357114791870117,
442
+ "learning_rate": 0.00019891963428360043,
443
+ "loss": 2.4336,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.056434179087495734,
448
+ "grad_norm": 0.37183457612991333,
449
+ "learning_rate": 0.00019887693189180633,
450
+ "loss": 2.3966,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.057344407782455344,
455
+ "grad_norm": 0.3586178123950958,
456
+ "learning_rate": 0.00019883340661592015,
457
+ "loss": 2.3195,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.05825463647741495,
462
+ "grad_norm": 0.37112224102020264,
463
+ "learning_rate": 0.00019878905881817252,
464
+ "loss": 2.3924,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.059164865172374556,
469
+ "grad_norm": 0.37623754143714905,
470
+ "learning_rate": 0.00019874388886763944,
471
+ "loss": 2.562,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.060075093867334166,
476
+ "grad_norm": 0.37167176604270935,
477
+ "learning_rate": 0.00019869789714023906,
478
+ "loss": 2.4175,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.060985322562293776,
483
+ "grad_norm": 0.35394376516342163,
484
+ "learning_rate": 0.00019865108401872857,
485
+ "loss": 2.2845,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.061895551257253385,
490
+ "grad_norm": 0.3475804030895233,
491
+ "learning_rate": 0.00019860344989270113,
492
+ "loss": 2.0894,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.062805779952213,
497
+ "grad_norm": 0.387608140707016,
498
+ "learning_rate": 0.0001985549951585825,
499
+ "loss": 2.2795,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.0637160086471726,
504
+ "grad_norm": 0.38371261954307556,
505
+ "learning_rate": 0.00019850572021962788,
506
+ "loss": 2.1714,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.06462623734213221,
511
+ "grad_norm": 0.397544264793396,
512
+ "learning_rate": 0.00019845562548591826,
513
+ "loss": 2.167,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.06553646603709182,
518
+ "grad_norm": 0.394674688577652,
519
+ "learning_rate": 0.00019840471137435746,
520
+ "loss": 2.266,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.06644669473205143,
525
+ "grad_norm": 0.3893704116344452,
526
+ "learning_rate": 0.00019835297830866826,
527
+ "loss": 2.2651,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.06735692342701104,
532
+ "grad_norm": 0.430054247379303,
533
+ "learning_rate": 0.00019830042671938904,
534
+ "loss": 2.4341,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.06826715212197064,
539
+ "grad_norm": 0.4117582440376282,
540
+ "learning_rate": 0.00019824705704387028,
541
+ "loss": 2.2562,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.06917738081693026,
546
+ "grad_norm": 0.40804898738861084,
547
+ "learning_rate": 0.00019819286972627066,
548
+ "loss": 2.1574,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.07008760951188986,
553
+ "grad_norm": 0.3954644501209259,
554
+ "learning_rate": 0.00019813786521755372,
555
+ "loss": 2.0693,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.07099783820684948,
560
+ "grad_norm": 0.4126876890659332,
561
+ "learning_rate": 0.00019808204397548377,
562
+ "loss": 2.2299,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.07190806690180908,
567
+ "grad_norm": 0.42160266637802124,
568
+ "learning_rate": 0.0001980254064646223,
569
+ "loss": 2.1759,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.07281829559676868,
574
+ "grad_norm": 0.4152994751930237,
575
+ "learning_rate": 0.00019796795315632395,
576
+ "loss": 2.1931,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.0737285242917283,
581
+ "grad_norm": 0.4207664728164673,
582
+ "learning_rate": 0.0001979096845287328,
583
+ "loss": 2.0727,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.0746387529866879,
588
+ "grad_norm": 0.41932612657546997,
589
+ "learning_rate": 0.00019785060106677818,
590
+ "loss": 2.3067,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.07554898168164752,
595
+ "grad_norm": 0.44273534417152405,
596
+ "learning_rate": 0.00019779070326217074,
597
+ "loss": 2.2838,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.07645921037660712,
602
+ "grad_norm": 0.4609782099723816,
603
+ "learning_rate": 0.00019772999161339833,
604
+ "loss": 2.2605,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.07736943907156674,
609
+ "grad_norm": 0.4551486074924469,
610
+ "learning_rate": 0.00019766846662572191,
611
+ "loss": 2.3159,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.07827966776652634,
616
+ "grad_norm": 0.4343845546245575,
617
+ "learning_rate": 0.00019760612881117125,
618
+ "loss": 2.1787,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.07918989646148594,
623
+ "grad_norm": 0.48003000020980835,
624
+ "learning_rate": 0.00019754297868854073,
625
+ "loss": 2.3255,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.08010012515644556,
630
+ "grad_norm": 0.4384368062019348,
631
+ "learning_rate": 0.00019747901678338496,
632
+ "loss": 2.2881,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.08101035385140516,
