JorgeDeC commited on
Commit
55a6b2d
1 Parent(s): 4850726

Upload folder using huggingface_hub

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db825eb96327ec98cd6c0be92184316c7c7935759efc56d7aef86ab27c6e62bb
3
  size 83946192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed38c3a897728c7451fe5f04d57503408be9cd307a61c7caf4214ac71572e1da
3
  size 83946192
checkpoint-1300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: alpindale/Mistral-7B-v0.2-hf
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 0.7.1
checkpoint-1300/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "up_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "k_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
checkpoint-1300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed38c3a897728c7451fe5f04d57503408be9cd307a61c7caf4214ac71572e1da
3
+ size 83946192
checkpoint-1300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4df5edb8f551a4d361318ef0e79e95c67b71660f900ab16d4463690dcaab2e0
3
+ size 168150290
checkpoint-1300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f02a8e9dfa7443b0ca634d6e58d813cc21f4ed67a97ce0f11e20256aece3eb
3
+ size 14244
checkpoint-1300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615aa276605a8265b5ac3e89b551e496a0ff1329b258503d845bc5d1f5727585
3
+ size 1064
checkpoint-1300/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-1300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1300/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1300/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
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
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-1300/trainer_state.json ADDED
@@ -0,0 +1,1848 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.19303586012324597,
5
+ "eval_steps": 500,
6
+ "global_step": 1300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 1.75,
14
+ "learning_rate": 2.9673590504451043e-07,
15
+ "loss": 1.433,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 1.578125,
21
+ "learning_rate": 1.483679525222552e-06,
22
+ "loss": 1.5006,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 1.4921875,
28
+ "learning_rate": 2.967359050445104e-06,
29
+ "loss": 1.4919,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 1.4921875,
35
+ "learning_rate": 4.451038575667656e-06,
36
+ "loss": 1.4531,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 1.0234375,
42
+ "learning_rate": 5.934718100890208e-06,
43
+ "loss": 1.4242,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 0.9453125,
49
+ "learning_rate": 7.418397626112759e-06,
50
+ "loss": 1.3932,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": 0.8359375,
56
+ "learning_rate": 8.902077151335312e-06,
57
+ "loss": 1.3661,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.01,
62
+ "grad_norm": 0.828125,
63
+ "learning_rate": 1.0385756676557864e-05,
64
+ "loss": 1.3677,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 0.59375,
70
+ "learning_rate": 1.1869436201780416e-05,
71
+ "loss": 1.3497,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 0.56640625,
77
+ "learning_rate": 1.3353115727002968e-05,
78
+ "loss": 1.3049,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 0.439453125,
84
+ "learning_rate": 1.4836795252225518e-05,
85
+ "loss": 1.2836,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 0.46484375,
91
+ "learning_rate": 1.6320474777448072e-05,
92
+ "loss": 1.3133,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "grad_norm": 0.40625,
98
+ "learning_rate": 1.7804154302670624e-05,
99
+ "loss": 1.2596,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.01,
104
+ "grad_norm": 0.408203125,
105
+ "learning_rate": 1.9287833827893176e-05,
106
+ "loss": 1.2612,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.01,
111
+ "grad_norm": 0.376953125,
112
+ "learning_rate": 2.0771513353115728e-05,
113
+ "loss": 1.2584,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.01,
118
+ "grad_norm": 0.40625,
119
+ "learning_rate": 2.225519287833828e-05,
120
+ "loss": 1.2386,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.01,
125
+ "grad_norm": 0.353515625,
126
+ "learning_rate": 2.3738872403560832e-05,
127
+ "loss": 1.1833,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "grad_norm": 0.349609375,
133
+ "learning_rate": 2.5222551928783384e-05,
134
+ "loss": 1.2411,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.01,
139
+ "grad_norm": 0.36328125,
140
+ "learning_rate": 2.6706231454005936e-05,
141
+ "loss": 1.1956,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.01,
146
+ "grad_norm": 0.369140625,
147
+ "learning_rate": 2.818991097922849e-05,
148
+ "loss": 1.2327,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.01,
153
+ "grad_norm": 0.353515625,
154
+ "learning_rate": 2.9673590504451037e-05,
155
+ "loss": 1.1896,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.02,
160
+ "grad_norm": 0.3984375,
161
+ "learning_rate": 3.115727002967359e-05,
162
+ "loss": 1.1979,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.02,
167
+ "grad_norm": 0.388671875,
168
+ "learning_rate": 3.2640949554896144e-05,
169
+ "loss": 1.2004,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.02,
174
+ "grad_norm": 0.392578125,
175
+ "learning_rate": 3.41246290801187e-05,
176
+ "loss": 1.1624,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.02,
181
+ "grad_norm": 0.400390625,
182
+ "learning_rate": 3.560830860534125e-05,
183
