ErrorAI commited on
Commit
3be1ff5
·
verified ·
1 Parent(s): d4cb040

Training in progress, step 256, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
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": "HuggingFaceH4/tiny-random-LlamaForCausalLM",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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
+ "down_proj",
24
+ "q_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b0760ae87993ad11418958fbe05a92a32b5de1abcf483de726ef06f4318f22
3
+ size 27024
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cf02bc3e80568600b331f52e79542ebb63411d648d110997ed6310ca2d2e96
3
+ size 64038
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a593139440290e5915ac0336f5f9168eafffc54720526bd95ffafd43678a988a
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e0648f95438f89c7830b6f8c80a26c46f77f9ad47a892e79bb4601ee3155c8
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1841 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2509188924283264,
5
+ "eval_steps": 256,
6
+ "global_step": 256,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00098015192354815,
13
+ "grad_norm": 0.03393253684043884,
14
+ "learning_rate": 2e-05,
15
+ "loss": 10.36,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00098015192354815,
20
+ "eval_loss": 10.363512992858887,
21
+ "eval_runtime": 1.2869,
22
+ "eval_samples_per_second": 334.128,
23
+ "eval_steps_per_second": 167.064,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0019603038470963,
28
+ "grad_norm": 0.0322628878057003,
29
+ "learning_rate": 4e-05,
30
+ "loss": 10.3648,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.00294045577064445,
35
+ "grad_norm": 0.034470945596694946,
36
+ "learning_rate": 6e-05,
37
+ "loss": 10.3652,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0039206076941926,
42
+ "grad_norm": 0.03184035047888756,
43
+ "learning_rate": 8e-05,
44
+ "loss": 10.3651,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.00490075961774075,
49
+ "grad_norm": 0.03771933168172836,
50
+ "learning_rate": 0.0001,
51
+ "loss": 10.3613,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.0058809115412889,
56
+ "grad_norm": 0.03542574122548103,
57
+ "learning_rate": 0.00012,
58
+ "loss": 10.3634,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.00686106346483705,
63
+ "grad_norm": 0.033706825226545334,
64
+ "learning_rate": 0.00014,
65
+ "loss": 10.3632,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0078412153883852,
70
+ "grad_norm": 0.027565520256757736,
71
+ "learning_rate": 0.00016,
72
+ "loss": 10.3609,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.008821367311933349,
77
+ "grad_norm": 0.03486132621765137,
78
+ "learning_rate": 0.00018,
79
+ "loss": 10.3617,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.0098015192354815,
84
+ "grad_norm": 0.03684212639927864,
85
+ "learning_rate": 0.0002,
86
+ "loss": 10.361,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.01078167115902965,
91
+ "grad_norm": 0.030727731063961983,
92
+ "learning_rate": 0.0001999995172001916,
93
+ "loss": 10.363,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.0117618230825778,
98
+ "grad_norm": 0.034488506615161896,
99
+ "learning_rate": 0.0001999980688054283,
100
+ "loss": 10.3624,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.01274197500612595,
105
+ "grad_norm": 0.042144183069467545,
106
+ "learning_rate": 0.00019999565482969577,
107
+ "loss": 10.3668,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.0137221269296741,
112
+ "grad_norm": 0.03401128575205803,
113
+ "learning_rate": 0.00019999227529630343,
114
+ "loss": 10.365,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.014702278853222249,
119
+ "grad_norm": 0.03642333671450615,
120
+ "learning_rate": 0.00019998793023788392,
121
+ "loss": 10.3635,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.0156824307767704,
126
+ "grad_norm": 0.02629292570054531,
127
+ "learning_rate": 0.00019998261969639324,
128
+ "loss": 10.3645,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.01666258270031855,
133
+ "grad_norm": 0.038107167929410934,
134
+ "learning_rate": 0.00019997634372310988,
135
+ "loss": 10.3627,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.017642734623866698,
140
+ "grad_norm": 0.0386173315346241,
141
+ "learning_rate": 0.0001999691023786346,
142
+ "loss": 10.3624,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.018622886547414848,
147
+ "grad_norm": 0.044137127697467804,
148
+ "learning_rate": 0.00019996089573288983,
149
+ "loss": 10.3635,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.019603038470963,
154
+ "grad_norm": 0.03782758116722107,
155
+ "learning_rate": 0.0001999517238651189,
156
+ "loss": 10.3627,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.02058319039451115,
161
+ "grad_norm": 0.0326075442135334,
162
+ "learning_rate": 0.00019994158686388534,
163
+ "loss": 10.3655,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.0215633423180593,
168
+ "grad_norm": 0.038778215646743774,
169
+ "learning_rate": 0.000199930484827072,
170
+ "loss": 10.3622,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.02254349424160745,
175
+ "grad_norm": 0.03823216259479523,
176
+ "learning_rate": 0.00019991841786188007,
177
+ "loss": 10.3608,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.0235236461651556,
182
+ "grad_norm": 0.045197129249572754,
183
+ "learning_rate": 0.00019990538608482815,
184
+ "loss": 10.3598,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.02450379808870375,
189
+ "grad_norm": 0.033213067799806595,
190
+ "learning_rate": 0.00019989138962175104,
191
+ "loss": 10.3571,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.0254839500122519,
196
+ "grad_norm": 0.05107394605875015,
197
+ "learning_rate": 0.00019987642860779849,
198
+ "loss": 10.3618,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.02646410193580005,
203
+ "grad_norm": 0.046492043882608414,
204
+ "learning_rate": 0.00019986050318743402,
205
+ "loss": 10.3611,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.0274442538593482,
210
+ "grad_norm": 0.05486287549138069,
211