637
+ "grad_norm": 0.5119354724884033,
638
+ "learning_rate": 0.00019741424362801452,
639
+ "loss": 2.3529,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.08192058254636478,
644
+ "grad_norm": 0.4595087766647339,
645
+ "learning_rate": 0.00019734865976149145,
646
+ "loss": 2.2495,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.08283081124132438,
651
+ "grad_norm": 0.4848781228065491,
652
+ "learning_rate": 0.00019728226572962473,
653
+ "loss": 2.446,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.083741039936284,
658
+ "grad_norm": 0.4848371148109436,
659
+ "learning_rate": 0.00019721506208496585,
660
+ "loss": 2.2737,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.0846512686312436,
665
+ "grad_norm": 0.4835449755191803,
666
+ "learning_rate": 0.00019714704938680408,
667
+ "loss": 2.224,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.0855614973262032,
672
+ "grad_norm": 0.48262766003608704,
673
+ "learning_rate": 0.00019707822820116193,
674
+ "loss": 2.2449,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.08647172602116282,
679
+ "grad_norm": 0.49700936675071716,
680
+ "learning_rate": 0.00019700859910079036,
681
+ "loss": 2.1856,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.08738195471612242,
686
+ "grad_norm": 0.5965728163719177,
687
+ "learning_rate": 0.00019693816266516407,
688
+ "loss": 2.6448,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.08829218341108204,
693
+ "grad_norm": 0.6164146661758423,
694
+ "learning_rate": 0.00019686691948047664,
695
+ "loss": 2.4917,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.08920241210604164,
700
+ "grad_norm": 0.6717427372932434,
701
+ "learning_rate": 0.00019679487013963564,
702
+ "loss": 2.7093,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.09011264080100125,
707
+ "grad_norm": 0.808948278427124,
708
+ "learning_rate": 0.00019672201524225776,
709
+ "loss": 2.766,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.09102286949596086,
714
+ "grad_norm": 1.4683064222335815,
715
+ "learning_rate": 0.0001966483553946637,
716
+ "loss": 2.7288,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.09193309819092046,
721
+ "grad_norm": 1.0303999185562134,
722
+ "learning_rate": 0.00019657389120987333,
723
+ "loss": 2.8246,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.09284332688588008,
728
+ "grad_norm": 0.49279651045799255,
729
+ "learning_rate": 0.00019649862330760036,
730
+ "loss": 2.722,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.09375355558083968,
735
+ "grad_norm": 0.43273016810417175,
736
+ "learning_rate": 0.00019642255231424729,
737
+ "loss": 2.5446,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.0946637842757993,
742
+ "grad_norm": 0.4434455335140228,
743
+ "learning_rate": 0.00019634567886290025,
744
+ "loss": 2.4578,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.0955740129707589,
749
+ "grad_norm": 0.4245634973049164,
750
+ "learning_rate": 0.00019626800359332362,
751
+ "loss": 2.5472,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.0964842416657185,
756
+ "grad_norm": 0.42879197001457214,
757
+ "learning_rate": 0.00019618952715195475,
758
+ "loss": 2.5313,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.09739447036067812,
763
+ "grad_norm": 0.4644932150840759,
764
+ "learning_rate": 0.0001961102501918986,
765
+ "loss": 2.3859,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.09830469905563773,
770
+ "grad_norm": 0.40692242980003357,
771
+ "learning_rate": 0.00019603017337292236,
772
+ "loss": 2.433,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.09921492775059734,
777
+ "grad_norm": 0.36667487025260925,
778
+ "learning_rate": 0.00019594929736144976,
779
+ "loss": 2.3352,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.10012515644555695,
784
+ "grad_norm": 0.41123342514038086,
785
+ "learning_rate": 0.00019586762283055573,
786
+ "loss": 2.3494,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.10103538514051655,
791
+ "grad_norm": 0.40255314111709595,
792
+ "learning_rate": 0.00019578515045996073,
793
+ "loss": 2.4524,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.10194561383547616,
798
+ "grad_norm": 0.38136208057403564,
799
+ "learning_rate": 0.0001957018809360251,
800
+ "loss": 2.3937,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.10285584253043577,
805
+ "grad_norm": 0.4538716673851013,
806
+ "learning_rate": 0.00019561781495174328,
807
+ "loss": 2.3144,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.10376607122539538,
812
+ "grad_norm": 0.3876875042915344,
813
+ "learning_rate": 0.00019553295320673807,
814
+ "loss": 2.2868,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.10467629992035499,
819
+ "grad_norm": 0.40529122948646545,
820
+ "learning_rate": 0.00019544729640725498,
821
+ "loss": 2.4219,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.1055865286153146,
826
+ "grad_norm": 0.36852964758872986,
827
+ "learning_rate": 0.0001953608452661561,
828
+ "loss": 2.3485,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.1064967573102742,
