ErrorAI commited on
Commit
c89dcc2
·
verified ·
1 Parent(s): a5cde40

Training in progress, step 287, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: beomi/polyglot-ko-12.8b-safetensors
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "beomi/polyglot-ko-12.8b-safetensors",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "dense_4h_to_h",
24
+ "dense_h_to_4h",
25
+ "dense",
26
+ "query_key_value"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894c679e66191475663ff31d911229b0184d2b9c1adf7a554f34cdd5fe702203
3
+ size 104902272
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db799934561153f3ff36b05608f05055eb963bf784356aea066487d7fbb2eaf
3
+ size 53623316
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c581024c74a3cea17de2c46d87701f0bdd045076e0a273123f5123b93593b4c6
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ccacda6f618dad4f70591742bced172b2e5f1a08ed5cc91a6e8aa8210d6c52
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|unused0|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|unused1|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|sep|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30000": {
36
+ "content": "<|acc|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30001": {
44
+ "content": "<|tel|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30002": {
52
+ "content": "<|rrn|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<|endoftext|>",
62
+ "<|sep|>",
63
+ "<|acc|>",
64
+ "<|tel|>",
65
+ "<|rrn|>"
66
+ ],
67
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
68
+ "clean_up_tokenization_spaces": true,
69
+ "eos_token": "<|endoftext|>",
70
+ "model_max_length": 1000000000000000019884624838656,
71
+ "pad_token": "<|endoftext|>",
72
+ "tokenizer_class": "PreTrainedTokenizerFast"
73
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,2058 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.25010893246187366,
5
+ "eval_steps": 287,
6
+ "global_step": 287,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0008714596949891067,
13
+ "grad_norm": 0.680671215057373,
14
+ "learning_rate": 2e-05,
15
+ "loss": 13.3022,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0008714596949891067,
20
+ "eval_loss": 3.2851531505584717,
21
+ "eval_runtime": 36.2933,
22
+ "eval_samples_per_second": 13.336,
23
+ "eval_steps_per_second": 6.668,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0017429193899782135,
28
+ "grad_norm": 0.60734623670578,
29
+ "learning_rate": 4e-05,
30
+ "loss": 12.7052,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.00261437908496732,
35
+ "grad_norm": 0.6666874289512634,
36
+ "learning_rate": 6e-05,
37
+ "loss": 13.1762,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.003485838779956427,
42
+ "grad_norm": 0.7367079854011536,
43
+ "learning_rate": 8e-05,
44
+ "loss": 13.1438,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.004357298474945534,
49
+ "grad_norm": 0.9108680486679077,
50
+ "learning_rate": 0.0001,
51
+ "loss": 12.6651,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.00522875816993464,
56
+ "grad_norm": 1.180690884590149,
57
+ "learning_rate": 0.00012,
58
+ "loss": 13.7955,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.006100217864923747,
63
+ "grad_norm": 1.57722806930542,
64
+ "learning_rate": 0.00014,
65
+ "loss": 12.338,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.006971677559912854,
70
+ "grad_norm": 1.6677275896072388,
71
+ "learning_rate": 0.00016,
72
+ "loss": 12.4497,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.00784313725490196,
77
+ "grad_norm": 2.204782724380493,
78
+ "learning_rate": 0.00018,
79
+ "loss": 12.2081,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.008714596949891068,
84
+ "grad_norm": 3.125051975250244,
85
+ "learning_rate": 0.0002,
86
+ "loss": 11.4096,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.009586056644880174,
91
+ "grad_norm": 4.625213623046875,
92
+ "learning_rate": 0.000199999618947382,
93
+ "loss": 11.7585,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.01045751633986928,
98
+ "grad_norm": 2.739525079727173,
99
+ "learning_rate": 0.00019999847579243193,
100
+ "loss": 10.207,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.011328976034858388,
105
+ "grad_norm": 3.9526243209838867,
106
+ "learning_rate": 0.00019999657054386194,
107
+ "loss": 10.8658,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.012200435729847494,
112
+ "grad_norm": 5.227208137512207,
113
+ "learning_rate": 0.00019999390321619192,
114
+ "loss": 10.7903,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.013071895424836602,
119
+ "grad_norm": 2.937030076980591,
120
+ "learning_rate": 0.00019999047382974984,
121
+ "loss": 10.1651,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.013943355119825708,
126
+ "grad_norm": 4.163013935089111,
127
+ "learning_rate": 0.00019998628241067113,
128
+ "loss": 9.7829,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.014814814814814815,
133
+ "grad_norm": 2.8028531074523926,
134
+ "learning_rate": 0.0001999813289908988,
135
+ "loss": 9.3255,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.01568627450980392,
140
+ "grad_norm": 3.5442142486572266,
141
+ "learning_rate": 0.00019997561360818322,
142
+ "loss": 9.3367,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.016557734204793027,
147
+ "grad_norm": 3.128521680831909,
148
+ "learning_rate": 0.00019996913630608156,
149
+ "loss": 10.021,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.017429193899782137,
154
+ "grad_norm": 2.5402672290802,
155
+ "learning_rate": 0.00019996189713395766,
156
+ "loss": 9.5093,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.018300653594771243,
161
+ "grad_norm": 3.152247667312622,
162
+ "learning_rate": 0.0001999538961469817,
163
+ "loss": 8.6684,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.01917211328976035,
168
+ "grad_norm": 2.1982603073120117,
169
+ "learning_rate": 0.00019994513340612958,
170
+ "loss": 8.4312,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.020043572984749455,
175
+ "grad_norm": 3.4315600395202637,
176
+ "learning_rate": 0.00019993560897818257,
177
+ "loss": 9.3834,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.02091503267973856,