+ "learning_rate": 0.00019984361351443343,
212
+ "loss": 10.3586,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.028424405782896348,
217
+ "grad_norm": 0.04061867669224739,
218
+ "learning_rate": 0.00019982575975188336,
219
+ "loss": 10.3629,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.029404557706444498,
224
+ "grad_norm": 0.037819452583789825,
225
+ "learning_rate": 0.00019980694207217962,
226
+ "loss": 10.36,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.030384709629992648,
231
+ "grad_norm": 0.039589010179042816,
232
+ "learning_rate": 0.00019978716065702568,
233
+ "loss": 10.355,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.0313648615535408,
238
+ "grad_norm": 0.037119120359420776,
239
+ "learning_rate": 0.0001997664156974308,
240
+ "loss": 10.3618,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.03234501347708895,
245
+ "grad_norm": 0.047167617827653885,
246
+ "learning_rate": 0.00019974470739370827,
247
+ "loss": 10.3585,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.0333251654006371,
252
+ "grad_norm": 0.049722686409950256,
253
+ "learning_rate": 0.00019972203595547335,
254
+ "loss": 10.3574,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.03430531732418525,
259
+ "grad_norm": 0.04044399410486221,
260
+ "learning_rate": 0.00019969840160164134,
261
+ "loss": 10.3602,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.035285469247733396,
266
+ "grad_norm": 0.045635733753442764,
267
+ "learning_rate": 0.00019967380456042554,
268
+ "loss": 10.3593,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.03626562117128155,
273
+ "grad_norm": 0.044429581612348557,
274
+ "learning_rate": 0.0001996482450693348,
275
+ "loss": 10.3565,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.037245773094829696,
280
+ "grad_norm": 0.04384756460785866,
281
+ "learning_rate": 0.00019962172337517154,
282
+ "loss": 10.3534,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.03822592501837785,
287
+ "grad_norm": 0.04187103733420372,
288
+ "learning_rate": 0.00019959423973402908,
289
+ "loss": 10.3542,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.039206076941926,
294
+ "grad_norm": 0.053002797067165375,
295
+ "learning_rate": 0.00019956579441128943,
296
+ "loss": 10.3599,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.04018622886547415,
301
+ "grad_norm": 0.05618283152580261,
302
+ "learning_rate": 0.00019953638768162042,
303
+ "loss": 10.3582,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.0411663807890223,
308
+ "grad_norm": 0.03795917332172394,
309
+ "learning_rate": 0.00019950601982897338,
310
+ "loss": 10.3573,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.04214653271257045,
315
+ "grad_norm": 0.05406888946890831,
316
+ "learning_rate": 0.00019947469114658017,
317
+ "loss": 10.3514,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.0431266846361186,
322
+ "grad_norm": 0.05596392974257469,
323
+ "learning_rate": 0.00019944240193695042,
324
+ "loss": 10.3542,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.04410683655966675,
329
+ "grad_norm": 0.05652241408824921,
330
+ "learning_rate": 0.00019940915251186864,
331
+ "loss": 10.3572,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.0450869884832149,
336
+ "grad_norm": 0.06376025825738907,
337
+ "learning_rate": 0.00019937494319239113,
338
+ "loss": 10.354,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.046067140406763046,
343
+ "grad_norm": 0.05525796115398407,
344
+ "learning_rate": 0.00019933977430884294,
345
+ "loss": 10.3541,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.0470472923303112,
350
+ "grad_norm": 0.06877251714468002,
351
+ "learning_rate": 0.00019930364620081469,
352
+ "loss": 10.3469,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.048027444253859346,
357
+ "grad_norm": 0.05842923745512962,
358
+ "learning_rate": 0.00019926655921715923,
359
+ "loss": 10.3525,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.0490075961774075,
364
+ "grad_norm": 0.058936551213264465,
365
+ "learning_rate": 0.00019922851371598834,
366
+ "loss": 10.3519,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.049987748100955645,
371
+ "grad_norm": 0.051272790879011154,
372
+ "learning_rate": 0.00019918951006466927,
373
+ "loss": 10.3572,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.0509679000245038,
378
+ "grad_norm": 0.06522233784198761,
379
+ "learning_rate": 0.00019914954863982107,
380
+ "loss": 10.3526,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.05194805194805195,
385
+ "grad_norm": 0.060904137790203094,
386
+ "learning_rate": 0.00019910862982731113,
387
+ "loss": 10.3507,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.0529282038716001,
392
+ "grad_norm": 0.05767803639173508,
393
+ "learning_rate": 0.00019906675402225137,
394
+ "loss": 10.3492,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.05390835579514825,
399
+ "grad_norm": 0.06423420459032059,
400
+ "learning_rate": 0.0001990239216289944,
401
+ "loss": 10.3469,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.0548885077186964,
406
+ "grad_norm": 0.06816960126161575,
407
+ "learning_rate": 0.0001989801330611296,
408
+ "loss": 10.3516,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.05586865964224455,
413
+ "grad_norm": 0.055402230471372604,
414
+ "learning_rate": 0.00019893538874147927,
415
+ "loss": 10.3479,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.056848811565792697,
420
+ "grad_norm": 0.0635310709476471,
421
+ "learning_rate": 0.00019888968910209434,
422
+ "loss": 10.3507,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.05782896348934085,
427
+ "grad_norm": 0.05946547910571098,
428
+ "learning_rate": 0.00019884303458425037,
429
+ "loss": 10.3543,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.058809115412888996,
434
+ "grad_norm": 0.08972356468439102,
435
+ "learning_rate": 0.00019879542563844323,
436
+ "loss": 10.347,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.05978926733643715,
441
+ "grad_norm": 0.08404406905174255,
442
+ "learning_rate": 0.00019874686272438466,
443
+ "loss": 10.3478,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.060769419259985295,