833
+ "grad_norm": 0.3608396053314209,
834
+ "learning_rate": 0.0001952736005029142,
835
+ "loss": 2.2813,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.10740698600523381,
840
+ "grad_norm": 0.3647065758705139,
841
+ "learning_rate": 0.00019518556284360696,
842
+ "loss": 2.2284,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.10831721470019343,
847
+ "grad_norm": 0.3692014217376709,
848
+ "learning_rate": 0.00019509673302091075,
849
+ "loss": 2.3005,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.10922744339515303,
854
+ "grad_norm": 0.3861401379108429,
855
+ "learning_rate": 0.00019500711177409454,
856
+ "loss": 2.3023,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.11013767209011265,
861
+ "grad_norm": 0.38329821825027466,
862
+ "learning_rate": 0.00019491669984901379,
863
+ "loss": 2.0692,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.11104790078507225,
868
+ "grad_norm": 0.3725563585758209,
869
+ "learning_rate": 0.00019482549799810413,
870
+ "loss": 2.2495,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.11195812948003186,
875
+ "grad_norm": 0.37789279222488403,
876
+ "learning_rate": 0.00019473350698037535,
877
+ "loss": 2.1242,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.11286835817499147,
882
+ "grad_norm": 0.4199522137641907,
883
+ "learning_rate": 0.00019464072756140486,
884
+ "loss": 2.2501,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.11377858686995107,
889
+ "grad_norm": 0.4012223184108734,
890
+ "learning_rate": 0.00019454716051333135,
891
+ "loss": 2.2263,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.11468881556491069,
896
+ "grad_norm": 0.4205365478992462,
897
+ "learning_rate": 0.00019445280661484847,
898
+ "loss": 2.1445,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.11559904425987029,
903
+ "grad_norm": 0.41000694036483765,
904
+ "learning_rate": 0.0001943576666511982,
905
+ "loss": 2.198,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.1165092729548299,
910
+ "grad_norm": 0.43458715081214905,
911
+ "learning_rate": 0.00019426174141416448,
912
+ "loss": 2.1884,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.11741950164978951,
917
+ "grad_norm": 0.4233211874961853,
918
+ "learning_rate": 0.00019416503170206645,
919
+ "loss": 2.311,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.11832973034474911,
924
+ "grad_norm": 0.411350816488266,
925
+ "learning_rate": 0.00019406753831975203,
926
+ "loss": 2.1085,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.11923995903970873,
931
+ "grad_norm": 0.42890501022338867,
932
+ "learning_rate": 0.00019396926207859084,
933
+ "loss": 2.0548,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.12015018773466833,
938
+ "grad_norm": 0.45003724098205566,
939
+ "learning_rate": 0.00019387020379646797,
940
+ "loss": 2.2063,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.12106041642962795,
945
+ "grad_norm": 0.4295034408569336,
946
+ "learning_rate": 0.00019377036429777672,
947
+ "loss": 2.1306,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.12197064512458755,
952
+ "grad_norm": 0.4310653805732727,
953
+ "learning_rate": 0.0001936697444134119,
954
+ "loss": 2.1307,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.12288087381954717,
959
+ "grad_norm": 0.4377802014350891,
960
+ "learning_rate": 0.0001935683449807631,
961
+ "loss": 2.2982,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.12379110251450677,
966
+ "grad_norm": 0.45586827397346497,
967
+ "learning_rate": 0.0001934661668437073,
968
+ "loss": 2.2334,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.12470133120946637,
973
+ "grad_norm": 0.4612938463687897,
974
+ "learning_rate": 0.00019336321085260236,
975
+ "loss": 2.2488,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.125611559904426,
980
+ "grad_norm": 0.48157835006713867,
981
+ "learning_rate": 0.00019325947786427952,
982
+ "loss": 2.2068,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.1265217885993856,
987
+ "grad_norm": 0.46901848912239075,
988
+ "learning_rate": 0.0001931549687420364,
989
+ "loss": 2.2526,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.1274320172943452,
994
+ "grad_norm": 0.4637078046798706,
995
+ "learning_rate": 0.00019304968435562993,
996
+ "loss": 2.1521,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.12834224598930483,
1001
+ "grad_norm": 0.5239959955215454,
1002
+ "learning_rate": 0.00019294362558126905,
1003
+ "loss": 2.3988,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.12925247468426443,
1008
+ "grad_norm": 0.462212473154068,
1009
+ "learning_rate": 0.00019283679330160726,
1010
+ "loss": 2.3085,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.13016270337922403,
1015
+ "grad_norm": 0.49486446380615234,
1016
+ "learning_rate": 0.00019272918840573558,
1017
+ "loss": 2.2851,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.13107293207418363,
1022
+ "grad_norm": 0.5234097838401794,
1023
+ "learning_rate": 0.00019262081178917482,
1024