182
+ "grad_norm": 2.5089111328125,
183
+ "learning_rate": 0.00019992532293572687,
184
+ "loss": 8.1622,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.02178649237472767,
189
+ "grad_norm": 3.1182727813720703,
190
+ "learning_rate": 0.00019991427535715297,
191
+ "loss": 7.9338,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.022657952069716776,
196
+ "grad_norm": 2.477149248123169,
197
+ "learning_rate": 0.000199902466326655,
198
+ "loss": 8.9115,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.023529411764705882,
203
+ "grad_norm": 2.0672333240509033,
204
+ "learning_rate": 0.00019988989593423023,
205
+ "loss": 7.3406,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.024400871459694988,
210
+ "grad_norm": 2.7209792137145996,
211
+ "learning_rate": 0.0001998765642756783,
212
+ "loss": 8.7029,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.025272331154684097,
217
+ "grad_norm": 3.008445978164673,
218
+ "learning_rate": 0.0001998624714526004,
219
+ "loss": 8.6305,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.026143790849673203,
224
+ "grad_norm": 3.54339861869812,
225
+ "learning_rate": 0.00019984761757239875,
226
+ "loss": 8.7717,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.02701525054466231,
231
+ "grad_norm": 3.165290117263794,
232
+ "learning_rate": 0.0001998320027482755,
233
+ "loss": 8.4816,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.027886710239651415,
238
+ "grad_norm": 3.5009524822235107,
239
+ "learning_rate": 0.0001998156270992321,
240
+ "loss": 8.1248,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.02875816993464052,
245
+ "grad_norm": 3.006110906600952,
246
+ "learning_rate": 0.00019979849075006816,
247
+ "loss": 8.0753,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.02962962962962963,
252
+ "grad_norm": 2.5773518085479736,
253
+ "learning_rate": 0.00019978059383138073,
254
+ "loss": 8.3531,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.030501089324618737,
259
+ "grad_norm": 2.345578670501709,
260
+ "learning_rate": 0.00019976193647956313,
261
+ "loss": 7.4162,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.03137254901960784,
266
+ "grad_norm": 2.8506760597229004,
267
+ "learning_rate": 0.00019974251883680407,
268
+ "loss": 7.4984,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.03224400871459695,
273
+ "grad_norm": 2.7859225273132324,
274
+ "learning_rate": 0.0001997223410510864,
275
+ "loss": 8.5058,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.033115468409586055,
280
+ "grad_norm": 2.985344648361206,
281
+ "learning_rate": 0.0001997014032761861,
282
+ "loss": 7.3735,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.03398692810457516,
287
+ "grad_norm": 2.3483641147613525,
288
+ "learning_rate": 0.000199679705671671,
289
+ "loss": 7.94,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.034858387799564274,
294
+ "grad_norm": 2.677859306335449,
295
+ "learning_rate": 0.0001996572484028997,
296
+ "loss": 7.4677,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.03572984749455338,
301
+ "grad_norm": 3.67486310005188,
302
+ "learning_rate": 0.00019963403164102023,
303
+ "loss": 7.464,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.036601307189542485,
308
+ "grad_norm": 3.123943567276001,
309
+ "learning_rate": 0.00019961005556296874,
310
+ "loss": 7.3675,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.03747276688453159,
315
+ "grad_norm": 2.849947452545166,
316
+ "learning_rate": 0.0001995853203514682,
317
+ "loss": 7.2305,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.0383442265795207,
322
+ "grad_norm": 3.0516927242279053,
323
+ "learning_rate": 0.00019955982619502692,
324
+ "loss": 8.0985,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.0392156862745098,
329
+ "grad_norm": 2.9423375129699707,
330
+ "learning_rate": 0.00019953357328793725,
331
+ "loss": 7.2214,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.04008714596949891,
336
+ "grad_norm": 3.1682639122009277,
337
+ "learning_rate": 0.0001995065618302739,
338
+ "loss": 7.3553,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.040958605664488015,
343
+ "grad_norm": 3.309410810470581,
344
+ "learning_rate": 0.00019947879202789266,
345
+ "loss": 7.6454,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.04183006535947712,
350
+ "grad_norm": 3.1530559062957764,
351
+ "learning_rate": 0.00019945026409242859,
352
+ "loss": 7.1703,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.042701525054466234,
357
+ "grad_norm": 3.1763932704925537,
358
+ "learning_rate": 0.00019942097824129468,
359
+ "loss": 7.4116,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.04357298474945534,
364
+ "grad_norm": 3.0348143577575684,
365
+ "learning_rate": 0.0001993909346976798,
366
+ "loss": 6.7981,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.044444444444444446,
371
+ "grad_norm": 2.6799118518829346,
372
+ "learning_rate": 0.00019936013369054747,
373
+ "loss": 6.6832,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.04531590413943355,
378
+ "grad_norm": 3.460106372833252,
379
+ "learning_rate": 0.00019932857545463376,
380
+ "loss": 7.3217,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.04618736383442266,
385
+ "grad_norm": 3.0749166011810303,
386
+ "learning_rate": 0.0001992962602304456,
387
+ "loss": 7.3473,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.047058823529411764,
392
+ "grad_norm": 2.8054497241973877,
393
+ "learning_rate": 0.00019926318826425906,
394
+ "loss": 6.7988,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.04793028322440087,
399
+ "grad_norm": 3.135683298110962,
400
+ "learning_rate": 0.0001992293598081173,
401
+ "loss": 7.3798,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.048801742919389976,
406
+ "grad_norm": 3.180582046508789,
407
+ "learning_rate": 0.0001991947751198287,
408
+ "loss": 7.5615,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.04967320261437908,
413
+ "grad_norm": 3.264227867126465,
414
+ "learning_rate": 0.00019915943446296508,
415
+ "loss": 6.33,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.050544662309368195,
420
+ "grad_norm": 3.140679359436035,
421
