Nishanth1904 commited on
Commit
6d72ade
·
verified ·
1 Parent(s): 1d2a1b4

Initial commit of the trained model

Browse files
checkpoint-500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.1
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
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "up_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5020252b6dda630f386cc00648df953e7aa041c89a93387f58fa5f9a670c2e85
3
+ size 167832240
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecc2415fcba69e6f44c9a0be6bf8a5876438b091f7bfd664f7fa0b74fa1be68
3
+ size 335813370
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf644e4051a25d1da857228adb6fa62fb34f4c7d3faad960abb3a53655116b2
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c9c5b95f141449146a415f99890c970673c6d2d0ffc572796645c8f7c69fd5
3
+ size 1064
checkpoint-500/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-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
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-500/trainer_state.json ADDED
@@ -0,0 +1,3549 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5555555555555556,
5
+ "eval_steps": 180,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0011111111111111111,
13
+ "grad_norm": 102.33568572998047,
14
+ "learning_rate": 2e-05,
15
+ "loss": 3.3917,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0022222222222222222,
20
+ "grad_norm": 71.03678131103516,
21
+ "learning_rate": 4e-05,
22
+ "loss": 2.41,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0033333333333333335,
27
+ "grad_norm": 87.6119613647461,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.5286,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0044444444444444444,
34
+ "grad_norm": 168.13177490234375,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.872,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.005555555555555556,
41
+ "grad_norm": 79.02127075195312,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.7781,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.006666666666666667,
48
+ "grad_norm": 22.797664642333984,
49
+ "learning_rate": 0.00012,
50
+ "loss": 0.5446,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0077777777777777776,
55
+ "grad_norm": 58.89269256591797,
56
+ "learning_rate": 0.00014,
57
+ "loss": 0.9359,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.008888888888888889,
62
+ "grad_norm": 105.92550659179688,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.5341,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 50.487552642822266,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.2262,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.011111111111111112,
76
+ "grad_norm": 7.341404438018799,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.0504,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.012222222222222223,
83
+ "grad_norm": 372.3419494628906,
84
+ "learning_rate": 0.00019977528089887642,
85
+ "loss": 3.4513,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.013333333333333334,
90
+ "grad_norm": 163.1732635498047,
91
+ "learning_rate": 0.00019955056179775282,
92
+ "loss": 3.9998,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.014444444444444444,
97
+ "grad_norm": 69.76704406738281,
98
+ "learning_rate": 0.00019932584269662923,
99
+ "loss": 1.9473,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.015555555555555555,
104
+ "grad_norm": 45.57712936401367,
105
+ "learning_rate": 0.00019910112359550563,
106
+ "loss": 1.1652,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.016666666666666666,
111
+ "grad_norm": 39.4128303527832,
112
+ "learning_rate": 0.00019887640449438204,
113
+ "loss": 0.8517,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.017777777777777778,
118
+ "grad_norm": 93.79644012451172,
119
+ "learning_rate": 0.00019865168539325844,
120
+ "loss": 0.8844,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.01888888888888889,
125
+ "grad_norm": 1860.2127685546875,
126
+ "learning_rate": 0.00019842696629213485,
127
+ "loss": 5.8394,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "grad_norm": 76.54264831542969,
133
+ "learning_rate": 0.00019820224719101123,
134
+ "loss": 1.1913,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.021111111111111112,
139
+ "grad_norm": 41.7098388671875,
140
+ "learning_rate": 0.00019797752808988766,
141
+ "loss": 0.561,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.022222222222222223,
146
+ "grad_norm": 43.46533203125,
147
+ "learning_rate": 0.00019775280898876404,
148
+ "loss": 2.4911,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.023333333333333334,
153
+ "grad_norm": 42.68752670288086,
154
+ "learning_rate": 0.00019752808988764047,
155
+ "loss": 1.5327,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.024444444444444446,
160
+ "grad_norm": 65.04448699951172,
161
+ "learning_rate": 0.00019730337078651685,
162
+ "loss": 1.6131,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.025555555555555557,
167
+ "grad_norm": 32.08937454223633,
168
+ "learning_rate": 0.00019707865168539328,
169
+ "loss": 0.2861,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.02666666666666667,
174
+ "grad_norm": 1.7243651151657104,
175
+ "learning_rate": 0.00019685393258426966,
176
+ "loss": 0.0135,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.027777777777777776,
181
+ "grad_norm": 93.21721649169922,
182
+ "learning_rate": 0.00019662921348314607,
183
+ "loss": 3.2007,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.028888888888888888,
188
+ "grad_norm": 23.15020179748535,
189
+ "learning_rate": 0.00019640449438202247,
190
+ "loss": 0.0246,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03,
195
+ "grad_norm": 56.31058120727539,
196
+ "learning_rate": 0.00019617977528089888,
197
+ "loss": 2.8603,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03111111111111111,
202
+ "grad_norm": 135.88888549804688,
203
+ "learning_rate": 0.00019595505617977529,
204
+ "loss": 6.8809,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.03222222222222222,
209
+ "grad_norm": 88.67620086669922,
210
+ "learning_rate": 0.0001957303370786517,
211
+ "loss": 2.0075,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.03333333333333333,
216
+ "grad_norm": 85.91276550292969,
217
+ "learning_rate": 0.0001955056179775281,
218
+ "loss": 1.8484,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.034444444444444444,
223
+ "grad_norm": 71.02606201171875,
224
+ "learning_rate": 0.0001952808988764045,
225
+ "loss": 2.6128,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.035555555555555556,
230
+ "grad_norm": 41.15143966674805,
231
+ "learning_rate": 0.0001950561797752809,
232
+ "loss": 0.6923,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.03666666666666667,
237
+ "grad_norm": 45.82410430908203,
238
+ "learning_rate": 0.00019483146067415731,
239
+ "loss": 1.292,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.03777777777777778,
244
+ "grad_norm": 16.980424880981445,
245
+ "learning_rate": 0.00019460674157303372,
246
+ "loss": 0.1813,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.03888888888888889,
251
+ "grad_norm": 3.7061498165130615,
252
+ "learning_rate": 0.00019438202247191013,
253
+ "loss": 0.0345,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "grad_norm": 147.18873596191406,
259
+ "learning_rate": 0.00019415730337078653,
260
+ "loss": 6.575,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04111111111111111,
265
+ "grad_norm": 111.18973541259766,
266
+ "learning_rate": 0.0001939325842696629,
267
+ "loss": 5.2346,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.042222222222222223,
272
+ "grad_norm": 63.744571685791016,
273
+ "learning_rate": 0.00019370786516853934,
274
+ "loss": 0.3574,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.043333333333333335,
279
+ "grad_norm": 30.728620529174805,
280
+ "learning_rate": 0.00019348314606741572,
281
+ "loss": 1.4175,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.044444444444444446,
286
+ "grad_norm": 47.28567123413086,
287
+ "learning_rate": 0.00019325842696629215,
288
+ "loss": 1.0363,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.04555555555555556,
293
+ "grad_norm": 29.539644241333008,
294
+ "learning_rate": 0.00019303370786516853,
295
+ "loss": 0.8918,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.04666666666666667,
300
+ "grad_norm": 22.79755973815918,
301
+ "learning_rate": 0.00019280898876404497,
302
+ "loss": 0.7274,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.04777777777777778,
307
+ "grad_norm": 11.035167694091797,
308
+ "learning_rate": 0.00019258426966292134,
309
+ "loss": 0.4017,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.04888888888888889,
314
+ "grad_norm": 68.46575164794922,
315
+ "learning_rate": 0.00019235955056179775,
316
+ "loss": 3.0663,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05,
321
+ "grad_norm": 31.108537673950195,
322
+ "learning_rate": 0.00019213483146067416,
323
+ "loss": 1.5863,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.051111111111111114,
328
+ "grad_norm": 19.158594131469727,
329
+ "learning_rate": 0.00019191011235955056,
330
+ "loss": 0.2838,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.052222222222222225,
335
+ "grad_norm": 12.934436798095703,
336
+ "learning_rate": 0.000191685393258427,
337
+ "loss": 0.1824,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.05333333333333334,
342
+ "grad_norm": 25.561677932739258,
343
+ "learning_rate": 0.00019146067415730337,
344
+ "loss": 0.9833,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.05444444444444444,
349
+ "grad_norm": 25.601179122924805,
350
+ "learning_rate": 0.0001912359550561798,
351
+ "loss": 1.035,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.05555555555555555,
356
+ "grad_norm": 23.406396865844727,
357
+ "learning_rate": 0.00019101123595505618,
358
+ "loss": 0.7995,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.056666666666666664,
363
+ "grad_norm": 47.66502380371094,
364
+ "learning_rate": 0.0001907865168539326,
365
+ "loss": 2.2336,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.057777777777777775,
370
+ "grad_norm": 20.437515258789062,
371
+ "learning_rate": 0.000190561797752809,
372
+ "loss": 0.6255,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.058888888888888886,
377
+ "grad_norm": 46.9986686706543,
378
+ "learning_rate": 0.0001903370786516854,
379
+ "loss": 1.7097,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.06,
384
+ "grad_norm": 11.840008735656738,
385
+ "learning_rate": 0.0001901123595505618,
386
+ "loss": 0.2338,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06111111111111111,
391
+ "grad_norm": 121.63400268554688,
392
+ "learning_rate": 0.0001898876404494382,
393
+ "loss": 4.0565,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.06222222222222222,
398
+ "grad_norm": 4.394570827484131,
399
+ "learning_rate": 0.00018966292134831462,
400
+ "loss": 0.0483,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.06333333333333334,
405
+ "grad_norm": 44.12479782104492,
406
+ "learning_rate": 0.00018943820224719102,
407
+ "loss": 1.63,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.06444444444444444,
412
+ "grad_norm": 49.296104431152344,
413
+ "learning_rate": 0.0001892134831460674,
414
+ "loss": 2.5672,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.06555555555555556,
419
+ "grad_norm": 50.54252624511719,
420
+ "learning_rate": 0.00018898876404494384,
421
+ "loss": 1.8064,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.06666666666666667,
426
+ "grad_norm": 19.075288772583008,
427
+ "learning_rate": 0.00018876404494382024,
428
+ "loss": 0.7887,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.06777777777777778,
433