+ "loss": 2.3942,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.13198316076914324,
1029
+ "grad_norm": 0.525196373462677,
1030
+ "learning_rate": 0.0001925116643538684,
1031
+ "loss": 2.3057,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.13289338946410287,
1036
+ "grad_norm": 0.5571113228797913,
1037
+ "learning_rate": 0.00019240174700817464,
1038
+ "loss": 2.2406,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.13380361815906247,
1043
+ "grad_norm": 0.6122002601623535,
1044
+ "learning_rate": 0.00019229106066685937,
1045
+ "loss": 2.42,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.13471384685402207,
1050
+ "grad_norm": 0.6147793531417847,
1051
+ "learning_rate": 0.0001921796062510882,
1052
+ "loss": 2.5769,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.13562407554898168,
1057
+ "grad_norm": 0.7194758653640747,
1058
+ "learning_rate": 0.0001920673846884189,
1059
+ "loss": 2.5508,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.13653430424394128,
1064
+ "grad_norm": 1.1327760219573975,
1065
+ "learning_rate": 0.00019195439691279363,
1066
+ "loss": 2.776,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.1374445329389009,
1071
+ "grad_norm": 0.5275815725326538,
1072
+ "learning_rate": 0.00019184064386453128,
1073
+ "loss": 2.6188,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.1383547616338605,
1078
+ "grad_norm": 0.5287826657295227,
1079
+ "learning_rate": 0.00019172612649031952,
1080
+ "loss": 2.6061,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.13926499032882012,
1085
+ "grad_norm": 0.4138477146625519,
1086
+ "learning_rate": 0.00019161084574320696,
1087
+ "loss": 2.355,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.14017521902377972,
1092
+ "grad_norm": 0.4219213128089905,
1093
+ "learning_rate": 0.00019149480258259533,
1094
+ "loss": 2.5719,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.14108544771873932,
1099
+ "grad_norm": 0.39532896876335144,
1100
+ "learning_rate": 0.00019137799797423126,
1101
+ "loss": 2.4734,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.14199567641369895,
1106
+ "grad_norm": 0.4149189889431,
1107
+ "learning_rate": 0.00019126043289019852,
1108
+ "loss": 2.5212,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.14290590510865855,
1113
+ "grad_norm": 0.45758771896362305,
1114
+ "learning_rate": 0.00019114210830890969,
1115
+ "loss": 2.5216,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.14381613380361816,
1120
+ "grad_norm": 0.4397677779197693,
1121
+ "learning_rate": 0.00019102302521509815,
1122
+ "loss": 2.6222,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.14472636249857776,
1127
+ "grad_norm": 0.4018581211566925,
1128
+ "learning_rate": 0.00019090318459980986,
1129
+ "loss": 2.546,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.14563659119353736,
1134
+ "grad_norm": 0.3948480486869812,
1135
+ "learning_rate": 0.00019078258746039507,
1136
+ "loss": 2.5202,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.146546819888497,
1141
+ "grad_norm": 0.37651899456977844,
1142
+ "learning_rate": 0.00019066123480050015,
1143
+ "loss": 2.3166,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.1474570485834566,
1148
+ "grad_norm": 0.3794865310192108,
1149
+ "learning_rate": 0.00019053912763005907,
1150
+ "loss": 2.1592,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.1483672772784162,
1155
+ "grad_norm": 0.39368098974227905,
1156
+ "learning_rate": 0.00019041626696528503,
1157
+ "loss": 2.3273,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.1492775059733758,
1162
+ "grad_norm": 0.39652615785598755,
1163
+ "learning_rate": 0.00019029265382866214,
1164
+ "loss": 2.4105,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.15018773466833543,
1169
+ "grad_norm": 0.4029604196548462,
1170
+ "learning_rate": 0.0001901682892489367,
1171
+ "loss": 2.3814,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.15109796336329503,
1176
+ "grad_norm": 0.40106695890426636,
1177
+ "learning_rate": 0.0001900431742611089,
1178
+ "loss": 2.3963,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.15200819205825464,
1183
+ "grad_norm": 0.3830929696559906,
1184
+ "learning_rate": 0.00018991730990642388,
1185
+ "loss": 2.2472,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.15291842075321424,
1190
+ "grad_norm": 0.36839723587036133,
1191
+ "learning_rate": 0.00018979069723236333,
1192
+ "loss": 2.2463,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.15382864944817384,
1197
+ "grad_norm": 0.36918777227401733,
1198
+ "learning_rate": 0.00018966333729263674,
1199
+ "loss": 2.2286,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.15473887814313347,
1204
+ "grad_norm": 0.37009552121162415,
1205
+ "learning_rate": 0.00018953523114717245,
1206
+ "loss": 2.2823,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.15564910683809308,
1211
+ "grad_norm": 0.38302165269851685,
1212
+ "learning_rate": 0.00018940637986210906,
1213
+ "loss": 2.1199,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.15655933553305268,