+ "learning_rate": 0.0001991233381068594,
422
+ "loss": 6.889,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.0514161220043573,
427
+ "grad_norm": 2.7237389087677,
428
+ "learning_rate": 0.00019908648632660384,
429
+ "loss": 6.5348,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.05228758169934641,
434
+ "grad_norm": 3.147747039794922,
435
+ "learning_rate": 0.0001990488794030478,
436
+ "loss": 7.3343,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.05315904139433551,
441
+ "grad_norm": 3.4708566665649414,
442
+ "learning_rate": 0.00019901051762279557,
443
+ "loss": 7.5022,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.05403050108932462,
448
+ "grad_norm": 3.421638011932373,
449
+ "learning_rate": 0.0001989714012782043,
450
+ "loss": 7.1205,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.054901960784313725,
455
+ "grad_norm": 3.340749740600586,
456
+ "learning_rate": 0.00019893153066738174,
457
+ "loss": 6.8214,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.05577342047930283,
462
+ "grad_norm": 2.9868993759155273,
463
+ "learning_rate": 0.00019889090609418383,
464
+ "loss": 6.5204,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.05664488017429194,
469
+ "grad_norm": 3.6563544273376465,
470
+ "learning_rate": 0.00019884952786821262,
471
+ "loss": 6.825,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.05751633986928104,
476
+ "grad_norm": 3.3555402755737305,
477
+ "learning_rate": 0.00019880739630481376,
478
+ "loss": 6.5682,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.058387799564270156,
483
+ "grad_norm": 3.969329595565796,
484
+ "learning_rate": 0.00019876451172507405,
485
+ "loss": 7.147,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.05925925925925926,
490
+ "grad_norm": 3.1107804775238037,
491
+ "learning_rate": 0.0001987208744558191,
492
+ "loss": 7.2729,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.06013071895424837,
497
+ "grad_norm": 3.0024502277374268,
498
+ "learning_rate": 0.0001986764848296109,
499
+ "loss": 7.0344,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.06100217864923747,
504
+ "grad_norm": 3.157567262649536,
505
+ "learning_rate": 0.00019863134318474503,
506
+ "loss": 6.4804,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.06187363834422658,
511
+ "grad_norm": 3.0120584964752197,
512
+ "learning_rate": 0.00019858544986524842,
513
+ "loss": 6.6174,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.06274509803921569,
518
+ "grad_norm": 2.7023561000823975,
519
+ "learning_rate": 0.0001985388052208764,
520
+ "loss": 6.4292,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.0636165577342048,
525
+ "grad_norm": 3.1930267810821533,
526
+ "learning_rate": 0.00019849140960711024,
527
+ "loss": 6.4055,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.0644880174291939,
532
+ "grad_norm": 3.755228281021118,
533
+ "learning_rate": 0.00019844326338515442,
534
+ "loss": 6.4323,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.06535947712418301,
539
+ "grad_norm": 2.9738314151763916,
540
+ "learning_rate": 0.00019839436692193382,
541
+ "loss": 6.3896,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.06623093681917211,
546
+ "grad_norm": 3.826676368713379,
547
+ "learning_rate": 0.00019834472059009094,
548
+ "loss": 6.9625,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.06710239651416122,
553
+ "grad_norm": 3.9622623920440674,
554
+ "learning_rate": 0.00019829432476798305,
555
+ "loss": 6.4479,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.06797385620915032,
560
+ "grad_norm": 3.611128807067871,
561
+ "learning_rate": 0.0001982431798396794,
562
+ "loss": 6.7138,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.06884531590413943,
567
+ "grad_norm": 4.133875846862793,
568
+ "learning_rate": 0.00019819128619495815,
569
+ "loss": 6.5333,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.06971677559912855,
574
+ "grad_norm": 3.640047073364258,
575
+ "learning_rate": 0.00019813864422930347,
576
+ "loss": 6.6399,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.07058823529411765,
581
+ "grad_norm": 4.111522674560547,
582
+ "learning_rate": 0.00019808525434390252,
583
+ "loss": 6.4246,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.07145969498910676,
588
+ "grad_norm": 3.350358486175537,
589
+ "learning_rate": 0.00019803111694564245,
590
+ "loss": 6.6735,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.07233115468409586,
595
+ "grad_norm": 2.8375182151794434,
596
+ "learning_rate": 0.00019797623244710718,
597
+ "loss": 6.7033,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.07320261437908497,
602
+ "grad_norm": 4.679914474487305,
603
+ "learning_rate": 0.00019792060126657435,
604
+ "loss": 6.5279,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.07407407407407407,
609
+ "grad_norm": 4.829922199249268,
610
+ "learning_rate": 0.0001978642238280121,
611
+ "loss": 7.1854,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.07494553376906318,
616
+ "grad_norm": 3.765516519546509,
617
+ "learning_rate": 0.00019780710056107586,
618
+ "loss": 6.6842,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.07581699346405228,
623
+ "grad_norm": 4.241717338562012,
624
+ "learning_rate": 0.00019774923190110503,
625
+ "loss": 6.9138,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.0766884531590414,
630
+ "grad_norm": 3.3606960773468018,
631
+ "learning_rate": 0.00019769061828911968,
632
+ "loss": 6.0427,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.07755991285403051,
637
+ "grad_norm": 3.7323086261749268,
638
+ "learning_rate": 0.00019763126017181723,
639
+ "loss": 6.9421,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.0784313725490196,
644
+ "grad_norm": 3.045558452606201,
645
+ "learning_rate": 0.000197571158001569,
646
+ "loss": 7.0787,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.07930283224400872,
651
+ "grad_norm": 3.1116671562194824,
652
+ "learning_rate": 0.0001975103122364168,
653
+ "loss": 7.5127,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.08017429193899782,
658
+ "grad_norm": 3.6309802532196045,
659
+ "learning_rate": 0.00019744872334006934,
660
+ "loss": 6.8363,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.08104575163398693,