+ "grad_norm": 70.84690856933594,
434
+ "learning_rate": 0.00018853932584269665,
435
+ "loss": 2.4248,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.06888888888888889,
440
+ "grad_norm": 30.741424560546875,
441
+ "learning_rate": 0.00018831460674157305,
442
+ "loss": 1.1513,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07,
447
+ "grad_norm": 30.2637996673584,
448
+ "learning_rate": 0.00018808988764044946,
449
+ "loss": 0.8171,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.07111111111111111,
454
+ "grad_norm": 41.01294708251953,
455
+ "learning_rate": 0.00018786516853932586,
456
+ "loss": 0.9415,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.07222222222222222,
461
+ "grad_norm": 26.83118438720703,
462
+ "learning_rate": 0.00018764044943820224,
463
+ "loss": 0.9202,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.07333333333333333,
468
+ "grad_norm": 24.340272903442383,
469
+ "learning_rate": 0.00018741573033707868,
470
+ "loss": 0.8994,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.07444444444444444,
475
+ "grad_norm": 25.56220817565918,
476
+ "learning_rate": 0.00018719101123595506,
477
+ "loss": 0.6151,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.07555555555555556,
482
+ "grad_norm": 12.082819938659668,
483
+ "learning_rate": 0.0001869662921348315,
484
+ "loss": 0.1408,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.07666666666666666,
489
+ "grad_norm": 195.4864959716797,
490
+ "learning_rate": 0.00018674157303370787,
491
+ "loss": 5.9085,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.07777777777777778,
496
+ "grad_norm": 348.45538330078125,
497
+ "learning_rate": 0.00018651685393258427,
498
+ "loss": 1.5429,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.07888888888888888,
503
+ "grad_norm": 45.640830993652344,
504
+ "learning_rate": 0.00018629213483146068,
505
+ "loss": 1.324,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08,
510
+ "grad_norm": 533.3115234375,
511
+ "learning_rate": 0.00018606741573033708,
512
+ "loss": 5.3813,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.0811111111111111,
517
+ "grad_norm": 295.1285400390625,
518
+ "learning_rate": 0.0001858426966292135,
519
+ "loss": 1.6313,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.08222222222222222,
524
+ "grad_norm": 67.95643615722656,
525
+ "learning_rate": 0.0001856179775280899,
526
+ "loss": 0.9918,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.08333333333333333,
531
+ "grad_norm": 34.739707946777344,
532
+ "learning_rate": 0.0001853932584269663,
533
+ "loss": 0.6434,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.08444444444444445,
538
+ "grad_norm": 15.449280738830566,
539
+ "learning_rate": 0.0001851685393258427,
540
+ "loss": 0.4317,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.08555555555555555,
545
+ "grad_norm": 23.836057662963867,
546
+ "learning_rate": 0.0001849438202247191,
547
+ "loss": 0.2306,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.08666666666666667,
552
+ "grad_norm": 132.614990234375,
553
+ "learning_rate": 0.00018471910112359552,
554
+ "loss": 2.1745,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.08777777777777777,
559
+ "grad_norm": 1.841304898262024,
560
+ "learning_rate": 0.00018449438202247192,
561
+ "loss": 0.0162,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.08888888888888889,
566
+ "grad_norm": 32.16089630126953,
567
+ "learning_rate": 0.00018426966292134833,
568
+ "loss": 1.412,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.09,
573
+ "grad_norm": 89.44088745117188,
574
+ "learning_rate": 0.00018404494382022474,
575
+ "loss": 5.179,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.09111111111111111,
580
+ "grad_norm": 1.6586976051330566,
581
+ "learning_rate": 0.00018382022471910114,
582
+ "loss": 0.0157,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.09222222222222222,
587
+ "grad_norm": 75.9631576538086,
588
+ "learning_rate": 0.00018359550561797755,
589
+ "loss": 3.738,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.09333333333333334,
594
+ "grad_norm": 25.27899932861328,
595
+ "learning_rate": 0.00018337078651685393,
596
+ "loss": 0.8753,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.09444444444444444,
601
+ "grad_norm": 56.37656784057617,
602
+ "learning_rate": 0.00018314606741573036,
603
+ "loss": 1.9006,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.09555555555555556,
608
+ "grad_norm": 9.31638240814209,
609
+ "learning_rate": 0.00018292134831460674,
610
+ "loss": 0.4875,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.09666666666666666,
615
+ "grad_norm": 14.741087913513184,
616
+ "learning_rate": 0.00018269662921348317,
617
+ "loss": 0.5705,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.09777777777777778,
622
+ "grad_norm": 61.590110778808594,
623
+ "learning_rate": 0.00018247191011235955,
624
+ "loss": 2.0326,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.09888888888888889,
629
+ "grad_norm": 15.012186050415039,
630
+ "learning_rate": 0.00018224719101123598,
631
+ "loss": 0.2379,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.1,
636
+ "grad_norm": 28.546709060668945,
637
+ "learning_rate": 0.00018202247191011236,
638
+ "loss": 0.9058,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.10111111111111111,
643
+ "grad_norm": 18.589202880859375,
644
+ "learning_rate": 0.00018179775280898877,
645
+ "loss": 0.7318,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.10222222222222223,
650
+ "grad_norm": 37.87327194213867,
651
+ "learning_rate": 0.00018157303370786517,
652
+ "loss": 1.2634,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.10333333333333333,
657
+ "grad_norm": 18.840261459350586,
658
+ "learning_rate": 0.00018134831460674158,
659
+ "loss": 0.6082,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.10444444444444445,
664
+ "grad_norm": 10.736745834350586,
665
+ "learning_rate": 0.00018112359550561798,
666
+ "loss": 0.4443,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.10555555555555556,
671
+ "grad_norm": 26.20573616027832,
672
+ "learning_rate": 0.0001808988764044944,
673
+ "loss": 0.9038,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.10666666666666667,
678
+ "grad_norm": 10.82790470123291,
679
+ "learning_rate": 0.0001806741573033708,
680
+ "loss": 0.3573,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.10777777777777778,
685
+ "grad_norm": 37.660911560058594,
686
+ "learning_rate": 0.0001804494382022472,
687
+ "loss": 0.901,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.10888888888888888,
692
+ "grad_norm": 42.1888313293457,
693
+ "learning_rate": 0.0001802247191011236,
694
+ "loss": 0.7758,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.11,
699
+ "grad_norm": 67.9056167602539,
700
+ "learning_rate": 0.00018,
701
+ "loss": 2.444,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.1111111111111111,
706
+ "grad_norm": 1.2387319803237915,
707
+ "learning_rate": 0.00017977528089887642,
708
+ "loss": 0.0135,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.11222222222222222,
713
+ "grad_norm": 230.72996520996094,
714
+ "learning_rate": 0.00017955056179775282,
715
+ "loss": 3.7946,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.11333333333333333,
720
+ "grad_norm": 147.30657958984375,
721
+ "learning_rate": 0.00017932584269662923,
722
+ "loss": 2.9107,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.11444444444444445,
727
+ "grad_norm": 47.93574905395508,
728
+ "learning_rate": 0.0001791011235955056,
729
+ "loss": 2.0105,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.11555555555555555,
734
+ "grad_norm": 31.017885208129883,
735
+ "learning_rate": 0.00017887640449438204,
736
+ "loss": 0.7397,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.11666666666666667,
741
+ "grad_norm": 24.44668960571289,
742
+ "learning_rate": 0.00017865168539325842,
743
+ "loss": 0.2795,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.11777777777777777,
748
+ "grad_norm": 21.630537033081055,
749
+ "learning_rate": 0.00017842696629213485,
750
+ "loss": 0.4511,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.11888888888888889,
755
+ "grad_norm": 60.735191345214844,
756
+ "learning_rate": 0.00017820224719101123,
757
+ "loss": 0.6812,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.12,
762
+ "grad_norm": 3.938781976699829,
763
+ "learning_rate": 0.00017797752808988766,
764
+ "loss": 0.0504,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.12111111111111111,
769
+ "grad_norm": 19.881391525268555,
770
+ "learning_rate": 0.00017775280898876404,
771
+ "loss": 0.3306,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.12222222222222222,
776
+ "grad_norm": 38.422508239746094,
777
+ "learning_rate": 0.00017752808988764045,
778
+ "loss": 1.2349,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.12333333333333334,
783
+ "grad_norm": 110.60405731201172,
784
+ "learning_rate": 0.00017730337078651685,
785
+ "loss": 3.4469,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.12444444444444444,
790
+ "grad_norm": 2.1574478149414062,
791
+ "learning_rate": 0.00017707865168539326,
792
+ "loss": 0.0222,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.12555555555555556,
797
+ "grad_norm": 36.75973129272461,
798
+ "learning_rate": 0.00017685393258426966,
799
+ "loss": 2.277,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.12666666666666668,
804
+ "grad_norm": 24.548324584960938,
805
+ "learning_rate": 0.00017662921348314607,
806
+ "loss": 1.0237,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.12777777777777777,
811
+ "grad_norm": 23.797250747680664,
812
+ "learning_rate": 0.00017640449438202248,
813
+ "loss": 0.6428,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.1288888888888889,
818
+ "grad_norm": 56.43831253051758,
819
+ "learning_rate": 0.00017617977528089888,
820
+ "loss": 1.6894,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.13,
825
+ "grad_norm": 37.36240768432617,
826
+ "learning_rate": 0.0001759550561797753,
827
+ "loss": 0.7076,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.13111111111111112,
832
+ "grad_norm": 17.362285614013672,
833
+ "learning_rate": 0.0001757303370786517,
834
+ "loss": 0.4112,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.1322222222222222,
839
+ "grad_norm": 18.96011734008789,
840
+ "learning_rate": 0.0001755056179775281,
841
+ "loss": 0.4187,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.13333333333333333,
846
+ "grad_norm": 10.313982963562012,
847
+ "learning_rate": 0.0001752808988764045,
848
+ "loss": 0.2138,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.13444444444444445,
853
+ "grad_norm": 15.248143196105957,
854
+ "learning_rate": 0.0001750561797752809,
855
+ "loss": 0.4422,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.13555555555555557,
860
+ "grad_norm": 12.482340812683105,
861
+ "learning_rate": 0.00017483146067415732,
862
+ "loss": 0.2538,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.13666666666666666,
867
+ "grad_norm": 25.393978118896484,
868
+ "learning_rate": 0.00017460674157303372,
869
+ "loss": 0.3031,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.13777777777777778,
874
+ "grad_norm": 89.2987289428711,
875
+ "learning_rate": 0.0001743820224719101,
876
+ "loss": 2.5174,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.1388888888888889,
881
+ "grad_norm": 59.19680404663086,
882
+ "learning_rate": 0.00017415730337078653,
883
+ "loss": 3.8405,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.14,
888
+ "grad_norm": 23.57353401184082,
889
+ "learning_rate": 0.0001739325842696629,
890
+ "loss": 1.4165,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.1411111111111111,
895
+ "grad_norm": 19.143470764160156,
896
+ "learning_rate": 0.00017370786516853934,
897
+ "loss": 0.7185,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.14222222222222222,
902
+ "grad_norm": 15.651366233825684,
903
+ "learning_rate": 0.00017348314606741572,
904
+ "loss": 0.434,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.14333333333333334,
909
+ "grad_norm": 5.860520839691162,
910
+ "learning_rate": 0.00017325842696629216,
911
+ "loss": 0.3389,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.14444444444444443,
916
+ "grad_norm": 408.245361328125,
917
+ "learning_rate": 0.00017303370786516853,
918
+ "loss": 3.212,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.14555555555555555,
923
+ "grad_norm": 23.224733352661133,
924
+ "learning_rate": 0.00017280898876404494,
925
+ "loss": 0.6577,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.14666666666666667,
930
+ "grad_norm": 38.35893249511719,
931
+ "learning_rate": 0.00017258426966292137,
932
+ "loss": 0.365,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.14777777777777779,
937
+ "grad_norm": 170.56166076660156,
938
+ "learning_rate": 0.00017235955056179775,
939
+ "loss": 1.5118,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.14888888888888888,
944
+ "grad_norm": 60.7258186340332,
945
+ "learning_rate": 0.00017213483146067418,
946
+ "loss": 0.5725,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.15,
951
+ "grad_norm": 17.91878890991211,
952
+ "learning_rate": 0.00017191011235955056,
953
+ "loss": 0.3609,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.1511111111111111,
958
+ "grad_norm": 209.5665740966797,
959
+ "learning_rate": 0.000171685393258427,
960
+ "loss": 2.0971,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.15222222222222223,
965
+ "grad_norm": 629.0282592773438,
966
+ "learning_rate": 0.00017146067415730337,
967
+ "loss": 7.3174,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.15333333333333332,
972
+ "grad_norm": 650.0385131835938,
973
+ "learning_rate": 0.00017123595505617978,
974
+ "loss": 8.6883,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.15444444444444444,
979
+ "grad_norm": 575.3070678710938,
980
+ "learning_rate": 0.00017101123595505619,
981
+ "loss": 4.08,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.15555555555555556,
986
+ "grad_norm": 1292.37744140625,
987
+ "learning_rate": 0.0001707865168539326,
988
+ "loss": 7.8023,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.15666666666666668,
993
+ "grad_norm": 184.1406707763672,
994
+ "learning_rate": 0.000170561797752809,
995
+ "loss": 15.3245,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.15777777777777777,
1000
+ "grad_norm": 1247.0816650390625,
1001
+ "learning_rate": 0.0001703370786516854,
1002
+ "loss": 4.6827,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.15888888888888889,
1007
+ "grad_norm": 153.21849060058594,
1008
+ "learning_rate": 0.00017011235955056178,
1009
+ "loss": 21.3168,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.16,
1014
+ "grad_norm": 172.53648376464844,
1015
+ "learning_rate": 0.00016988764044943822,
1016
+ "loss": 10.1605,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.16111111111111112,
1021
+ "grad_norm": 76.09978485107422,
1022
+ "learning_rate": 0.00016966292134831462,
1023
+ "loss": 1.1253,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.1622222222222222,
1028
+ "grad_norm": 10.127947807312012,
1029
+ "learning_rate": 0.00016943820224719103,
1030
+ "loss": 0.1717,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.16333333333333333,
1035
+ "grad_norm": 25.834461212158203,
1036
+ "learning_rate": 0.00016921348314606743,
1037
+ "loss": 0.6494,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.16444444444444445,
1042
+ "grad_norm": 18.16613006591797,
1043
+ "learning_rate": 0.00016898876404494384,
1044
+ "loss": 0.4913,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.16555555555555557,
1049
+ "grad_norm": 1973.9840087890625,
1050
+ "learning_rate": 0.00016876404494382024,
1051
+ "loss": 1.3598,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.16666666666666666,
1056
+ "grad_norm": 23.60765266418457,
1057
+ "learning_rate": 0.00016853932584269662,
1058
+ "loss": 0.4692,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.16777777777777778,
1063
+ "grad_norm": 504.2148742675781,
1064
+ "learning_rate": 0.00016831460674157306,
1065
+ "loss": 11.6522,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.1688888888888889,
1070
+ "grad_norm": 87.10939025878906,
1071
+ "learning_rate": 0.00016808988764044943,
1072
+ "loss": 10.8182,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.17,
1077
+ "grad_norm": 31.426206588745117,
1078
+ "learning_rate": 0.00016786516853932587,
1079
+ "loss": 1.512,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.1711111111111111,
1084
+ "grad_norm": 177.4807586669922,
1085
+ "learning_rate": 0.00016764044943820225,
1086
+ "loss": 3.9284,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.17222222222222222,
1091
+ "grad_norm": 7.644647121429443,
1092
+ "learning_rate": 0.00016741573033707868,
1093
+ "loss": 0.2555,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.17333333333333334,
1098
+ "grad_norm": 19.08963394165039,
1099
+ "learning_rate": 0.00016719101123595506,
1100
+ "loss": 0.7381,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.17444444444444446,
1105
+ "grad_norm": 23.4483585357666,
1106
+ "learning_rate": 0.00016696629213483146,
1107
+ "loss": 0.5942,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.17555555555555555,
1112
+ "grad_norm": 9.067717552185059,
1113
+ "learning_rate": 0.00016674157303370787,
1114
+ "loss": 0.1365,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.17666666666666667,
1119
+ "grad_norm": 10.63211727142334,
1120
+ "learning_rate": 0.00016651685393258427,
1121
+ "loss": 0.3078,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.17777777777777778,
1126
+ "grad_norm": 70.5125503540039,
1127
+ "learning_rate": 0.00016629213483146068,
1128
+ "loss": 1.8492,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.17888888888888888,
1133
+ "grad_norm": 45.161231994628906,
1134
+ "learning_rate": 0.00016606741573033709,
1135
+ "loss": 1.4257,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.18,
1140
+ "grad_norm": 3.695596933364868,
1141
+ "learning_rate": 0.0001658426966292135,
1142
+ "loss": 0.0426,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.1811111111111111,
1147
+ "grad_norm": 26.803974151611328,
1148
+ "learning_rate": 0.0001656179775280899,
1149
+ "loss": 1.1486,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.18222222222222223,
1154
+ "grad_norm": 2.259025812149048,
1155
+ "learning_rate": 0.0001653932584269663,
1156
+ "loss": 0.0266,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.18333333333333332,
1161
+ "grad_norm": 45.783992767333984,
1162
+ "learning_rate": 0.0001651685393258427,
1163
+ "loss": 1.8611,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.18444444444444444,
1168
+ "grad_norm": 43.95121765136719,
1169
+ "learning_rate": 0.00016494382022471911,
1170
+ "loss": 1.6204,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.18555555555555556,
1175
+ "grad_norm": 17.024168014526367,
1176
+ "learning_rate": 0.00016471910112359552,
1177
+ "loss": 0.5817,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.18666666666666668,
1182
+ "grad_norm": 14.731273651123047,
1183
+ "learning_rate": 0.00016449438202247193,
1184
+ "loss": 0.4974,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.18777777777777777,
1189
+ "grad_norm": 97.03413391113281,
1190
+ "learning_rate": 0.00016426966292134833,
1191
+ "loss": 2.7158,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.18888888888888888,
1196
+ "grad_norm": 21.881189346313477,
1197
+ "learning_rate": 0.00016404494382022474,
1198
+ "loss": 0.9915,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.19,
1203
+ "grad_norm": 26.148059844970703,
1204
+ "learning_rate": 0.00016382022471910112,
1205
+ "loss": 1.2371,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.19111111111111112,
1210
+ "grad_norm": 15.849732398986816,
1211
+ "learning_rate": 0.00016359550561797755,
1212
+ "loss": 0.7417,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.1922222222222222,
1217
+ "grad_norm": 35.608787536621094,
1218
+ "learning_rate": 0.00016337078651685393,
1219
+ "loss": 1.1444,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.19333333333333333,
1224
+ "grad_norm": 313.6637268066406,
1225
+ "learning_rate": 0.00016314606741573036,
1226
+ "loss": 1.3129,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.19444444444444445,
1231
+ "grad_norm": 35.658935546875,
1232
+ "learning_rate": 0.00016292134831460674,
1233
+ "loss": 1.1562,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.19555555555555557,
1238
+ "grad_norm": 20.081708908081055,
1239
+ "learning_rate": 0.00016269662921348317,
1240
+ "loss": 0.953,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.19666666666666666,
1245
+ "grad_norm": 237.23558044433594,
1246
+ "learning_rate": 0.00016247191011235955,
1247
+ "loss": 0.9067,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.19777777777777777,
1252
+ "grad_norm": 14.085380554199219,
1253
+ "learning_rate": 0.00016224719101123596,
1254
+ "loss": 0.6052,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.1988888888888889,
1259
+ "grad_norm": 17.453121185302734,
1260
+ "learning_rate": 0.00016202247191011236,
1261
+ "loss": 0.3606,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.2,
1266
+ "grad_norm": 9.049514770507812,
1267
+ "learning_rate": 0.00016179775280898877,
1268
+ "loss": 0.4557,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.2,
1273
+ "eval_loss": 0.9586671590805054,
1274
+ "eval_runtime": 21.7348,
1275
+ "eval_samples_per_second": 9.202,
1276
+ "eval_steps_per_second": 9.202,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.2011111111111111,
1281
+ "grad_norm": 46.25217819213867,
1282
+ "learning_rate": 0.00016157303370786517,
1283
+ "loss": 1.8674,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.20222222222222222,
1288
+ "grad_norm": 6.772250652313232,
1289
+ "learning_rate": 0.00016134831460674158,
1290
+ "loss": 0.3823,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.20333333333333334,
1295
+ "grad_norm": 39.23698425292969,
1296
+ "learning_rate": 0.00016112359550561798,
1297
+ "loss": 2.0507,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.20444444444444446,
1302
+ "grad_norm": 30.432716369628906,
1303
+ "learning_rate": 0.0001608988764044944,
1304
+ "loss": 0.6654,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.20555555555555555,
1309
+ "grad_norm": 75.6773452758789,
1310
+ "learning_rate": 0.0001606741573033708,
1311
+ "loss": 3.0721,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.20666666666666667,
1316
+ "grad_norm": 12.808838844299316,
1317
+ "learning_rate": 0.0001604494382022472,
1318
+ "loss": 0.2123,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.20777777777777778,
1323
+ "grad_norm": 9.990399360656738,
1324
+ "learning_rate": 0.0001602247191011236,
1325
+ "loss": 0.4268,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.2088888888888889,
1330
+ "grad_norm": 10.55019760131836,
1331
+ "learning_rate": 0.00016,
1332
+ "loss": 0.5379,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.21,
1337
+ "grad_norm": 6.222032070159912,
1338
+ "learning_rate": 0.00015977528089887642,
1339
+ "loss": 0.3611,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.2111111111111111,
1344
+ "grad_norm": 22.25773811340332,
1345
+ "learning_rate": 0.0001595505617977528,
1346
+ "loss": 0.4645,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.21222222222222223,
1351
+ "grad_norm": 14.081616401672363,
1352
+ "learning_rate": 0.00015932584269662923,
1353
+ "loss": 0.2267,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.21333333333333335,
1358
+ "grad_norm": 12.858074188232422,
1359
+ "learning_rate": 0.0001591011235955056,
1360
+ "loss": 0.4497,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.21444444444444444,
1365
+ "grad_norm": 13.450520515441895,
1366
+ "learning_rate": 0.00015887640449438204,
1367
+ "loss": 0.4342,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.21555555555555556,
1372
+ "grad_norm": 26.104228973388672,
1373
+ "learning_rate": 0.00015865168539325842,
1374
+ "loss": 0.4767,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.21666666666666667,
1379
+ "grad_norm": 4.591059684753418,
1380
+ "learning_rate": 0.00015842696629213485,
1381
+ "loss": 0.2366,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.21777777777777776,
1386
+ "grad_norm": 14.392906188964844,
1387
+ "learning_rate": 0.00015820224719101123,
1388
+ "loss": 0.4592,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.21888888888888888,
1393
+ "grad_norm": 10.795453071594238,
1394
+ "learning_rate": 0.00015797752808988764,
1395
+ "loss": 0.2973,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.22,
1400
+ "grad_norm": 40.464500427246094,
1401
+ "learning_rate": 0.00015775280898876404,
1402
+ "loss": 3.2891,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.22111111111111112,
1407
+ "grad_norm": 7.494422912597656,
1408
+ "learning_rate": 0.00015752808988764045,
1409
+ "loss": 0.0861,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.2222222222222222,
1414
+ "grad_norm": 2.1873579025268555,
1415
+ "learning_rate": 0.00015730337078651685,
1416
+ "loss": 0.0244,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.22333333333333333,
1421
+ "grad_norm": 20.587146759033203,
1422
+ "learning_rate": 0.00015707865168539326,
1423
+ "loss": 0.6676,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.22444444444444445,
1428
+ "grad_norm": 22.635517120361328,
1429
+ "learning_rate": 0.0001568539325842697,
1430
+ "loss": 0.7746,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.22555555555555556,
1435
+ "grad_norm": 18.5538330078125,
1436
+ "learning_rate": 0.00015662921348314607,
1437
+ "loss": 0.6253,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.22666666666666666,
1442
+ "grad_norm": 27.429336547851562,
1443
+ "learning_rate": 0.00015640449438202248,
1444
+ "loss": 0.6195,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.22777777777777777,
1449
+ "grad_norm": 11.472082138061523,
1450
+ "learning_rate": 0.00015617977528089888,
1451
+ "loss": 0.2599,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.2288888888888889,
1456
+ "grad_norm": 22.041595458984375,
1457
+ "learning_rate": 0.0001559550561797753,
1458
+ "loss": 0.5591,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.23,
1463
+ "grad_norm": 4.466843128204346,
1464
+ "learning_rate": 0.0001557303370786517,
1465
+ "loss": 0.08,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.2311111111111111,
1470
+ "grad_norm": 19.16107940673828,
1471
+ "learning_rate": 0.0001555056179775281,
1472
+ "loss": 0.7391,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.23222222222222222,
1477
+ "grad_norm": 54.27048873901367,
1478
+ "learning_rate": 0.0001552808988764045,
1479
+ "loss": 0.6387,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.23333333333333334,
1484
+ "grad_norm": 104.3814468383789,
1485
+ "learning_rate": 0.0001550561797752809,
1486
+ "loss": 2.1719,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.23444444444444446,
1491
+ "grad_norm": 6.0464630126953125,
1492
+ "learning_rate": 0.0001548314606741573,
1493
+ "loss": 0.0536,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.23555555555555555,
1498
+ "grad_norm": 90.455322265625,
1499
+ "learning_rate": 0.00015460674157303372,
1500
+ "loss": 2.9465,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.23666666666666666,
1505
+ "grad_norm": 79.5234146118164,
1506
+ "learning_rate": 0.0001543820224719101,
1507
+ "loss": 2.3244,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.23777777777777778,
1512
+ "grad_norm": 12.400897026062012,
1513
+ "learning_rate": 0.00015415730337078654,
1514
+ "loss": 0.8499,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.2388888888888889,
1519
+ "grad_norm": 2.4573168754577637,
1520
+ "learning_rate": 0.00015393258426966294,
1521
+ "loss": 0.0274,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.24,
1526
+ "grad_norm": 48.44986343383789,
1527
+ "learning_rate": 0.00015370786516853932,
1528
+ "loss": 1.2728,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.2411111111111111,
1533
+ "grad_norm": 12.331904411315918,
1534
+ "learning_rate": 0.00015348314606741575,
1535
+ "loss": 0.5468,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.24222222222222223,
1540
+ "grad_norm": 0.6902552247047424,
1541
+ "learning_rate": 0.00015325842696629213,
1542
+ "loss": 0.0093,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.24333333333333335,
1547
+ "grad_norm": 58.01213455200195,
1548
+ "learning_rate": 0.00015303370786516856,
1549
+ "loss": 1.0199,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.24444444444444444,
1554
+ "grad_norm": 46.95642852783203,
1555
+ "learning_rate": 0.00015280898876404494,
1556
+ "loss": 0.4096,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.24555555555555555,
1561
+ "grad_norm": 78.12667083740234,
1562
+ "learning_rate": 0.00015258426966292138,
1563
+ "loss": 1.5734,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.24666666666666667,
1568
+ "grad_norm": 60.07728958129883,
1569
+ "learning_rate": 0.00015235955056179775,
1570
+ "loss": 2.308,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.2477777777777778,
1575
+ "grad_norm": 111.45307922363281,
1576
+ "learning_rate": 0.00015213483146067416,
1577
+ "loss": 2.8641,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.24888888888888888,
1582
+ "grad_norm": 64.12454986572266,
1583
+ "learning_rate": 0.00015191011235955057,
1584
+ "loss": 0.8217,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.25,
1589
+ "grad_norm": 23.798734664916992,
1590
+ "learning_rate": 0.00015168539325842697,
1591
+ "loss": 0.2274,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.2511111111111111,
1596
+ "grad_norm": 5.194398403167725,
1597
+ "learning_rate": 0.00015146067415730338,
1598
+ "loss": 0.0536,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.25222222222222224,
1603
+ "grad_norm": 83.6928939819336,
1604
+ "learning_rate": 0.00015123595505617978,
1605
+ "loss": 0.3165,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.25333333333333335,
1610
+ "grad_norm": 70.6972885131836,
1611
+ "learning_rate": 0.0001510112359550562,
1612
+ "loss": 2.8958,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.2544444444444444,
1617
+ "grad_norm": 153.9397735595703,
1618
+ "learning_rate": 0.0001507865168539326,
1619
+ "loss": 1.2906,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 0.25555555555555554,
1624
+ "grad_norm": 72.6391830444336,
1625
+ "learning_rate": 0.000150561797752809,
1626
+ "loss": 1.0536,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 0.25666666666666665,
1631
+ "grad_norm": 58.73434066772461,
1632
+ "learning_rate": 0.0001503370786516854,
1633
+ "loss": 2.2182,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 0.2577777777777778,
1638
+ "grad_norm": 38.57413864135742,
1639
+ "learning_rate": 0.0001501123595505618,
1640
+ "loss": 0.8086,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 0.2588888888888889,
1645
+ "grad_norm": 24.48200035095215,
1646
+ "learning_rate": 0.00014988764044943822,
1647
+ "loss": 0.6905,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 0.26,
1652
+ "grad_norm": 36.161224365234375,
1653
+ "learning_rate": 0.00014966292134831462,
1654
+ "loss": 0.5894,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 0.2611111111111111,
1659
+ "grad_norm": 20.57100486755371,
1660
+ "learning_rate": 0.00014943820224719103,
1661
+ "loss": 0.4743,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 0.26222222222222225,
1666
+ "grad_norm": 47.52665328979492,
1667
+ "learning_rate": 0.00014921348314606743,
1668
+ "loss": 1.004,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 0.2633333333333333,
1673
+ "grad_norm": 5.654721736907959,
1674
+ "learning_rate": 0.0001489887640449438,
1675
+ "loss": 0.0797,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 0.2644444444444444,
1680
+ "grad_norm": 28.35422706604004,
1681
+ "learning_rate": 0.00014876404494382025,
1682
+ "loss": 0.3419,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 0.26555555555555554,
1687
+ "grad_norm": 26.79831886291504,
1688
+ "learning_rate": 0.00014853932584269662,
1689
+ "loss": 0.3605,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 0.26666666666666666,
1694
+ "grad_norm": 26.465702056884766,
1695
+ "learning_rate": 0.00014831460674157306,
1696
+ "loss": 1.3787,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 0.2677777777777778,
1701
+ "grad_norm": 33.86037826538086,
1702
+ "learning_rate": 0.00014808988764044944,
1703
+ "loss": 0.6661,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 0.2688888888888889,
1708
+ "grad_norm": 26.28860855102539,
1709
+ "learning_rate": 0.00014786516853932587,
1710
+ "loss": 0.3242,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 0.27,
1715
+ "grad_norm": 74.44789123535156,
1716
+ "learning_rate": 0.00014764044943820225,
1717
+ "loss": 2.6075,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 0.27111111111111114,
1722
+ "grad_norm": 21.634658813476562,
1723
+ "learning_rate": 0.00014741573033707865,
1724
+ "loss": 0.2489,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 0.2722222222222222,
1729
+ "grad_norm": 26.98589324951172,
1730
+ "learning_rate": 0.00014719101123595506,
1731
+ "loss": 0.1793,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 0.2733333333333333,
1736
+ "grad_norm": 23.336448669433594,
1737
+ "learning_rate": 0.00014696629213483146,
1738
+ "loss": 0.1288,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 0.27444444444444444,
1743
+ "grad_norm": 28.19605827331543,
1744
+ "learning_rate": 0.00014674157303370787,
1745
+ "loss": 0.207,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 0.27555555555555555,
1750
+ "grad_norm": 24.533512115478516,
1751
+ "learning_rate": 0.00014651685393258428,
1752
+ "loss": 0.5185,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 0.27666666666666667,
1757
+ "grad_norm": 19.79844093322754,
1758
+ "learning_rate": 0.00014629213483146068,
1759
+ "loss": 0.7139,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 0.2777777777777778,
1764
+ "grad_norm": 4.048962116241455,
1765
+ "learning_rate": 0.0001460674157303371,
1766
+ "loss": 0.107,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 0.2788888888888889,
1771
+ "grad_norm": 18.35643196105957,
1772
+ "learning_rate": 0.0001458426966292135,
1773
+ "loss": 0.7667,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 0.28,
1778
+ "grad_norm": 16.87841033935547,
1779
+ "learning_rate": 0.0001456179775280899,
1780
+ "loss": 0.3365,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 0.2811111111111111,
1785
+ "grad_norm": 35.028202056884766,
1786
+ "learning_rate": 0.0001453932584269663,
1787
+ "loss": 2.9941,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 0.2822222222222222,
1792
+ "grad_norm": 15.129505157470703,
1793
+ "learning_rate": 0.0001451685393258427,
1794
+ "loss": 0.4904,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 0.2833333333333333,
1799
+ "grad_norm": 19.395526885986328,
1800
+ "learning_rate": 0.00014494382022471912,
1801
+ "loss": 0.7099,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 0.28444444444444444,
1806
+ "grad_norm": 25.081811904907227,
1807
+ "learning_rate": 0.0001447191011235955,
1808
+ "loss": 0.6348,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 0.28555555555555556,
1813
+ "grad_norm": 17.35590362548828,
1814
+ "learning_rate": 0.00014449438202247193,
1815
+ "loss": 0.502,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 0.2866666666666667,
1820
+ "grad_norm": 34.557701110839844,
1821
+ "learning_rate": 0.0001442696629213483,
1822
+ "loss": 1.7023,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 0.2877777777777778,
1827
+ "grad_norm": 18.527753829956055,
1828
+ "learning_rate": 0.00014404494382022474,
1829
+ "loss": 0.4003,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 0.28888888888888886,
1834
+ "grad_norm": 12.486297607421875,
1835
+ "learning_rate": 0.00014382022471910112,
1836
+ "loss": 0.6373,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 0.29,
1841
+ "grad_norm": 46.8276481628418,
1842
+ "learning_rate": 0.00014359550561797755,
1843
+ "loss": 0.6996,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 0.2911111111111111,
1848
+ "grad_norm": 41.41952896118164,
1849
+ "learning_rate": 0.00014337078651685393,
1850
+ "loss": 0.7001,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 0.2922222222222222,
1855
+ "grad_norm": 7.149509429931641,
1856
+ "learning_rate": 0.00014314606741573033,
1857
+ "loss": 0.0629,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 0.29333333333333333,
1862
+ "grad_norm": 11.161998748779297,
1863
+ "learning_rate": 0.00014292134831460674,
1864
+ "loss": 0.2907,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 0.29444444444444445,
1869
+ "grad_norm": 1.1274341344833374,
1870
+ "learning_rate": 0.00014269662921348315,
1871
+ "loss": 0.0106,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 0.29555555555555557,
1876
+ "grad_norm": 145.78924560546875,
1877
+ "learning_rate": 0.00014247191011235955,
1878
+ "loss": 3.6351,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 0.2966666666666667,
1883
+ "grad_norm": 19.36644172668457,
1884
+ "learning_rate": 0.00014224719101123596,
1885
+ "loss": 0.7037,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 0.29777777777777775,
1890
+ "grad_norm": 2.9904894828796387,
1891
+ "learning_rate": 0.00014202247191011236,
1892
+ "loss": 0.0155,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 0.29888888888888887,
1897
+ "grad_norm": 12.372429847717285,
1898
+ "learning_rate": 0.00014179775280898877,
1899
+ "loss": 0.4678,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 0.3,
1904
+ "grad_norm": 76.71543884277344,
1905
+ "learning_rate": 0.00014157303370786517,
1906
+ "loss": 2.0245,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 0.3011111111111111,
1911
+ "grad_norm": 90.91097259521484,
1912
+ "learning_rate": 0.00014134831460674158,
1913
+ "loss": 6.0536,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 0.3022222222222222,
1918
+ "grad_norm": 4.851652145385742,
1919
+ "learning_rate": 0.00014112359550561799,
1920
+ "loss": 0.0957,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 0.30333333333333334,
1925
+ "grad_norm": 462.81170654296875,
1926
+ "learning_rate": 0.0001408988764044944,
1927
+ "loss": 2.4226,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 0.30444444444444446,
1932
+ "grad_norm": 78.40040588378906,
1933
+ "learning_rate": 0.0001406741573033708,
1934
+ "loss": 1.9069,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 0.3055555555555556,
1939
+ "grad_norm": 61.69697570800781,
1940
+ "learning_rate": 0.0001404494382022472,
1941
+ "loss": 2.2227,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 0.30666666666666664,
1946
+ "grad_norm": 335.6866760253906,
1947
+ "learning_rate": 0.0001402247191011236,
1948
+ "loss": 2.4249,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 0.30777777777777776,
1953
+ "grad_norm": 443.064208984375,
1954
+ "learning_rate": 0.00014,
1955
+ "loss": 3.6504,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 0.3088888888888889,
1960
+ "grad_norm": 90.0848159790039,
1961
+ "learning_rate": 0.00013977528089887642,
1962
+ "loss": 0.7661,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 0.31,
1967
+ "grad_norm": 33.07680892944336,
1968
+ "learning_rate": 0.0001395505617977528,
1969
+ "loss": 0.8765,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 0.3111111111111111,
1974
+ "grad_norm": 24.65880012512207,
1975
+ "learning_rate": 0.00013932584269662923,
1976
+ "loss": 0.8646,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 0.31222222222222223,
1981
+ "grad_norm": 10.202621459960938,
1982
+ "learning_rate": 0.0001391011235955056,
1983
+ "loss": 0.2138,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 0.31333333333333335,
1988
+ "grad_norm": 25.05742835998535,
1989
+ "learning_rate": 0.00013887640449438204,
1990
+ "loss": 0.3206,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 0.31444444444444447,
1995
+ "grad_norm": 2.6368494033813477,
1996
+ "learning_rate": 0.00013865168539325842,
1997
+ "loss": 0.0184,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 0.31555555555555553,
2002
+ "grad_norm": 0.8122342228889465,
2003
+ "learning_rate": 0.00013842696629213483,
2004
+ "loss": 0.0067,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 0.31666666666666665,
2009
+ "grad_norm": 29.582595825195312,
2010
+ "learning_rate": 0.00013820224719101123,
2011
+ "loss": 0.1801,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 0.31777777777777777,
2016
+ "grad_norm": 71.09741973876953,
2017
+ "learning_rate": 0.00013797752808988764,
2018
+ "loss": 3.2103,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 0.3188888888888889,
2023
+ "grad_norm": 293.1402587890625,
2024
+ "learning_rate": 0.00013775280898876407,
2025
+ "loss": 0.3851,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 0.32,
2030
+ "grad_norm": 114.82374572753906,
2031
+ "learning_rate": 0.00013752808988764045,
2032
+ "loss": 6.6017,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 0.3211111111111111,
2037
+ "grad_norm": 260.7164306640625,
2038
+ "learning_rate": 0.00013730337078651686,
2039
+ "loss": 1.2204,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 0.32222222222222224,
2044
+ "grad_norm": 336.4567565917969,
2045
+ "learning_rate": 0.00013707865168539326,
2046
+ "loss": 6.4889,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 0.3233333333333333,
2051
+ "grad_norm": 197.8843536376953,
2052
+ "learning_rate": 0.00013685393258426967,
2053
+ "loss": 2.3984,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 0.3244444444444444,
2058
+ "grad_norm": 113.60430145263672,
2059
+ "learning_rate": 0.00013662921348314607,
2060
+ "loss": 2.9447,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 0.32555555555555554,
2065
+ "grad_norm": 60.774139404296875,
2066
+ "learning_rate": 0.00013640449438202248,
2067
+ "loss": 2.3389,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 0.32666666666666666,
2072
+ "grad_norm": 1.963387131690979,
2073
+ "learning_rate": 0.00013617977528089889,
2074
+ "loss": 0.0095,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 0.3277777777777778,
2079
+ "grad_norm": 103.31419372558594,
2080
+ "learning_rate": 0.0001359550561797753,
2081
+ "loss": 2.8595,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 0.3288888888888889,
2086
+ "grad_norm": 173.69976806640625,
2087
+ "learning_rate": 0.00013573033707865167,
2088
+ "loss": 1.1675,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 0.33,
2093
+ "grad_norm": 87.6607666015625,
2094
+ "learning_rate": 0.0001355056179775281,
2095
+ "loss": 0.0988,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 0.33111111111111113,
2100
+ "grad_norm": 8.575819969177246,
2101
+ "learning_rate": 0.00013528089887640448,
2102
+ "loss": 0.0149,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 0.3322222222222222,
2107
+ "grad_norm": 219.31256103515625,
2108
+ "learning_rate": 0.00013505617977528091,
2109
+ "loss": 1.0188,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 0.3333333333333333,
2114
+ "grad_norm": 43.600521087646484,
2115
+ "learning_rate": 0.00013483146067415732,
2116
+ "loss": 1.8352,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 0.33444444444444443,
2121
+ "grad_norm": 54.150577545166016,
2122
+ "learning_rate": 0.00013460674157303373,
2123
+ "loss": 1.2275,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 0.33555555555555555,
2128
+ "grad_norm": 37.19937515258789,
2129
+ "learning_rate": 0.00013438202247191013,
2130
+ "loss": 0.6973,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 0.33666666666666667,
2135
+ "grad_norm": 16.893003463745117,
2136
+ "learning_rate": 0.0001341573033707865,
2137
+ "loss": 0.6046,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 0.3377777777777778,
2142
+ "grad_norm": 12.911994934082031,
2143
+ "learning_rate": 0.00013393258426966294,
2144
+ "loss": 0.4968,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 0.3388888888888889,
2149
+ "grad_norm": 52.52392578125,
2150
+ "learning_rate": 0.00013370786516853932,
2151
+ "loss": 1.9279,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 0.34,
2156
+ "grad_norm": 32.607486724853516,
2157
+ "learning_rate": 0.00013348314606741575,
2158
+ "loss": 0.9346,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 0.3411111111111111,
2163
+ "grad_norm": 20.18949317932129,
2164
+ "learning_rate": 0.00013325842696629213,
2165
+ "loss": 0.4332,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 0.3422222222222222,
2170
+ "grad_norm": 45.2260627746582,
2171
+ "learning_rate": 0.00013303370786516857,
2172
+ "loss": 1.075,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 0.3433333333333333,
2177
+ "grad_norm": 27.173877716064453,
2178
+ "learning_rate": 0.00013280898876404494,
2179
+ "loss": 0.6184,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 0.34444444444444444,
2184
+ "grad_norm": 5.545594215393066,
2185
+ "learning_rate": 0.00013258426966292135,
2186
+ "loss": 0.0489,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 0.34555555555555556,
2191
+ "grad_norm": 62.96205520629883,
2192
+ "learning_rate": 0.00013235955056179776,
2193
+ "loss": 4.2513,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 0.3466666666666667,
2198
+ "grad_norm": 28.67704963684082,
2199
+ "learning_rate": 0.00013213483146067416,
2200
+ "loss": 0.704,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 0.3477777777777778,
2205
+ "grad_norm": 7.951623916625977,
2206
+ "learning_rate": 0.00013191011235955057,
2207
+ "loss": 0.0773,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 0.3488888888888889,
2212
+ "grad_norm": 47.64936828613281,
2213
+ "learning_rate": 0.00013168539325842697,
2214
+ "loss": 2.298,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 0.35,
2219
+ "grad_norm": 62.51755142211914,
2220
+ "learning_rate": 0.00013146067415730338,
2221
+ "loss": 2.2698,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 0.3511111111111111,
2226
+ "grad_norm": 24.34674072265625,
2227
+ "learning_rate": 0.00013123595505617978,
2228
+ "loss": 0.6177,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 0.3522222222222222,
2233
+ "grad_norm": 21.337310791015625,
2234
+ "learning_rate": 0.0001310112359550562,
2235
+ "loss": 1.3295,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 0.35333333333333333,
2240
+ "grad_norm": 14.385358810424805,
2241
+ "learning_rate": 0.0001307865168539326,
2242
+ "loss": 0.8708,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 0.35444444444444445,
2247
+ "grad_norm": 31.037155151367188,
2248
+ "learning_rate": 0.000130561797752809,
2249
+ "loss": 1.0502,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 0.35555555555555557,
2254
+ "grad_norm": 23.21908187866211,
2255
+ "learning_rate": 0.0001303370786516854,
2256
+ "loss": 1.2208,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 0.3566666666666667,
2261
+ "grad_norm": 20.67865562438965,
2262
+ "learning_rate": 0.0001301123595505618,
2263
+ "loss": 1.0481,
2264
+ "step": 321
2265
+ },
2266
+ {
2267
+ "epoch": 0.35777777777777775,
2268
+ "grad_norm": 19.378515243530273,
2269
+ "learning_rate": 0.00012988764044943822,
2270
+ "loss": 0.669,
2271
+ "step": 322
2272
+ },
2273
+ {
2274
+ "epoch": 0.35888888888888887,
2275
+ "grad_norm": 36.10619354248047,
2276
+ "learning_rate": 0.00012966292134831462,
2277
+ "loss": 1.5777,
2278
+ "step": 323
2279
+ },
2280
+ {
2281
+ "epoch": 0.36,
2282
+ "grad_norm": 30.89909553527832,
2283
+ "learning_rate": 0.000129438202247191,
2284
+ "loss": 1.2628,
2285
+ "step": 324
2286
+ },
2287
+ {
2288
+ "epoch": 0.3611111111111111,
2289
+ "grad_norm": 16.61541175842285,
2290
+ "learning_rate": 0.00012921348314606744,
2291
+ "loss": 0.8509,
2292
+ "step": 325
2293
+ },
2294
+ {
2295
+ "epoch": 0.3622222222222222,
2296
+ "grad_norm": 38.65313720703125,
2297
+ "learning_rate": 0.00012898876404494381,
2298
+ "loss": 0.7803,
2299
+ "step": 326
2300
+ },
2301
+ {
2302
+ "epoch": 0.36333333333333334,
2303
+ "grad_norm": 17.27694320678711,
2304
+ "learning_rate": 0.00012876404494382025,
2305
+ "loss": 0.7421,
2306
+ "step": 327
2307
+ },
2308
+ {
2309
+ "epoch": 0.36444444444444446,
2310
+ "grad_norm": 31.267465591430664,
2311
+ "learning_rate": 0.00012853932584269663,
2312
+ "loss": 1.2773,
2313
+ "step": 328
2314
+ },
2315
+ {
2316
+ "epoch": 0.3655555555555556,
2317
+ "grad_norm": 29.790102005004883,
2318
+ "learning_rate": 0.00012831460674157303,
2319
+ "loss": 1.2942,
2320
+ "step": 329
2321
+ },
2322
+ {
2323
+ "epoch": 0.36666666666666664,
2324
+ "grad_norm": 13.621098518371582,
2325
+ "learning_rate": 0.00012808988764044944,
2326
+ "loss": 0.6459,
2327
+ "step": 330
2328
+ },
2329
+ {
2330
+ "epoch": 0.36777777777777776,
2331
+ "grad_norm": 34.90887451171875,
2332
+ "learning_rate": 0.00012786516853932584,
2333
+ "loss": 0.7019,
2334
+ "step": 331
2335
+ },
2336
+ {
2337
+ "epoch": 0.3688888888888889,
2338
+ "grad_norm": 9.209269523620605,
2339
+ "learning_rate": 0.00012764044943820225,
2340
+ "loss": 0.2508,
2341
+ "step": 332
2342
+ },
2343
+ {
2344
+ "epoch": 0.37,
2345
+ "grad_norm": 79.69686889648438,
2346
+ "learning_rate": 0.00012741573033707865,
2347
+ "loss": 1.3363,
2348
+ "step": 333
2349
+ },
2350
+ {
2351
+ "epoch": 0.3711111111111111,
2352
+ "grad_norm": 22.871986389160156,
2353
+ "learning_rate": 0.00012719101123595506,
2354
+ "loss": 0.4177,
2355
+ "step": 334
2356
+ },
2357
+ {
2358
+ "epoch": 0.37222222222222223,
2359
+ "grad_norm": 44.5619010925293,
2360
+ "learning_rate": 0.00012696629213483147,
2361
+ "loss": 0.6455,
2362
+ "step": 335
2363
+ },
2364
+ {
2365
+ "epoch": 0.37333333333333335,
2366
+ "grad_norm": 15.637091636657715,
2367
+ "learning_rate": 0.00012674157303370787,
2368
+ "loss": 0.285,
2369
+ "step": 336
2370
+ },
2371
+ {
2372
+ "epoch": 0.37444444444444447,
2373
+ "grad_norm": 42.44564437866211,
2374
+ "learning_rate": 0.00012651685393258428,
2375
+ "loss": 1.0172,
2376
+ "step": 337
2377
+ },
2378
+ {
2379
+ "epoch": 0.37555555555555553,
2380
+ "grad_norm": 37.76460266113281,
2381
+ "learning_rate": 0.00012629213483146068,
2382
+ "loss": 0.906,
2383
+ "step": 338
2384
+ },
2385
+ {
2386
+ "epoch": 0.37666666666666665,
2387
+ "grad_norm": 12.70263671875,
2388
+ "learning_rate": 0.0001260674157303371,
2389
+ "loss": 0.1087,
2390
+ "step": 339
2391
+ },
2392
+ {
2393
+ "epoch": 0.37777777777777777,
2394
+ "grad_norm": 17.172117233276367,
2395
+ "learning_rate": 0.0001258426966292135,
2396
+ "loss": 0.7321,
2397
+ "step": 340
2398
+ },
2399
+ {
2400
+ "epoch": 0.3788888888888889,
2401
+ "grad_norm": 16.033613204956055,
2402
+ "learning_rate": 0.0001256179775280899,
2403
+ "loss": 0.1847,
2404
+ "step": 341
2405
+ },
2406
+ {
2407
+ "epoch": 0.38,
2408
+ "grad_norm": 2.197965145111084,
2409
+ "learning_rate": 0.0001253932584269663,
2410
+ "loss": 0.0401,
2411
+ "step": 342
2412
+ },
2413
+ {
2414
+ "epoch": 0.3811111111111111,
2415
+ "grad_norm": 99.00371551513672,
2416
+ "learning_rate": 0.00012516853932584268,
2417
+ "loss": 0.4878,
2418
+ "step": 343
2419
+ },
2420
+ {
2421
+ "epoch": 0.38222222222222224,
2422
+ "grad_norm": 1.5232975482940674,
2423
+ "learning_rate": 0.00012494382022471912,
2424
+ "loss": 0.0095,
2425
+ "step": 344
2426
+ },
2427
+ {
2428
+ "epoch": 0.38333333333333336,
2429
+ "grad_norm": 41.44043731689453,
2430
+ "learning_rate": 0.0001247191011235955,
2431
+ "loss": 1.1659,
2432
+ "step": 345
2433
+ },
2434
+ {
2435
+ "epoch": 0.3844444444444444,
2436
+ "grad_norm": 1.7756760120391846,
2437
+ "learning_rate": 0.00012449438202247193,
2438
+ "loss": 0.026,
2439
+ "step": 346
2440
+ },
2441
+ {
2442
+ "epoch": 0.38555555555555554,
2443
+ "grad_norm": 47.530113220214844,
2444
+ "learning_rate": 0.0001242696629213483,
2445
+ "loss": 1.3107,
2446
+ "step": 347
2447
+ },
2448
+ {
2449
+ "epoch": 0.38666666666666666,
2450
+ "grad_norm": 53.38481903076172,
2451
+ "learning_rate": 0.00012404494382022474,
2452
+ "loss": 0.1255,
2453
+ "step": 348
2454
+ },
2455
+ {
2456
+ "epoch": 0.3877777777777778,
2457
+ "grad_norm": 49.65568542480469,
2458
+ "learning_rate": 0.00012382022471910112,
2459
+ "loss": 2.0143,
2460
+ "step": 349
2461
+ },
2462
+ {
2463
+ "epoch": 0.3888888888888889,
2464
+ "grad_norm": 11.063892364501953,
2465
+ "learning_rate": 0.00012359550561797752,
2466
+ "loss": 0.1394,
2467
+ "step": 350
2468
+ },
2469
+ {
2470
+ "epoch": 0.39,
2471
+ "grad_norm": 34.083335876464844,
2472
+ "learning_rate": 0.00012337078651685393,
2473
+ "loss": 1.293,
2474
+ "step": 351
2475
+ },
2476
+ {
2477
+ "epoch": 0.39111111111111113,
2478
+ "grad_norm": 59.75748825073242,
2479
+ "learning_rate": 0.00012314606741573034,
2480
+ "loss": 1.0112,
2481
+ "step": 352
2482
+ },
2483
+ {
2484
+ "epoch": 0.39222222222222225,
2485
+ "grad_norm": 24.95011329650879,
2486
+ "learning_rate": 0.00012292134831460674,
2487
+ "loss": 0.6223,
2488
+ "step": 353
2489
+ },
2490
+ {
2491
+ "epoch": 0.3933333333333333,
2492
+ "grad_norm": 10.812705993652344,
2493
+ "learning_rate": 0.00012269662921348315,
2494
+ "loss": 0.3139,
2495
+ "step": 354
2496
+ },
2497
+ {
2498
+ "epoch": 0.39444444444444443,
2499
+ "grad_norm": 27.64237403869629,
2500
+ "learning_rate": 0.00012247191011235955,
2501
+ "loss": 0.6873,
2502
+ "step": 355
2503
+ },
2504
+ {
2505
+ "epoch": 0.39555555555555555,
2506
+ "grad_norm": 2.540048599243164,
2507
+ "learning_rate": 0.00012224719101123596,
2508
+ "loss": 0.0385,
2509
+ "step": 356
2510
+ },
2511
+ {
2512
+ "epoch": 0.39666666666666667,
2513
+ "grad_norm": 36.161773681640625,
2514
+ "learning_rate": 0.00012202247191011235,
2515
+ "loss": 1.2431,
2516
+ "step": 357
2517
+ },
2518
+ {
2519
+ "epoch": 0.3977777777777778,
2520
+ "grad_norm": 36.051639556884766,
2521
+ "learning_rate": 0.00012179775280898877,
2522
+ "loss": 0.786,
2523
+ "step": 358
2524
+ },
2525
+ {
2526
+ "epoch": 0.3988888888888889,
2527
+ "grad_norm": 79.82186889648438,
2528
+ "learning_rate": 0.00012157303370786516,
2529
+ "loss": 1.2626,
2530
+ "step": 359
2531
+ },
2532
+ {
2533
+ "epoch": 0.4,
2534
+ "grad_norm": 3.922207832336426,
2535
+ "learning_rate": 0.00012134831460674158,
2536
+ "loss": 0.0702,
2537
+ "step": 360
2538
+ },
2539
+ {
2540
+ "epoch": 0.4,
2541
+ "eval_loss": 0.8874453902244568,
2542
+ "eval_runtime": 21.7322,
2543
+ "eval_samples_per_second": 9.203,
2544
+ "eval_steps_per_second": 9.203,
2545
+ "step": 360
2546
+ },
2547
+ {
2548
+ "epoch": 0.4011111111111111,
2549
+ "grad_norm": 0.6870169043540955,
2550
+ "learning_rate": 0.00012112359550561799,
2551
+ "loss": 0.0097,
2552
+ "step": 361
2553
+ },
2554
+ {
2555
+ "epoch": 0.4022222222222222,
2556
+ "grad_norm": 11.284960746765137,
2557
+ "learning_rate": 0.0001208988764044944,
2558
+ "loss": 0.2928,
2559
+ "step": 362
2560
+ },
2561
+ {
2562
+ "epoch": 0.4033333333333333,
2563
+ "grad_norm": 12.265844345092773,
2564
+ "learning_rate": 0.0001206741573033708,
2565
+ "loss": 0.2504,
2566
+ "step": 363
2567
+ },
2568
+ {
2569
+ "epoch": 0.40444444444444444,
2570
+ "grad_norm": 36.629920959472656,
2571
+ "learning_rate": 0.00012044943820224719,
2572
+ "loss": 1.6985,
2573
+ "step": 364
2574
+ },
2575
+ {
2576
+ "epoch": 0.40555555555555556,
2577
+ "grad_norm": 0.05139336735010147,
2578
+ "learning_rate": 0.00012022471910112361,
2579
+ "loss": 0.0006,
2580
+ "step": 365
2581
+ },
2582
+ {
2583
+ "epoch": 0.4066666666666667,
2584
+ "grad_norm": 64.978515625,
2585
+ "learning_rate": 0.00012,
2586
+ "loss": 3.1202,
2587
+ "step": 366
2588
+ },
2589
+ {
2590
+ "epoch": 0.4077777777777778,
2591
+ "grad_norm": 135.02467346191406,
2592
+ "learning_rate": 0.00011977528089887642,
2593
+ "loss": 4.0585,
2594
+ "step": 367
2595
+ },
2596
+ {
2597
+ "epoch": 0.4088888888888889,
2598
+ "grad_norm": 176.93165588378906,
2599
+ "learning_rate": 0.00011955056179775281,
2600
+ "loss": 1.9061,
2601
+ "step": 368
2602
+ },
2603
+ {
2604
+ "epoch": 0.41,
2605
+ "grad_norm": 28.170381546020508,
2606
+ "learning_rate": 0.0001193258426966292,
2607
+ "loss": 0.1486,
2608
+ "step": 369
2609
+ },
2610
+ {
2611
+ "epoch": 0.4111111111111111,
2612
+ "grad_norm": 26.527143478393555,
2613
+ "learning_rate": 0.00011910112359550563,
2614
+ "loss": 0.1515,
2615
+ "step": 370
2616
+ },
2617
+ {
2618
+ "epoch": 0.4122222222222222,
2619
+ "grad_norm": 666.6262817382812,
2620
+ "learning_rate": 0.00011887640449438202,
2621
+ "loss": 0.9005,
2622
+ "step": 371
2623
+ },
2624
+ {
2625
+ "epoch": 0.41333333333333333,
2626
+ "grad_norm": 5.227572441101074,
2627
+ "learning_rate": 0.00011865168539325844,
2628
+ "loss": 0.0394,
2629
+ "step": 372
2630
+ },
2631
+ {
2632
+ "epoch": 0.41444444444444445,
2633
+ "grad_norm": 29.46449089050293,
2634
+ "learning_rate": 0.00011842696629213483,
2635
+ "loss": 0.9362,
2636
+ "step": 373
2637
+ },
2638
+ {
2639
+ "epoch": 0.41555555555555557,
2640
+ "grad_norm": 31.59153175354004,
2641
+ "learning_rate": 0.00011820224719101125,
2642
+ "loss": 0.5208,
2643
+ "step": 374
2644
+ },
2645
+ {
2646
+ "epoch": 0.4166666666666667,
2647
+ "grad_norm": 21.449756622314453,
2648
+ "learning_rate": 0.00011797752808988764,
2649
+ "loss": 0.1552,
2650
+ "step": 375
2651
+ },
2652
+ {
2653
+ "epoch": 0.4177777777777778,
2654
+ "grad_norm": 46.2059440612793,
2655
+ "learning_rate": 0.00011775280898876405,
2656
+ "loss": 0.4223,
2657
+ "step": 376
2658
+ },
2659
+ {
2660
+ "epoch": 0.41888888888888887,
2661
+ "grad_norm": 23.437589645385742,
2662
+ "learning_rate": 0.00011752808988764045,
2663
+ "loss": 0.3077,
2664
+ "step": 377
2665
+ },
2666
+ {
2667
+ "epoch": 0.42,
2668
+ "grad_norm": 35.39571762084961,
2669
+ "learning_rate": 0.00011730337078651686,
2670
+ "loss": 0.7621,
2671
+ "step": 378
2672
+ },
2673
+ {
2674
+ "epoch": 0.4211111111111111,
2675
+ "grad_norm": 49.20778274536133,
2676
+ "learning_rate": 0.00011707865168539326,
2677
+ "loss": 1.4349,
2678
+ "step": 379
2679
+ },
2680
+ {
2681
+ "epoch": 0.4222222222222222,
2682
+ "grad_norm": 13.266507148742676,
2683
+ "learning_rate": 0.00011685393258426967,
2684
+ "loss": 0.1736,
2685
+ "step": 380
2686
+ },
2687
+ {
2688
+ "epoch": 0.42333333333333334,
2689
+ "grad_norm": 190.1759796142578,
2690
+ "learning_rate": 0.00011662921348314609,
2691
+ "loss": 1.2734,
2692
+ "step": 381
2693
+ },
2694
+ {
2695
+ "epoch": 0.42444444444444446,
2696
+ "grad_norm": 3.4909679889678955,
2697
+ "learning_rate": 0.00011640449438202248,
2698
+ "loss": 0.0465,
2699
+ "step": 382
2700
+ },
2701
+ {
2702
+ "epoch": 0.4255555555555556,
2703
+ "grad_norm": 57.63570022583008,
2704
+ "learning_rate": 0.00011617977528089887,
2705
+ "loss": 3.569,
2706
+ "step": 383
2707
+ },
2708
+ {
2709
+ "epoch": 0.4266666666666667,
2710
+ "grad_norm": 125.24996948242188,
2711
+ "learning_rate": 0.00011595505617977529,
2712
+ "loss": 2.1932,
2713
+ "step": 384
2714
+ },
2715
+ {
2716
+ "epoch": 0.42777777777777776,
2717
+ "grad_norm": 57.574668884277344,
2718
+ "learning_rate": 0.00011573033707865168,
2719
+ "loss": 0.8419,
2720
+ "step": 385
2721
+ },
2722
+ {
2723
+ "epoch": 0.4288888888888889,
2724
+ "grad_norm": 1.0757412910461426,
2725
+ "learning_rate": 0.0001155056179775281,
2726
+ "loss": 0.0143,
2727
+ "step": 386
2728
+ },
2729
+ {
2730
+ "epoch": 0.43,
2731
+ "grad_norm": 27.834121704101562,
2732
+ "learning_rate": 0.0001152808988764045,
2733
+ "loss": 0.5317,
2734
+ "step": 387
2735
+ },
2736
+ {
2737
+ "epoch": 0.4311111111111111,
2738
+ "grad_norm": 19.531600952148438,
2739
+ "learning_rate": 0.00011505617977528092,
2740
+ "loss": 0.6175,
2741
+ "step": 388
2742
+ },
2743
+ {
2744
+ "epoch": 0.43222222222222223,
2745
+ "grad_norm": 1.998550295829773,
2746
+ "learning_rate": 0.00011483146067415731,
2747
+ "loss": 0.0227,
2748
+ "step": 389
2749
+ },
2750
+ {
2751
+ "epoch": 0.43333333333333335,
2752
+ "grad_norm": 36.122833251953125,
2753
+ "learning_rate": 0.0001146067415730337,
2754
+ "loss": 0.3222,
2755
+ "step": 390
2756
+ },
2757
+ {
2758
+ "epoch": 0.43444444444444447,
2759
+ "grad_norm": 132.46629333496094,
2760
+ "learning_rate": 0.00011438202247191012,
2761
+ "loss": 1.2882,
2762
+ "step": 391
2763
+ },
2764
+ {
2765
+ "epoch": 0.43555555555555553,
2766
+ "grad_norm": 30.841115951538086,
2767
+ "learning_rate": 0.00011415730337078651,
2768
+ "loss": 0.4993,
2769
+ "step": 392
2770
+ },
2771
+ {
2772
+ "epoch": 0.43666666666666665,
2773
+ "grad_norm": 12.828961372375488,
2774
+ "learning_rate": 0.00011393258426966293,
2775
+ "loss": 0.0142,
2776
+ "step": 393
2777
+ },
2778
+ {
2779
+ "epoch": 0.43777777777777777,
2780
+ "grad_norm": 106.47073364257812,
2781
+ "learning_rate": 0.00011370786516853932,
2782
+ "loss": 5.1087,
2783
+ "step": 394
2784
+ },
2785
+ {
2786
+ "epoch": 0.4388888888888889,
2787
+ "grad_norm": 0.5514873266220093,
2788
+ "learning_rate": 0.00011348314606741574,
2789
+ "loss": 0.0032,
2790
+ "step": 395
2791
+ },
2792
+ {
2793
+ "epoch": 0.44,
2794
+ "grad_norm": 953.7054443359375,
2795
+ "learning_rate": 0.00011325842696629215,
2796
+ "loss": 0.4015,
2797
+ "step": 396
2798
+ },
2799
+ {
2800
+ "epoch": 0.4411111111111111,
2801
+ "grad_norm": 0.8753119707107544,
2802
+ "learning_rate": 0.00011303370786516854,
2803
+ "loss": 0.0031,
2804
+ "step": 397
2805
+ },
2806
+ {
2807
+ "epoch": 0.44222222222222224,
2808
+ "grad_norm": 25.872417449951172,
2809
+ "learning_rate": 0.00011280898876404496,
2810
+ "loss": 0.2134,
2811
+ "step": 398
2812
+ },
2813
+ {
2814
+ "epoch": 0.44333333333333336,
2815
+ "grad_norm": 123.84212493896484,
2816
+ "learning_rate": 0.00011258426966292135,
2817
+ "loss": 1.7148,
2818
+ "step": 399
2819
+ },
2820
+ {
2821
+ "epoch": 0.4444444444444444,
2822
+ "grad_norm": 10.738250732421875,
2823
+ "learning_rate": 0.00011235955056179777,
2824
+ "loss": 0.0075,
2825
+ "step": 400
2826
+ },
2827
+ {
2828
+ "epoch": 0.44555555555555554,
2829
+ "grad_norm": 12.850424766540527,
2830
+ "learning_rate": 0.00011213483146067416,
2831
+ "loss": 0.5974,
2832
+ "step": 401
2833
+ },
2834
+ {
2835
+ "epoch": 0.44666666666666666,
2836
+ "grad_norm": 20.977840423583984,
2837
+ "learning_rate": 0.00011191011235955056,
2838
+ "loss": 0.5209,
2839
+ "step": 402
2840
+ },
2841
+ {
2842
+ "epoch": 0.4477777777777778,
2843
+ "grad_norm": 260.0442199707031,
2844
+ "learning_rate": 0.00011168539325842697,
2845
+ "loss": 1.928,
2846
+ "step": 403
2847
+ },
2848
+ {
2849
+ "epoch": 0.4488888888888889,
2850
+ "grad_norm": 186.64476013183594,
2851
+ "learning_rate": 0.00011146067415730337,
2852
+ "loss": 0.4375,
2853
+ "step": 404
2854
+ },
2855
+ {
2856
+ "epoch": 0.45,
2857
+ "grad_norm": 27.23136329650879,
2858
+ "learning_rate": 0.00011123595505617979,
2859
+ "loss": 0.8106,
2860
+ "step": 405
2861
+ },
2862
+ {
2863
+ "epoch": 0.45111111111111113,
2864
+ "grad_norm": 24.54252052307129,
2865
+ "learning_rate": 0.00011101123595505618,
2866
+ "loss": 0.4154,
2867
+ "step": 406
2868
+ },
2869
+ {
2870
+ "epoch": 0.45222222222222225,
2871
+ "grad_norm": 5.4926958084106445,
2872
+ "learning_rate": 0.0001107865168539326,
2873
+ "loss": 0.0496,
2874
+ "step": 407
2875
+ },
2876
+ {
2877
+ "epoch": 0.4533333333333333,
2878
+ "grad_norm": 15.589746475219727,
2879
+ "learning_rate": 0.00011056179775280899,
2880
+ "loss": 0.8639,
2881
+ "step": 408
2882
+ },
2883
+ {
2884
+ "epoch": 0.45444444444444443,
2885
+ "grad_norm": 72.841064453125,
2886
+ "learning_rate": 0.00011033707865168538,
2887
+ "loss": 0.8028,
2888
+ "step": 409
2889
+ },
2890
+ {
2891
+ "epoch": 0.45555555555555555,
2892
+ "grad_norm": 75.0212631225586,
2893
+ "learning_rate": 0.0001101123595505618,
2894
+ "loss": 0.7039,
2895
+ "step": 410
2896
+ },
2897
+ {
2898
+ "epoch": 0.45666666666666667,
2899
+ "grad_norm": 53.94396209716797,
2900
+ "learning_rate": 0.00010988764044943821,
2901
+ "loss": 1.072,
2902
+ "step": 411
2903
+ },
2904
+ {
2905
+ "epoch": 0.4577777777777778,
2906
+ "grad_norm": 0.5978874564170837,
2907
+ "learning_rate": 0.00010966292134831461,
2908
+ "loss": 0.0087,
2909
+ "step": 412
2910
+ },
2911
+ {
2912
+ "epoch": 0.4588888888888889,
2913
+ "grad_norm": 26.721378326416016,
2914
+ "learning_rate": 0.00010943820224719102,
2915
+ "loss": 1.0121,
2916
+ "step": 413
2917
+ },
2918
+ {
2919
+ "epoch": 0.46,
2920
+ "grad_norm": 15.128684997558594,
2921
+ "learning_rate": 0.00010921348314606742,
2922
+ "loss": 0.2752,
2923
+ "step": 414
2924
+ },
2925
+ {
2926
+ "epoch": 0.46111111111111114,
2927
+ "grad_norm": 23.618616104125977,
2928
+ "learning_rate": 0.00010898876404494383,
2929
+ "loss": 0.9684,
2930
+ "step": 415
2931
+ },
2932
+ {
2933
+ "epoch": 0.4622222222222222,
2934
+ "grad_norm": 23.219255447387695,
2935
+ "learning_rate": 0.00010876404494382022,
2936
+ "loss": 0.7851,
2937
+ "step": 416
2938
+ },
2939
+ {
2940
+ "epoch": 0.4633333333333333,
2941
+ "grad_norm": 8.236587524414062,
2942
+ "learning_rate": 0.00010853932584269664,
2943
+ "loss": 0.22,
2944
+ "step": 417
2945
+ },
2946
+ {
2947
+ "epoch": 0.46444444444444444,
2948
+ "grad_norm": 30.10824203491211,
2949
+ "learning_rate": 0.00010831460674157303,
2950
+ "loss": 0.5875,
2951
+ "step": 418
2952
+ },
2953
+ {
2954
+ "epoch": 0.46555555555555556,
2955
+ "grad_norm": 19.3294677734375,
2956
+ "learning_rate": 0.00010808988764044945,
2957
+ "loss": 0.3949,
2958
+ "step": 419
2959
+ },
2960
+ {
2961
+ "epoch": 0.4666666666666667,
2962
+ "grad_norm": 5.817005157470703,
2963
+ "learning_rate": 0.00010786516853932584,
2964
+ "loss": 0.1485,
2965
+ "step": 420
2966
+ },
2967
+ {
2968
+ "epoch": 0.4677777777777778,
2969
+ "grad_norm": 72.81584930419922,
2970
+ "learning_rate": 0.00010764044943820226,
2971
+ "loss": 1.1419,
2972
+ "step": 421
2973
+ },
2974
+ {
2975
+ "epoch": 0.4688888888888889,
2976
+ "grad_norm": 12.993364334106445,
2977
+ "learning_rate": 0.00010741573033707866,
2978
+ "loss": 0.2881,
2979
+ "step": 422
2980
+ },
2981
+ {
2982
+ "epoch": 0.47,
2983
+ "grad_norm": 18.64270782470703,
2984
+ "learning_rate": 0.00010719101123595505,
2985
+ "loss": 0.1767,
2986
+ "step": 423
2987
+ },
2988
+ {
2989
+ "epoch": 0.4711111111111111,
2990
+ "grad_norm": 72.509033203125,
2991
+ "learning_rate": 0.00010696629213483147,
2992
+ "loss": 0.6925,
2993
+ "step": 424
2994
+ },
2995
+ {
2996
+ "epoch": 0.4722222222222222,
2997
+ "grad_norm": 14.434927940368652,
2998
+ "learning_rate": 0.00010674157303370786,
2999
+ "loss": 0.3044,
3000
+ "step": 425
3001
+ },
3002
+ {
3003
+ "epoch": 0.47333333333333333,
3004
+ "grad_norm": 6.451004505157471,
3005
+ "learning_rate": 0.00010651685393258428,
3006
+ "loss": 0.0977,
3007
+ "step": 426
3008
+ },
3009
+ {
3010
+ "epoch": 0.47444444444444445,
3011
+ "grad_norm": 15.574492454528809,
3012
+ "learning_rate": 0.00010629213483146067,
3013
+ "loss": 0.0716,
3014
+ "step": 427
3015
+ },
3016
+ {
3017
+ "epoch": 0.47555555555555556,
3018
+ "grad_norm": 41.221458435058594,
3019
+ "learning_rate": 0.00010606741573033709,
3020
+ "loss": 0.7872,
3021
+ "step": 428
3022
+ },
3023
+ {
3024
+ "epoch": 0.4766666666666667,
3025
+ "grad_norm": 5.579776287078857,
3026
+ "learning_rate": 0.00010584269662921348,
3027
+ "loss": 0.079,
3028
+ "step": 429
3029
+ },
3030
+ {
3031
+ "epoch": 0.4777777777777778,
3032
+ "grad_norm": 47.014583587646484,
3033
+ "learning_rate": 0.00010561797752808989,
3034
+ "loss": 0.8383,
3035
+ "step": 430
3036
+ },
3037
+ {
3038
+ "epoch": 0.47888888888888886,
3039
+ "grad_norm": 32.69986343383789,
3040
+ "learning_rate": 0.00010539325842696631,
3041
+ "loss": 0.5386,
3042
+ "step": 431
3043
+ },
3044
+ {
3045
+ "epoch": 0.48,
3046
+ "grad_norm": 4.975848197937012,
3047
+ "learning_rate": 0.0001051685393258427,
3048
+ "loss": 0.0674,
3049
+ "step": 432
3050
+ },
3051
+ {
3052
+ "epoch": 0.4811111111111111,
3053
+ "grad_norm": 7.464103698730469,
3054
+ "learning_rate": 0.00010494382022471912,
3055
+ "loss": 0.1145,
3056
+ "step": 433
3057
+ },
3058
+ {
3059
+ "epoch": 0.4822222222222222,
3060
+ "grad_norm": 1.2781155109405518,
3061
+ "learning_rate": 0.00010471910112359551,
3062
+ "loss": 0.014,
3063
+ "step": 434
3064
+ },
3065
+ {
3066
+ "epoch": 0.48333333333333334,
3067
+ "grad_norm": 28.900177001953125,
3068
+ "learning_rate": 0.00010449438202247193,
3069
+ "loss": 1.4421,
3070
+ "step": 435
3071
+ },
3072
+ {
3073
+ "epoch": 0.48444444444444446,
3074
+ "grad_norm": 3.9803850650787354,
3075
+ "learning_rate": 0.00010426966292134832,
3076
+ "loss": 0.024,
3077
+ "step": 436
3078
+ },
3079
+ {
3080
+ "epoch": 0.4855555555555556,
3081
+ "grad_norm": 12.956731796264648,
3082
+ "learning_rate": 0.00010404494382022472,
3083
+ "loss": 0.0175,
3084
+ "step": 437
3085
+ },
3086
+ {
3087
+ "epoch": 0.4866666666666667,
3088
+ "grad_norm": 115.45230102539062,
3089
+ "learning_rate": 0.00010382022471910113,
3090
+ "loss": 2.7973,
3091
+ "step": 438
3092
+ },
3093
+ {
3094
+ "epoch": 0.48777777777777775,
3095
+ "grad_norm": 347.68499755859375,
3096
+ "learning_rate": 0.00010359550561797753,
3097
+ "loss": 0.364,
3098
+ "step": 439
3099
+ },
3100
+ {
3101
+ "epoch": 0.4888888888888889,
3102
+ "grad_norm": 0.02836551144719124,
3103
+ "learning_rate": 0.00010337078651685395,
3104
+ "loss": 0.0003,
3105
+ "step": 440
3106
+ },
3107
+ {
3108
+ "epoch": 0.49,
3109
+ "grad_norm": 0.7754154801368713,
3110
+ "learning_rate": 0.00010314606741573034,
3111
+ "loss": 0.0041,
3112
+ "step": 441
3113
+ },
3114
+ {
3115
+ "epoch": 0.4911111111111111,
3116
+ "grad_norm": 162.77394104003906,
3117
+ "learning_rate": 0.00010292134831460673,
3118
+ "loss": 0.4385,
3119
+ "step": 442
3120
+ },
3121
+ {
3122
+ "epoch": 0.4922222222222222,
3123
+ "grad_norm": 65.08900451660156,
3124
+ "learning_rate": 0.00010269662921348315,
3125
+ "loss": 2.4515,
3126
+ "step": 443
3127
+ },
3128
+ {
3129
+ "epoch": 0.49333333333333335,
3130
+ "grad_norm": 77.23931884765625,
3131
+ "learning_rate": 0.00010247191011235954,
3132
+ "loss": 0.0998,
3133
+ "step": 444
3134
+ },
3135
+ {
3136
+ "epoch": 0.49444444444444446,
3137
+ "grad_norm": 54.98646545410156,
3138
+ "learning_rate": 0.00010224719101123596,
3139
+ "loss": 2.2212,
3140
+ "step": 445
3141
+ },
3142
+ {
3143
+ "epoch": 0.4955555555555556,
3144
+ "grad_norm": 333.53759765625,
3145
+ "learning_rate": 0.00010202247191011237,
3146
+ "loss": 2.1804,
3147
+ "step": 446
3148
+ },
3149
+ {
3150
+ "epoch": 0.49666666666666665,
3151
+ "grad_norm": 0.4334656000137329,
3152
+ "learning_rate": 0.00010179775280898877,