1218
+ "grad_norm": 0.40206897258758545,
1219
+ "learning_rate": 0.0001892767845097864,
1220
+ "loss": 2.3254,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.15746956422801228,
1225
+ "grad_norm": 0.3847138285636902,
1226
+ "learning_rate": 0.00018914644616873657,
1227
+ "loss": 2.0739,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.15837979292297188,
1232
+ "grad_norm": 0.37638360261917114,
1233
+ "learning_rate": 0.0001890153659236753,
1234
+ "loss": 2.1024,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.15929002161793152,
1239
+ "grad_norm": 0.38801488280296326,
1240
+ "learning_rate": 0.00018888354486549237,
1241
+ "loss": 2.1634,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.16020025031289112,
1246
+ "grad_norm": 0.4164554178714752,
1247
+ "learning_rate": 0.00018875098409124302,
1248
+ "loss": 2.2987,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.16111047900785072,
1253
+ "grad_norm": 0.38982319831848145,
1254
+ "learning_rate": 0.0001886176847041386,
1255
+ "loss": 2.1834,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.16202070770281032,
1260
+ "grad_norm": 0.42200496792793274,
1261
+ "learning_rate": 0.00018848364781353744,
1262
+ "loss": 2.2793,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.16293093639776993,
1267
+ "grad_norm": 0.4152745306491852,
1268
+ "learning_rate": 0.0001883488745349355,
1269
+ "loss": 2.1988,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.16384116509272956,
1274
+ "grad_norm": 0.41070255637168884,
1275
+ "learning_rate": 0.0001882133659899573,
1276
+ "loss": 1.8985,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.16475139378768916,
1281
+ "grad_norm": 0.4259546399116516,
1282
+ "learning_rate": 0.00018807712330634642,
1283
+ "loss": 2.4285,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.16566162248264876,
1288
+ "grad_norm": 0.44458258152008057,
1289
+ "learning_rate": 0.0001879401476179562,
1290
+ "loss": 2.2561,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.16657185117760837,
1295
+ "grad_norm": 0.4640187621116638,
1296
+ "learning_rate": 0.0001878024400647402,
1297
+ "loss": 2.4091,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.167482079872568,
1302
+ "grad_norm": 0.40832704305648804,
1303
+ "learning_rate": 0.00018766400179274286,
1304
+ "loss": 1.9156,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.1683923085675276,
1309
+ "grad_norm": 0.4358328878879547,
1310
+ "learning_rate": 0.00018752483395408987,
1311
+ "loss": 2.0592,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.1693025372624872,
1316
+ "grad_norm": 0.45089927315711975,
1317
+ "learning_rate": 0.00018738493770697852,
1318
+ "loss": 2.2189,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.1702127659574468,
1323
+ "grad_norm": 0.45900994539260864,
1324
+ "learning_rate": 0.00018724431421566823,
1325
+ "loss": 2.3023,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.1711229946524064,
1330
+ "grad_norm": 0.4608750641345978,
1331
+ "learning_rate": 0.00018710296465047075,
1332
+ "loss": 2.2467,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.17203322334736604,
1337
+ "grad_norm": 0.44717609882354736,
1338
+ "learning_rate": 0.0001869608901877404,
1339
+ "loss": 2.0313,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.17294345204232564,
1344
+ "grad_norm": 0.40987592935562134,
1345
+ "learning_rate": 0.0001868180920098644,
1346
+ "loss": 2.0965,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.17385368073728524,
1351
+ "grad_norm": 0.502581775188446,
1352
+ "learning_rate": 0.00018667457130525284,
1353
+ "loss": 2.1991,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.17476390943224485,
1358
+ "grad_norm": 0.4770600199699402,
1359
+ "learning_rate": 0.00018653032926832896,
1360
+ "loss": 2.2258,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.17567413812720445,
1365
+ "grad_norm": 0.48825547099113464,
1366
+ "learning_rate": 0.00018638536709951917,
1367
+ "loss": 2.2884,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.17658436682216408,
1372
+ "grad_norm": 0.5004613995552063,
1373
+ "learning_rate": 0.000186239686005243,
1374
+ "loss": 2.2927,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.17749459551712368,
1379
+ "grad_norm": 0.5268414616584778,
1380
+ "learning_rate": 0.0001860932871979031,
1381
+ "loss": 2.356,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.17840482421208329,
1386
+ "grad_norm": 0.5261876583099365,
1387
+ "learning_rate": 0.00018594617189587512,
1388
+ "loss": 2.2864,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.1793150529070429,
1393
+ "grad_norm": 0.6071822643280029,
1394
+ "learning_rate": 0.00018579834132349772,
1395
+ "loss": 2.684,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.1802252816020025,
1400
+ "grad_norm": 0.659428060054779,
1401
+ "learning_rate": 0.0001856497967110621,
1402
+ "loss": 2.5811,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.18113551029696212,
1407
+ "grad_norm": 0.828525960445404,
1408
+ "learning_rate": 0.00018550053929480202,