448
+ "grad_norm": 0.0777248665690422,
449
+ "learning_rate": 0.00019869734631099807,
450
+ "loss": 10.3491,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.06174957118353345,
455
+ "grad_norm": 0.11122234910726547,
456
+ "learning_rate": 0.00019864687687641362,
457
+ "loss": 10.3514,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.0627297231070816,
462
+ "grad_norm": 0.07634624093770981,
463
+ "learning_rate": 0.00019859545490796411,
464
+ "loss": 10.3451,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.06370987503062975,
469
+ "grad_norm": 0.08347706496715546,
470
+ "learning_rate": 0.0001985430809021798,
471
+ "loss": 10.3441,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.0646900269541779,
476
+ "grad_norm": 0.07445404678583145,
477
+ "learning_rate": 0.00019848975536478392,
478
+ "loss": 10.3481,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.06567017887772605,
483
+ "grad_norm": 0.08683221787214279,
484
+ "learning_rate": 0.00019843547881068764,
485
+ "loss": 10.3464,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.0666503308012742,
490
+ "grad_norm": 0.0768030434846878,
491
+ "learning_rate": 0.00019838025176398513,
492
+ "loss": 10.3427,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.06763048272482235,
497
+ "grad_norm": 0.07461600005626678,
498
+ "learning_rate": 0.00019832407475794858,
499
+ "loss": 10.3469,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.0686106346483705,
504
+ "grad_norm": 0.09208466112613678,
505
+ "learning_rate": 0.00019826694833502295,
506
+ "loss": 10.3378,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.06959078657191865,
511
+ "grad_norm": 0.08798057585954666,
512
+ "learning_rate": 0.00019820887304682075,
513
+ "loss": 10.3436,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.07057093849546679,
518
+ "grad_norm": 0.061295825988054276,
519
+ "learning_rate": 0.0001981498494541167,
520
+ "loss": 10.3417,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.07155109041901495,
525
+ "grad_norm": 0.08548232167959213,
526
+ "learning_rate": 0.00019808987812684246,
527
+ "loss": 10.3386,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.0725312423425631,
532
+ "grad_norm": 0.0652792826294899,
533
+ "learning_rate": 0.00019802895964408086,
534
+ "loss": 10.3396,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.07351139426611125,
539
+ "grad_norm": 0.05445623770356178,
540
+ "learning_rate": 0.0001979670945940606,
541
+ "loss": 10.345,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.07449154618965939,
546
+ "grad_norm": 0.07501140981912613,
547
+ "learning_rate": 0.00019790428357415032,
548
+ "loss": 10.3448,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.07547169811320754,
553
+ "grad_norm": 0.07913709431886673,
554
+ "learning_rate": 0.000197840527190853,
555
+ "loss": 10.3398,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.0764518500367557,
560
+ "grad_norm": 0.06459881365299225,
561
+ "learning_rate": 0.00019777582605980007,
562
+ "loss": 10.3379,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.07743200196030385,
567
+ "grad_norm": 0.06900092214345932,
568
+ "learning_rate": 0.00019771018080574535,
569
+ "loss": 10.3427,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.078412153883852,
574
+ "grad_norm": 0.06645660102367401,
575
+ "learning_rate": 0.00019764359206255917,
576
+ "loss": 10.3421,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.07939230580740014,
581
+ "grad_norm": 0.09902693331241608,
582
+ "learning_rate": 0.00019757606047322225,
583
+ "loss": 10.3373,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.0803724577309483,
588
+ "grad_norm": 0.07565230131149292,
589
+ "learning_rate": 0.00019750758668981924,
590
+ "loss": 10.335,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.08135260965449645,
595
+ "grad_norm": 0.06608269363641739,
596
+ "learning_rate": 0.00019743817137353283,
597
+ "loss": 10.3428,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.0823327615780446,
602
+ "grad_norm": 0.05490798130631447,
603
+ "learning_rate": 0.000197367815194637,
604
+ "loss": 10.3433,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.08331291350159274,
609
+ "grad_norm": 0.06788680702447891,
610
+ "learning_rate": 0.00019729651883249074,
611
+ "loss": 10.3357,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.0842930654251409,
616
+ "grad_norm": 0.05157417431473732,
617
+ "learning_rate": 0.00019722428297553148,
618
+ "loss": 10.3393,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.08527321734868905,
623
+ "grad_norm": 0.06847544759511948,
624
+ "learning_rate": 0.00019715110832126836,
625
+ "loss": 10.3343,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.0862533692722372,
630
+ "grad_norm": 0.07157266139984131,
631
+ "learning_rate": 0.00019707699557627555,
632
+ "loss": 10.3393,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.08723352119578534,
637
+ "grad_norm": 0.06525205820798874,
638
+ "learning_rate": 0.00019700194545618543,
639
+ "loss": 10.3349,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.0882136731193335,
644
+ "grad_norm": 0.051932092756032944,
645
+ "learning_rate": 0.0001969259586856817,
646
+ "loss": 10.3414,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.08919382504288165,
651
+ "grad_norm": 0.058794520795345306,
652
+ "learning_rate": 0.00019684903599849233,
653
+ "loss": 10.3365,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.0901739769664298,
658
+ "grad_norm": 0.0768020898103714,
659
+ "learning_rate": 0.00019677117813738244,
660
+ "loss": 10.3359,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.09115412888997795,
665
+ "grad_norm": 0.06225645914673805,
666
+ "learning_rate": 0.0001966923858541473,
667
+ "loss": 10.3347,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.09213428081352609,
672
+ "grad_norm": 0.0840778648853302,
673
+ "learning_rate": 0.00019661265990960483,
674
+ "loss": 10.3335,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.09311443273707425,
679
+ "grad_norm": 0.06573595851659775,
680
+ "learning_rate": 0.00019653200107358853,
681