+ "loss": 1.1914,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.02,
188
+ "grad_norm": 0.41796875,
189
+ "learning_rate": 3.70919881305638e-05,
190
+ "loss": 1.1952,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.02,
195
+ "grad_norm": 0.4140625,
196
+ "learning_rate": 3.857566765578635e-05,
197
+ "loss": 1.1538,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.02,
202
+ "grad_norm": 0.4375,
203
+ "learning_rate": 4.005934718100891e-05,
204
+ "loss": 1.1702,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.02,
209
+ "grad_norm": 0.44140625,
210
+ "learning_rate": 4.1543026706231456e-05,
211
+ "loss": 1.1683,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.02,
216
+ "grad_norm": 0.443359375,
217
+ "learning_rate": 4.3026706231454005e-05,
218
+ "loss": 1.1822,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.02,
223
+ "grad_norm": 0.482421875,
224
+ "learning_rate": 4.451038575667656e-05,
225
+ "loss": 1.1649,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.02,
230
+ "grad_norm": 0.46484375,
231
+ "learning_rate": 4.5994065281899116e-05,
232
+ "loss": 1.1868,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.02,
237
+ "grad_norm": 0.5,
238
+ "learning_rate": 4.7477744807121664e-05,
239
+ "loss": 1.161,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.02,
244
+ "grad_norm": 0.451171875,
245
+ "learning_rate": 4.896142433234421e-05,
246
+ "loss": 1.1454,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.03,
251
+ "grad_norm": 0.45703125,
252
+ "learning_rate": 5.044510385756677e-05,
253
+ "loss": 1.1388,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.03,
258
+ "grad_norm": 0.490234375,
259
+ "learning_rate": 5.1928783382789324e-05,
260
+ "loss": 1.1253,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.03,
265
+ "grad_norm": 0.51171875,
266
+ "learning_rate": 5.341246290801187e-05,
267
+ "loss": 1.1527,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.03,
272
+ "grad_norm": 0.486328125,
273
+ "learning_rate": 5.489614243323442e-05,
274
+ "loss": 1.1234,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.03,
279
+ "grad_norm": 0.46875,
280
+ "learning_rate": 5.637982195845698e-05,
281
+ "loss": 1.113,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.03,
286
+ "grad_norm": 0.458984375,
287
+ "learning_rate": 5.7863501483679525e-05,
288
+ "loss": 1.1368,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.03,
293
+ "grad_norm": 0.484375,
294
+ "learning_rate": 5.9347181008902074e-05,
295
+ "loss": 1.137,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.03,
300
+ "grad_norm": 0.4765625,
301
+ "learning_rate": 6.0830860534124636e-05,
302
+ "loss": 1.1286,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.03,
307
+ "grad_norm": 0.484375,
308
+ "learning_rate": 6.231454005934718e-05,
309
+ "loss": 1.1277,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.03,
314
+ "grad_norm": 0.474609375,
315
+ "learning_rate": 6.379821958456974e-05,
316
+ "loss": 1.1268,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.03,
321
+ "grad_norm": 0.47265625,
322
+ "learning_rate": 6.528189910979229e-05,
323
+ "loss": 1.0993,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.03,
328
+ "grad_norm": 0.50390625,
329
+ "learning_rate": 6.676557863501484e-05,
330
+ "loss": 1.1017,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.03,
335
+ "grad_norm": 0.4609375,
336
+ "learning_rate": 6.82492581602374e-05,
337
+ "loss": 1.1345,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.03,
342
+ "grad_norm": 0.48828125,
343
+ "learning_rate": 6.973293768545995e-05,
344
+ "loss": 1.1086,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.04,
349
+ "grad_norm": 0.45703125,
350
+ "learning_rate": 7.12166172106825e-05,
351
+ "loss": 1.0791,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.04,
356
+ "grad_norm": 0.470703125,
357
+ "learning_rate": 7.270029673590505e-05,
358
+ "loss": 1.1158,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.04,
363
+ "grad_norm": 0.46875,
364
+ "learning_rate": 7.41839762611276e-05,
365
+ "loss": 1.132,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.04,
370
+ "grad_norm": 0.4609375,
371
+ "learning_rate": 7.566765578635016e-05,
372
+ "loss": 1.1438,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.04,
377
+ "grad_norm": 0.470703125,
378
+ "learning_rate": 7.71513353115727e-05,
379
+ "loss": 1.1405,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.04,
384
+ "grad_norm": 0.447265625,
385
+ "learning_rate": 7.863501483679525e-05,
386
+ "loss": 1.1124,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.04,
391
+ "grad_norm": 0.486328125,
392
+ "learning_rate": 8.011869436201782e-05,
393
+ "loss": 1.0813,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.04,
398
+ "grad_norm": 0.48046875,
399
+ "learning_rate": 8.160237388724036e-05,
400
+ "loss": 1.1194,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.04,
405
+ "grad_norm": 0.462890625,
406
+ "learning_rate": 8.308605341246291e-05,
407
+ "loss": 1.0927,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.04,
412
+ "grad_norm": 0.48046875,
413
+ "learning_rate": 8.456973293768546e-05,
414
+ "loss": 1.1277,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.04,
419
+ "grad_norm": 0.4453125,
420
+ "learning_rate": 8.605341246290801e-05,
421
+ "loss": 1.1271,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.04,
426
+ "grad_norm": 0.435546875,
427
+ "learning_rate": 8.753709198813057e-05,
428