1409
+ "loss": 2.7052,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.18204573899192172,
1414
+ "grad_norm": 1.9569804668426514,
1415
+ "learning_rate": 0.00018535057031688335,
1416
+ "loss": 2.9428,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.18295596768688133,
1421
+ "grad_norm": 0.6459002494812012,
1422
+ "learning_rate": 0.0001851998910253939,
1423
+ "loss": 2.6936,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.18386619638184093,
1428
+ "grad_norm": 0.6431388854980469,
1429
+ "learning_rate": 0.0001850485026743328,
1430
+ "loss": 2.5446,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.18477642507680053,
1435
+ "grad_norm": 0.5401524305343628,
1436
+ "learning_rate": 0.00018489640652360022,
1437
+ "loss": 2.4508,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.18568665377176016,
1442
+ "grad_norm": 0.4280170500278473,
1443
+ "learning_rate": 0.00018474360383898694,
1444
+ "loss": 2.5167,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.18659688246671977,
1449
+ "grad_norm": 0.4014836847782135,
1450
+ "learning_rate": 0.00018459009589216364,
1451
+ "loss": 2.4456,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.18750711116167937,
1456
+ "grad_norm": 0.41716477274894714,
1457
+ "learning_rate": 0.0001844358839606705,
1458
+ "loss": 2.4357,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.18841733985663897,
1463
+ "grad_norm": 0.40400266647338867,
1464
+ "learning_rate": 0.00018428096932790632,
1465
+ "loss": 2.5122,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.1893275685515986,
1470
+ "grad_norm": 0.4276406764984131,
1471
+ "learning_rate": 0.00018412535328311814,
1472
+ "loss": 2.3581,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.1902377972465582,
1477
+ "grad_norm": 0.42548567056655884,
1478
+ "learning_rate": 0.0001839690371213903,
1479
+ "loss": 2.4639,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.1911480259415178,
1484
+ "grad_norm": 0.3912813365459442,
1485
+ "learning_rate": 0.0001838120221436338,
1486
+ "loss": 2.4395,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.1920582546364774,
1491
+ "grad_norm": 0.40997177362442017,
1492
+ "learning_rate": 0.00018365430965657526,
1493
+ "loss": 2.4833,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.192968483331437,
1498
+ "grad_norm": 0.3765038847923279,
1499
+ "learning_rate": 0.00018349590097274632,
1500
+ "loss": 2.2293,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.19387871202639664,
1505
+ "grad_norm": 0.3960655629634857,
1506
+ "learning_rate": 0.00018333679741047254,
1507
+ "loss": 2.2261,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.19478894072135625,
1512
+ "grad_norm": 0.3758634030818939,
1513
+ "learning_rate": 0.00018317700029386245,
1514
+ "loss": 2.0951,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.19569916941631585,
1519
+ "grad_norm": 0.4159095883369446,
1520
+ "learning_rate": 0.00018301651095279655,
1521
+ "loss": 2.3568,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.19660939811127545,
1526
+ "grad_norm": 0.4104447662830353,
1527
+ "learning_rate": 0.0001828553307229163,
1528
+ "loss": 2.2262,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.19751962680623505,
1533
+ "grad_norm": 0.3676728308200836,
1534
+ "learning_rate": 0.0001826934609456129,
1535
+ "loss": 2.2557,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.19842985550119469,
1540
+ "grad_norm": 0.39037179946899414,
1541
+ "learning_rate": 0.00018253090296801614,
1542
+ "loss": 2.2632,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.1993400841961543,
1547
+ "grad_norm": 0.38477587699890137,
1548
+ "learning_rate": 0.0001823676581429833,
1549
+ "loss": 2.1344,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.2002503128911139,
1554
+ "grad_norm": 0.38563740253448486,
1555
+ "learning_rate": 0.00018220372782908777,
1556
+ "loss": 2.2298,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.2011605415860735,
1561
+ "grad_norm": 0.38280826807022095,
1562
+ "learning_rate": 0.00018203911339060783,
1563
+ "loss": 2.0098,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.2020707702810331,
1568
+ "grad_norm": 0.4058510661125183,
1569
+ "learning_rate": 0.00018187381619751516,
1570
+ "loss": 2.2295,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.20298099897599273,
1575
+ "grad_norm": 0.42094549536705017,
1576
+ "learning_rate": 0.00018170783762546365,
1577
+ "loss": 2.1706,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.20389122767095233,
1582
+ "grad_norm": 0.42036664485931396,
1583
+ "learning_rate": 0.00018154117905577776,
1584
+ "loss": 2.1802,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.20480145636591193,
1589
+ "grad_norm": 0.39867401123046875,
1590
+ "learning_rate": 0.00018137384187544116,
1591
+ "loss": 2.165,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.20571168506087154,
1596
+ "grad_norm": 0.3934602737426758,
1597
+ "learning_rate": 0.00018120582747708502,
1598
+ "loss": 1.9683,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.20662191375583117,