665
+ "grad_norm": 2.775420904159546,
666
+ "learning_rate": 0.00019738639178189883,
667
+ "loss": 6.5252,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.08191721132897603,
672
+ "grad_norm": 3.130296230316162,
673
+ "learning_rate": 0.0001973233180369374,
674
+ "loss": 5.8967,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.08278867102396514,
679
+ "grad_norm": 2.956561803817749,
680
+ "learning_rate": 0.0001972595025858733,
681
+ "loss": 6.5943,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.08366013071895424,
686
+ "grad_norm": 2.9787437915802,
687
+ "learning_rate": 0.00019719494591504744,
688
+ "loss": 6.4199,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.08453159041394336,
693
+ "grad_norm": 3.30118989944458,
694
+ "learning_rate": 0.00019712964851644965,
695
+ "loss": 6.6019,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.08540305010893247,
700
+ "grad_norm": 3.159437894821167,
701
+ "learning_rate": 0.00019706361088771472,
702
+ "loss": 5.9469,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.08627450980392157,
707
+ "grad_norm": 2.987762928009033,
708
+ "learning_rate": 0.00019699683353211893,
709
+ "loss": 6.5373,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.08714596949891068,
714
+ "grad_norm": 3.388303279876709,
715
+ "learning_rate": 0.000196929316958576,
716
+ "loss": 6.0649,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.08801742919389978,
721
+ "grad_norm": 3.4630284309387207,
722
+ "learning_rate": 0.00019686106168163327,
723
+ "loss": 6.2865,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.08888888888888889,
728
+ "grad_norm": 3.4285342693328857,
729
+ "learning_rate": 0.00019679206822146775,
730
+ "loss": 6.4433,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.08976034858387799,
735
+ "grad_norm": 3.0801186561584473,
736
+ "learning_rate": 0.0001967223371038823,
737
+ "loss": 6.596,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.0906318082788671,
742
+ "grad_norm": 3.4587998390197754,
743
+ "learning_rate": 0.00019665186886030133,
744
+ "loss": 6.521,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.0915032679738562,
749
+ "grad_norm": 3.3617069721221924,
750
+ "learning_rate": 0.00019658066402776706,
751
+ "loss": 6.9697,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.09237472766884532,
756
+ "grad_norm": 3.0659825801849365,
757
+ "learning_rate": 0.00019650872314893523,
758
+ "loss": 7.2013,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.09324618736383443,
763
+ "grad_norm": 3.546934127807617,
764
+ "learning_rate": 0.00019643604677207103,
765
+ "loss": 6.8245,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.09411764705882353,
770
+ "grad_norm": 3.335144519805908,
771
+ "learning_rate": 0.00019636263545104498,
772
+ "loss": 7.0101,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.09498910675381264,
777
+ "grad_norm": 3.5335874557495117,
778
+ "learning_rate": 0.00019628848974532855,
779
+ "loss": 6.4184,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.09586056644880174,
784
+ "grad_norm": 3.3602793216705322,
785
+ "learning_rate": 0.00019621361021999008,
786
+ "loss": 6.0741,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.09673202614379085,
791
+ "grad_norm": 3.7194743156433105,
792
+ "learning_rate": 0.00019613799744569032,
793
+ "loss": 7.4648,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.09760348583877995,
798
+ "grad_norm": 3.468130350112915,
799
+ "learning_rate": 0.0001960616519986782,
800
+ "loss": 6.2788,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.09847494553376906,
805
+ "grad_norm": 3.2204012870788574,
806
+ "learning_rate": 0.0001959845744607864,
807
+ "loss": 6.6341,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.09934640522875816,
812
+ "grad_norm": 4.461580276489258,
813
+ "learning_rate": 0.00019590676541942682,
814
+ "loss": 6.4272,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.10021786492374728,
819
+ "grad_norm": 4.378835201263428,
820
+ "learning_rate": 0.00019582822546758625,
821
+ "loss": 6.7239,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.10108932461873639,
826
+ "grad_norm": 3.6370136737823486,
827
+ "learning_rate": 0.0001957489552038218,
828
+ "loss": 6.9987,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.10196078431372549,
833
+ "grad_norm": 4.5622711181640625,
834
+ "learning_rate": 0.00019566895523225633,
835
+ "loss": 7.0158,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.1028322440087146,
840
+ "grad_norm": 4.150580883026123,
841
+ "learning_rate": 0.0001955882261625737,
842
+ "loss": 6.3564,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.1037037037037037,
847
+ "grad_norm": 3.783479928970337,
848
+ "learning_rate": 0.0001955067686100145,
849
+ "loss": 5.9852,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.10457516339869281,
854
+ "grad_norm": 3.7131097316741943,
855
+ "learning_rate": 0.00019542458319537093,
856
+ "loss": 6.5572,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.10544662309368191,
861
+ "grad_norm": 4.567185878753662,
862
+ "learning_rate": 0.00019534167054498236,
863
+ "loss": 6.306,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.10631808278867103,
868
+ "grad_norm": 3.159900426864624,
869
+ "learning_rate": 0.00019525803129073044,
870
+ "loss": 6.638,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.10718954248366012,
875
+ "grad_norm": 3.7048301696777344,
876
+ "learning_rate": 0.0001951736660700343,
877
+ "loss": 5.781,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.10806100217864924,
882
+ "grad_norm": 3.313795328140259,
883
+ "learning_rate": 0.00019508857552584573,
884
+ "loss": 6.2093,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.10893246187363835,
889
+ "grad_norm": 3.3425116539001465,
890
+ "learning_rate": 0.00019500276030664417,
891
+ "loss": 7.2947,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.10980392156862745,
896
+ "grad_norm": 3.8515169620513916,
897
+ "learning_rate": 0.00019491622106643193,
898
+ "loss": 6.4162,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.11067538126361656,
903
+ "grad_norm": 4.335968017578125,
904
+ "learning_rate": 0.0001948289584647291,
905
+ "loss": 6.3625,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.11154684095860566,
910
+ "grad_norm": 4.06256628036499,
911
+ "learning_rate": 0.00019474097316656854,
912
+ "loss": 6.5272,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.11241830065359477,
917
+ "grad_norm": 3.4232616424560547,
918
+ "learning_rate": 0.00019465226584249078,
919
+ "loss": 7.1087,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.11328976034858387,
924
+ "grad_norm": 3.563251256942749,
925
+ "learning_rate": 0.00019456283716853904,
926
+ "loss": 6.3773,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.11416122004357299,
931
+ "grad_norm": 3.37127685546875,
932
+ "learning_rate": 0.00019447268782625388,
933
+ "loss": 6.9801,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.11503267973856209,
938
+ "grad_norm": 2.7950453758239746,
939
+ "learning_rate": 0.00019438181850266816,
940
+ "loss": 6.34,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.1159041394335512,
945
+ "grad_norm": 3.2177419662475586,
946
+ "learning_rate": 0.00019429022989030177,
947
+ "loss": 6.0368,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.11677559912854031,
952
+ "grad_norm": 3.2216238975524902,
953
+ "learning_rate": 0.0001941979226871563,
954
+ "loss": 6.6545,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.11764705882352941,
959
+ "grad_norm": 3.5392940044403076,
960
+ "learning_rate": 0.00019410489759670978,
961
+ "loss": 5.9823,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.11851851851851852,
966
+ "grad_norm": 2.938032627105713,
967
+ "learning_rate": 0.00019401115532791132,
968
+ "loss": 6.0543,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.11938997821350762,
973
+ "grad_norm": 2.959646224975586,
974
+ "learning_rate": 0.00019391669659517564,
975
+ "loss": 6.0081,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.12026143790849673,
980
+ "grad_norm": 3.716583728790283,
981
+ "learning_rate": 0.0001938215221183777,
982
+ "loss": 6.5377,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.12113289760348583,
987
+ "grad_norm": 3.7605812549591064,
988
+ "learning_rate": 0.00019372563262284715,
989
+ "loss": 6.7841,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.12200435729847495,
994
+ "grad_norm": 3.480034589767456,
995
+ "learning_rate": 0.00019362902883936288,
996
+ "loss": 7.1711,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.12287581699346405,
1001
+ "grad_norm": 3.155122995376587,
1002
+ "learning_rate": 0.00019353171150414736,
1003
+ "loss": 6.1188,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.12374727668845316,
1008
+ "grad_norm": 3.922962188720703,
1009
+ "learning_rate": 0.00019343368135886114,
1010
+ "loss": 7.4891,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.12461873638344227,
1015
+ "grad_norm": 3.394144296646118,
1016
+ "learning_rate": 0.00019333493915059703,
1017
+ "loss": 6.3209,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.12549019607843137,
1022
+ "grad_norm": 3.116760730743408,
1023
+ "learning_rate": 0.0001932354856318746,
1024
+ "loss": 6.4714,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.12636165577342048,
1029
+ "grad_norm": 3.450144052505493,
1030
+ "learning_rate": 0.0001931353215606343,
1031
+ "loss": 6.2738,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.1272331154684096,
1036
+ "grad_norm": 3.2067205905914307,
1037
+ "learning_rate": 0.00019303444770023184,
1038
+ "loss": 6.1241,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.12810457516339868,
1043
+ "grad_norm": 3.24552059173584,
1044
+ "learning_rate": 0.0001929328648194321,
1045
+ "loss": 6.5917,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.1289760348583878,
1050
+ "grad_norm": 3.2059834003448486,
1051
+ "learning_rate": 0.00019283057369240357,
1052
+ "loss": 6.7524,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.1298474945533769,
1057
+ "grad_norm": 3.5542874336242676,
1058
+ "learning_rate": 0.00019272757509871232,
1059
+ "loss": 6.6428,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.13071895424836602,
1064
+ "grad_norm": 3.5958824157714844,
1065
+ "learning_rate": 0.00019262386982331594,
1066
+ "loss": 6.1798,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.13159041394335513,
1071
+ "grad_norm": 2.9370152950286865,
1072
+ "learning_rate": 0.00019251945865655782,
1073
+ "loss": 5.6334,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.13246187363834422,
1078
+ "grad_norm": 3.0617597103118896,
1079
+ "learning_rate": 0.00019241434239416095,
1080
+ "loss": 6.4162,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.13333333333333333,
1085
+ "grad_norm": 3.3482141494750977,
1086
+ "learning_rate": 0.00019230852183722182,
1087
+ "loss": 6.6717,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.13420479302832244,
1092
+ "grad_norm": 3.2366411685943604,
1093
+ "learning_rate": 0.00019220199779220446,
1094
+ "loss": 6.7417,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.13507625272331156,
1099
+ "grad_norm": 3.4498870372772217,
1100
+ "learning_rate": 0.0001920947710709342,
1101
+ "loss": 6.6616,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.13594771241830064,
1106
+ "grad_norm": 3.071847438812256,
1107
+ "learning_rate": 0.0001919868424905915,
1108
+ "loss": 7.1704,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.13681917211328976,
1113
+ "grad_norm": 2.8072800636291504,
1114
+ "learning_rate": 0.00019187821287370568,
1115
+ "loss": 6.2717,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.13769063180827887,
1120
+ "grad_norm": 2.722471237182617,
1121
+ "learning_rate": 0.00019176888304814883,
1122
+ "loss": 6.1792,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.13856209150326798,
1127
+ "grad_norm": 3.434514284133911,
1128
+ "learning_rate": 0.00019165885384712916,
1129
+ "loss": 6.574,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.1394335511982571,
1134
+ "grad_norm": 3.995135545730591,
1135
+ "learning_rate": 0.00019154812610918501,
1136
+ "loss": 5.9547,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.14030501089324618,
1141
+ "grad_norm": 3.9248478412628174,
1142
+ "learning_rate": 0.0001914367006781783,
1143
+ "loss": 6.9711,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.1411764705882353,
1148
+ "grad_norm": 3.2751011848449707,
1149
+ "learning_rate": 0.00019132457840328811,
1150
+ "loss": 6.3862,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.1420479302832244,
1155
+ "grad_norm": 2.9850356578826904,
1156
+ "learning_rate": 0.0001912117601390041,
1157
+ "loss": 6.1286,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.14291938997821352,
1162
+ "grad_norm": 3.267690896987915,
1163
+ "learning_rate": 0.00019109824674512014,
1164
+ "loss": 6.1965,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.1437908496732026,
1169
+ "grad_norm": 3.1468505859375,
1170
+ "learning_rate": 0.0001909840390867278,
1171
+ "loss": 6.865,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.14466230936819172,
1176
+ "grad_norm": 2.709254503250122,
1177
+ "learning_rate": 0.00019086913803420966,
1178
+ "loss": 6.2319,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.14553376906318083,
1183
+ "grad_norm": 3.203265905380249,
1184
+ "learning_rate": 0.0001907535444632326,
1185
+ "loss": 6.0057,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.14640522875816994,
1190
+ "grad_norm": 2.994889736175537,
1191
+ "learning_rate": 0.0001906372592547413,
1192
+ "loss": 6.7063,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.14727668845315905,
1197
+ "grad_norm": 3.4088401794433594,
1198
+ "learning_rate": 0.0001905202832949514,
1199
+ "loss": 5.8675,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.14814814814814814,
1204
+ "grad_norm": 3.7288787364959717,
1205
+ "learning_rate": 0.00019040261747534283,
1206
+ "loss": 5.8542,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.14901960784313725,
1211
+ "grad_norm": 4.366305828094482,
1212
+ "learning_rate": 0.00019028426269265299,
1213
+ "loss": 6.0556,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.14989106753812637,
1218
+ "grad_norm": 3.3466691970825195,
1219
+ "learning_rate": 0.00019016521984886983,
1220
+ "loss": 6.6329,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.15076252723311548,
1225
+ "grad_norm": 2.9854562282562256,
1226
+ "learning_rate": 0.00019004548985122514,
1227
+ "loss": 5.7907,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.15163398692810456,
1232
+ "grad_norm": 4.434035778045654,
1233
+ "learning_rate": 0.0001899250736121874,
1234
+ "loss": 6.4903,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.15250544662309368,
1239
+ "grad_norm": 3.617687225341797,
1240
+ "learning_rate": 0.00018980397204945522,
1241
+ "loss": 6.353,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.1533769063180828,
1246
+ "grad_norm": 3.2313356399536133,
1247
+ "learning_rate": 0.00018968218608594986,
1248
+ "loss": 6.3903,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.1542483660130719,
1253
+ "grad_norm": 3.2535009384155273,
1254
+ "learning_rate": 0.00018955971664980854,
1255
+ "loss": 6.1581,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.15511982570806102,
1260
+ "grad_norm": 3.6953959465026855,
1261
+ "learning_rate": 0.00018943656467437724,
1262
+ "loss": 5.9416,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.1559912854030501,
1267
+ "grad_norm": 3.7896955013275146,
1268
+ "learning_rate": 0.00018931273109820364,
1269
+ "loss": 6.3745,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.1568627450980392,
1274
+ "grad_norm": 3.284451961517334,
1275
+ "learning_rate": 0.00018918821686502989,
1276
+ "loss": 6.5936,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.15773420479302833,
1281
+ "grad_norm": 3.3078837394714355,
1282
+ "learning_rate": 0.00018906302292378549,
1283
+ "loss": 6.3766,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.15860566448801744,
1288
+ "grad_norm": 2.928623676300049,
1289
+ "learning_rate": 0.00018893715022857998,
1290
+ "loss": 6.1763,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.15947712418300652,
1295
+ "grad_norm": 3.517934560775757,
1296
+ "learning_rate": 0.0001888105997386958,
1297
+ "loss": 7.0927,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.16034858387799564,
1302
+ "grad_norm": 5.320308685302734,
1303
+ "learning_rate": 0.0001886833724185809,
1304
+ "loss": 7.4936,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.16122004357298475,
1309
+ "grad_norm": 3.246738910675049,
1310
+ "learning_rate": 0.00018855546923784124,
1311
+ "loss": 5.9404,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.16209150326797386,
1316
+ "grad_norm": 3.304151773452759,
1317
+ "learning_rate": 0.00018842689117123376,
1318
+ "loss": 5.8871,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.16296296296296298,
1323
+ "grad_norm": 3.847766399383545,
1324
+ "learning_rate": 0.00018829763919865858,
1325
+ "loss": 6.5487,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.16383442265795206,
1330
+ "grad_norm": 3.1779181957244873,
1331
+ "learning_rate": 0.00018816771430515177,
1332
+ "loss": 6.2279,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.16470588235294117,
1337
+ "grad_norm": 3.6784069538116455,
1338
+ "learning_rate": 0.00018803711748087773,
1339
+ "loss": 7.3388,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.1655773420479303,
1344
+ "grad_norm": 3.748657703399658,
1345
+ "learning_rate": 0.00018790584972112174,
1346
+ "loss": 6.1629,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 0.1664488017429194,
1351
+ "grad_norm": 3.3160455226898193,
1352
+ "learning_rate": 0.0001877739120262822,
1353
+ "loss": 5.6017,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 0.16732026143790849,
1358
+ "grad_norm": 3.8499162197113037,
1359
+ "learning_rate": 0.00018764130540186328,
1360
+ "loss": 6.6374,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 0.1681917211328976,
1365
+ "grad_norm": 3.7523679733276367,
1366
+ "learning_rate": 0.0001875080308584669,
1367
+ "loss": 6.3529,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 0.1690631808278867,
1372
+ "grad_norm": 3.095731496810913,
1373
+ "learning_rate": 0.00018737408941178543,
1374
+ "loss": 6.5641,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 0.16993464052287582,
1379
+ "grad_norm": 3.698686122894287,
1380
+ "learning_rate": 0.0001872394820825936,
1381
+ "loss": 5.9233,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 0.17080610021786494,
1386
+ "grad_norm": 3.3824868202209473,
1387
+ "learning_rate": 0.00018710420989674091,
1388
+ "loss": 6.262,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 0.17167755991285402,
1393
+ "grad_norm": 3.9130444526672363,
1394
+ "learning_rate": 0.0001869682738851438,
1395
+ "loss": 6.7302,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 0.17254901960784313,
1400
+ "grad_norm": 4.361310958862305,
1401
+ "learning_rate": 0.00018683167508377774,
1402
+ "loss": 7.2424,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 0.17342047930283225,
1407
+ "grad_norm": 3.0834221839904785,
1408
+ "learning_rate": 0.0001866944145336693,
1409
+ "loss": 5.7327,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 0.17429193899782136,
1414
+ "grad_norm": 3.402498722076416,
1415
+ "learning_rate": 0.00018655649328088835,
1416
+ "loss": 6.1162,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.17516339869281045,
1421
+ "grad_norm": 4.900463581085205,
1422
+ "learning_rate": 0.00018641791237654,
1423
+ "loss": 7.5089,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.17603485838779956,
1428
+ "grad_norm": 3.0102016925811768,
1429
+ "learning_rate": 0.0001862786728767565,
1430
+ "loss": 6.6401,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.17690631808278867,
1435
+ "grad_norm": 3.4192609786987305,
1436
+ "learning_rate": 0.00018613877584268944,
1437
+ "loss": 5.8015,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.17777777777777778,
1442
+ "grad_norm": 3.483651876449585,
1443
+ "learning_rate": 0.00018599822234050141,
1444
+ "loss": 5.9493,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.1786492374727669,
1449
+ "grad_norm": 3.289872884750366,
1450
+ "learning_rate": 0.00018585701344135807,
1451
+ "loss": 6.7852,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.17952069716775598,
1456
+ "grad_norm": 3.382138252258301,
1457
+ "learning_rate": 0.00018571515022141976,
1458
+ "loss": 6.5197,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.1803921568627451,
1463
+ "grad_norm": 3.1128950119018555,
1464
+ "learning_rate": 0.0001855726337618335,
1465
+ "loss": 6.764,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.1812636165577342,
1470
+ "grad_norm": 2.732131004333496,
1471
+ "learning_rate": 0.00018542946514872477,
1472
+ "loss": 5.8167,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.18213507625272332,
1477
+ "grad_norm": 3.122868537902832,
1478
+ "learning_rate": 0.00018528564547318902,
1479
+ "loss": 6.0786,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.1830065359477124,
1484
+ "grad_norm": 2.85406231880188,
1485
+ "learning_rate": 0.00018514117583128347,
1486
+ "loss": 5.4824,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.18387799564270152,
1491
+ "grad_norm": 2.9424877166748047,
1492
+ "learning_rate": 0.00018499605732401895,
1493
+ "loss": 6.106,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.18474945533769063,
1498
+ "grad_norm": 3.1483314037323,
1499
+ "learning_rate": 0.0001848502910573511,
1500
+ "loss": 6.5205,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.18562091503267975,
1505
+ "grad_norm": 3.3453025817871094,
1506
+ "learning_rate": 0.00018470387814217232,
1507
+ "loss": 6.1123,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.18649237472766886,
1512
+ "grad_norm": 2.945319414138794,
1513
+ "learning_rate": 0.00018455681969430307,
1514
+ "loss": 5.8776,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.18736383442265794,
1519
+ "grad_norm": 3.3796839714050293,
1520
+ "learning_rate": 0.0001844091168344835,
1521
+ "loss": 6.8702,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.18823529411764706,
1526
+ "grad_norm": 2.9702494144439697,
1527
+ "learning_rate": 0.00018426077068836488,
1528
+ "loss": 5.8691,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.18910675381263617,
1533
+ "grad_norm": 2.9386281967163086,
1534
+ "learning_rate": 0.0001841117823865009,
1535
+ "loss": 6.0198,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.18997821350762528,
1540
+ "grad_norm": 2.764477491378784,
1541
+ "learning_rate": 0.00018396215306433922,
1542
+ "loss": 5.4371,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.19084967320261437,
1547
+ "grad_norm": 3.959301471710205,
1548
+ "learning_rate": 0.00018381188386221275,
1549
+ "loss": 6.1633,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.19172113289760348,
1554
+ "grad_norm": 3.0180444717407227,
1555
+ "learning_rate": 0.00018366097592533093,
1556
+ "loss": 5.5212,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.1925925925925926,
1561
+ "grad_norm": 3.3983206748962402,
1562
+ "learning_rate": 0.00018350943040377105,
1563
+ "loss": 6.1409,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.1934640522875817,
1568
+ "grad_norm": 3.186225652694702,
1569
+ "learning_rate": 0.0001833572484524695,
1570
+ "loss": 6.0513,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.19433551198257082,
1575
+ "grad_norm": 3.2218050956726074,
1576
+ "learning_rate": 0.00018320443123121284,
1577
+ "loss": 6.6948,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.1952069716775599,
1582
+ "grad_norm": 2.7722697257995605,
1583
+ "learning_rate": 0.0001830509799046292,
1584
+ "loss": 5.7941,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.19607843137254902,
1589
+ "grad_norm": 3.123589515686035,
1590
+ "learning_rate": 0.0001828968956421791,
1591
+ "loss": 6.1152,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.19694989106753813,
1596
+ "grad_norm": 2.928809404373169,
1597
+ "learning_rate": 0.0001827421796181468,
1598
+ "loss": 5.9507,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.19782135076252724,
1603
+ "grad_norm": 3.9273805618286133,
1604
+ "learning_rate": 0.0001825868330116312,
1605
+ "loss": 5.8818,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.19869281045751633,
1610
+ "grad_norm": 3.857663631439209,
1611
+ "learning_rate": 0.00018243085700653697,
1612
+ "loss": 5.8865,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.19956427015250544,
1617
+ "grad_norm": 3.6917290687561035,
1618
+ "learning_rate": 0.00018227425279156536,