+ "loss": 1.1162,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.04,
433
+ "grad_norm": 0.44921875,
434
+ "learning_rate": 8.902077151335312e-05,
435
+ "loss": 1.0857,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.05,
440
+ "grad_norm": 0.4375,
441
+ "learning_rate": 9.050445103857568e-05,
442
+ "loss": 1.0869,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.05,
447
+ "grad_norm": 0.4453125,
448
+ "learning_rate": 9.198813056379823e-05,
449
+ "loss": 1.0655,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.05,
454
+ "grad_norm": 0.4296875,
455
+ "learning_rate": 9.347181008902077e-05,
456
+ "loss": 1.0585,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.05,
461
+ "grad_norm": 0.41796875,
462
+ "learning_rate": 9.495548961424333e-05,
463
+ "loss": 1.1144,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.05,
468
+ "grad_norm": 0.43359375,
469
+ "learning_rate": 9.643916913946588e-05,
470
+ "loss": 1.0719,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.05,
475
+ "grad_norm": 0.416015625,
476
+ "learning_rate": 9.792284866468843e-05,
477
+ "loss": 1.0919,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.05,
482
+ "grad_norm": 0.423828125,
483
+ "learning_rate": 9.940652818991099e-05,
484
+ "loss": 1.1223,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.05,
489
+ "grad_norm": 0.431640625,
490
+ "learning_rate": 0.00010089020771513354,
491
+ "loss": 1.0565,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.05,
496
+ "grad_norm": 0.431640625,
497
+ "learning_rate": 0.00010237388724035609,
498
+ "loss": 1.0962,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.05,
503
+ "grad_norm": 0.44921875,
504
+ "learning_rate": 0.00010385756676557865,
505
+ "loss": 1.0959,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.05,
510
+ "grad_norm": 0.43359375,
511
+ "learning_rate": 0.0001053412462908012,
512
+ "loss": 1.0628,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.05,
517
+ "grad_norm": 0.431640625,
518
+ "learning_rate": 0.00010682492581602374,
519
+ "loss": 1.0975,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.05,
524
+ "grad_norm": 0.42578125,
525
+ "learning_rate": 0.0001083086053412463,
526
+ "loss": 1.0727,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.05,
531
+ "grad_norm": 0.416015625,
532
+ "learning_rate": 0.00010979228486646884,
533
+ "loss": 1.0649,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.06,
538
+ "grad_norm": 0.4296875,
539
+ "learning_rate": 0.00011127596439169139,
540
+ "loss": 1.0904,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.06,
545
+ "grad_norm": 0.3984375,
546
+ "learning_rate": 0.00011275964391691397,
547
+ "loss": 1.079,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.06,
552
+ "grad_norm": 0.40234375,
553
+ "learning_rate": 0.0001142433234421365,
554
+ "loss": 1.0522,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.06,
559
+ "grad_norm": 0.431640625,
560
+ "learning_rate": 0.00011572700296735905,
561
+ "loss": 1.0579,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.06,
566
+ "grad_norm": 0.396484375,
567
+ "learning_rate": 0.0001172106824925816,
568
+ "loss": 1.0871,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.06,
573
+ "grad_norm": 0.41015625,
574
+ "learning_rate": 0.00011869436201780415,
575
+ "loss": 1.0936,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.06,
580
+ "grad_norm": 0.412109375,
581
+ "learning_rate": 0.00012017804154302672,
582
+ "loss": 1.0734,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.06,
587
+ "grad_norm": 0.392578125,
588
+ "learning_rate": 0.00012166172106824927,
589
+ "loss": 1.0657,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.06,
594
+ "grad_norm": 0.4140625,
595
+ "learning_rate": 0.00012314540059347182,
596
+ "loss": 1.0884,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.06,
601
+ "grad_norm": 0.408203125,
602
+ "learning_rate": 0.00012462908011869436,
603
+ "loss": 1.0683,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.06,
608
+ "grad_norm": 0.3984375,
609
+ "learning_rate": 0.00012611275964391692,
610
+ "loss": 1.1073,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.06,
615
+ "grad_norm": 0.412109375,
616
+ "learning_rate": 0.00012759643916913948,
617
+ "loss": 1.0849,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.06,
622
+ "grad_norm": 0.40625,
623
+ "learning_rate": 0.00012908011869436204,
624
+ "loss": 1.0798,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.07,
629
+ "grad_norm": 0.404296875,
630
+ "learning_rate": 0.00013056379821958458,
631
+ "loss": 1.1029,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.07,
636
+ "grad_norm": 0.3828125,
637
+ "learning_rate": 0.0001320474777448071,
638
+ "loss": 1.0664,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.07,
643
+ "grad_norm": 0.38671875,
644
+ "learning_rate": 0.00013353115727002967,
645
+ "loss": 1.0998,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.07,
650
+ "grad_norm": 0.40234375,
651
+ "learning_rate": 0.00013501483679525224,
652
+ "loss": 1.0834,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.07,
657
+ "grad_norm": 0.400390625,
658
+ "learning_rate": 0.0001364985163204748,
659
+ "loss": 1.062,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.07,
664
+ "grad_norm": 0.3984375,
665
+ "learning_rate": 0.00013798219584569733,
666
+ "loss": 1.0825,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.07,
671
+ "grad_norm": 0.388671875,
672