1603
+ "grad_norm": 0.3914499282836914,
1604
+ "learning_rate": 0.0001810371372589766,
1605
+ "loss": 1.9805,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.20753214245079077,
1610
+ "grad_norm": 0.4222523868083954,
1611
+ "learning_rate": 0.0001808677726250076,
1612
+ "loss": 2.185,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.20844237114575037,
1617
+ "grad_norm": 0.3909006118774414,
1618
+ "learning_rate": 0.00018069773498468223,
1619
+ "loss": 2.0038,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 0.20935259984070997,
1624
+ "grad_norm": 0.42738041281700134,
1625
+ "learning_rate": 0.00018052702575310588,
1626
+ "loss": 2.2352,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 0.21026282853566958,
1631
+ "grad_norm": 0.4195539653301239,
1632
+ "learning_rate": 0.00018035564635097298,
1633
+ "loss": 2.0254,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 0.2111730572306292,
1638
+ "grad_norm": 0.4464121460914612,
1639
+ "learning_rate": 0.00018018359820455536,
1640
+ "loss": 2.2766,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 0.2120832859255888,
1645
+ "grad_norm": 0.42468565702438354,
1646
+ "learning_rate": 0.00018001088274569038,
1647
+ "loss": 2.1718,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 0.2129935146205484,
1652
+ "grad_norm": 0.41730690002441406,
1653
+ "learning_rate": 0.00017983750141176895,
1654
+ "loss": 2.0959,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 0.21390374331550802,
1659
+ "grad_norm": 0.4425525665283203,
1660
+ "learning_rate": 0.0001796634556457236,
1661
+ "loss": 2.1538,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 0.21481397201046762,
1666
+ "grad_norm": 0.4559743106365204,
1667
+ "learning_rate": 0.0001794887468960165,
1668
+ "loss": 2.1299,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 0.21572420070542725,
1673
+ "grad_norm": 0.43843337893486023,
1674
+ "learning_rate": 0.00017931337661662727,
1675
+ "loss": 2.1172,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 0.21663442940038685,
1680
+ "grad_norm": 0.46661749482154846,
1681
+ "learning_rate": 0.0001791373462670411,
1682
+ "loss": 2.1352,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 0.21754465809534645,
1687
+ "grad_norm": 0.4997507333755493,
1688
+ "learning_rate": 0.00017896065731223644,
1689
+ "loss": 2.1185,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 0.21845488679030606,
1694
+ "grad_norm": 0.480398029088974,
1695
+ "learning_rate": 0.00017878331122267284,
1696
+ "loss": 2.3208,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 0.21936511548526566,
1701
+ "grad_norm": 0.4819256365299225,
1702
+ "learning_rate": 0.00017860530947427875,
1703
+ "loss": 2.3114,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 0.2202753441802253,
1708
+ "grad_norm": 0.5086483359336853,
1709
+ "learning_rate": 0.00017842665354843922,
1710
+ "loss": 2.1578,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 0.2211855728751849,
1715
+ "grad_norm": 0.5267627239227295,
1716
+ "learning_rate": 0.0001782473449319835,
1717
+ "loss": 2.3594,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 0.2220958015701445,
1722
+ "grad_norm": 0.5265729427337646,
1723
+ "learning_rate": 0.0001780673851171728,
1724
+ "loss": 2.2083,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 0.2230060302651041,
1729
+ "grad_norm": 0.5762265920639038,
1730
+ "learning_rate": 0.00017788677560168784,
1731
+ "loss": 2.4887,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 0.22391625896006373,
1736
+ "grad_norm": 0.5499774217605591,
1737
+ "learning_rate": 0.0001777055178886162,
1738
+ "loss": 2.4169,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 0.22482648765502333,
1743
+ "grad_norm": 0.613876223564148,
1744
+ "learning_rate": 0.0001775236134864401,
1745
+ "loss": 2.5177,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 0.22573671634998294,
1750
+ "grad_norm": 0.6267974376678467,
1751
+ "learning_rate": 0.00017734106390902366,
1752
+ "loss": 2.5212,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 0.22664694504494254,
1757
+ "grad_norm": 0.7940219640731812,
1758
+ "learning_rate": 0.0001771578706756003,
1759
+ "loss": 2.5769,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 0.22755717373990214,
1764
+ "grad_norm": 1.3050237894058228,
1765
+ "learning_rate": 0.0001769740353107602,
1766
+ "loss": 2.3235,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 0.22846740243486177,
1771
+ "grad_norm": 0.5289978981018066,
1772
+ "learning_rate": 0.00017678955934443758,
1773
+ "loss": 2.5637,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 0.22937763112982137,
1778
+ "grad_norm": 0.5574918389320374,
1779
+ "learning_rate": 0.0001766044443118978,
1780
+ "loss": 2.5542,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 0.23028785982478098,
1785
+ "grad_norm": 0.47572481632232666,
1786
+ "learning_rate": 0.00017641869175372493,
1787
+ "loss": 2.4325,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 0.23119808851974058,