3153
+ "loss": 0.0005,
3154
+ "step": 447
3155
+ },
3156
+ {
3157
+ "epoch": 0.49777777777777776,
3158
+ "grad_norm": 92.5488052368164,
3159
+ "learning_rate": 0.00010157303370786518,
3160
+ "loss": 5.9994,
3161
+ "step": 448
3162
+ },
3163
+ {
3164
+ "epoch": 0.4988888888888889,
3165
+ "grad_norm": 1.4919911623001099,
3166
+ "learning_rate": 0.00010134831460674157,
3167
+ "loss": 0.0071,
3168
+ "step": 449
3169
+ },
3170
+ {
3171
+ "epoch": 0.5,
3172
+ "grad_norm": 1118.8466796875,
3173
+ "learning_rate": 0.00010112359550561799,
3174
+ "loss": 2.6433,
3175
+ "step": 450
3176
+ },
3177
+ {
3178
+ "epoch": 0.5011111111111111,
3179
+ "grad_norm": 90.92044830322266,
3180
+ "learning_rate": 0.00010089887640449438,
3181
+ "loss": 2.6771,
3182
+ "step": 451
3183
+ },
3184
+ {
3185
+ "epoch": 0.5022222222222222,
3186
+ "grad_norm": 44.722774505615234,
3187
+ "learning_rate": 0.0001006741573033708,
3188
+ "loss": 1.6866,
3189
+ "step": 452
3190
+ },
3191
+ {
3192
+ "epoch": 0.5033333333333333,
3193
+ "grad_norm": 11.702170372009277,
3194
+ "learning_rate": 0.0001004494382022472,
3195
+ "loss": 0.5277,
3196
+ "step": 453
3197
+ },
3198
+ {
3199
+ "epoch": 0.5044444444444445,
3200
+ "grad_norm": 39.63846206665039,
3201
+ "learning_rate": 0.00010022471910112361,
3202
+ "loss": 3.0422,
3203
+ "step": 454
3204
+ },
3205
+ {
3206
+ "epoch": 0.5055555555555555,
3207
+ "grad_norm": 13.576400756835938,
3208
+ "learning_rate": 0.0001,
3209
+ "loss": 0.5816,
3210
+ "step": 455
3211
+ },
3212
+ {
3213
+ "epoch": 0.5066666666666667,
3214
+ "grad_norm": 31.162992477416992,
3215
+ "learning_rate": 9.977528089887641e-05,
3216
+ "loss": 2.0922,
3217
+ "step": 456
3218
+ },
3219
+ {
3220
+ "epoch": 0.5077777777777778,
3221
+ "grad_norm": 192.13531494140625,
3222
+ "learning_rate": 9.955056179775282e-05,
3223
+ "loss": 3.7398,
3224
+ "step": 457
3225
+ },
3226
+ {
3227
+ "epoch": 0.5088888888888888,
3228
+ "grad_norm": 67.36595916748047,
3229
+ "learning_rate": 9.932584269662922e-05,
3230
+ "loss": 3.31,
3231
+ "step": 458
3232
+ },
3233
+ {
3234
+ "epoch": 0.51,
3235
+ "grad_norm": 9.05526065826416,
3236
+ "learning_rate": 9.910112359550561e-05,
3237
+ "loss": 0.2878,
3238
+ "step": 459
3239
+ },
3240
+ {
3241
+ "epoch": 0.5111111111111111,
3242
+ "grad_norm": 39.264671325683594,
3243
+ "learning_rate": 9.887640449438202e-05,
3244
+ "loss": 1.2509,
3245
+ "step": 460
3246
+ },
3247
+ {
3248
+ "epoch": 0.5122222222222222,
3249
+ "grad_norm": 50.258724212646484,
3250
+ "learning_rate": 9.865168539325843e-05,
3251
+ "loss": 0.5284,
3252
+ "step": 461
3253
+ },
3254
+ {
3255
+ "epoch": 0.5133333333333333,
3256
+ "grad_norm": 113.38192749023438,
3257
+ "learning_rate": 9.842696629213483e-05,
3258
+ "loss": 0.3407,
3259
+ "step": 462
3260
+ },
3261
+ {
3262
+ "epoch": 0.5144444444444445,
3263
+ "grad_norm": 12.214896202087402,
3264
+ "learning_rate": 9.820224719101124e-05,
3265
+ "loss": 0.0849,
3266
+ "step": 463
3267
+ },
3268
+ {
3269
+ "epoch": 0.5155555555555555,
3270
+ "grad_norm": 33.33673858642578,
3271
+ "learning_rate": 9.797752808988764e-05,
3272
+ "loss": 1.2038,
3273
+ "step": 464
3274
+ },
3275
+ {
3276
+ "epoch": 0.5166666666666667,
3277
+ "grad_norm": 57.25215530395508,
3278
+ "learning_rate": 9.775280898876405e-05,
3279
+ "loss": 1.0402,
3280
+ "step": 465
3281
+ },
3282
+ {
3283
+ "epoch": 0.5177777777777778,
3284
+ "grad_norm": 30.840652465820312,
3285
+ "learning_rate": 9.752808988764045e-05,
3286
+ "loss": 1.0461,
3287
+ "step": 466
3288
+ },
3289
+ {
3290
+ "epoch": 0.5188888888888888,
3291
+ "grad_norm": 25.450763702392578,
3292
+ "learning_rate": 9.730337078651686e-05,
3293
+ "loss": 0.595,
3294
+ "step": 467
3295
+ },
3296
+ {
3297
+ "epoch": 0.52,
3298
+ "grad_norm": 18.255313873291016,
3299
+ "learning_rate": 9.707865168539327e-05,
3300
+ "loss": 0.6212,
3301
+ "step": 468
3302
+ },
3303
+ {
3304
+ "epoch": 0.5211111111111111,
3305
+ "grad_norm": 17.35516929626465,
3306
+ "learning_rate": 9.685393258426967e-05,
3307
+ "loss": 0.2399,
3308
+ "step": 469
3309
+ },
3310
+ {
3311
+ "epoch": 0.5222222222222223,
3312
+ "grad_norm": 21.07298469543457,
3313
+ "learning_rate": 9.662921348314608e-05,
3314
+ "loss": 0.3365,
3315
+ "step": 470
3316
+ },
3317
+ {
3318
+ "epoch": 0.5233333333333333,
3319
+ "grad_norm": 124.3791275024414,
3320
+ "learning_rate": 9.640449438202248e-05,
3321
+ "loss": 0.3354,
3322
+ "step": 471
3323
+ },
3324
+ {
3325
+ "epoch": 0.5244444444444445,
3326
+ "grad_norm": 69.94832611083984,
3327
+ "learning_rate": 9.617977528089888e-05,
3328
+ "loss": 1.155,
3329
+ "step": 472
3330
+ },
3331
+ {
3332
+ "epoch": 0.5255555555555556,
3333
+ "grad_norm": 15.040170669555664,
3334
+ "learning_rate": 9.595505617977528e-05,
3335
+ "loss": 0.2461,
3336
+ "step": 473
3337
+ },
3338
+ {
3339
+ "epoch": 0.5266666666666666,
3340
+ "grad_norm": 130.7023468017578,
3341
+ "learning_rate": 9.573033707865169e-05,
3342
+ "loss": 0.1469,
3343
+ "step": 474
3344
+ },
3345
+ {
3346
+ "epoch": 0.5277777777777778,
3347
+ "grad_norm": 39.584781646728516,
3348
+ "learning_rate": 9.550561797752809e-05,
3349
+ "loss": 0.2987,
3350
+ "step": 475
3351
+ },
3352
+ {
3353
+ "epoch": 0.5288888888888889,
3354
+ "grad_norm": 8.145970344543457,
3355
+ "learning_rate": 9.52808988764045e-05,
3356
+ "loss": 0.1188,
3357
+ "step": 476
3358
+ },
3359
+ {
3360
+ "epoch": 0.53,
3361
+ "grad_norm": 278.3324279785156,
3362
+ "learning_rate": 9.50561797752809e-05,
3363
+ "loss": 0.7326,
3364
+ "step": 477
3365
+ },
3366
+ {
3367
+ "epoch": 0.5311111111111111,
3368
+ "grad_norm": 111.15706634521484,
3369
+ "learning_rate": 9.483146067415731e-05,
3370
+ "loss": 0.3635,
3371
+ "step": 478
3372
+ },
3373
+ {
3374
+ "epoch": 0.5322222222222223,
3375
+ "grad_norm": 8.148956298828125,
3376
+ "learning_rate": 9.46067415730337e-05,
3377
+ "loss": 0.1156,
3378
+ "step": 479
3379
+ },
3380
+ {
3381
+ "epoch": 0.5333333333333333,
3382
+ "grad_norm": 19.501976013183594,
3383
+ "learning_rate": 9.438202247191012e-05,
3384
+ "loss": 0.3261,
3385
+ "step": 480
3386
+ },
3387
+ {
3388
+ "epoch": 0.5344444444444445,
3389
+ "grad_norm": 10.242660522460938,
3390
+ "learning_rate": 9.415730337078653e-05,
3391
+ "loss": 0.2744,
3392
+ "step": 481
3393
+ },
3394
+ {
3395
+ "epoch": 0.5355555555555556,
3396
+ "grad_norm": 9.074132919311523,
3397
+ "learning_rate": 9.393258426966293e-05,
3398
+ "loss": 0.1255,
3399
+ "step": 482
3400
+ },
3401
+ {
3402
+ "epoch": 0.5366666666666666,
3403
+ "grad_norm": 52.14421463012695,
3404
+ "learning_rate": 9.370786516853934e-05,
3405
+ "loss": 0.2988,
3406
+ "step": 483
3407
+ },
3408
+ {
3409
+ "epoch": 0.5377777777777778,
3410
+ "grad_norm": 0.7315455675125122,
3411
+ "learning_rate": 9.348314606741574e-05,
3412
+ "loss": 0.0083,
3413
+ "step": 484
3414
+ },
3415
+ {
3416
+ "epoch": 0.5388888888888889,
3417
+ "grad_norm": 57.13528060913086,
3418
+ "learning_rate": 9.325842696629214e-05,
3419
+ "loss": 0.5395,
3420
+ "step": 485
3421
+ },
3422
+ {
3423
+ "epoch": 0.54,
3424
+ "grad_norm": 19.480281829833984,
3425
+ "learning_rate": 9.303370786516854e-05,
3426
+ "loss": 0.2192,
3427
+ "step": 486
3428
+ },
3429
+ {
3430
+ "epoch": 0.5411111111111111,
3431
+ "grad_norm": 32.7698860168457,
3432
+ "learning_rate": 9.280898876404495e-05,
3433
+ "loss": 1.3419,
3434
+ "step": 487
3435
+ },
3436
+ {
3437
+ "epoch": 0.5422222222222223,
3438
+ "grad_norm": 87.57260131835938,
3439
+ "learning_rate": 9.258426966292135e-05,
3440
+ "loss": 3.0696,
3441
+ "step": 488
3442
+ },
3443
+ {
3444
+ "epoch": 0.5433333333333333,
3445
+ "grad_norm": 48.37082290649414,
3446
+ "learning_rate": 9.235955056179776e-05,
3447
+ "loss": 1.0391,
3448
+ "step": 489
3449
+ },
3450
+ {
3451
+ "epoch": 0.5444444444444444,
3452
+ "grad_norm": 15.431656837463379,
3453
+ "learning_rate": 9.213483146067416e-05,
3454
+ "loss": 0.1289,
3455
+ "step": 490
3456
+ },
3457
+ {
3458
+ "epoch": 0.5455555555555556,
3459
+ "grad_norm": 51.22895812988281,
3460
+ "learning_rate": 9.191011235955057e-05,
3461
+ "loss": 1.7931,
3462
+ "step": 491
3463
+ },
3464
+ {
3465
+ "epoch": 0.5466666666666666,
3466
+ "grad_norm": 136.01736450195312,
3467
+ "learning_rate": 9.168539325842696e-05,
3468
+ "loss": 1.3817,
3469
+ "step": 492
3470
+ },
3471
+ {
3472
+ "epoch": 0.5477777777777778,
3473
+ "grad_norm": 31.37152671813965,
3474
+ "learning_rate": 9.146067415730337e-05,
3475
+ "loss": 0.5657,
3476
+ "step": 493
3477
+ },
3478
+ {
3479
+ "epoch": 0.5488888888888889,
3480
+ "grad_norm": 7.320507526397705,
3481
+ "learning_rate": 9.123595505617977e-05,
3482
+ "loss": 0.1268,
3483
+ "step": 494
3484
+ },
3485
+ {
3486
+ "epoch": 0.55,
3487
+ "grad_norm": 89.08702850341797,
3488
+ "learning_rate": 9.101123595505618e-05,
3489
+ "loss": 2.6738,
3490
+ "step": 495
3491
+ },
3492
+ {
3493
+ "epoch": 0.5511111111111111,
3494
+ "grad_norm": 2.1967666149139404,
3495
+ "learning_rate": 9.078651685393259e-05,
3496
+ "loss": 0.0208,
3497
+ "step": 496
3498
+ },
3499
+ {
3500
+ "epoch": 0.5522222222222222,
3501
+ "grad_norm": 34.614620208740234,
3502
+ "learning_rate": 9.056179775280899e-05,
3503
+ "loss": 0.6955,
3504
+ "step": 497
3505
+ },
3506
+ {
3507
+ "epoch": 0.5533333333333333,
3508
+ "grad_norm": 10.201793670654297,
3509
+ "learning_rate": 9.03370786516854e-05,
3510
+ "loss": 0.0708,
3511
+ "step": 498
3512
+ },
3513
+ {
3514
+ "epoch": 0.5544444444444444,
3515
+ "grad_norm": 86.25459289550781,
3516
+ "learning_rate": 9.01123595505618e-05,
3517
+ "loss": 2.1702,
3518
+ "step": 499
3519
+ },
3520
+ {
3521
+ "epoch": 0.5555555555555556,
3522
+ "grad_norm": 1.9402846097946167,
3523
+ "learning_rate": 8.988764044943821e-05,
3524
+ "loss": 0.0193,
3525
+ "step": 500
3526
+ }
3527
+ ],
3528
+ "logging_steps": 1,
3529
+ "max_steps": 900,
3530
+ "num_input_tokens_seen": 0,
3531
+ "num_train_epochs": 1,
3532
+ "save_steps": 500,
3533
+ "stateful_callbacks": {
3534
+ "TrainerControl": {
3535
+ "args": {
3536
+ "should_epoch_stop": false,
3537
+ "should_evaluate": false,
3538
+ "should_log": false,
3539
+ "should_save": true,
3540
+ "should_training_stop": false
3541
+ },
3542
+ "attributes": {}
3543
+ }
3544
+ },
3545
+ "total_flos": 3078208590815232.0,
3546
+ "train_batch_size": 1,
3547
+ "trial_name": null,
3548
+ "trial_params": null
3549
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1d99ad67ccc4445db8196d9b9e8523395f4321458f041ce1a5f074f2b72630
3
+ size 5496
checkpoint-900/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-v0.1
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
checkpoint-900/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
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": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "o_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "up_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-900/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26236b33d8b8d28f496790c6c7cd9a1af279e1cc7eac38e236a2fcd1cdf562c0
3
+ size 167832240
checkpoint-900/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a5d7200c035d8dc9c19abf78ac8cc4f54c863b09598be4bdff31abcc7b79bc
3
+ size 335813370
checkpoint-900/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b450091d673dc14a6f8eaed76ce5864e7429832e86ab10c164e8c1bccc2019dd
3
+ size 14244
checkpoint-900/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8241b28596309b6efdc6344cd50ddd93f72d5ff3654ee306ee63a9192d368a28
3
+ size 1064
checkpoint-900/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-900/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
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-900/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1d99ad67ccc4445db8196d9b9e8523395f4321458f041ce1a5f074f2b72630
3
+ size 5496