+ "learning_rate": 0.0001394658753709199,
673
+ "loss": 1.0689,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.07,
678
+ "grad_norm": 0.392578125,
679
+ "learning_rate": 0.00014094955489614243,
680
+ "loss": 1.0557,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.07,
685
+ "grad_norm": 0.380859375,
686
+ "learning_rate": 0.000142433234421365,
687
+ "loss": 1.0582,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.07,
692
+ "grad_norm": 0.380859375,
693
+ "learning_rate": 0.00014391691394658756,
694
+ "loss": 1.0921,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.07,
699
+ "grad_norm": 0.384765625,
700
+ "learning_rate": 0.0001454005934718101,
701
+ "loss": 1.0544,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.07,
706
+ "grad_norm": 0.39453125,
707
+ "learning_rate": 0.00014688427299703265,
708
+ "loss": 1.0333,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.07,
713
+ "grad_norm": 0.384765625,
714
+ "learning_rate": 0.0001483679525222552,
715
+ "loss": 1.0454,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.07,
720
+ "grad_norm": 0.37890625,
721
+ "learning_rate": 0.00014985163204747775,
722
+ "loss": 1.0434,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.08,
727
+ "grad_norm": 0.390625,
728
+ "learning_rate": 0.0001513353115727003,
729
+ "loss": 1.0768,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.08,
734
+ "grad_norm": 0.376953125,
735
+ "learning_rate": 0.00015281899109792285,
736
+ "loss": 1.0774,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.08,
741
+ "grad_norm": 0.365234375,
742
+ "learning_rate": 0.0001543026706231454,
743
+ "loss": 1.0438,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.08,
748
+ "grad_norm": 0.373046875,
749
+ "learning_rate": 0.00015578635014836794,
750
+ "loss": 1.0573,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.08,
755
+ "grad_norm": 0.380859375,
756
+ "learning_rate": 0.0001572700296735905,
757
+ "loss": 1.0501,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.08,
762
+ "grad_norm": 0.392578125,
763
+ "learning_rate": 0.00015875370919881307,
764
+ "loss": 1.0413,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.08,
769
+ "grad_norm": 0.37109375,
770
+ "learning_rate": 0.00016023738872403563,
771
+ "loss": 1.0234,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.08,
776
+ "grad_norm": 0.3671875,
777
+ "learning_rate": 0.00016172106824925817,
778
+ "loss": 1.0538,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.08,
783
+ "grad_norm": 0.41015625,
784
+ "learning_rate": 0.00016320474777448073,
785
+ "loss": 1.0493,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.08,
790
+ "grad_norm": 0.35546875,
791
+ "learning_rate": 0.00016468842729970326,
792
+ "loss": 1.0686,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.08,
797
+ "grad_norm": 0.36328125,
798
+ "learning_rate": 0.00016617210682492583,
799
+ "loss": 1.0794,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.08,
804
+ "grad_norm": 0.380859375,
805
+ "learning_rate": 0.0001676557863501484,
806
+ "loss": 1.0575,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.08,
811
+ "grad_norm": 0.37109375,
812
+ "learning_rate": 0.00016913946587537092,
813
+ "loss": 1.0682,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.09,
818
+ "grad_norm": 0.361328125,
819
+ "learning_rate": 0.00017062314540059348,
820
+ "loss": 1.0237,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.09,
825
+ "grad_norm": 0.37109375,
826
+ "learning_rate": 0.00017210682492581602,
827
+ "loss": 1.0493,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.09,
832
+ "grad_norm": 0.361328125,
833
+ "learning_rate": 0.00017359050445103858,
834
+ "loss": 1.0613,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.09,
839
+ "grad_norm": 0.380859375,
840
+ "learning_rate": 0.00017507418397626114,
841
+ "loss": 1.0346,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.09,
846
+ "grad_norm": 0.375,
847
+ "learning_rate": 0.00017655786350148368,
848
+ "loss": 1.0749,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.09,
853
+ "grad_norm": 0.34765625,
854
+ "learning_rate": 0.00017804154302670624,
855
+ "loss": 1.0289,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.09,
860
+ "grad_norm": 0.353515625,
861
+ "learning_rate": 0.00017952522255192878,
862
+ "loss": 1.0606,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.09,
867
+ "grad_norm": 0.36328125,
868
+ "learning_rate": 0.00018100890207715137,
869
+ "loss": 1.0166,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.09,
874
+ "grad_norm": 0.375,
875
+ "learning_rate": 0.0001824925816023739,
876
+ "loss": 1.0347,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.09,
881
+ "grad_norm": 0.3671875,
882
+ "learning_rate": 0.00018397626112759646,
883
+ "loss": 1.0388,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.09,
888
+ "grad_norm": 0.365234375,
889
+ "learning_rate": 0.000185459940652819,
890
+ "loss": 1.0545,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.09,
895
+ "grad_norm": 0.361328125,
896
+ "learning_rate": 0.00018694362017804153,
897
+ "loss": 1.0281,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.09,
902
+ "grad_norm": 0.34765625,
903
+ "learning_rate": 0.0001884272997032641,
904
+ "loss": 1.0347,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.1,
909
+ "grad_norm": 0.353515625,
910
+ "learning_rate": 0.00018991097922848666,
911
+ "loss": 1.0347,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.1,
916
+ "grad_norm": 0.357421875,
917
+ "learning_rate": 0.00019139465875370922,
918
+ "loss": 1.0594,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.1,
923
+ "grad_norm": 0.353515625,
924
+ "learning_rate": 0.00019287833827893175,
925
+ "loss": 1.0201,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.1,
930
+ "grad_norm": 0.384765625,
931
+ "learning_rate": 0.00019436201780415432,
932
+ "loss": 1.0287,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.1,
937
+ "grad_norm": 0.359375,
938
+ "learning_rate": 0.00019584569732937685,
939
+ "loss": 1.0777,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.1,
944
+ "grad_norm": 0.349609375,
945
+ "learning_rate": 0.00019732937685459941,
946
+ "loss": 1.0157,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.1,
951
+ "grad_norm": 0.349609375,
952
+ "learning_rate": 0.00019881305637982198,
953
+ "loss": 1.0474,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.1,
958
+ "grad_norm": 0.353515625,
959
+ "learning_rate": 0.0001999999865623139,
960
+ "loss": 1.0452,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.1,
965
+ "grad_norm": 0.3828125,
966
+ "learning_rate": 0.00019999951624367985,
967
+ "loss": 1.02,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.1,
972
+ "grad_norm": 0.345703125,
973
+ "learning_rate": 0.0001999983740443526,
974
+ "loss": 1.041,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.1,
979
+ "grad_norm": 0.353515625,
980
+ "learning_rate": 0.00019999655997200635,
981
+ "loss": 1.0305,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.1,
986
+ "grad_norm": 0.359375,
987
+ "learning_rate": 0.0001999940740388296,
988
+ "loss": 1.032,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.1,
993
+ "grad_norm": 0.35546875,
994
+ "learning_rate": 0.00019999091626152492,
995
+ "loss": 1.0027,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.1,
1000
+ "grad_norm": 0.349609375,
1001
+ "learning_rate": 0.00019998708666130893,
1002
+ "loss": 1.0311,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.11,
1007
+ "grad_norm": 0.37109375,
1008
+ "learning_rate": 0.00019998258526391207,
1009
+ "loss": 1.0165,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.11,
1014
+ "grad_norm": 0.361328125,
1015
+ "learning_rate": 0.00019997741209957853,
1016
+ "loss": 1.013,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.11,
1021
+ "grad_norm": 0.357421875,
1022
+ "learning_rate": 0.00019997156720306597,
1023
+ "loss": 0.9992,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.11,
1028
+ "grad_norm": 0.34765625,
1029
+ "learning_rate": 0.00019996505061364527,
1030
+ "loss": 1.044,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.11,
1035
+ "grad_norm": 0.55859375,
1036
+ "learning_rate": 0.0001999578623751004,
1037
+ "loss": 0.998,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.11,
1042
+ "grad_norm": 0.349609375,
1043
+ "learning_rate": 0.00019995000253572798,
1044
+ "loss": 1.0354,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.11,
1049
+ "grad_norm": 0.353515625,
1050
+ "learning_rate": 0.00019994147114833698,
1051
+ "loss": 1.0083,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.11,
1056
+ "grad_norm": 0.359375,
1057
+ "learning_rate": 0.00019993226827024843,
1058
+ "loss": 1.012,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.11,
1063
+ "grad_norm": 0.359375,
1064
+ "learning_rate": 0.00019992239396329498,
1065
+ "loss": 0.9953,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.11,
1070
+ "grad_norm": 0.3515625,
1071
+ "learning_rate": 0.00019991184829382057,
1072
+ "loss": 1.0095,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.11,
1077
+ "grad_norm": 0.349609375,
1078
+ "learning_rate": 0.00019990063133267975,
1079
+ "loss": 1.0518,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.11,
1084
+ "grad_norm": 0.369140625,
1085
+ "learning_rate": 0.0001998887431552376,
1086
+ "loss": 1.0357,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.11,
1091
+ "grad_norm": 0.359375,
1092
+ "learning_rate": 0.00019987618384136879,
1093
+ "loss": 1.0542,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.12,
1098
+ "grad_norm": 0.361328125,
1099
+ "learning_rate": 0.0001998629534754574,
1100
+ "loss": 1.0071,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.12,
1105
+ "grad_norm": 0.34375,
1106
+ "learning_rate": 0.00019984905214639608,
1107
+ "loss": 1.0414,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.12,
1112
+ "grad_norm": 0.376953125,
1113
+ "learning_rate": 0.00019983447994758563,
1114
+ "loss": 1.003,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.12,
1119
+ "grad_norm": 0.3515625,
1120
+ "learning_rate": 0.00019981923697693437,
1121
+ "loss": 1.0482,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.12,
1126
+ "grad_norm": 0.361328125,
1127
+ "learning_rate": 0.00019980332333685729,
1128
+ "loss": 1.0394,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.12,
1133
+ "grad_norm": 0.353515625,
1134
+ "learning_rate": 0.00019978673913427568,
1135
+ "loss": 0.985,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.12,
1140
+ "grad_norm": 0.33984375,
1141
+ "learning_rate": 0.00019976948448061603,
1142
+ "loss": 1.0149,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.12,
1147
+ "grad_norm": 0.345703125,
1148
+ "learning_rate": 0.00019975155949180967,
1149
+ "loss": 1.0253,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.12,
1154
+ "grad_norm": 0.34765625,
1155
+ "learning_rate": 0.00019973296428829168,
1156
+ "loss": 1.0067,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.12,
1161
+ "grad_norm": 0.3515625,
1162
+ "learning_rate": 0.00019971369899500024,
1163
+ "loss": 1.013,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.12,
1168
+ "grad_norm": 0.3515625,
1169
+ "learning_rate": 0.00019969376374137578,
1170
+ "loss": 1.0253,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.12,
1175
+ "grad_norm": 0.345703125,
1176
+ "learning_rate": 0.0001996731586613601,
1177
+ "loss": 1.0505,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.12,
1182
+ "grad_norm": 0.3671875,
1183
+ "learning_rate": 0.00019965188389339537,
1184
+ "loss": 1.0199,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.12,
1189
+ "grad_norm": 0.345703125,
1190
+ "learning_rate": 0.00019962993958042336,
1191
+ "loss": 1.0066,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.13,
1196
+ "grad_norm": 0.33203125,
1197
+ "learning_rate": 0.00019960732586988438,
1198
+ "loss": 1.0226,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.13,
1203
+ "grad_norm": 0.345703125,
1204
+ "learning_rate": 0.00019958404291371635,
1205
+ "loss": 0.9902,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.13,
1210
+ "grad_norm": 0.365234375,
1211
+ "learning_rate": 0.0001995600908683537,
1212
+ "loss": 1.0338,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.13,
1217
+ "grad_norm": 0.349609375,
1218
+ "learning_rate": 0.00019953546989472633,
1219
+ "loss": 1.0103,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.13,
1224
+ "grad_norm": 0.3515625,
1225
+ "learning_rate": 0.00019951018015825866,
1226
+ "loss": 1.0237,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.13,
1231
+ "grad_norm": 0.349609375,
1232
+ "learning_rate": 0.00019948422182886833,
1233
+ "loss": 0.972,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.13,
1238
+ "grad_norm": 0.357421875,
1239
+ "learning_rate": 0.00019945759508096527,
1240
+ "loss": 1.0472,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.13,
1245
+ "grad_norm": 0.34765625,
1246
+ "learning_rate": 0.00019943030009345023,
1247
+ "loss": 1.0156,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.13,
1252
+ "grad_norm": 0.3515625,
1253
+ "learning_rate": 0.00019940233704971388,
1254
+ "loss": 1.0365,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.13,
1259
+ "grad_norm": 0.33984375,
1260
+ "learning_rate": 0.00019937370613763543,
1261
+ "loss": 1.0098,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.13,
1266
+ "grad_norm": 0.33203125,
1267
+ "learning_rate": 0.00019934440754958136,
1268
+ "loss": 1.0042,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.13,
1273
+ "grad_norm": 0.33984375,
1274
+ "learning_rate": 0.00019931444148240423,
1275
+ "loss": 1.0053,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.13,
1280
+ "grad_norm": 0.353515625,
1281
+ "learning_rate": 0.00019928380813744119,
1282
+ "loss": 1.0311,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.14,
1287
+ "grad_norm": 0.345703125,
1288
+ "learning_rate": 0.00019925250772051276,
1289
+ "loss": 0.9973,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.14,
1294
+ "grad_norm": 0.353515625,
1295
+ "learning_rate": 0.00019922054044192145,
1296
+ "loss": 1.0023,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.14,
1301
+ "grad_norm": 0.341796875,
1302
+ "learning_rate": 0.00019918790651645023,
1303
+ "loss": 1.0097,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.14,
1308
+ "grad_norm": 0.34375,
1309
+ "learning_rate": 0.00019915460616336126,
1310
+ "loss": 1.013,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.14,
1315
+ "grad_norm": 0.34765625,
1316
+ "learning_rate": 0.0001991206396063942,
1317
+ "loss": 0.9989,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.14,
1322
+ "grad_norm": 0.34375,
1323
+ "learning_rate": 0.00019908600707376495,
1324
+ "loss": 0.9815,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.14,
1329
+ "grad_norm": 0.3515625,
1330
+ "learning_rate": 0.0001990507087981639,
1331
+ "loss": 0.9753,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.14,
1336
+ "grad_norm": 0.33984375,
1337
+ "learning_rate": 0.0001990147450167545,
1338
+ "loss": 1.0145,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.14,
1343
+ "grad_norm": 0.35546875,
1344
+ "learning_rate": 0.00019897811597117168,
1345
+ "loss": 1.0359,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.14,
1350
+ "grad_norm": 0.333984375,
1351
+ "learning_rate": 0.00019894082190751998,
1352
+ "loss": 0.9902,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.14,
1357
+ "grad_norm": 0.349609375,
1358
+ "learning_rate": 0.00019890286307637237,
1359
+ "loss": 0.9997,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.14,
1364
+ "grad_norm": 0.33984375,
1365
+ "learning_rate": 0.0001988642397327681,
1366
+ "loss": 1.0412,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 0.14,
1371
+ "grad_norm": 0.33984375,
1372
+ "learning_rate": 0.00019882495213621116,
1373
+ "loss": 0.9552,
1374
+ "step": 970
1375
+ },
1376
+ {
1377
+ "epoch": 0.14,
1378
+ "grad_norm": 0.3515625,
1379
+ "learning_rate": 0.00019878500055066866,
1380
+ "loss": 0.9901,
1381
+ "step": 975
1382
+ },
1383
+ {
1384
+ "epoch": 0.15,
1385
+ "grad_norm": 0.337890625,
1386
+ "learning_rate": 0.00019874438524456888,
1387
+ "loss": 1.035,
1388
+ "step": 980
1389
+ },
1390
+ {
1391
+ "epoch": 0.15,
1392
+ "grad_norm": 0.34765625,
1393
+ "learning_rate": 0.0001987031064907995,
1394
+ "loss": 0.996,
1395
+ "step": 985
1396
+ },
1397
+ {
1398
+ "epoch": 0.15,
1399
+ "grad_norm": 0.333984375,
1400
+ "learning_rate": 0.0001986611645667059,
1401
+ "loss": 1.0248,
1402
+ "step": 990
1403
+ },
1404
+ {
1405
+ "epoch": 0.15,
1406
+ "grad_norm": 0.3515625,
1407
+ "learning_rate": 0.0001986185597540891,
1408
+ "loss": 0.9889,
1409
+ "step": 995
1410
+ },
1411
+ {
1412
+ "epoch": 0.15,
1413
+ "grad_norm": 0.341796875,
1414
+ "learning_rate": 0.00019857529233920397,
1415
+ "loss": 1.0151,
1416
+ "step": 1000
1417
+ },
1418
+ {
1419
+ "epoch": 0.15,
1420
+ "grad_norm": 0.3671875,
1421
+ "learning_rate": 0.00019853136261275737,
1422
+ "loss": 0.9882,
1423
+ "step": 1005
1424
+ },
1425
+ {
1426
+ "epoch": 0.15,
1427
+ "grad_norm": 0.33984375,
1428
+ "learning_rate": 0.00019848677086990605,
1429
+ "loss": 1.0051,
1430
+ "step": 1010
1431
+ },
1432
+ {
1433
+ "epoch": 0.15,
1434
+ "grad_norm": 0.34375,
1435
+ "learning_rate": 0.0001984415174102548,
1436
+ "loss": 0.9904,
1437
+ "step": 1015
1438
+ },
1439
+ {
1440
+ "epoch": 0.15,
1441
+ "grad_norm": 0.34765625,
1442
+ "learning_rate": 0.0001983956025378543,
1443
+ "loss": 0.9899,
1444
+ "step": 1020
1445
+ },
1446
+ {
1447
+ "epoch": 0.15,
1448
+ "grad_norm": 0.341796875,
1449
+ "learning_rate": 0.00019834902656119924,
1450
+ "loss": 0.999,
1451
+ "step": 1025
1452
+ },
1453
+ {
1454
+ "epoch": 0.15,
1455
+ "grad_norm": 0.3515625,
1456
+ "learning_rate": 0.00019830178979322614,
1457
+ "loss": 0.9798,
1458
+ "step": 1030
1459
+ },
1460
+ {
1461
+ "epoch": 0.15,
1462
+ "grad_norm": 0.349609375,
1463
+ "learning_rate": 0.00019825389255131125,
1464
+ "loss": 0.984,
1465
+ "step": 1035
1466
+ },
1467
+ {
1468
+ "epoch": 0.15,
1469
+ "grad_norm": 0.34765625,
1470
+ "learning_rate": 0.0001982053351572684,
1471
+ "loss": 1.0014,
1472
+ "step": 1040
1473
+ },
1474
+ {
1475
+ "epoch": 0.16,
1476
+ "grad_norm": 0.345703125,
1477
+ "learning_rate": 0.000198156117937347,
1478
+ "loss": 1.0148,
1479
+ "step": 1045
1480
+ },
1481
+ {
1482
+ "epoch": 0.16,
1483
+ "grad_norm": 0.330078125,
1484
+ "learning_rate": 0.0001981062412222296,
1485
+ "loss": 1.0271,
1486
+ "step": 1050
1487
+ },
1488
+ {
1489
+ "epoch": 0.16,
1490
+ "grad_norm": 0.341796875,
1491
+ "learning_rate": 0.00019805570534702987,
1492
+ "loss": 0.9902,
1493
+ "step": 1055
1494
+ },
1495
+ {
1496
+ "epoch": 0.16,
1497
+ "grad_norm": 0.330078125,
1498
+ "learning_rate": 0.00019800451065129018,
1499
+ "loss": 0.9699,
1500
+ "step": 1060
1501
+ },
1502
+ {
1503
+ "epoch": 0.16,
1504
+ "grad_norm": 0.337890625,
1505
+ "learning_rate": 0.00019795265747897956,
1506
+ "loss": 0.9911,
1507
+ "step": 1065
1508
+ },
1509
+ {
1510
+ "epoch": 0.16,
1511
+ "grad_norm": 0.345703125,
1512
+ "learning_rate": 0.00019790014617849106,
1513
+ "loss": 0.9923,
1514
+ "step": 1070
1515
+ },
1516
+ {
1517
+ "epoch": 0.16,
1518
+ "grad_norm": 0.341796875,
1519
+ "learning_rate": 0.00019784697710263974,
1520
+ "loss": 0.9976,
1521
+ "step": 1075
1522
+ },
1523
+ {
1524
+ "epoch": 0.16,
1525
+ "grad_norm": 0.3515625,
1526
+ "learning_rate": 0.00019779315060866007,
1527
+ "loss": 0.9647,
1528
+ "step": 1080
1529
+ },
1530
+ {
1531
+ "epoch": 0.16,
1532
+ "grad_norm": 0.353515625,
1533
+ "learning_rate": 0.00019773866705820363,
1534
+ "loss": 0.9589,
1535
+ "step": 1085
1536
+ },
1537
+ {
1538
+ "epoch": 0.16,
1539
+ "grad_norm": 0.330078125,
1540
+ "learning_rate": 0.00019768352681733662,
1541
+ "loss": 1.005,
1542
+ "step": 1090
1543
+ },
1544
+ {
1545
+ "epoch": 0.16,
1546
+ "grad_norm": 0.341796875,
1547
+ "learning_rate": 0.00019762773025653747,
1548
+ "loss": 1.0066,
1549
+ "step": 1095
1550
+ },
1551
+ {
1552
+ "epoch": 0.16,
1553
+ "grad_norm": 0.345703125,
1554
+ "learning_rate": 0.0001975712777506943,
1555
+ "loss": 1.0118,
1556
+ "step": 1100
1557
+ },
1558
+ {
1559
+ "epoch": 0.16,
1560
+ "grad_norm": 0.34375,
1561
+ "learning_rate": 0.00019751416967910248,
1562
+ "loss": 1.0445,
1563
+ "step": 1105
1564
+ },
1565
+ {
1566
+ "epoch": 0.16,
1567
+ "grad_norm": 0.34765625,
1568
+ "learning_rate": 0.00019745640642546196,
1569
+ "loss": 0.9766,
1570
+ "step": 1110
1571
+ },
1572
+ {
1573
+ "epoch": 0.17,
1574
+ "grad_norm": 0.353515625,
1575
+ "learning_rate": 0.0001973979883778747,
1576
+ "loss": 0.9897,
1577
+ "step": 1115
1578
+ },
1579
+ {
1580
+ "epoch": 0.17,
1581
+ "grad_norm": 0.3515625,
1582
+ "learning_rate": 0.00019733891592884227,
1583
+ "loss": 0.9826,
1584
+ "step": 1120
1585
+ },
1586
+ {
1587
+ "epoch": 0.17,
1588
+ "grad_norm": 0.34765625,
1589
+ "learning_rate": 0.00019727918947526292,
1590
+ "loss": 0.988,
1591
+ "step": 1125
1592
+ },
1593
+ {
1594
+ "epoch": 0.17,
1595
+ "grad_norm": 0.349609375,
1596
+ "learning_rate": 0.00019721880941842913,
1597
+ "loss": 1.0101,
1598
+ "step": 1130
1599
+ },
1600
+ {
1601
+ "epoch": 0.17,
1602
+ "grad_norm": 0.34375,
1603
+ "learning_rate": 0.00019715777616402479,
1604
+ "loss": 0.9744,
1605
+ "step": 1135
1606
+ },
1607
+ {
1608
+ "epoch": 0.17,
1609
+ "grad_norm": 0.33984375,
1610
+ "learning_rate": 0.0001970960901221225,
1611
+ "loss": 0.9896,
1612
+ "step": 1140
1613
+ },
1614
+ {
1615
+ "epoch": 0.17,
1616
+ "grad_norm": 0.357421875,
1617
+ "learning_rate": 0.00019703375170718093,
1618
+ "loss": 0.9786,
1619
+ "step": 1145
1620
+ },
1621
+ {
1622
+ "epoch": 0.17,
1623
+ "grad_norm": 0.34765625,
1624
+ "learning_rate": 0.00019697076133804185,
1625
+ "loss": 0.9958,
1626
+ "step": 1150
1627
+ },
1628
+ {
1629
+ "epoch": 0.17,
1630
+ "grad_norm": 0.341796875,
1631
+ "learning_rate": 0.0001969071194379275,
1632
+ "loss": 0.9803,
1633
+ "step": 1155
1634
+ },
1635
+ {
1636
+ "epoch": 0.17,
1637
+ "grad_norm": 0.3515625,
1638
+ "learning_rate": 0.00019684282643443748,
1639
+ "loss": 0.9894,
1640
+ "step": 1160
1641
+ },
1642
+ {
1643
+ "epoch": 0.17,
1644
+ "grad_norm": 0.357421875,
1645
+ "learning_rate": 0.00019677788275954624,
1646
+ "loss": 1.0073,
1647
+ "step": 1165
1648
+ },
1649
+ {
1650
+ "epoch": 0.17,
1651
+ "grad_norm": 0.33984375,
1652
+ "learning_rate": 0.00019671228884959987,
1653
+ "loss": 1.0145,
1654
+ "step": 1170
1655
+ },
1656
+ {
1657
+ "epoch": 0.17,
1658
+ "grad_norm": 0.357421875,
1659
+ "learning_rate": 0.00019664604514531332,
1660
+ "loss": 1.0035,
1661
+ "step": 1175
1662
+ },
1663
+ {
1664
+ "epoch": 0.18,
1665
+ "grad_norm": 0.353515625,
1666
+ "learning_rate": 0.0001965791520917674,
1667
+ "loss": 0.9856,
1668
+ "step": 1180
1669
+ },
1670
+ {
1671
+ "epoch": 0.18,
1672
+ "grad_norm": 0.33984375,
1673
+ "learning_rate": 0.00019651161013840583,
1674
+ "loss": 0.9573,
1675
+ "step": 1185
1676
+ },
1677
+ {
1678
+ "epoch": 0.18,
1679
+ "grad_norm": 0.328125,
1680
+ "learning_rate": 0.00019644341973903208,
1681
+ "loss": 0.9824,
1682
+ "step": 1190
1683
+ },
1684
+ {
1685
+ "epoch": 0.18,
1686
+ "grad_norm": 0.333984375,
1687
+ "learning_rate": 0.00019637458135180657,
1688
+ "loss": 0.9873,
1689
+ "step": 1195
1690
+ },
1691
+ {
1692
+ "epoch": 0.18,
1693
+ "grad_norm": 0.3515625,
1694
+ "learning_rate": 0.0001963050954392433,
1695
+ "loss": 0.9743,
1696
+ "step": 1200
1697
+ },
1698
+ {
1699
+ "epoch": 0.18,
1700
+ "grad_norm": 0.345703125,
1701
+ "learning_rate": 0.00019623496246820704,
1702
+ "loss": 0.9987,
1703
+ "step": 1205
1704
+ },
1705
+ {
1706
+ "epoch": 0.18,
1707
+ "grad_norm": 0.349609375,
1708
+ "learning_rate": 0.00019616418290990993,
1709
+ "loss": 1.0153,
1710
+ "step": 1210
1711
+ },
1712
+ {
1713
+ "epoch": 0.18,
1714
+ "grad_norm": 0.39453125,
1715
+ "learning_rate": 0.0001960927572399084,
1716
+ "loss": 0.9907,
1717
+ "step": 1215
1718
+ },
1719
+ {
1720
+ "epoch": 0.18,
1721
+ "grad_norm": 0.337890625,
1722
+ "learning_rate": 0.00019602068593810014,
1723
+ "loss": 1.0148,
1724
+ "step": 1220
1725
+ },
1726
+ {
1727
+ "epoch": 0.18,
1728
+ "grad_norm": 0.34375,
1729
+ "learning_rate": 0.0001959479694887206,
1730
+ "loss": 1.0024,
1731
+ "step": 1225
1732
+ },
1733
+ {
1734
+ "epoch": 0.18,
1735
+ "grad_norm": 0.34765625,
1736
+ "learning_rate": 0.00019587460838033996,
1737
+ "loss": 1.0298,
1738
+ "step": 1230
1739
+ },
1740
+ {
1741
+ "epoch": 0.18,
1742
+ "grad_norm": 0.357421875,
1743
+ "learning_rate": 0.00019580060310585973,
1744
+ "loss": 0.9946,
1745
+ "step": 1235
1746
+ },
1747
+ {
1748
+ "epoch": 0.18,
1749
+ "grad_norm": 0.349609375,
1750
+ "learning_rate": 0.00019572595416250942,
1751
+ "loss": 0.9961,
1752
+ "step": 1240
1753
+ },
1754
+ {
1755
+ "epoch": 0.18,
1756
+ "grad_norm": 0.333984375,
1757
+ "learning_rate": 0.00019565066205184332,
1758
+ "loss": 1.0016,
1759
+ "step": 1245
1760
+ },
1761
+ {
1762
+ "epoch": 0.19,
1763
+ "grad_norm": 0.353515625,
1764
+ "learning_rate": 0.00019557472727973707,
1765
+ "loss": 0.9829,
1766
+ "step": 1250
1767
+ },
1768
+ {
1769
+ "epoch": 0.19,
1770
+ "grad_norm": 0.34765625,
1771
+ "learning_rate": 0.00019549815035638414,
1772
+ "loss": 0.9781,
1773
+ "step": 1255
1774
+ },
1775
+ {
1776
+ "epoch": 0.19,
1777
+ "grad_norm": 0.353515625,
1778
+ "learning_rate": 0.00019542093179629268,
1779
+ "loss": 1.0089,
1780
+ "step": 1260
1781
+ },
1782
+ {
1783
+ "epoch": 0.19,
1784
+ "grad_norm": 0.34375,
1785
+ "learning_rate": 0.0001953430721182817,
1786
+ "loss": 0.9942,
1787
+ "step": 1265
1788
+ },
1789
+ {
1790
+ "epoch": 0.19,
1791
+ "grad_norm": 0.357421875,
1792
+ "learning_rate": 0.00019526457184547793,
1793
+ "loss": 0.9818,
1794
+ "step": 1270
1795
+ },
1796
+ {
1797
+ "epoch": 0.19,
1798
+ "grad_norm": 0.359375,
1799
+ "learning_rate": 0.00019518543150531207,
1800
+ "loss": 1.018,
1801
+ "step": 1275
1802
+ },
1803
+ {
1804
+ "epoch": 0.19,
1805
+ "grad_norm": 0.345703125,
1806
+ "learning_rate": 0.00019510565162951537,
1807
+ "loss": 0.9697,
1808
+ "step": 1280
1809
+ },
1810
+ {
1811
+ "epoch": 0.19,
1812
+ "grad_norm": 0.359375,
1813
+ "learning_rate": 0.00019502523275411599,
1814
+ "loss": 1.0331,
1815
+ "step": 1285
1816
+ },
1817
+ {
1818
+ "epoch": 0.19,
1819
+ "grad_norm": 0.34375,
1820
+ "learning_rate": 0.00019494417541943547,
1821
+ "loss": 1.0071,
1822
+ "step": 1290
1823
+ },
1824
+ {
1825
+ "epoch": 0.19,
1826
+ "grad_norm": 0.345703125,
1827
+ "learning_rate": 0.00019486248017008503,
1828
+ "loss": 0.9699,
1829
+ "step": 1295
1830
+ },
1831
+ {
1832
+ "epoch": 0.19,
1833
+ "grad_norm": 0.34765625,
1834
+ "learning_rate": 0.00019478014755496196,
1835
+ "loss": 1.0168,
1836
+ "step": 1300
1837
+ }
1838
+ ],
1839
+ "logging_steps": 5,
1840
+ "max_steps": 6734,
1841
+ "num_input_tokens_seen": 0,
1842
+ "num_train_epochs": 1,
1843
+ "save_steps": 100,
1844
+ "total_flos": 1.8281367660962775e+18,
1845
+ "train_batch_size": 2,
1846
+ "trial_name": null,
1847
+ "trial_params": null
1848
+ }
checkpoint-1300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa607b4c9da9ebfc565f13d64324b7945d1ef5e182ff6164c71a2bc73b18b7c
3
+ size 4984