1792
+ "grad_norm": 0.41480204463005066,
1793
+ "learning_rate": 0.00017623230321580854,
1794
+ "loss": 2.5176,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 0.23210831721470018,
1799
+ "grad_norm": 0.4072042405605316,
1800
+ "learning_rate": 0.00017604528024933115,
1801
+ "loss": 2.4798,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 0.2330185459096598,
1806
+ "grad_norm": 0.3996100127696991,
1807
+ "learning_rate": 0.00017585762441075503,
1808
+ "loss": 2.35,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 0.23392877460461942,
1813
+ "grad_norm": 0.4213111698627472,
1814
+ "learning_rate": 0.00017566933726180964,
1815
+ "loss": 2.526,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 0.23483900329957902,
1820
+ "grad_norm": 0.42595675587654114,
1821
+ "learning_rate": 0.0001754804203694782,
1822
+ "loss": 2.4724,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 0.23574923199453862,
1827
+ "grad_norm": 0.407141774892807,
1828
+ "learning_rate": 0.0001752908753059849,
1829
+ "loss": 2.3349,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 0.23665946068949822,
1834
+ "grad_norm": 0.4092378616333008,
1835
+ "learning_rate": 0.00017510070364878177,
1836
+ "loss": 2.4487,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 0.23756968938445785,
1841
+ "grad_norm": 0.38301384449005127,
1842
+ "learning_rate": 0.00017490990698053563,
1843
+ "loss": 2.3245,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 0.23847991807941746,
1848
+ "grad_norm": 0.3946523666381836,
1849
+ "learning_rate": 0.00017471848688911464,
1850
+ "loss": 2.3614,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 0.23939014677437706,
1855
+ "grad_norm": 0.41228440403938293,
1856
+ "learning_rate": 0.0001745264449675755,
1857
+ "loss": 2.3525,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 0.24030037546933666,
1862
+ "grad_norm": 0.39352720975875854,
1863
+ "learning_rate": 0.00017433378281414975,
1864
+ "loss": 2.3851,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 0.24121060416429627,
1869
+ "grad_norm": 0.39706528186798096,
1870
+ "learning_rate": 0.0001741405020322309,
1871
+ "loss": 2.417,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 0.2421208328592559,
1876
+ "grad_norm": 0.3801213204860687,
1877
+ "learning_rate": 0.00017394660423036075,
1878
+ "loss": 2.1036,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 0.2430310615542155,
1883
+ "grad_norm": 0.37401556968688965,
1884
+ "learning_rate": 0.00017375209102221613,
1885
+ "loss": 2.1668,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 0.2439412902491751,
1890
+ "grad_norm": 0.3884643614292145,
1891
+ "learning_rate": 0.00017355696402659548,
1892
+ "loss": 2.3057,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 0.2448515189441347,
1897
+ "grad_norm": 0.38754650950431824,
1898
+ "learning_rate": 0.00017336122486740548,
1899
+ "loss": 2.1363,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 0.24576174763909434,
1904
+ "grad_norm": 0.3861556053161621,
1905
+ "learning_rate": 0.00017316487517364721,
1906
+ "loss": 2.2378,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 0.24667197633405394,
1911
+ "grad_norm": 0.3905907869338989,
1912
+ "learning_rate": 0.000172967916579403,
1913
+ "loss": 2.2011,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 0.24758220502901354,
1918
+ "grad_norm": 0.40004828572273254,
1919
+ "learning_rate": 0.00017277035072382253,
1920
+ "loss": 2.1316,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 0.24849243372397314,
1925
+ "grad_norm": 0.39059486985206604,
1926
+ "learning_rate": 0.00017257217925110933,
1927
+ "loss": 2.1582,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 0.24940266241893275,
1932
+ "grad_norm": 0.3994196355342865,
1933
+ "learning_rate": 0.00017237340381050703,
1934
+ "loss": 2.0078,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 0.2503128911138924,
1939
+ "grad_norm": 0.41038015484809875,
1940
+ "learning_rate": 0.00017217402605628572,
1941
+ "loss": 2.0799,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 0.2503128911138924,
1946
+ "eval_loss": 2.2957444190979004,
1947
+ "eval_runtime": 203.8901,
1948
+ "eval_samples_per_second": 9.078,
1949
+ "eval_steps_per_second": 4.542,
1950
+ "step": 275
1951
+ }
1952
+ ],
1953
+ "logging_steps": 1,
1954
+ "max_steps": 1099,
1955
+ "num_input_tokens_seen": 0,
1956
+ "num_train_epochs": 2,
1957
+ "save_steps": 275,
1958
+ "stateful_callbacks": {
1959
+ "TrainerControl": {
1960
+ "args": {
1961
+ "should_epoch_stop": false,
1962
+ "should_evaluate": false,
1963
+ "should_log": false,
1964
+ "should_save": true,
1965
+ "should_training_stop": false
1966
+ },
1967
+ "attributes": {}
1968
+ }
1969
+ },
1970
+ "total_flos": 5.1442616080583885e+17,
1971
+ "train_batch_size": 2,
1972
+ "trial_name": null,
1973
+ "trial_params": null
1974
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e3f1344d98c787aaf28c115f4535fed9403a775fab35e2c660e275263e038a
3
+ size 6776
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff