MaruchanPark commited on
Commit
238475b
1 Parent(s): 2553876

add_adapter_model

Browse files
README copy.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /online/konanllm-studio/release_models/kylin-7b-chat-2406-v2/hf_style/release
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 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/model/kylin-7b-chat-2406-v2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6cd5b33beae45d984f2caedac61d45fbd49454489a9183763da5928d4b16a23
3
+ size 335605144
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebc0ae38b34619bacfea5adb863d972f890d325f9fc43982cadf95524539857
3
+ size 671466589
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b15cc79e4623eaf2c6091b6b0da668871980e8ff0c2b682514445bd182df88
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
3
+ size 627
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": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": "<unk>"
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
31
+ "content": "<|tel|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "32001": {
39
+ "content": "<|rnn|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "32002": {
47
+ "content": "<|email|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "32003": {
55
+ "content": "<|crd|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "32004": {
63
+ "content": "<|acc|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "51510": {
71
+ "content": "<|im_start|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "51511": {
79
+ "content": "<|im_end|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ }
86
+ },
87
+ "bos_token": "<s>",
88
+ "chat_template": "{{('<|im_start|>assistant\n' + messages[0]['content'].strip() + '<|im_end|>' + '\n' if messages[0]['role'] == 'system' else '')}}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>' + '\n' + '<|im_start|>assistant\n'}}{% elif message['role'] == 'assistant' %}{{message['content']}}{% if loop.last %}{% if add_generation_prompt %}{{'<|im_end|>'}}{% endif %}{% else %}{{'<|im_end|>'}}{% endif %}{% endif %}{% endfor %}",
89
+ "clean_up_tokenization_spaces": true,
90
+ "eos_token": "</s>",
91
+ "legacy": true,
92
+ "model_max_length": 1000000000000000019884624838656,
93
+ "model_name": "kylin-7b",
94
+ "pad_token": "</s>",
95
+ "tokenizer_class": "LlamaTokenizer",
96
+ "unk_token": "<unk>",
97
+ "use_default_system_prompt": false
98
+ }
trainer_state.json ADDED
@@ -0,0 +1,3533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.26737967914438504,
5
+ "eval_steps": 500,
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": 0.0005347593582887701,
13
+ "grad_norm": 10.25,
14
+ "learning_rate": 0.0002,
15
+ "loss": 5.5244,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0010695187165775401,
20
+ "grad_norm": 5.65625,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.5152,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0016042780748663102,
27
+ "grad_norm": 5.0,
28
+ "learning_rate": 0.0002,
29
+ "loss": 0.9678,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0021390374331550803,
34
+ "grad_norm": 1.09375,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.2586,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.00267379679144385,
41
+ "grad_norm": 2.21875,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.8375,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0032085561497326204,
48
+ "grad_norm": 2.359375,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.8124,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0037433155080213902,
55
+ "grad_norm": 1.3515625,
56
+ "learning_rate": 0.0002,
57
+ "loss": 0.4274,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0042780748663101605,
62
+ "grad_norm": 1.9765625,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.6398,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.004812834224598931,
69
+ "grad_norm": 1.1796875,
70
+ "learning_rate": 0.0002,
71
+ "loss": 0.4485,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0053475935828877,
76
+ "grad_norm": 0.48828125,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.3639,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.0058823529411764705,
83
+ "grad_norm": 0.7265625,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.3139,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.006417112299465241,
90
+ "grad_norm": 1.3671875,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.1684,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.006951871657754011,
97
+ "grad_norm": 1.359375,
98
+ "learning_rate": 0.0002,
99
+ "loss": 0.4753,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0074866310160427805,
104
+ "grad_norm": 0.56640625,
105
+ "learning_rate": 0.0002,
106
+ "loss": 0.0907,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.008021390374331552,
111
+ "grad_norm": 1.9375,
112
+ "learning_rate": 0.0002,
113
+ "loss": 0.3021,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.008556149732620321,
118
+ "grad_norm": 1.421875,
119
+ "learning_rate": 0.0002,
120
+ "loss": 0.292,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.00909090909090909,
125
+ "grad_norm": 0.4453125,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.2465,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.009625668449197862,
132
+ "grad_norm": 1.0703125,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.2335,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.010160427807486631,
139
+ "grad_norm": 4.84375,
140
+ "learning_rate": 0.0002,
141
+ "loss": 0.2976,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0106951871657754,
146
+ "grad_norm": 4.84375,
147
+ "learning_rate": 0.0002,
148
+ "loss": 0.6077,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.011229946524064172,
153
+ "grad_norm": 2.25,
154
+ "learning_rate": 0.0002,
155
+ "loss": 0.3396,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.011764705882352941,
160
+ "grad_norm": 1.4453125,
161
+ "learning_rate": 0.0002,
162
+ "loss": 0.218,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.01229946524064171,
167
+ "grad_norm": 1.1640625,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.0862,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.012834224598930482,
174
+ "grad_norm": 2.65625,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.4492,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.013368983957219251,
181
+ "grad_norm": 1.1796875,
182
+ "learning_rate": 0.0002,
183
+ "loss": 0.1986,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.013903743315508022,
188
+ "grad_norm": 1.03125,
189
+ "learning_rate": 0.0002,
190
+ "loss": 0.2902,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.014438502673796792,
195
+ "grad_norm": 1.5703125,
196
+ "learning_rate": 0.0002,
197
+ "loss": 0.6038,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.014973262032085561,
202
+ "grad_norm": 1.359375,
203
+ "learning_rate": 0.0002,
204
+ "loss": 0.2869,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.015508021390374332,
209
+ "grad_norm": 0.455078125,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.2646,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.016042780748663103,
216
+ "grad_norm": 0.45703125,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.1653,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.016577540106951873,
223
+ "grad_norm": 0.84765625,
224
+ "learning_rate": 0.0002,
225
+ "loss": 0.2535,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.017112299465240642,
230
+ "grad_norm": 1.1015625,
231
+ "learning_rate": 0.0002,
232
+ "loss": 0.2485,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.01764705882352941,
237
+ "grad_norm": 0.74609375,
238
+ "learning_rate": 0.0002,
239
+ "loss": 0.2425,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.01818181818181818,
244
+ "grad_norm": 0.353515625,
245
+ "learning_rate": 0.0002,
246
+ "loss": 0.0913,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.01871657754010695,
251
+ "grad_norm": 0.546875,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.1082,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.019251336898395723,
258
+ "grad_norm": 1.0,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.4729,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.019786096256684493,
265
+ "grad_norm": 1.265625,
266
+ "learning_rate": 0.0002,
267
+ "loss": 0.3255,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.020320855614973262,
272
+ "grad_norm": 2.734375,
273
+ "learning_rate": 0.0002,
274
+ "loss": 0.4583,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.02085561497326203,
279
+ "grad_norm": 0.203125,
280
+ "learning_rate": 0.0002,
281
+ "loss": 0.1099,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.0213903743315508,
286
+ "grad_norm": 0.71875,
287
+ "learning_rate": 0.0002,
288
+ "loss": 0.1941,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.021925133689839574,
293
+ "grad_norm": 0.64453125,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.278,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.022459893048128343,
300
+ "grad_norm": 0.69921875,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.4062,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.022994652406417113,
307
+ "grad_norm": 1.2109375,
308
+ "learning_rate": 0.0002,
309
+ "loss": 0.4801,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.023529411764705882,
314
+ "grad_norm": 0.3515625,
315
+ "learning_rate": 0.0002,
316
+ "loss": 0.2161,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.02406417112299465,
321
+ "grad_norm": 1.109375,
322
+ "learning_rate": 0.0002,
323
+ "loss": 0.2423,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.02459893048128342,
328
+ "grad_norm": 0.69921875,
329
+ "learning_rate": 0.0002,
330
+ "loss": 0.208,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.025133689839572194,
335
+ "grad_norm": 0.37890625,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.2149,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.025668449197860963,
342
+ "grad_norm": 0.6796875,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.2528,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.026203208556149733,
349
+ "grad_norm": 0.2890625,
350
+ "learning_rate": 0.0002,
351
+ "loss": 0.2094,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.026737967914438502,
356
+ "grad_norm": 0.228515625,
357
+ "learning_rate": 0.0002,
358
+ "loss": 0.1544,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.02727272727272727,
363
+ "grad_norm": 0.62109375,
364
+ "learning_rate": 0.0002,
365
+ "loss": 0.2201,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.027807486631016044,
370
+ "grad_norm": 2.859375,
371
+ "learning_rate": 0.0002,
372
+ "loss": 0.3119,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.028342245989304814,
377
+ "grad_norm": 0.578125,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.2003,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.028877005347593583,
384
+ "grad_norm": 0.80078125,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.2708,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.029411764705882353,
391
+ "grad_norm": 1.515625,
392
+ "learning_rate": 0.0002,
393
+ "loss": 0.2502,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.029946524064171122,
398
+ "grad_norm": 0.6796875,
399
+ "learning_rate": 0.0002,
400
+ "loss": 0.2379,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.03048128342245989,
405
+ "grad_norm": 0.4140625,
406
+ "learning_rate": 0.0002,
407
+ "loss": 0.1,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.031016042780748664,
412
+ "grad_norm": 0.271484375,
413
+ "learning_rate": 0.0002,
414
+ "loss": 0.0705,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.03155080213903743,
419
+ "grad_norm": 0.51953125,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.2252,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.03208556149732621,
426
+ "grad_norm": 1.8359375,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.2479,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.032620320855614976,
433
+ "grad_norm": 1.25,
434
+ "learning_rate": 0.0002,
435
+ "loss": 0.3067,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.033155080213903745,
440
+ "grad_norm": 1.390625,
441
+ "learning_rate": 0.0002,
442
+ "loss": 0.2026,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.033689839572192515,
447
+ "grad_norm": 0.255859375,
448
+ "learning_rate": 0.0002,
449
+ "loss": 0.1771,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.034224598930481284,
454
+ "grad_norm": 1.2421875,
455
+ "learning_rate": 0.0002,
456
+ "loss": 0.1886,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.034759358288770054,
461
+ "grad_norm": 0.59765625,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.1603,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.03529411764705882,
468
+ "grad_norm": 0.298828125,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.1577,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.03582887700534759,
475
+ "grad_norm": 0.48046875,
476
+ "learning_rate": 0.0002,
477
+ "loss": 0.2385,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.03636363636363636,
482
+ "grad_norm": 0.291015625,
483
+ "learning_rate": 0.0002,
484
+ "loss": 0.2457,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.03689839572192513,
489
+ "grad_norm": 1.203125,
490
+ "learning_rate": 0.0002,
491
+ "loss": 0.2403,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.0374331550802139,
496
+ "grad_norm": 1.34375,
497
+ "learning_rate": 0.0002,
498
+ "loss": 0.2959,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.03796791443850268,
503
+ "grad_norm": 0.47265625,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.2408,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.038502673796791446,
510
+ "grad_norm": 2.0625,
511
+ "learning_rate": 0.0002,
512
+ "loss": 0.5305,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.039037433155080216,
517
+ "grad_norm": 0.87109375,
518
+ "learning_rate": 0.0002,
519
+ "loss": 0.1871,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.039572192513368985,
524
+ "grad_norm": 0.98046875,
525
+ "learning_rate": 0.0002,
526
+ "loss": 0.2837,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.040106951871657755,
531
+ "grad_norm": 0.515625,
532
+ "learning_rate": 0.0002,
533
+ "loss": 0.133,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.040641711229946524,
538
+ "grad_norm": 0.59375,
539
+ "learning_rate": 0.0002,
540
+ "loss": 0.2151,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.041176470588235294,
545
+ "grad_norm": 0.4765625,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.1379,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.04171122994652406,
552
+ "grad_norm": 0.62109375,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.1798,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.04224598930481283,
559
+ "grad_norm": 0.396484375,
560
+ "learning_rate": 0.0002,
561
+ "loss": 0.1735,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.0427807486631016,
566
+ "grad_norm": 0.546875,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.2279,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.04331550802139037,
573
+ "grad_norm": 0.455078125,
574
+ "learning_rate": 0.0002,
575
+ "loss": 0.2083,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.04385026737967915,
580
+ "grad_norm": 0.453125,
581
+ "learning_rate": 0.0002,
582
+ "loss": 0.2038,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.04438502673796792,
587
+ "grad_norm": 0.259765625,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.2185,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.044919786096256686,
594
+ "grad_norm": 0.1044921875,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.1184,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.045454545454545456,
601
+ "grad_norm": 0.21484375,
602
+ "learning_rate": 0.0002,
603
+ "loss": 0.1767,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.045989304812834225,
608
+ "grad_norm": 0.10107421875,
609
+ "learning_rate": 0.0002,
610
+ "loss": 0.1461,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.046524064171122995,
615
+ "grad_norm": 0.283203125,
616
+ "learning_rate": 0.0002,
617
+ "loss": 0.1723,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.047058823529411764,
622
+ "grad_norm": 0.314453125,
623
+ "learning_rate": 0.0002,
624
+ "loss": 0.1796,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.04759358288770053,
629
+ "grad_norm": 0.98828125,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.1747,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.0481283422459893,
636
+ "grad_norm": 0.419921875,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.1606,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.04866310160427807,
643
+ "grad_norm": 0.1640625,
644
+ "learning_rate": 0.0002,
645
+ "loss": 0.1675,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.04919786096256684,
650
+ "grad_norm": 2.203125,
651
+ "learning_rate": 0.0002,
652
+ "loss": 0.3444,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.04973262032085562,
657
+ "grad_norm": 0.326171875,
658
+ "learning_rate": 0.0002,
659
+ "loss": 0.2217,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.05026737967914439,
664
+ "grad_norm": 0.27734375,
665
+ "learning_rate": 0.0002,
666
+ "loss": 0.2684,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.05080213903743316,
671
+ "grad_norm": 1.4921875,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.2776,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.051336898395721926,
678
+ "grad_norm": 0.10107421875,
679
+ "learning_rate": 0.0002,
680
+ "loss": 0.1626,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.051871657754010696,
685
+ "grad_norm": 0.6953125,
686
+ "learning_rate": 0.0002,
687
+ "loss": 0.1733,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.052406417112299465,
692
+ "grad_norm": 0.46875,
693
+ "learning_rate": 0.0002,
694
+ "loss": 0.2631,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.052941176470588235,
699
+ "grad_norm": 5.78125,
700
+ "learning_rate": 0.0002,
701
+ "loss": 0.3128,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.053475935828877004,
706
+ "grad_norm": 1.7421875,
707
+ "learning_rate": 0.0002,
708
+ "loss": 0.3108,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.05401069518716577,
713
+ "grad_norm": 0.87890625,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.4231,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.05454545454545454,
720
+ "grad_norm": 0.171875,
721
+ "learning_rate": 0.0002,
722
+ "loss": 0.1636,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.05508021390374331,
727
+ "grad_norm": 0.8203125,
728
+ "learning_rate": 0.0002,
729
+ "loss": 0.4548,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.05561497326203209,
734
+ "grad_norm": 0.208984375,
735
+ "learning_rate": 0.0002,
736
+ "loss": 0.1718,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.05614973262032086,
741
+ "grad_norm": 0.28125,
742
+ "learning_rate": 0.0002,
743
+ "loss": 0.1438,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.05668449197860963,
748
+ "grad_norm": 0.55078125,
749
+ "learning_rate": 0.0002,
750
+ "loss": 0.2534,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.0572192513368984,
755
+ "grad_norm": 0.412109375,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.2303,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.057754010695187166,
762
+ "grad_norm": 0.322265625,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.2488,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.058288770053475936,
769
+ "grad_norm": 0.85546875,
770
+ "learning_rate": 0.0002,
771
+ "loss": 0.2962,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.058823529411764705,
776
+ "grad_norm": 0.357421875,
777
+ "learning_rate": 0.0002,
778
+ "loss": 0.2266,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.059358288770053474,
783
+ "grad_norm": 0.236328125,
784
+ "learning_rate": 0.0002,
785
+ "loss": 0.2208,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.059893048128342244,
790
+ "grad_norm": 0.56640625,
791
+ "learning_rate": 0.0002,
792
+ "loss": 0.2489,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.06042780748663101,
797
+ "grad_norm": 0.2490234375,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.3115,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.06096256684491978,
804
+ "grad_norm": 0.498046875,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.2222,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.06149732620320856,
811
+ "grad_norm": 1.2421875,
812
+ "learning_rate": 0.0002,
813
+ "loss": 0.389,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.06203208556149733,
818
+ "grad_norm": 0.58984375,
819
+ "learning_rate": 0.0002,
820
+ "loss": 0.2148,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.06256684491978609,
825
+ "grad_norm": 0.3515625,
826
+ "learning_rate": 0.0002,
827
+ "loss": 0.2527,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.06310160427807486,
832
+ "grad_norm": 0.341796875,
833
+ "learning_rate": 0.0002,
834
+ "loss": 0.2395,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.06363636363636363,
839
+ "grad_norm": 1.1171875,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.3902,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.06417112299465241,
846
+ "grad_norm": 0.46484375,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.2973,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.06470588235294118,
853
+ "grad_norm": 0.671875,
854
+ "learning_rate": 0.0002,
855
+ "loss": 0.2476,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.06524064171122995,
860
+ "grad_norm": 0.462890625,
861
+ "learning_rate": 0.0002,
862
+ "loss": 0.186,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.06577540106951872,
867
+ "grad_norm": 0.244140625,
868
+ "learning_rate": 0.0002,
869
+ "loss": 0.165,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.06631016042780749,
874
+ "grad_norm": 1.546875,
875
+ "learning_rate": 0.0002,
876
+ "loss": 0.5423,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.06684491978609626,
881
+ "grad_norm": 0.95703125,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.4157,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.06737967914438503,
888
+ "grad_norm": 3.40625,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.5118,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.0679144385026738,
895
+ "grad_norm": 0.5546875,
896
+ "learning_rate": 0.0002,
897
+ "loss": 0.1738,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.06844919786096257,
902
+ "grad_norm": 0.1396484375,
903
+ "learning_rate": 0.0002,
904
+ "loss": 0.0812,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.06898395721925134,
909
+ "grad_norm": 0.2392578125,
910
+ "learning_rate": 0.0002,
911
+ "loss": 0.1073,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.06951871657754011,
916
+ "grad_norm": 0.193359375,
917
+ "learning_rate": 0.0002,
918
+ "loss": 0.1118,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.07005347593582888,
923
+ "grad_norm": 1.015625,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.2042,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.07058823529411765,
930
+ "grad_norm": 0.400390625,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.1226,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.07112299465240642,
937
+ "grad_norm": 0.234375,
938
+ "learning_rate": 0.0002,
939
+ "loss": 0.1684,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.07165775401069518,
944
+ "grad_norm": 0.1630859375,
945
+ "learning_rate": 0.0002,
946
+ "loss": 0.1795,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.07219251336898395,
951
+ "grad_norm": 0.60546875,
952
+ "learning_rate": 0.0002,
953
+ "loss": 0.2594,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.07272727272727272,
958
+ "grad_norm": 0.138671875,
959
+ "learning_rate": 0.0002,
960
+ "loss": 0.0331,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.0732620320855615,
965
+ "grad_norm": 0.193359375,
966
+ "learning_rate": 0.0002,
967
+ "loss": 0.1815,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.07379679144385026,
972
+ "grad_norm": 0.9375,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.458,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.07433155080213903,
979
+ "grad_norm": 0.5859375,
980
+ "learning_rate": 0.0002,
981
+ "loss": 0.266,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.0748663101604278,
986
+ "grad_norm": 0.5859375,
987
+ "learning_rate": 0.0002,
988
+ "loss": 0.2798,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.07540106951871657,
993
+ "grad_norm": 0.494140625,
994
+ "learning_rate": 0.0002,
995
+ "loss": 0.2428,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.07593582887700535,
1000
+ "grad_norm": 0.2060546875,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 0.1931,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.07647058823529412,
1007
+ "grad_norm": 0.49609375,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 0.2107,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.07700534759358289,
1014
+ "grad_norm": 0.2490234375,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.1649,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.07754010695187166,
1021
+ "grad_norm": 0.1396484375,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 0.1408,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.07807486631016043,
1028
+ "grad_norm": 1.5234375,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 0.3663,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.0786096256684492,
1035
+ "grad_norm": 0.70703125,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 0.2539,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.07914438502673797,
1042
+ "grad_norm": 0.51171875,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 0.2954,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.07967914438502674,
1049
+ "grad_norm": 0.404296875,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.3071,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.08021390374331551,
1056
+ "grad_norm": 0.3671875,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.1121,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.08074866310160428,
1063
+ "grad_norm": 0.251953125,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 0.1059,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.08128342245989305,
1070
+ "grad_norm": 0.490234375,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 0.2265,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.08181818181818182,
1077
+ "grad_norm": 0.36328125,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 0.1875,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.08235294117647059,
1084
+ "grad_norm": 0.51171875,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 0.2944,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.08288770053475936,
1091
+ "grad_norm": 0.6796875,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.2663,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.08342245989304813,
1098
+ "grad_norm": 0.58984375,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 0.1909,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.0839572192513369,
1105
+ "grad_norm": 0.24609375,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 0.1816,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.08449197860962566,
1112
+ "grad_norm": 0.267578125,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 0.0903,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.08502673796791443,
1119
+ "grad_norm": 0.8359375,
1120
+ "learning_rate": 0.0002,
1121
+ "loss": 0.1757,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.0855614973262032,
1126
+ "grad_norm": 0.283203125,
1127
+ "learning_rate": 0.0002,
1128
+ "loss": 0.1636,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.08609625668449197,
1133
+ "grad_norm": 0.2451171875,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.1363,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.08663101604278074,
1140
+ "grad_norm": 0.318359375,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 0.1262,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.08716577540106951,
1147
+ "grad_norm": 0.5,
1148
+ "learning_rate": 0.0002,
1149
+ "loss": 0.2162,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.0877005347593583,
1154
+ "grad_norm": 0.1123046875,
1155
+ "learning_rate": 0.0002,
1156
+ "loss": 0.0586,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.08823529411764706,
1161
+ "grad_norm": 0.0771484375,
1162
+ "learning_rate": 0.0002,
1163
+ "loss": 0.0908,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.08877005347593583,
1168
+ "grad_norm": 0.486328125,
1169
+ "learning_rate": 0.0002,
1170
+ "loss": 0.109,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.0893048128342246,
1175
+ "grad_norm": 0.2333984375,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 0.1283,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.08983957219251337,
1182
+ "grad_norm": 0.0023651123046875,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 0.0003,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.09037433155080214,
1189
+ "grad_norm": 0.87890625,
1190
+ "learning_rate": 0.0002,
1191
+ "loss": 0.0709,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.09090909090909091,
1196
+ "grad_norm": 0.1845703125,
1197
+ "learning_rate": 0.0002,
1198
+ "loss": 0.1616,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.09144385026737968,
1203
+ "grad_norm": 0.83203125,
1204
+ "learning_rate": 0.0002,
1205
+ "loss": 0.1496,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.09197860962566845,
1210
+ "grad_norm": 1.2421875,
1211
+ "learning_rate": 0.0002,
1212
+ "loss": 0.3648,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.09251336898395722,
1217
+ "grad_norm": 1.1484375,
1218
+ "learning_rate": 0.0002,
1219
+ "loss": 0.4267,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.09304812834224599,
1224
+ "grad_norm": 1.71875,
1225
+ "learning_rate": 0.0002,
1226
+ "loss": 0.1812,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.09358288770053476,
1231
+ "grad_norm": 3.34375,
1232
+ "learning_rate": 0.0002,
1233
+ "loss": 0.3108,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.09411764705882353,
1238
+ "grad_norm": 1.21875,
1239
+ "learning_rate": 0.0002,
1240
+ "loss": 0.2502,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.0946524064171123,
1245
+ "grad_norm": 0.8671875,
1246
+ "learning_rate": 0.0002,
1247
+ "loss": 0.3469,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.09518716577540107,
1252
+ "grad_norm": 0.2353515625,
1253
+ "learning_rate": 0.0002,
1254
+ "loss": 0.1502,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.09572192513368984,
1259
+ "grad_norm": 0.859375,
1260
+ "learning_rate": 0.0002,
1261
+ "loss": 0.3546,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.0962566844919786,
1266
+ "grad_norm": 0.42578125,
1267
+ "learning_rate": 0.0002,
1268
+ "loss": 0.2236,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.09679144385026738,
1273
+ "grad_norm": 0.2109375,
1274
+ "learning_rate": 0.0002,
1275
+ "loss": 0.0742,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.09732620320855614,
1280
+ "grad_norm": 0.2421875,
1281
+ "learning_rate": 0.0002,
1282
+ "loss": 0.2046,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.09786096256684491,
1287
+ "grad_norm": 0.2060546875,
1288
+ "learning_rate": 0.0002,
1289
+ "loss": 0.1355,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.09839572192513368,
1294
+ "grad_norm": 0.40234375,
1295
+ "learning_rate": 0.0002,
1296
+ "loss": 0.2228,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.09893048128342247,
1301
+ "grad_norm": 0.8046875,
1302
+ "learning_rate": 0.0002,
1303
+ "loss": 0.2756,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.09946524064171124,
1308
+ "grad_norm": 0.357421875,
1309
+ "learning_rate": 0.0002,
1310
+ "loss": 0.228,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.1,
1315
+ "grad_norm": 0.201171875,
1316
+ "learning_rate": 0.0002,
1317
+ "loss": 0.122,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.10053475935828877,
1322
+ "grad_norm": 0.4296875,
1323
+ "learning_rate": 0.0002,
1324
+ "loss": 0.1864,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.10106951871657754,
1329
+ "grad_norm": 0.2099609375,
1330
+ "learning_rate": 0.0002,
1331
+ "loss": 0.1586,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.10160427807486631,
1336
+ "grad_norm": 0.2734375,
1337
+ "learning_rate": 0.0002,
1338
+ "loss": 0.1432,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.10213903743315508,
1343
+ "grad_norm": 0.2265625,
1344
+ "learning_rate": 0.0002,
1345
+ "loss": 0.1971,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.10267379679144385,
1350
+ "grad_norm": 0.5625,
1351
+ "learning_rate": 0.0002,
1352
+ "loss": 0.2811,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.10320855614973262,
1357
+ "grad_norm": 0.3203125,
1358
+ "learning_rate": 0.0002,
1359
+ "loss": 0.1839,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.10374331550802139,
1364
+ "grad_norm": 0.291015625,
1365
+ "learning_rate": 0.0002,
1366
+ "loss": 0.2092,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.10427807486631016,
1371
+ "grad_norm": 0.6640625,
1372
+ "learning_rate": 0.0002,
1373
+ "loss": 0.2743,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.10481283422459893,
1378
+ "grad_norm": 0.328125,
1379
+ "learning_rate": 0.0002,
1380
+ "loss": 0.2752,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.1053475935828877,
1385
+ "grad_norm": 0.8359375,
1386
+ "learning_rate": 0.0002,
1387
+ "loss": 0.1735,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.10588235294117647,
1392
+ "grad_norm": 0.369140625,
1393
+ "learning_rate": 0.0002,
1394
+ "loss": 0.137,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.10641711229946524,
1399
+ "grad_norm": 0.53515625,
1400
+ "learning_rate": 0.0002,
1401
+ "loss": 0.2498,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.10695187165775401,
1406
+ "grad_norm": 0.376953125,
1407
+ "learning_rate": 0.0002,
1408
+ "loss": 0.1308,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.10748663101604278,
1413
+ "grad_norm": 0.88671875,
1414
+ "learning_rate": 0.0002,
1415
+ "loss": 0.2849,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.10802139037433155,
1420
+ "grad_norm": 0.291015625,
1421
+ "learning_rate": 0.0002,
1422
+ "loss": 0.1342,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.10855614973262032,
1427
+ "grad_norm": 0.26953125,
1428
+ "learning_rate": 0.0002,
1429
+ "loss": 0.105,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.10909090909090909,
1434
+ "grad_norm": 0.478515625,
1435
+ "learning_rate": 0.0002,
1436
+ "loss": 0.1172,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.10962566844919786,
1441
+ "grad_norm": 0.326171875,
1442
+ "learning_rate": 0.0002,
1443
+ "loss": 0.0579,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.11016042780748662,
1448
+ "grad_norm": 0.2060546875,
1449
+ "learning_rate": 0.0002,
1450
+ "loss": 0.1235,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.11069518716577541,
1455
+ "grad_norm": 1.375,
1456
+ "learning_rate": 0.0002,
1457
+ "loss": 0.5436,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.11122994652406418,
1462
+ "grad_norm": 0.21875,
1463
+ "learning_rate": 0.0002,
1464
+ "loss": 0.2197,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.11176470588235295,
1469
+ "grad_norm": 0.75,
1470
+ "learning_rate": 0.0002,
1471
+ "loss": 0.2319,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.11229946524064172,
1476
+ "grad_norm": 0.43359375,
1477
+ "learning_rate": 0.0002,
1478
+ "loss": 0.1091,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.11283422459893049,
1483
+ "grad_norm": 0.154296875,
1484
+ "learning_rate": 0.0002,
1485
+ "loss": 0.1932,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.11336898395721925,
1490
+ "grad_norm": 0.10009765625,
1491
+ "learning_rate": 0.0002,
1492
+ "loss": 0.1829,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.11390374331550802,
1497
+ "grad_norm": 0.0986328125,
1498
+ "learning_rate": 0.0002,
1499
+ "loss": 0.1738,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.1144385026737968,
1504
+ "grad_norm": 0.53125,
1505
+ "learning_rate": 0.0002,
1506
+ "loss": 0.1746,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.11497326203208556,
1511
+ "grad_norm": 0.484375,
1512
+ "learning_rate": 0.0002,
1513
+ "loss": 0.1831,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.11550802139037433,
1518
+ "grad_norm": 1.609375,
1519
+ "learning_rate": 0.0002,
1520
+ "loss": 0.4379,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.1160427807486631,
1525
+ "grad_norm": 0.265625,
1526
+ "learning_rate": 0.0002,
1527
+ "loss": 0.1707,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.11657754010695187,
1532
+ "grad_norm": 1.5625,
1533
+ "learning_rate": 0.0002,
1534
+ "loss": 0.1901,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.11711229946524064,
1539
+ "grad_norm": 0.1904296875,
1540
+ "learning_rate": 0.0002,
1541
+ "loss": 0.2282,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.11764705882352941,
1546
+ "grad_norm": 0.1982421875,
1547
+ "learning_rate": 0.0002,
1548
+ "loss": 0.1478,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.11818181818181818,
1553
+ "grad_norm": 0.408203125,
1554
+ "learning_rate": 0.0002,
1555
+ "loss": 0.2262,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.11871657754010695,
1560
+ "grad_norm": 0.271484375,
1561
+ "learning_rate": 0.0002,
1562
+ "loss": 0.1373,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.11925133689839572,
1567
+ "grad_norm": 0.34765625,
1568
+ "learning_rate": 0.0002,
1569
+ "loss": 0.123,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.11978609625668449,
1574
+ "grad_norm": 0.08837890625,
1575
+ "learning_rate": 0.0002,
1576
+ "loss": 0.1712,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.12032085561497326,
1581
+ "grad_norm": 0.4140625,
1582
+ "learning_rate": 0.0002,
1583
+ "loss": 0.1837,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.12085561497326203,
1588
+ "grad_norm": 1.171875,
1589
+ "learning_rate": 0.0002,
1590
+ "loss": 0.3184,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.1213903743315508,
1595
+ "grad_norm": 0.6640625,
1596
+ "learning_rate": 0.0002,
1597
+ "loss": 0.1646,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.12192513368983957,
1602
+ "grad_norm": 0.765625,
1603
+ "learning_rate": 0.0002,
1604
+ "loss": 0.1659,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.12245989304812835,
1609
+ "grad_norm": 0.126953125,
1610
+ "learning_rate": 0.0002,
1611
+ "loss": 0.151,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.12299465240641712,
1616
+ "grad_norm": 0.25,
1617
+ "learning_rate": 0.0002,
1618
+ "loss": 0.1841,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.12352941176470589,
1623
+ "grad_norm": 1.1171875,
1624
+ "learning_rate": 0.0002,
1625
+ "loss": 0.0834,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.12406417112299466,
1630
+ "grad_norm": 0.1728515625,
1631
+ "learning_rate": 0.0002,
1632
+ "loss": 0.1417,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.12459893048128343,
1637
+ "grad_norm": 0.099609375,
1638
+ "learning_rate": 0.0002,
1639
+ "loss": 0.1227,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.12513368983957218,
1644
+ "grad_norm": 0.8125,
1645
+ "learning_rate": 0.0002,
1646
+ "loss": 0.1835,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.12566844919786097,
1651
+ "grad_norm": 1.2109375,
1652
+ "learning_rate": 0.0002,
1653
+ "loss": 0.3382,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.12620320855614972,
1658
+ "grad_norm": 1.4296875,
1659
+ "learning_rate": 0.0002,
1660
+ "loss": 0.4302,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.1267379679144385,
1665
+ "grad_norm": 0.546875,
1666
+ "learning_rate": 0.0002,
1667
+ "loss": 0.1895,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.12727272727272726,
1672
+ "grad_norm": 2.5,
1673
+ "learning_rate": 0.0002,
1674
+ "loss": 0.3654,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.12780748663101604,
1679
+ "grad_norm": 1.0859375,
1680
+ "learning_rate": 0.0002,
1681
+ "loss": 0.4818,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.12834224598930483,
1686
+ "grad_norm": 0.65625,
1687
+ "learning_rate": 0.0002,
1688
+ "loss": 0.3575,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.12887700534759358,
1693
+ "grad_norm": 0.25,
1694
+ "learning_rate": 0.0002,
1695
+ "loss": 0.0789,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.12941176470588237,
1700
+ "grad_norm": 0.4765625,
1701
+ "learning_rate": 0.0002,
1702
+ "loss": 0.2638,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.12994652406417112,
1707
+ "grad_norm": 0.267578125,
1708
+ "learning_rate": 0.0002,
1709
+ "loss": 0.1225,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.1304812834224599,
1714
+ "grad_norm": 0.6015625,
1715
+ "learning_rate": 0.0002,
1716
+ "loss": 0.0733,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.13101604278074866,
1721
+ "grad_norm": 0.2158203125,
1722
+ "learning_rate": 0.0002,
1723
+ "loss": 0.0766,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.13155080213903744,
1728
+ "grad_norm": 0.7734375,
1729
+ "learning_rate": 0.0002,
1730
+ "loss": 0.3096,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.1320855614973262,
1735
+ "grad_norm": 0.94921875,
1736
+ "learning_rate": 0.0002,
1737
+ "loss": 0.2276,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.13262032085561498,
1742
+ "grad_norm": 0.345703125,
1743
+ "learning_rate": 0.0002,
1744
+ "loss": 0.2357,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.13315508021390374,
1749
+ "grad_norm": 0.134765625,
1750
+ "learning_rate": 0.0002,
1751
+ "loss": 0.1144,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.13368983957219252,
1756
+ "grad_norm": 0.2373046875,
1757
+ "learning_rate": 0.0002,
1758
+ "loss": 0.1118,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.13422459893048128,
1763
+ "grad_norm": 0.306640625,
1764
+ "learning_rate": 0.0002,
1765
+ "loss": 0.1682,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.13475935828877006,
1770
+ "grad_norm": 0.193359375,
1771
+ "learning_rate": 0.0002,
1772
+ "loss": 0.0453,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.13529411764705881,
1777
+ "grad_norm": 0.388671875,
1778
+ "learning_rate": 0.0002,
1779
+ "loss": 0.1895,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.1358288770053476,
1784
+ "grad_norm": 0.94921875,
1785
+ "learning_rate": 0.0002,
1786
+ "loss": 0.4819,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.13636363636363635,
1791
+ "grad_norm": 0.185546875,
1792
+ "learning_rate": 0.0002,
1793
+ "loss": 0.1763,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.13689839572192514,
1798
+ "grad_norm": 0.34765625,
1799
+ "learning_rate": 0.0002,
1800
+ "loss": 0.268,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.1374331550802139,
1805
+ "grad_norm": 0.2578125,
1806
+ "learning_rate": 0.0002,
1807
+ "loss": 0.1276,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.13796791443850268,
1812
+ "grad_norm": 0.2421875,
1813
+ "learning_rate": 0.0002,
1814
+ "loss": 0.1819,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.13850267379679143,
1819
+ "grad_norm": 0.076171875,
1820
+ "learning_rate": 0.0002,
1821
+ "loss": 0.0893,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.13903743315508021,
1826
+ "grad_norm": 0.65234375,
1827
+ "learning_rate": 0.0002,
1828
+ "loss": 0.2154,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.139572192513369,
1833
+ "grad_norm": 0.443359375,
1834
+ "learning_rate": 0.0002,
1835
+ "loss": 0.3956,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.14010695187165775,
1840
+ "grad_norm": 0.150390625,
1841
+ "learning_rate": 0.0002,
1842
+ "loss": 0.1585,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.14064171122994654,
1847
+ "grad_norm": 0.125,
1848
+ "learning_rate": 0.0002,
1849
+ "loss": 0.0876,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.1411764705882353,
1854
+ "grad_norm": 0.80078125,
1855
+ "learning_rate": 0.0002,
1856
+ "loss": 0.0673,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.14171122994652408,
1861
+ "grad_norm": 4.0625,
1862
+ "learning_rate": 0.0002,
1863
+ "loss": 0.184,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.14224598930481283,
1868
+ "grad_norm": 0.0830078125,
1869
+ "learning_rate": 0.0002,
1870
+ "loss": 0.1651,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.14278074866310161,
1875
+ "grad_norm": 0.2470703125,
1876
+ "learning_rate": 0.0002,
1877
+ "loss": 0.0828,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.14331550802139037,
1882
+ "grad_norm": 0.5625,
1883
+ "learning_rate": 0.0002,
1884
+ "loss": 0.1545,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.14385026737967915,
1889
+ "grad_norm": 0.30859375,
1890
+ "learning_rate": 0.0002,
1891
+ "loss": 0.1641,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.1443850267379679,
1896
+ "grad_norm": 0.625,
1897
+ "learning_rate": 0.0002,
1898
+ "loss": 0.3245,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.1449197860962567,
1903
+ "grad_norm": 0.45703125,
1904
+ "learning_rate": 0.0002,
1905
+ "loss": 0.1592,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.14545454545454545,
1910
+ "grad_norm": 0.1162109375,
1911
+ "learning_rate": 0.0002,
1912
+ "loss": 0.1406,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.14598930481283423,
1917
+ "grad_norm": 0.40625,
1918
+ "learning_rate": 0.0002,
1919
+ "loss": 0.1832,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.146524064171123,
1924
+ "grad_norm": 0.099609375,
1925
+ "learning_rate": 0.0002,
1926
+ "loss": 0.091,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.14705882352941177,
1931
+ "grad_norm": 0.416015625,
1932
+ "learning_rate": 0.0002,
1933
+ "loss": 0.0943,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.14759358288770053,
1938
+ "grad_norm": 2.359375,
1939
+ "learning_rate": 0.0002,
1940
+ "loss": 0.3355,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.1481283422459893,
1945
+ "grad_norm": 0.2138671875,
1946
+ "learning_rate": 0.0002,
1947
+ "loss": 0.1074,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.14866310160427806,
1952
+ "grad_norm": 0.3828125,
1953
+ "learning_rate": 0.0002,
1954
+ "loss": 0.157,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.14919786096256685,
1959
+ "grad_norm": 0.357421875,
1960
+ "learning_rate": 0.0002,
1961
+ "loss": 0.149,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.1497326203208556,
1966
+ "grad_norm": 0.478515625,
1967
+ "learning_rate": 0.0002,
1968
+ "loss": 0.2129,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.15026737967914439,
1973
+ "grad_norm": 0.73828125,
1974
+ "learning_rate": 0.0002,
1975
+ "loss": 0.3051,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.15080213903743314,
1980
+ "grad_norm": 1.1953125,
1981
+ "learning_rate": 0.0002,
1982
+ "loss": 0.147,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.15133689839572192,
1987
+ "grad_norm": 0.4375,
1988
+ "learning_rate": 0.0002,
1989
+ "loss": 0.1934,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.1518716577540107,
1994
+ "grad_norm": 0.2392578125,
1995
+ "learning_rate": 0.0002,
1996
+ "loss": 0.0722,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.15240641711229946,
2001
+ "grad_norm": 0.2353515625,
2002
+ "learning_rate": 0.0002,
2003
+ "loss": 0.062,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.15294117647058825,
2008
+ "grad_norm": 0.71484375,
2009
+ "learning_rate": 0.0002,
2010
+ "loss": 0.2352,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.153475935828877,
2015
+ "grad_norm": 1.0,
2016
+ "learning_rate": 0.0002,
2017
+ "loss": 0.2244,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.15401069518716579,
2022
+ "grad_norm": 0.388671875,
2023
+ "learning_rate": 0.0002,
2024
+ "loss": 0.1342,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.15454545454545454,
2029
+ "grad_norm": 0.1962890625,
2030
+ "learning_rate": 0.0002,
2031
+ "loss": 0.206,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.15508021390374332,
2036
+ "grad_norm": 1.375,
2037
+ "learning_rate": 0.0002,
2038
+ "loss": 0.3573,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.15561497326203208,
2043
+ "grad_norm": 0.294921875,
2044
+ "learning_rate": 0.0002,
2045
+ "loss": 0.1673,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.15614973262032086,
2050
+ "grad_norm": 0.1708984375,
2051
+ "learning_rate": 0.0002,
2052
+ "loss": 0.0897,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.15668449197860962,
2057
+ "grad_norm": 0.1572265625,
2058
+ "learning_rate": 0.0002,
2059
+ "loss": 0.0698,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.1572192513368984,
2064
+ "grad_norm": 0.0849609375,
2065
+ "learning_rate": 0.0002,
2066
+ "loss": 0.0981,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.15775401069518716,
2071
+ "grad_norm": 0.1162109375,
2072
+ "learning_rate": 0.0002,
2073
+ "loss": 0.0483,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.15828877005347594,
2078
+ "grad_norm": 0.1923828125,
2079
+ "learning_rate": 0.0002,
2080
+ "loss": 0.1486,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.1588235294117647,
2085
+ "grad_norm": 0.146484375,
2086
+ "learning_rate": 0.0002,
2087
+ "loss": 0.0981,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.15935828877005348,
2092
+ "grad_norm": 0.94140625,
2093
+ "learning_rate": 0.0002,
2094
+ "loss": 0.282,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.15989304812834224,
2099
+ "grad_norm": 0.318359375,
2100
+ "learning_rate": 0.0002,
2101
+ "loss": 0.1445,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.16042780748663102,
2106
+ "grad_norm": 0.25,
2107
+ "learning_rate": 0.0002,
2108
+ "loss": 0.1235,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.16096256684491977,
2113
+ "grad_norm": 0.10693359375,
2114
+ "learning_rate": 0.0002,
2115
+ "loss": 0.0835,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.16149732620320856,
2120
+ "grad_norm": 0.375,
2121
+ "learning_rate": 0.0002,
2122
+ "loss": 0.0934,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.1620320855614973,
2127
+ "grad_norm": 0.59765625,
2128
+ "learning_rate": 0.0002,
2129
+ "loss": 0.3041,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.1625668449197861,
2134
+ "grad_norm": 0.06640625,
2135
+ "learning_rate": 0.0002,
2136
+ "loss": 0.1435,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.16310160427807488,
2141
+ "grad_norm": 0.66796875,
2142
+ "learning_rate": 0.0002,
2143
+ "loss": 0.1957,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.16363636363636364,
2148
+ "grad_norm": 0.84765625,
2149
+ "learning_rate": 0.0002,
2150
+ "loss": 0.3342,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.16417112299465242,
2155
+ "grad_norm": 0.7265625,
2156
+ "learning_rate": 0.0002,
2157
+ "loss": 0.3299,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.16470588235294117,
2162
+ "grad_norm": 0.515625,
2163
+ "learning_rate": 0.0002,
2164
+ "loss": 0.1717,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.16524064171122996,
2169
+ "grad_norm": 0.4296875,
2170
+ "learning_rate": 0.0002,
2171
+ "loss": 0.2635,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.1657754010695187,
2176
+ "grad_norm": 0.1318359375,
2177
+ "learning_rate": 0.0002,
2178
+ "loss": 0.0933,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.1663101604278075,
2183
+ "grad_norm": 0.08642578125,
2184
+ "learning_rate": 0.0002,
2185
+ "loss": 0.0547,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.16684491978609625,
2190
+ "grad_norm": 0.46484375,
2191
+ "learning_rate": 0.0002,
2192
+ "loss": 0.2123,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.16737967914438504,
2197
+ "grad_norm": 0.095703125,
2198
+ "learning_rate": 0.0002,
2199
+ "loss": 0.1559,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.1679144385026738,
2204
+ "grad_norm": 1.0703125,
2205
+ "learning_rate": 0.0002,
2206
+ "loss": 0.243,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.16844919786096257,
2211
+ "grad_norm": 0.2578125,
2212
+ "learning_rate": 0.0002,
2213
+ "loss": 0.2638,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.16898395721925133,
2218
+ "grad_norm": 0.1435546875,
2219
+ "learning_rate": 0.0002,
2220
+ "loss": 0.1185,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.1695187165775401,
2225
+ "grad_norm": 0.5703125,
2226
+ "learning_rate": 0.0002,
2227
+ "loss": 0.2719,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.17005347593582887,
2232
+ "grad_norm": 1.375,
2233
+ "learning_rate": 0.0002,
2234
+ "loss": 0.4247,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.17058823529411765,
2239
+ "grad_norm": 0.34765625,
2240
+ "learning_rate": 0.0002,
2241
+ "loss": 0.3772,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.1711229946524064,
2246
+ "grad_norm": 0.10791015625,
2247
+ "learning_rate": 0.0002,
2248
+ "loss": 0.212,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.1716577540106952,
2253
+ "grad_norm": 0.419921875,
2254
+ "learning_rate": 0.0002,
2255
+ "loss": 0.1685,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.17219251336898395,
2260
+ "grad_norm": 0.255859375,
2261
+ "learning_rate": 0.0002,
2262
+ "loss": 0.2688,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.17272727272727273,
2267
+ "grad_norm": 0.11376953125,
2268
+ "learning_rate": 0.0002,
2269
+ "loss": 0.2073,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.17326203208556148,
2274
+ "grad_norm": 0.51953125,
2275
+ "learning_rate": 0.0002,
2276
+ "loss": 0.2158,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.17379679144385027,
2281
+ "grad_norm": 1.2734375,
2282
+ "learning_rate": 0.0002,
2283
+ "loss": 0.3103,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.17433155080213902,
2288
+ "grad_norm": 0.2421875,
2289
+ "learning_rate": 0.0002,
2290
+ "loss": 0.2458,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.1748663101604278,
2295
+ "grad_norm": 0.193359375,
2296
+ "learning_rate": 0.0002,
2297
+ "loss": 0.2203,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.1754010695187166,
2302
+ "grad_norm": 0.392578125,
2303
+ "learning_rate": 0.0002,
2304
+ "loss": 0.2319,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.17593582887700535,
2309
+ "grad_norm": 0.625,
2310
+ "learning_rate": 0.0002,
2311
+ "loss": 0.2094,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.17647058823529413,
2316
+ "grad_norm": 0.396484375,
2317
+ "learning_rate": 0.0002,
2318
+ "loss": 0.2354,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.17700534759358288,
2323
+ "grad_norm": 0.73046875,
2324
+ "learning_rate": 0.0002,
2325
+ "loss": 0.3425,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.17754010695187167,
2330
+ "grad_norm": 0.37109375,
2331
+ "learning_rate": 0.0002,
2332
+ "loss": 0.1983,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.17807486631016042,
2337
+ "grad_norm": 0.08984375,
2338
+ "learning_rate": 0.0002,
2339
+ "loss": 0.1281,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.1786096256684492,
2344
+ "grad_norm": 0.103515625,
2345
+ "learning_rate": 0.0002,
2346
+ "loss": 0.1543,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.17914438502673796,
2351
+ "grad_norm": 0.62890625,
2352
+ "learning_rate": 0.0002,
2353
+ "loss": 0.2649,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.17967914438502675,
2358
+ "grad_norm": 0.11572265625,
2359
+ "learning_rate": 0.0002,
2360
+ "loss": 0.1132,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.1802139037433155,
2365
+ "grad_norm": 1.0,
2366
+ "learning_rate": 0.0002,
2367
+ "loss": 0.428,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.18074866310160428,
2372
+ "grad_norm": 0.283203125,
2373
+ "learning_rate": 0.0002,
2374
+ "loss": 0.2577,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.18128342245989304,
2379
+ "grad_norm": 0.1357421875,
2380
+ "learning_rate": 0.0002,
2381
+ "loss": 0.1888,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.18181818181818182,
2386
+ "grad_norm": 0.5859375,
2387
+ "learning_rate": 0.0002,
2388
+ "loss": 0.2504,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.18235294117647058,
2393
+ "grad_norm": 0.90625,
2394
+ "learning_rate": 0.0002,
2395
+ "loss": 0.1937,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.18288770053475936,
2400
+ "grad_norm": 0.3671875,
2401
+ "learning_rate": 0.0002,
2402
+ "loss": 0.1778,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.18342245989304812,
2407
+ "grad_norm": 0.06298828125,
2408
+ "learning_rate": 0.0002,
2409
+ "loss": 0.0472,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.1839572192513369,
2414
+ "grad_norm": 0.455078125,
2415
+ "learning_rate": 0.0002,
2416
+ "loss": 0.1782,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.18449197860962566,
2421
+ "grad_norm": 0.494140625,
2422
+ "learning_rate": 0.0002,
2423
+ "loss": 0.2222,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.18502673796791444,
2428
+ "grad_norm": 0.3359375,
2429
+ "learning_rate": 0.0002,
2430
+ "loss": 0.1891,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.1855614973262032,
2435
+ "grad_norm": 0.51953125,
2436
+ "learning_rate": 0.0002,
2437
+ "loss": 0.3089,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.18609625668449198,
2442
+ "grad_norm": 2.734375,
2443
+ "learning_rate": 0.0002,
2444
+ "loss": 0.4823,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.18663101604278076,
2449
+ "grad_norm": 1.2890625,
2450
+ "learning_rate": 0.0002,
2451
+ "loss": 0.1879,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.18716577540106952,
2456
+ "grad_norm": 0.10546875,
2457
+ "learning_rate": 0.0002,
2458
+ "loss": 0.1862,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.1877005347593583,
2463
+ "grad_norm": 1.2578125,
2464
+ "learning_rate": 0.0002,
2465
+ "loss": 0.2416,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.18823529411764706,
2470
+ "grad_norm": 0.16796875,
2471
+ "learning_rate": 0.0002,
2472
+ "loss": 0.2126,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.18877005347593584,
2477
+ "grad_norm": 1.1484375,
2478
+ "learning_rate": 0.0002,
2479
+ "loss": 0.1726,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.1893048128342246,
2484
+ "grad_norm": 0.58203125,
2485
+ "learning_rate": 0.0002,
2486
+ "loss": 0.2085,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.18983957219251338,
2491
+ "grad_norm": 0.263671875,
2492
+ "learning_rate": 0.0002,
2493
+ "loss": 0.1478,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.19037433155080213,
2498
+ "grad_norm": 0.328125,
2499
+ "learning_rate": 0.0002,
2500
+ "loss": 0.1796,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.19090909090909092,
2505
+ "grad_norm": 0.72265625,
2506
+ "learning_rate": 0.0002,
2507
+ "loss": 0.3885,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.19144385026737967,
2512
+ "grad_norm": 0.2275390625,
2513
+ "learning_rate": 0.0002,
2514
+ "loss": 0.1843,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.19197860962566846,
2519
+ "grad_norm": 0.333984375,
2520
+ "learning_rate": 0.0002,
2521
+ "loss": 0.1804,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.1925133689839572,
2526
+ "grad_norm": 0.55859375,
2527
+ "learning_rate": 0.0002,
2528
+ "loss": 0.192,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.193048128342246,
2533
+ "grad_norm": 0.1220703125,
2534
+ "learning_rate": 0.0002,
2535
+ "loss": 0.0813,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.19358288770053475,
2540
+ "grad_norm": 0.1171875,
2541
+ "learning_rate": 0.0002,
2542
+ "loss": 0.0699,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.19411764705882353,
2547
+ "grad_norm": 0.453125,
2548
+ "learning_rate": 0.0002,
2549
+ "loss": 0.2945,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.1946524064171123,
2554
+ "grad_norm": 0.107421875,
2555
+ "learning_rate": 0.0002,
2556
+ "loss": 0.1997,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.19518716577540107,
2561
+ "grad_norm": 0.28125,
2562
+ "learning_rate": 0.0002,
2563
+ "loss": 0.2366,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.19572192513368983,
2568
+ "grad_norm": 0.58984375,
2569
+ "learning_rate": 0.0002,
2570
+ "loss": 0.2421,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.1962566844919786,
2575
+ "grad_norm": 0.2421875,
2576
+ "learning_rate": 0.0002,
2577
+ "loss": 0.1364,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.19679144385026737,
2582
+ "grad_norm": 0.45703125,
2583
+ "learning_rate": 0.0002,
2584
+ "loss": 0.1706,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.19732620320855615,
2589
+ "grad_norm": 0.1259765625,
2590
+ "learning_rate": 0.0002,
2591
+ "loss": 0.1628,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.19786096256684493,
2596
+ "grad_norm": 0.0927734375,
2597
+ "learning_rate": 0.0002,
2598
+ "loss": 0.1654,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.1983957219251337,
2603
+ "grad_norm": 0.29296875,
2604
+ "learning_rate": 0.0002,
2605
+ "loss": 0.0769,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.19893048128342247,
2610
+ "grad_norm": 0.255859375,
2611
+ "learning_rate": 0.0002,
2612
+ "loss": 0.2066,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.19946524064171123,
2617
+ "grad_norm": 0.376953125,
2618
+ "learning_rate": 0.0002,
2619
+ "loss": 0.12,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.2,
2624
+ "grad_norm": 0.2080078125,
2625
+ "learning_rate": 0.0002,
2626
+ "loss": 0.164,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.20053475935828877,
2631
+ "grad_norm": 0.375,
2632
+ "learning_rate": 0.0002,
2633
+ "loss": 0.251,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.20106951871657755,
2638
+ "grad_norm": 0.6640625,
2639
+ "learning_rate": 0.0002,
2640
+ "loss": 0.1263,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.2016042780748663,
2645
+ "grad_norm": 0.431640625,
2646
+ "learning_rate": 0.0002,
2647
+ "loss": 0.2442,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.2021390374331551,
2652
+ "grad_norm": 0.470703125,
2653
+ "learning_rate": 0.0002,
2654
+ "loss": 0.0631,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.20267379679144384,
2659
+ "grad_norm": 0.326171875,
2660
+ "learning_rate": 0.0002,
2661
+ "loss": 0.2238,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.20320855614973263,
2666
+ "grad_norm": 0.2890625,
2667
+ "learning_rate": 0.0002,
2668
+ "loss": 0.319,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.20374331550802138,
2673
+ "grad_norm": 0.298828125,
2674
+ "learning_rate": 0.0002,
2675
+ "loss": 0.1655,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.20427807486631017,
2680
+ "grad_norm": 0.205078125,
2681
+ "learning_rate": 0.0002,
2682
+ "loss": 0.1586,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.20481283422459892,
2687
+ "grad_norm": 0.318359375,
2688
+ "learning_rate": 0.0002,
2689
+ "loss": 0.2062,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.2053475935828877,
2694
+ "grad_norm": 0.365234375,
2695
+ "learning_rate": 0.0002,
2696
+ "loss": 0.2637,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.20588235294117646,
2701
+ "grad_norm": 0.271484375,
2702
+ "learning_rate": 0.0002,
2703
+ "loss": 0.203,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.20641711229946524,
2708
+ "grad_norm": 0.4140625,
2709
+ "learning_rate": 0.0002,
2710
+ "loss": 0.3365,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.206951871657754,
2715
+ "grad_norm": 0.2578125,
2716
+ "learning_rate": 0.0002,
2717
+ "loss": 0.2558,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.20748663101604278,
2722
+ "grad_norm": 0.380859375,
2723
+ "learning_rate": 0.0002,
2724
+ "loss": 0.1074,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.20802139037433154,
2729
+ "grad_norm": 0.2470703125,
2730
+ "learning_rate": 0.0002,
2731
+ "loss": 0.1507,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.20855614973262032,
2736
+ "grad_norm": 0.1474609375,
2737
+ "learning_rate": 0.0002,
2738
+ "loss": 0.2006,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.20909090909090908,
2743
+ "grad_norm": 0.224609375,
2744
+ "learning_rate": 0.0002,
2745
+ "loss": 0.2195,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.20962566844919786,
2750
+ "grad_norm": 0.193359375,
2751
+ "learning_rate": 0.0002,
2752
+ "loss": 0.1366,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.21016042780748664,
2757
+ "grad_norm": 0.3359375,
2758
+ "learning_rate": 0.0002,
2759
+ "loss": 0.2126,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.2106951871657754,
2764
+ "grad_norm": 0.20703125,
2765
+ "learning_rate": 0.0002,
2766
+ "loss": 0.0699,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.21122994652406418,
2771
+ "grad_norm": 0.248046875,
2772
+ "learning_rate": 0.0002,
2773
+ "loss": 0.1594,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.21176470588235294,
2778
+ "grad_norm": 0.265625,
2779
+ "learning_rate": 0.0002,
2780
+ "loss": 0.1362,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.21229946524064172,
2785
+ "grad_norm": 0.1328125,
2786
+ "learning_rate": 0.0002,
2787
+ "loss": 0.1458,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.21283422459893048,
2792
+ "grad_norm": 0.67578125,
2793
+ "learning_rate": 0.0002,
2794
+ "loss": 0.2377,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.21336898395721926,
2799
+ "grad_norm": 1.1171875,
2800
+ "learning_rate": 0.0002,
2801
+ "loss": 0.4138,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.21390374331550802,
2806
+ "grad_norm": 0.2197265625,
2807
+ "learning_rate": 0.0002,
2808
+ "loss": 0.1331,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.2144385026737968,
2813
+ "grad_norm": 0.703125,
2814
+ "learning_rate": 0.0002,
2815
+ "loss": 0.3063,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.21497326203208555,
2820
+ "grad_norm": 0.49609375,
2821
+ "learning_rate": 0.0002,
2822
+ "loss": 0.15,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.21550802139037434,
2827
+ "grad_norm": 0.59765625,
2828
+ "learning_rate": 0.0002,
2829
+ "loss": 0.1727,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.2160427807486631,
2834
+ "grad_norm": 0.328125,
2835
+ "learning_rate": 0.0002,
2836
+ "loss": 0.1833,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.21657754010695188,
2841
+ "grad_norm": 0.146484375,
2842
+ "learning_rate": 0.0002,
2843
+ "loss": 0.0712,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.21711229946524063,
2848
+ "grad_norm": 0.134765625,
2849
+ "learning_rate": 0.0002,
2850
+ "loss": 0.1766,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.21764705882352942,
2855
+ "grad_norm": 0.3203125,
2856
+ "learning_rate": 0.0002,
2857
+ "loss": 0.2309,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.21818181818181817,
2862
+ "grad_norm": 0.1298828125,
2863
+ "learning_rate": 0.0002,
2864
+ "loss": 0.1819,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.21871657754010695,
2869
+ "grad_norm": 0.146484375,
2870
+ "learning_rate": 0.0002,
2871
+ "loss": 0.1536,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.2192513368983957,
2876
+ "grad_norm": 0.177734375,
2877
+ "learning_rate": 0.0002,
2878
+ "loss": 0.1115,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.2197860962566845,
2883
+ "grad_norm": 0.181640625,
2884
+ "learning_rate": 0.0002,
2885
+ "loss": 0.1675,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.22032085561497325,
2890
+ "grad_norm": 1.171875,
2891
+ "learning_rate": 0.0002,
2892
+ "loss": 0.1975,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.22085561497326203,
2897
+ "grad_norm": 0.609375,
2898
+ "learning_rate": 0.0002,
2899
+ "loss": 0.2091,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.22139037433155082,
2904
+ "grad_norm": 0.431640625,
2905
+ "learning_rate": 0.0002,
2906
+ "loss": 0.2046,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.22192513368983957,
2911
+ "grad_norm": 0.11474609375,
2912
+ "learning_rate": 0.0002,
2913
+ "loss": 0.1062,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.22245989304812835,
2918
+ "grad_norm": 0.328125,
2919
+ "learning_rate": 0.0002,
2920
+ "loss": 0.252,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.2229946524064171,
2925
+ "grad_norm": 0.4296875,
2926
+ "learning_rate": 0.0002,
2927
+ "loss": 0.2299,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.2235294117647059,
2932
+ "grad_norm": 0.453125,
2933
+ "learning_rate": 0.0002,
2934
+ "loss": 0.1805,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.22406417112299465,
2939
+ "grad_norm": 0.2314453125,
2940
+ "learning_rate": 0.0002,
2941
+ "loss": 0.2925,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.22459893048128343,
2946
+ "grad_norm": 1.0546875,
2947
+ "learning_rate": 0.0002,
2948
+ "loss": 0.2782,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.2251336898395722,
2953
+ "grad_norm": 0.162109375,
2954
+ "learning_rate": 0.0002,
2955
+ "loss": 0.1329,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.22566844919786097,
2960
+ "grad_norm": 0.421875,
2961
+ "learning_rate": 0.0002,
2962
+ "loss": 0.2275,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.22620320855614973,
2967
+ "grad_norm": 0.2158203125,
2968
+ "learning_rate": 0.0002,
2969
+ "loss": 0.1434,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.2267379679144385,
2974
+ "grad_norm": 0.2119140625,
2975
+ "learning_rate": 0.0002,
2976
+ "loss": 0.1863,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.22727272727272727,
2981
+ "grad_norm": 0.69140625,
2982
+ "learning_rate": 0.0002,
2983
+ "loss": 0.2988,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.22780748663101605,
2988
+ "grad_norm": 0.5,
2989
+ "learning_rate": 0.0002,
2990
+ "loss": 0.2001,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.2283422459893048,
2995
+ "grad_norm": 0.251953125,
2996
+ "learning_rate": 0.0002,
2997
+ "loss": 0.2114,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.2288770053475936,
3002
+ "grad_norm": 0.1796875,
3003
+ "learning_rate": 0.0002,
3004
+ "loss": 0.1191,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.22941176470588234,
3009
+ "grad_norm": 0.52734375,
3010
+ "learning_rate": 0.0002,
3011
+ "loss": 0.2393,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.22994652406417113,
3016
+ "grad_norm": 0.671875,
3017
+ "learning_rate": 0.0002,
3018
+ "loss": 0.1093,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.23048128342245988,
3023
+ "grad_norm": 0.51171875,
3024
+ "learning_rate": 0.0002,
3025
+ "loss": 0.2828,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.23101604278074866,
3030
+ "grad_norm": 0.26953125,
3031
+ "learning_rate": 0.0002,
3032
+ "loss": 0.2073,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.23155080213903742,
3037
+ "grad_norm": 0.578125,
3038
+ "learning_rate": 0.0002,
3039
+ "loss": 0.3156,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.2320855614973262,
3044
+ "grad_norm": 0.2294921875,
3045
+ "learning_rate": 0.0002,
3046
+ "loss": 0.1862,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.232620320855615,
3051
+ "grad_norm": 0.10791015625,
3052
+ "learning_rate": 0.0002,
3053
+ "loss": 0.1061,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.23315508021390374,
3058
+ "grad_norm": 0.466796875,
3059
+ "learning_rate": 0.0002,
3060
+ "loss": 0.2721,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.23368983957219253,
3065
+ "grad_norm": 0.12060546875,
3066
+ "learning_rate": 0.0002,
3067
+ "loss": 0.0834,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.23422459893048128,
3072
+ "grad_norm": 0.380859375,
3073
+ "learning_rate": 0.0002,
3074
+ "loss": 0.1377,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.23475935828877006,
3079
+ "grad_norm": 0.671875,
3080
+ "learning_rate": 0.0002,
3081
+ "loss": 0.21,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.23529411764705882,
3086
+ "grad_norm": 0.2099609375,
3087
+ "learning_rate": 0.0002,
3088
+ "loss": 0.1004,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.2358288770053476,
3093
+ "grad_norm": 0.1611328125,
3094
+ "learning_rate": 0.0002,
3095
+ "loss": 0.1424,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.23636363636363636,
3100
+ "grad_norm": 0.1826171875,
3101
+ "learning_rate": 0.0002,
3102
+ "loss": 0.12,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.23689839572192514,
3107
+ "grad_norm": 0.28515625,
3108
+ "learning_rate": 0.0002,
3109
+ "loss": 0.155,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.2374331550802139,
3114
+ "grad_norm": 0.2255859375,
3115
+ "learning_rate": 0.0002,
3116
+ "loss": 0.1647,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.23796791443850268,
3121
+ "grad_norm": 0.2890625,
3122
+ "learning_rate": 0.0002,
3123
+ "loss": 0.1718,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.23850267379679144,
3128
+ "grad_norm": 0.103515625,
3129
+ "learning_rate": 0.0002,
3130
+ "loss": 0.0817,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.23903743315508022,
3135
+ "grad_norm": 0.25390625,
3136
+ "learning_rate": 0.0002,
3137
+ "loss": 0.1277,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.23957219251336898,
3142
+ "grad_norm": 0.353515625,
3143
+ "learning_rate": 0.0002,
3144
+ "loss": 0.1198,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.24010695187165776,
3149
+ "grad_norm": 0.06787109375,
3150
+ "learning_rate": 0.0002,
3151
+ "loss": 0.0802,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.24064171122994651,
3156
+ "grad_norm": 0.2490234375,
3157
+ "learning_rate": 0.0002,
3158
+ "loss": 0.0657,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.2411764705882353,
3163
+ "grad_norm": 0.1181640625,
3164
+ "learning_rate": 0.0002,
3165
+ "loss": 0.1076,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.24171122994652405,
3170
+ "grad_norm": 0.1181640625,
3171
+ "learning_rate": 0.0002,
3172
+ "loss": 0.0829,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.24224598930481284,
3177
+ "grad_norm": 0.1767578125,
3178
+ "learning_rate": 0.0002,
3179
+ "loss": 0.1498,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.2427807486631016,
3184
+ "grad_norm": 0.1025390625,
3185
+ "learning_rate": 0.0002,
3186
+ "loss": 0.0773,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.24331550802139038,
3191
+ "grad_norm": 0.1357421875,
3192
+ "learning_rate": 0.0002,
3193
+ "loss": 0.0283,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.24385026737967913,
3198
+ "grad_norm": 0.73046875,
3199
+ "learning_rate": 0.0002,
3200
+ "loss": 0.1534,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.24438502673796791,
3205
+ "grad_norm": 0.25390625,
3206
+ "learning_rate": 0.0002,
3207
+ "loss": 0.2006,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.2449197860962567,
3212
+ "grad_norm": 0.09814453125,
3213
+ "learning_rate": 0.0002,
3214
+ "loss": 0.0201,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.24545454545454545,
3219
+ "grad_norm": 0.458984375,
3220
+ "learning_rate": 0.0002,
3221
+ "loss": 0.3034,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.24598930481283424,
3226
+ "grad_norm": 0.63671875,
3227
+ "learning_rate": 0.0002,
3228
+ "loss": 0.3538,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.246524064171123,
3233
+ "grad_norm": 0.2001953125,
3234
+ "learning_rate": 0.0002,
3235
+ "loss": 0.138,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.24705882352941178,
3240
+ "grad_norm": 1.3671875,
3241
+ "learning_rate": 0.0002,
3242
+ "loss": 0.2199,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.24759358288770053,
3247
+ "grad_norm": 0.58984375,
3248
+ "learning_rate": 0.0002,
3249
+ "loss": 0.3079,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.24812834224598931,
3254
+ "grad_norm": 0.51171875,
3255
+ "learning_rate": 0.0002,
3256
+ "loss": 0.36,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.24866310160427807,
3261
+ "grad_norm": 0.91015625,
3262
+ "learning_rate": 0.0002,
3263
+ "loss": 0.3007,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.24919786096256685,
3268
+ "grad_norm": 1.0234375,
3269
+ "learning_rate": 0.0002,
3270
+ "loss": 0.2952,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.2497326203208556,
3275
+ "grad_norm": 0.2197265625,
3276
+ "learning_rate": 0.0002,
3277
+ "loss": 0.0584,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.25026737967914436,
3282
+ "grad_norm": 0.1923828125,
3283
+ "learning_rate": 0.0002,
3284
+ "loss": 0.0912,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.25080213903743315,
3289
+ "grad_norm": 0.21875,
3290
+ "learning_rate": 0.0002,
3291
+ "loss": 0.1412,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.25133689839572193,
3296
+ "grad_norm": 0.59765625,
3297
+ "learning_rate": 0.0002,
3298
+ "loss": 0.3287,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.2518716577540107,
3303
+ "grad_norm": 0.1708984375,
3304
+ "learning_rate": 0.0002,
3305
+ "loss": 0.2102,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.25240641711229944,
3310
+ "grad_norm": 0.259765625,
3311
+ "learning_rate": 0.0002,
3312
+ "loss": 0.2511,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.2529411764705882,
3317
+ "grad_norm": 0.388671875,
3318
+ "learning_rate": 0.0002,
3319
+ "loss": 0.2573,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.253475935828877,
3324
+ "grad_norm": 0.1025390625,
3325
+ "learning_rate": 0.0002,
3326
+ "loss": 0.1181,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.2540106951871658,
3331
+ "grad_norm": 0.291015625,
3332
+ "learning_rate": 0.0002,
3333
+ "loss": 0.1183,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.2545454545454545,
3338
+ "grad_norm": 0.330078125,
3339
+ "learning_rate": 0.0002,
3340
+ "loss": 0.1341,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.2550802139037433,
3345
+ "grad_norm": 0.31640625,
3346
+ "learning_rate": 0.0002,
3347
+ "loss": 0.16,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.2556149732620321,
3352
+ "grad_norm": 0.2392578125,
3353
+ "learning_rate": 0.0002,
3354
+ "loss": 0.2133,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.25614973262032087,
3359
+ "grad_norm": 0.373046875,
3360
+ "learning_rate": 0.0002,
3361
+ "loss": 0.2048,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.25668449197860965,
3366
+ "grad_norm": 0.2353515625,
3367
+ "learning_rate": 0.0002,
3368
+ "loss": 0.2218,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.2572192513368984,
3373
+ "grad_norm": 0.36328125,
3374
+ "learning_rate": 0.0002,
3375
+ "loss": 0.1959,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.25775401069518716,
3380
+ "grad_norm": 0.1318359375,
3381
+ "learning_rate": 0.0002,
3382
+ "loss": 0.1816,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.25828877005347595,
3387
+ "grad_norm": 0.458984375,
3388
+ "learning_rate": 0.0002,
3389
+ "loss": 0.1479,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.25882352941176473,
3394
+ "grad_norm": 0.33984375,
3395
+ "learning_rate": 0.0002,
3396
+ "loss": 0.189,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.25935828877005346,
3401
+ "grad_norm": 1.1953125,
3402
+ "learning_rate": 0.0002,
3403
+ "loss": 0.2001,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.25989304812834224,
3408
+ "grad_norm": 0.06591796875,
3409
+ "learning_rate": 0.0002,
3410
+ "loss": 0.0943,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.260427807486631,
3415
+ "grad_norm": 0.287109375,
3416
+ "learning_rate": 0.0002,
3417
+ "loss": 0.1934,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.2609625668449198,
3422
+ "grad_norm": 0.51171875,
3423
+ "learning_rate": 0.0002,
3424
+ "loss": 0.2581,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.26149732620320854,
3429
+ "grad_norm": 0.15625,
3430
+ "learning_rate": 0.0002,
3431
+ "loss": 0.0733,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.2620320855614973,
3436
+ "grad_norm": 0.494140625,
3437
+ "learning_rate": 0.0002,
3438
+ "loss": 0.2736,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.2625668449197861,
3443
+ "grad_norm": 0.271484375,
3444
+ "learning_rate": 0.0002,
3445
+ "loss": 0.1819,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.2631016042780749,
3450
+ "grad_norm": 0.302734375,
3451
+ "learning_rate": 0.0002,
3452
+ "loss": 0.2011,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.2636363636363636,
3457
+ "grad_norm": 0.3984375,
3458
+ "learning_rate": 0.0002,
3459
+ "loss": 0.1678,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.2641711229946524,
3464
+ "grad_norm": 0.94921875,
3465
+ "learning_rate": 0.0002,
3466
+ "loss": 0.1992,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.2647058823529412,
3471
+ "grad_norm": 1.0546875,
3472
+ "learning_rate": 0.0002,
3473
+ "loss": 0.3075,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.26524064171122996,
3478
+ "grad_norm": 0.21484375,
3479
+ "learning_rate": 0.0002,
3480
+ "loss": 0.1961,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.2657754010695187,
3485
+ "grad_norm": 0.236328125,
3486
+ "learning_rate": 0.0002,
3487
+ "loss": 0.1905,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.2663101604278075,
3492
+ "grad_norm": 0.1015625,
3493
+ "learning_rate": 0.0002,
3494
+ "loss": 0.1238,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.26684491978609626,
3499
+ "grad_norm": 0.1767578125,
3500
+ "learning_rate": 0.0002,
3501
+ "loss": 0.122,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.26737967914438504,
3506
+ "grad_norm": 0.70703125,
3507
+ "learning_rate": 0.0002,
3508
+ "loss": 0.192,
3509
+ "step": 500
3510
+ }
3511
+ ],
3512
+ "logging_steps": 1,
3513
+ "max_steps": 500,
3514
+ "num_input_tokens_seen": 0,
3515
+ "num_train_epochs": 1,
3516
+ "save_steps": 100,
3517
+ "stateful_callbacks": {
3518
+ "TrainerControl": {
3519
+ "args": {
3520
+ "should_epoch_stop": false,
3521
+ "should_evaluate": false,
3522
+ "should_log": false,
3523
+ "should_save": true,
3524
+ "should_training_stop": true
3525
+ },
3526
+ "attributes": {}
3527
+ }
3528
+ },
3529
+ "total_flos": 1.729911211451351e+17,
3530
+ "train_batch_size": 8,
3531
+ "trial_name": null,
3532
+ "trial_params": null
3533
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0dab36b31f865cab25580aa144d7531488eac3b96808da9d2810abda018ef66
3
+ size 4923