+ "loss": 10.3353,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.0940945846606224,
686
+ "grad_norm": 0.06430664658546448,
687
+ "learning_rate": 0.0001964504101249397,
688
+ "loss": 10.3369,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.09507473658417055,
693
+ "grad_norm": 0.06918983906507492,
694
+ "learning_rate": 0.00019636788785150038,
695
+ "loss": 10.3329,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.09605488850771869,
700
+ "grad_norm": 0.07587562501430511,
701
+ "learning_rate": 0.00019628443505010517,
702
+ "loss": 10.3336,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.09703504043126684,
707
+ "grad_norm": 0.07261679321527481,
708
+ "learning_rate": 0.0001962000525265741,
709
+ "loss": 10.3338,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.098015192354815,
714
+ "grad_norm": 0.07489949464797974,
715
+ "learning_rate": 0.00019611474109570444,
716
+ "loss": 10.333,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.09899534427836315,
721
+ "grad_norm": 0.06458555161952972,
722
+ "learning_rate": 0.00019602850158126307,
723
+ "loss": 10.3381,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.09997549620191129,
728
+ "grad_norm": 0.07608544826507568,
729
+ "learning_rate": 0.0001959413348159784,
730
+ "loss": 10.3291,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.10095564812545944,
735
+ "grad_norm": 0.07073905318975449,
736
+ "learning_rate": 0.00019585324164153237,
737
+ "loss": 10.3246,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.1019358000490076,
742
+ "grad_norm": 0.0759519711136818,
743
+ "learning_rate": 0.00019576422290855237,
744
+ "loss": 10.3271,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.10291595197255575,
749
+ "grad_norm": 0.0684719979763031,
750
+ "learning_rate": 0.0001956742794766029,
751
+ "loss": 10.3292,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.1038961038961039,
756
+ "grad_norm": 0.06708219647407532,
757
+ "learning_rate": 0.00019558341221417744,
758
+ "loss": 10.3291,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.10487625581965204,
763
+ "grad_norm": 0.06931280344724655,
764
+ "learning_rate": 0.0001954916219986899,
765
+ "loss": 10.3279,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.1058564077432002,
770
+ "grad_norm": 0.06903795897960663,
771
+ "learning_rate": 0.00019539890971646625,
772
+ "loss": 10.3236,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.10683655966674835,
777
+ "grad_norm": 0.08557268977165222,
778
+ "learning_rate": 0.00019530527626273591,
779
+ "loss": 10.3261,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.1078167115902965,
784
+ "grad_norm": 0.09294114261865616,
785
+ "learning_rate": 0.00019521072254162324,
786
+ "loss": 10.3277,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.10879686351384464,
791
+ "grad_norm": 0.09519539028406143,
792
+ "learning_rate": 0.0001951152494661385,
793
+ "loss": 10.324,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.1097770154373928,
798
+ "grad_norm": 0.07022909075021744,
799
+ "learning_rate": 0.00019501885795816936,
800
+ "loss": 10.3257,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.11075716736094095,
805
+ "grad_norm": 0.08392593264579773,
806
+ "learning_rate": 0.0001949215489484719,
807
+ "loss": 10.3241,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.1117373192844891,
812
+ "grad_norm": 0.07105713337659836,
813
+ "learning_rate": 0.00019482332337666155,
814
+ "loss": 10.3237,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.11271747120803724,
819
+ "grad_norm": 0.07048851251602173,
820
+ "learning_rate": 0.000194724182191204,
821
+ "loss": 10.3183,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.11369762313158539,
826
+ "grad_norm": 0.08710862696170807,
827
+ "learning_rate": 0.00019462412634940618,
828
+ "loss": 10.32,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.11467777505513355,
833
+ "grad_norm": 0.07351983338594437,
834
+ "learning_rate": 0.00019452315681740693,
835
+ "loss": 10.3186,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.1156579269786817,
840
+ "grad_norm": 0.07442864775657654,
841
+ "learning_rate": 0.00019442127457016767,
842
+ "loss": 10.3192,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.11663807890222985,
847
+ "grad_norm": 0.0686754435300827,
848
+ "learning_rate": 0.000194318480591463,
849
+ "loss": 10.3218,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.11761823082577799,
854
+ "grad_norm": 0.06783236563205719,
855
+ "learning_rate": 0.0001942147758738711,
856
+ "loss": 10.323,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.11859838274932614,
861
+ "grad_norm": 0.0699625313282013,
862
+ "learning_rate": 0.00019411016141876437,
863
+ "loss": 10.3187,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.1195785346728743,
868
+ "grad_norm": 0.06979627907276154,
869
+ "learning_rate": 0.00019400463823629962,
870
+ "loss": 10.3196,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.12055868659642245,
875
+ "grad_norm": 0.07828645408153534,
876
+ "learning_rate": 0.00019389820734540828,
877
+ "loss": 10.315,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.12153883851997059,
882
+ "grad_norm": 0.07804902642965317,
883
+ "learning_rate": 0.00019379086977378663,
884
+ "loss": 10.3233,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.12251899044351874,
889
+ "grad_norm": 0.07176949828863144,
890
+ "learning_rate": 0.00019368262655788585,
891
+ "loss": 10.3196,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.1234991423670669,
896
+ "grad_norm": 0.06255713850259781,
897
+ "learning_rate": 0.00019357347874290198,
898
+ "loss": 10.3263,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.12447929429061505,
903
+ "grad_norm": 0.07056183367967606,
904
+ "learning_rate": 0.00019346342738276592,
905
+ "loss": 10.3201,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.1254594462141632,
910
+ "grad_norm": 0.06492583453655243,
911
+ "learning_rate": 0.00019335247354013323,
912
+ "loss": 10.327,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.12643959813771136,
917
+ "grad_norm": 0.07965538650751114,
918
+ "learning_rate": 0.00019324061828637375,
919
+ "loss": 10.3173,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.1274197500612595,
924
+ "grad_norm": 0.07517515122890472,
925
+ "learning_rate": 0.00019312786270156136,
926
+ "loss": 10.3208,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.12839990198480764,
931
+ "grad_norm": 0.08055045455694199,
932
+ "learning_rate": 0.0001930142078744636,
933
+ "loss": 10.317,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.1293800539083558,
938
+ "grad_norm": 0.07122885435819626,
939
+ "learning_rate": 0.000192899654902531,
940
+ "loss": 10.3134,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.13036020583190394,
945
+ "grad_norm": 0.08456423878669739,
946
+ "learning_rate": 0.00019278420489188668,
947
+ "loss": 10.3055,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.1313403577554521,
952
+ "grad_norm": 0.07845564186573029,
953
+ "learning_rate": 0.00019266785895731542,
954
+ "loss": 10.3108,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.13232050967900025,
959
+ "grad_norm": 0.08686856925487518,
960
+ "learning_rate": 0.0001925506182222532,
961
+ "loss": 10.306,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.1333006616025484,
966
+ "grad_norm": 0.07293633371591568,
967
+ "learning_rate": 0.00019243248381877606,
968
+ "loss": 10.3123,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.13428081352609655,
973
+ "grad_norm": 0.08474186807870865,
974
+ "learning_rate": 0.00019231345688758934,
975
+ "loss": 10.3078,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.1352609654496447,
980
+ "grad_norm": 0.08087915182113647,
981
+ "learning_rate": 0.00019219353857801667,
982
+ "loss": 10.2999,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.13624111737319283,
987
+ "grad_norm": 0.06708812713623047,
988
+ "learning_rate": 0.00019207273004798872,
989
+ "loss": 10.3112,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.137221269296741,
994
+ "grad_norm": 0.07167868316173553,
995
+ "learning_rate": 0.0001919510324640323,
996
+ "loss": 10.3103,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.13820142122028914,
1001
+ "grad_norm": 0.08069724589586258,
1002
+ "learning_rate": 0.00019182844700125871,
1003
+ "loss": 10.3074,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.1391815731438373,
1008
+ "grad_norm": 0.08072102069854736,
1009
+ "learning_rate": 0.00019170497484335278,
1010
+ "loss": 10.3027,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.14016172506738545,
1015
+ "grad_norm": 0.0918784961104393,
1016
+ "learning_rate": 0.00019158061718256114,
1017
+ "loss": 10.3157,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.14114187699093358,
1022
+ "grad_norm": 0.08886507898569107,
1023
+ "learning_rate": 0.00019145537521968094,
1024
+ "loss": 10.3043,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.14212202891448175,
1029
+ "grad_norm": 0.07826115190982819,
1030
+ "learning_rate": 0.00019132925016404804,
1031
+ "loss": 10.3045,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.1431021808380299,
1036
+ "grad_norm": 0.06543730199337006,
1037
+ "learning_rate": 0.00019120224323352551,
1038
+ "loss": 10.3016,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.14408233276157806,
1043
+ "grad_norm": 0.07052000612020493,
1044
+ "learning_rate": 0.00019107435565449184,
1045
+ "loss": 10.2993,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.1450624846851262,
1050
+ "grad_norm": 0.06450888514518738,
1051
+ "learning_rate": 0.00019094558866182893,
1052
+ "loss": 10.3054,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.14604263660867434,
1057
+ "grad_norm": 0.06568868458271027,
1058
+ "learning_rate": 0.0001908159434989104,
1059
+ "loss": 10.3081,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.1470227885322225,
1064
+ "grad_norm": 0.07282079756259918,
1065
+ "learning_rate": 0.00019068542141758942,
1066
+ "loss": 10.3016,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.14800294045577064,
1071
+ "grad_norm": 0.05649902671575546,
1072
+ "learning_rate": 0.00019055402367818672,
1073
+ "loss": 10.2999,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.14898309237931878,
1078
+ "grad_norm": 0.07479693740606308,
1079
+ "learning_rate": 0.00019042175154947844,
1080
+ "loss": 10.305,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.14996324430286695,
1085
+ "grad_norm": 0.09553007036447525,
1086
+ "learning_rate": 0.00019028860630868364,
1087
+ "loss": 10.3068,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.1509433962264151,
1092
+ "grad_norm": 0.06522691249847412,
1093
+ "learning_rate": 0.00019015458924145228,
1094
+ "loss": 10.2978,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.15192354814996326,
1099
+ "grad_norm": 0.09592632949352264,
1100
+ "learning_rate": 0.0001900197016418527,
1101
+ "loss": 10.2939,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.1529037000735114,
1106
+ "grad_norm": 0.09996230900287628,
1107
+ "learning_rate": 0.000189883944812359,
1108
+ "loss": 10.3028,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.15388385199705953,
1113
+ "grad_norm": 0.05491139367222786,
1114
+ "learning_rate": 0.00018974732006383862,
1115
+ "loss": 10.2959,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.1548640039206077,
1120
+ "grad_norm": 0.06687158346176147,
1121
+ "learning_rate": 0.00018960982871553964,
1122
+ "loss": 10.305,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.15584415584415584,
1127
+ "grad_norm": 0.07389245927333832,
1128
+ "learning_rate": 0.0001894714720950779,
1129
+ "loss": 10.287,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.156824307767704,
1134
+ "grad_norm": 0.057053208351135254,
1135
+ "learning_rate": 0.00018933225153842446,
1136
+ "loss": 10.2943,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.15780445969125215,
1141
+ "grad_norm": 0.06835177540779114,
1142
+ "learning_rate": 0.0001891921683898925,
1143
+ "loss": 10.2958,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.1587846116148003,
1148
+ "grad_norm": 0.06674246490001678,
1149
+ "learning_rate": 0.00018905122400212433,
1150
+ "loss": 10.2891,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.15976476353834845,
1155
+ "grad_norm": 0.05715270712971687,
1156
+ "learning_rate": 0.00018890941973607843,
1157
+ "loss": 10.2962,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.1607449154618966,
1162
+ "grad_norm": 0.06741801649332047,
1163
+ "learning_rate": 0.00018876675696101626,
1164
+ "loss": 10.2962,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.16172506738544473,
1169
+ "grad_norm": 0.06996432691812515,
1170
+ "learning_rate": 0.000188623237054489,
1171
+ "loss": 10.2849,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.1627052193089929,
1176
+ "grad_norm": 0.05917774513363838,
1177
+ "learning_rate": 0.00018847886140232437,
1178
+ "loss": 10.2903,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.16368537123254104,
1183
+ "grad_norm": 0.059534668922424316,
1184
+ "learning_rate": 0.00018833363139861305,
1185
+ "loss": 10.2872,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.1646655231560892,
1190
+ "grad_norm": 0.054250460118055344,
1191
+ "learning_rate": 0.00018818754844569544,
1192
+ "loss": 10.2909,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.16564567507963734,
1197
+ "grad_norm": 0.0651603490114212,
1198
+ "learning_rate": 0.00018804061395414796,
1199
+ "loss": 10.298,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.16662582700318548,
1204
+ "grad_norm": 0.06586185097694397,
1205
+ "learning_rate": 0.0001878928293427695,
1206
+ "loss": 10.2852,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.16760597892673365,
1211
+ "grad_norm": 0.08052373677492142,
1212
+ "learning_rate": 0.0001877441960385677,
1213
+ "loss": 10.2965,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.1685861308502818,
1218
+ "grad_norm": 0.06096835061907768,
1219
+ "learning_rate": 0.0001875947154767452,
1220
+ "loss": 10.289,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.16956628277382996,
1225
+ "grad_norm": 0.058738164603710175,
1226
+ "learning_rate": 0.00018744438910068566,
1227
+ "loss": 10.2934,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.1705464346973781,
1232
+ "grad_norm": 0.05934350565075874,
1233
+ "learning_rate": 0.0001872932183619401,
1234
+ "loss": 10.2951,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.17152658662092624,
1239
+ "grad_norm": 0.05843985825777054,
1240
+ "learning_rate": 0.0001871412047202125,
1241
+ "loss": 10.3027,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.1725067385444744,
1246
+ "grad_norm": 0.05647007003426552,
1247
+ "learning_rate": 0.00018698834964334603,
1248
+ "loss": 10.2911,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.17348689046802254,
1253
+ "grad_norm": 0.06416981667280197,
1254
+ "learning_rate": 0.00018683465460730877,
1255
+ "loss": 10.2833,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.17446704239157068,
1260
+ "grad_norm": 0.08939030766487122,
1261
+ "learning_rate": 0.00018668012109617933,
1262
+ "loss": 10.2881,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.17544719431511885,
1267
+ "grad_norm": 0.061299391090869904,
1268
+ "learning_rate": 0.00018652475060213275,
1269
+ "loss": 10.2895,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.176427346238667,
1274
+ "grad_norm": 0.06778676807880402,
1275
+ "learning_rate": 0.0001863685446254259,
1276
+ "loss": 10.2927,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.17740749816221515,
1281
+ "grad_norm": 0.08366002142429352,
1282
+ "learning_rate": 0.00018621150467438308,
1283
+ "loss": 10.3028,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.1783876500857633,
1288
+ "grad_norm": 0.07463819533586502,
1289
+ "learning_rate": 0.0001860536322653815,
1290
+ "loss": 10.2869,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.17936780200931143,
1295
+ "grad_norm": 0.06123226135969162,
1296
+ "learning_rate": 0.00018589492892283653,
1297
+ "loss": 10.2816,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.1803479539328596,
1302
+ "grad_norm": 0.05946613848209381,
1303
+ "learning_rate": 0.000185735396179187,
1304
+ "loss": 10.2924,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.18132810585640774,
1309
+ "grad_norm": 0.06064407899975777,
1310
+ "learning_rate": 0.00018557503557488052,
1311
+ "loss": 10.293,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.1823082577799559,
1316
+ "grad_norm": 0.07262761890888214,
1317
+ "learning_rate": 0.0001854138486583584,
1318
+ "loss": 10.2776,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.18328840970350405,
1323
+ "grad_norm": 0.05569390952587128,
1324
+ "learning_rate": 0.00018525183698604096,
1325
+ "loss": 10.2958,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.18426856162705219,
1330
+ "grad_norm": 0.06951788067817688,
1331
+ "learning_rate": 0.00018508900212231224,
1332
+ "loss": 10.2839,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.18524871355060035,
1337
+ "grad_norm": 0.06283560395240784,
1338
+ "learning_rate": 0.0001849253456395051,
1339
+ "loss": 10.2936,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.1862288654741485,
1344
+ "grad_norm": 0.06301750242710114,
1345
+ "learning_rate": 0.00018476086911788585,
1346
+ "loss": 10.2933,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.18720901739769663,
1351
+ "grad_norm": 0.06285573542118073,
1352
+ "learning_rate": 0.00018459557414563922,
1353
+ "loss": 10.278,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.1881891693212448,
1358
+ "grad_norm": 0.055618856102228165,
1359
+ "learning_rate": 0.0001844294623188528,
1360
+ "loss": 10.2921,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.18916932124479294,
1365
+ "grad_norm": 0.059772469103336334,
1366
+ "learning_rate": 0.00018426253524150176,
1367
+ "loss": 10.2763,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.1901494731683411,
1372
+ "grad_norm": 0.054670438170433044,
1373
+ "learning_rate": 0.0001840947945254333,
1374
+ "loss": 10.2887,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.19112962509188924,
1379
+ "grad_norm": 0.06009044498205185,
1380
+ "learning_rate": 0.00018392624179035117,
1381
+ "loss": 10.2844,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.19210977701543738,
1386
+ "grad_norm": 0.05665768310427666,
1387
+ "learning_rate": 0.0001837568786637999,
1388
+ "loss": 10.2766,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.19308992893898555,
1393
+ "grad_norm": 0.052141569554805756,
1394
+ "learning_rate": 0.00018358670678114916,
1395
+ "loss": 10.2764,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.1940700808625337,
1400
+ "grad_norm": 0.05321452021598816,
1401
+ "learning_rate": 0.00018341572778557806,
1402
+ "loss": 10.287,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.19505023278608186,
1407
+ "grad_norm": 0.059462688863277435,
1408
+ "learning_rate": 0.00018324394332805912,
1409
+ "loss": 10.2825,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.19603038470963,
1414
+ "grad_norm": 0.0724351704120636,
1415
+ "learning_rate": 0.00018307135506734237,
1416
+ "loss": 10.2792,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.19701053663317813,
1421
+ "grad_norm": 0.0535559207201004,
1422
+ "learning_rate": 0.0001828979646699394,
1423
+ "loss": 10.2861,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.1979906885567263,
1428
+ "grad_norm": 0.04985260218381882,
1429
+ "learning_rate": 0.00018272377381010725,
1430
+ "loss": 10.2848,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.19897084048027444,
1435
+ "grad_norm": 0.05065443739295006,
1436
+ "learning_rate": 0.00018254878416983217,
1437
+ "loss": 10.2896,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.19995099240382258,
1442
+ "grad_norm": 0.05093695968389511,
1443
+ "learning_rate": 0.0001823729974388135,
1444
+ "loss": 10.2797,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.20093114432737075,
1449
+ "grad_norm": 0.052415069192647934,
1450
+ "learning_rate": 0.00018219641531444714,
1451
+ "loss": 10.2737,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.2019112962509189,
1456
+ "grad_norm": 0.07654762268066406,
1457
+ "learning_rate": 0.0001820190395018095,
1458
+ "loss": 10.2853,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.20289144817446705,
1463
+ "grad_norm": 0.05033020302653313,
1464
+ "learning_rate": 0.00018184087171364073,
1465
+ "loss": 10.2882,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.2038716000980152,
1470
+ "grad_norm": 0.07350358366966248,
1471
+ "learning_rate": 0.0001816619136703283,
1472
+ "loss": 10.277,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.20485175202156333,
1477
+ "grad_norm": 0.05510148033499718,
1478
+ "learning_rate": 0.00018148216709989036,
1479
+ "loss": 10.2849,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.2058319039451115,
1484
+ "grad_norm": 0.060754965990781784,
1485
+ "learning_rate": 0.00018130163373795917,
1486
+ "loss": 10.2945,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.20681205586865964,
1491
+ "grad_norm": 0.0759405791759491,
1492
+ "learning_rate": 0.0001811203153277641,
1493
+ "loss": 10.28,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.2077922077922078,
1498
+ "grad_norm": 0.07087575644254684,
1499
+ "learning_rate": 0.0001809382136201151,
1500
+ "loss": 10.2782,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.20877235971575595,
1505
+ "grad_norm": 0.04751194640994072,
1506
+ "learning_rate": 0.00018075533037338552,
1507
+ "loss": 10.2789,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.20975251163930408,
1512
+ "grad_norm": 0.07423141598701477,
1513
+ "learning_rate": 0.0001805716673534953,
1514
+ "loss": 10.2929,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.21073266356285225,
1519
+ "grad_norm": 0.06241486221551895,
1520
+ "learning_rate": 0.00018038722633389385,
1521
+ "loss": 10.2755,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.2117128154864004,
1526
+ "grad_norm": 0.06510082632303238,
1527
+ "learning_rate": 0.000180202009095543,
1528
+ "loss": 10.278,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.21269296740994853,
1533
+ "grad_norm": 0.06282279640436172,
1534
+ "learning_rate": 0.0001800160174268996,
1535
+ "loss": 10.2767,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.2136731193334967,
1540
+ "grad_norm": 0.05622153729200363,
1541
+ "learning_rate": 0.00017982925312389855,
1542
+ "loss": 10.2816,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.21465327125704484,
1547
+ "grad_norm": 0.059719186276197433,
1548
+ "learning_rate": 0.00017964171798993524,
1549
+ "loss": 10.2787,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.215633423180593,
1554
+ "grad_norm": 0.05622966215014458,
1555
+ "learning_rate": 0.00017945341383584818,
1556
+ "loss": 10.2818,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.21661357510414114,
1561
+ "grad_norm": 0.05255772918462753,
1562
+ "learning_rate": 0.0001792643424799016,
1563
+ "loss": 10.2863,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.21759372702768928,
1568
+ "grad_norm": 0.07454317063093185,
1569
+ "learning_rate": 0.00017907450574776776,
1570
+ "loss": 10.2829,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.21857387895123745,
1575
+ "grad_norm": 0.0762372687458992,
1576
+ "learning_rate": 0.0001788839054725094,
1577
+ "loss": 10.2778,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.2195540308747856,
1582
+ "grad_norm": 0.06432796269655228,
1583
+ "learning_rate": 0.00017869254349456212,
1584
+ "loss": 10.2708,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.22053418279833376,
1589
+ "grad_norm": 0.07389936596155167,
1590
+ "learning_rate": 0.00017850042166171637,
1591
+ "loss": 10.277,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.2215143347218819,
1596
+ "grad_norm": 0.06542690843343735,
1597
+ "learning_rate": 0.00017830754182909984,
1598
+ "loss": 10.2726,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.22249448664543003,
1603
+ "grad_norm": 0.059309400618076324,
1604
+ "learning_rate": 0.00017811390585915947,
1605
+ "loss": 10.2767,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.2234746385689782,
1610
+ "grad_norm": 0.06343331933021545,
1611
+ "learning_rate": 0.00017791951562164351,
1612
+ "loss": 10.2767,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.22445479049252634,
1617
+ "grad_norm": 0.05924232304096222,
1618
+ "learning_rate": 0.0001777243729935832,
1619
+ "loss": 10.2793,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 0.22543494241607448,
1624
+ "grad_norm": 0.06097643822431564,
1625
+ "learning_rate": 0.00017752847985927516,
1626
+ "loss": 10.2779,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 0.22641509433962265,
1631
+ "grad_norm": 0.05870823189616203,
1632
+ "learning_rate": 0.00017733183811026267,
1633
+ "loss": 10.2753,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 0.22739524626317079,
1638
+ "grad_norm": 0.05590877681970596,
1639
+ "learning_rate": 0.0001771344496453177,
1640
+ "loss": 10.2852,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 0.22837539818671895,
1645
+ "grad_norm": 0.06208738684654236,
1646
+ "learning_rate": 0.00017693631637042255,
1647
+ "loss": 10.2676,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 0.2293555501102671,
1652
+ "grad_norm": 0.05166775360703468,
1653
+ "learning_rate": 0.00017673744019875128,
1654
+ "loss": 10.2804,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 0.23033570203381523,
1659
+ "grad_norm": 0.04918437451124191,
1660
+ "learning_rate": 0.00017653782305065158,
1661
+ "loss": 10.2755,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 0.2313158539573634,
1666
+ "grad_norm": 0.06052442267537117,
1667
+ "learning_rate": 0.00017633746685362573,
1668
+ "loss": 10.2777,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 0.23229600588091154,
1673
+ "grad_norm": 0.05635480955243111,
1674
+ "learning_rate": 0.0001761363735423125,
1675
+ "loss": 10.2753,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 0.2332761578044597,
1680
+ "grad_norm": 0.07220935076475143,
1681
+ "learning_rate": 0.00017593454505846805,
1682
+ "loss": 10.2693,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 0.23425630972800784,
1687
+ "grad_norm": 0.06622850149869919,
1688
+ "learning_rate": 0.0001757319833509475,
1689
+ "loss": 10.2738,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 0.23523646165155598,
1694
+ "grad_norm": 0.04966101050376892,
1695
+ "learning_rate": 0.00017552869037568592,
1696
+ "loss": 10.2743,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 0.23621661357510415,
1701
+ "grad_norm": 0.06329089403152466,
1702
+ "learning_rate": 0.00017532466809567948,
1703
+ "loss": 10.2727,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 0.2371967654986523,
1708
+ "grad_norm": 0.05935171619057655,
1709
+ "learning_rate": 0.00017511991848096655,
1710
+ "loss": 10.2618,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 0.23817691742220043,
1715
+ "grad_norm": 0.04739683121442795,
1716
+ "learning_rate": 0.0001749144435086086,
1717
+ "loss": 10.2696,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 0.2391570693457486,
1722
+ "grad_norm": 0.052098359912633896,
1723
+ "learning_rate": 0.00017470824516267123,
1724
+ "loss": 10.2715,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 0.24013722126929674,
1729
+ "grad_norm": 0.05652803182601929,
1730
+ "learning_rate": 0.00017450132543420481,
1731
+ "loss": 10.2592,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 0.2411173731928449,
1736
+ "grad_norm": 0.0495261512696743,
1737
+ "learning_rate": 0.0001742936863212255,
1738
+ "loss": 10.2796,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 0.24209752511639304,
1743
+ "grad_norm": 0.06257561594247818,
1744
+ "learning_rate": 0.00017408532982869575,
1745
+ "loss": 10.2744,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 0.24307767703994118,
1750
+ "grad_norm": 0.0569571852684021,
1751
+ "learning_rate": 0.00017387625796850506,
1752
+ "loss": 10.2782,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 0.24405782896348935,
1757
+ "grad_norm": 0.053176023066043854,
1758
+ "learning_rate": 0.00017366647275945048,
1759
+ "loss": 10.2743,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 0.2450379808870375,
1764
+ "grad_norm": 0.0659627690911293,
1765
+ "learning_rate": 0.00017345597622721727,
1766
+ "loss": 10.2882,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 0.24601813281058565,
1771
+ "grad_norm": 0.05973871797323227,
1772
+ "learning_rate": 0.00017324477040435906,
1773
+ "loss": 10.2654,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 0.2469982847341338,
1778
+ "grad_norm": 0.055256184190511703,
1779
+ "learning_rate": 0.00017303285733027849,
1780
+ "loss": 10.2801,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 0.24797843665768193,
1785
+ "grad_norm": 0.06216263771057129,
1786
+ "learning_rate": 0.00017282023905120742,
1787
+ "loss": 10.2799,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 0.2489585885812301,
1792
+ "grad_norm": 0.049992430955171585,
1793
+ "learning_rate": 0.0001726069176201871,
1794
+ "loss": 10.2795,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 0.24993874050477824,
1799
+ "grad_norm": 0.05813110992312431,
1800
+ "learning_rate": 0.0001723928950970484,
1801
+ "loss": 10.2664,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 0.2509188924283264,
1806
+ "grad_norm": 0.04984869062900543,
1807
+ "learning_rate": 0.00017217817354839212,
1808
+ "loss": 10.2852,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 0.2509188924283264,
1813
+ "eval_loss": 10.270017623901367,
1814
+ "eval_runtime": 1.2708,
1815
+ "eval_samples_per_second": 338.376,
1816
+ "eval_steps_per_second": 169.188,
1817
+ "step": 256
1818
+ }
1819
+ ],
1820
+ "logging_steps": 1,
1821
+ "max_steps": 1021,
1822
+ "num_input_tokens_seen": 0,
1823
+ "num_train_epochs": 2,
1824
+ "save_steps": 256,
1825
+ "stateful_callbacks": {
1826
+ "TrainerControl": {
1827
+ "args": {
1828
+ "should_epoch_stop": false,
1829
+ "should_evaluate": false,
1830
+ "should_log": false,
1831
+ "should_save": true,
1832
+ "should_training_stop": false
1833
+ },
1834
+ "attributes": {}
1835
+ }
1836
+ },
1837
+ "total_flos": 3374967029760.0,
1838
+ "train_batch_size": 2,
1839
+ "trial_name": null,
1840
+ "trial_params": null
1841
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5093db795d92357d9fbc81ffba49bc8a20065a92062c23afe1851ce0c805c7c4
3
+ size 6776