1619
+ "loss": 6.6875,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 0.20043572984749455,
1624
+ "grad_norm": 3.376311779022217,
1625
+ "learning_rate": 0.0001821170215602053,
1626
+ "loss": 6.2749,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 0.20130718954248367,
1631
+ "grad_norm": 3.929055690765381,
1632
+ "learning_rate": 0.00018195916451072428,
1633
+ "loss": 6.7266,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 0.20217864923747278,
1638
+ "grad_norm": 3.159097671508789,
1639
+ "learning_rate": 0.0001818006828461591,
1640
+ "loss": 5.859,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 0.20305010893246186,
1645
+ "grad_norm": 3.784909248352051,
1646
+ "learning_rate": 0.00018164157777430682,
1647
+ "loss": 6.3503,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 0.20392156862745098,
1652
+ "grad_norm": 4.014029502868652,
1653
+ "learning_rate": 0.00018148185050771554,
1654
+ "loss": 6.4046,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 0.2047930283224401,
1659
+ "grad_norm": 2.901723861694336,
1660
+ "learning_rate": 0.00018132150226367512,
1661
+ "loss": 6.1373,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 0.2056644880174292,
1666
+ "grad_norm": 3.193726062774658,
1667
+ "learning_rate": 0.00018116053426420794,
1668
+ "loss": 6.2137,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 0.2065359477124183,
1673
+ "grad_norm": 3.4831013679504395,
1674
+ "learning_rate": 0.0001809989477360595,
1675
+ "loss": 6.9075,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 0.2074074074074074,
1680
+ "grad_norm": 2.7948129177093506,
1681
+ "learning_rate": 0.00018083674391068924,
1682
+ "loss": 5.8719,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 0.20827886710239651,
1687
+ "grad_norm": 3.455291986465454,
1688
+ "learning_rate": 0.00018067392402426103,
1689
+ "loss": 6.0601,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 0.20915032679738563,
1694
+ "grad_norm": 3.306884288787842,
1695
+ "learning_rate": 0.00018051048931763366,
1696
+ "loss": 6.5009,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 0.21002178649237474,
1701
+ "grad_norm": 3.174142599105835,
1702
+ "learning_rate": 0.00018034644103635166,
1703
+ "loss": 5.1709,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 0.21089324618736383,
1708
+ "grad_norm": 3.9862282276153564,
1709
+ "learning_rate": 0.00018018178043063555,
1710
+ "loss": 6.5155,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 0.21176470588235294,
1715
+ "grad_norm": 3.0755395889282227,
1716
+ "learning_rate": 0.0001800165087553724,
1717
+ "loss": 6.4159,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 0.21263616557734205,
1722
+ "grad_norm": 3.4993367195129395,
1723
+ "learning_rate": 0.0001798506272701064,
1724
+ "loss": 5.8788,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 0.21350762527233116,
1729
+ "grad_norm": 3.3749759197235107,
1730
+ "learning_rate": 0.00017968413723902887,
1731
+ "loss": 6.5896,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 0.21437908496732025,
1736
+ "grad_norm": 3.2183454036712646,
1737
+ "learning_rate": 0.0001795170399309692,
1738
+ "loss": 5.8676,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 0.21525054466230936,
1743
+ "grad_norm": 3.839151620864868,
1744
+ "learning_rate": 0.00017934933661938466,
1745
+ "loss": 5.7902,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 0.21612200435729848,
1750
+ "grad_norm": 5.124701976776123,
1751
+ "learning_rate": 0.00017918102858235102,
1752
+ "loss": 6.4626,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 0.2169934640522876,
1757
+ "grad_norm": 3.1410319805145264,
1758
+ "learning_rate": 0.00017901211710255255,
1759
+ "loss": 5.8767,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 0.2178649237472767,
1764
+ "grad_norm": 3.26542592048645,
1765
+ "learning_rate": 0.00017884260346727254,
1766
+ "loss": 5.8412,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 0.21873638344226579,
1771
+ "grad_norm": 3.5896737575531006,
1772
+ "learning_rate": 0.0001786724889683833,
1773
+ "loss": 6.1054,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 0.2196078431372549,
1778
+ "grad_norm": 3.036224842071533,
1779
+ "learning_rate": 0.00017850177490233633,
1780
+ "loss": 6.306,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 0.220479302832244,
1785
+ "grad_norm": 2.9149057865142822,
1786
+ "learning_rate": 0.0001783304625701524,
1787
+ "loss": 5.7077,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 0.22135076252723312,
1792
+ "grad_norm": 3.4123952388763428,
1793
+ "learning_rate": 0.00017815855327741185,
1794
+ "loss": 5.6122,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 0.2222222222222222,
1799
+ "grad_norm": 3.3414759635925293,
1800
+ "learning_rate": 0.00017798604833424434,
1801
+ "loss": 6.2309,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 0.22309368191721132,
1806
+ "grad_norm": 2.8341996669769287,
1807
+ "learning_rate": 0.00017781294905531907,
1808
+ "loss": 5.7753,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 0.22396514161220044,
1813
+ "grad_norm": 2.8891713619232178,
1814
+ "learning_rate": 0.00017763925675983475,
1815
+ "loss": 6.259,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 0.22483660130718955,
1820
+ "grad_norm": 3.7543976306915283,
1821
+ "learning_rate": 0.00017746497277150943,
1822
+ "loss": 6.2447,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 0.22570806100217866,
1827
+ "grad_norm": 3.6341092586517334,
1828
+ "learning_rate": 0.00017729009841857053,
1829
+ "loss": 6.503,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 0.22657952069716775,
1834
+ "grad_norm": 3.1001079082489014,
1835
+ "learning_rate": 0.00017711463503374466,
1836
+ "loss": 5.544,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 0.22745098039215686,
1841
+ "grad_norm": 3.5646779537200928,
1842
+ "learning_rate": 0.00017693858395424742,
1843
+ "loss": 6.8872,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 0.22832244008714597,
1848
+ "grad_norm": 3.1725387573242188,
1849
+ "learning_rate": 0.00017676194652177334,
1850
+ "loss": 5.8004,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 0.22919389978213509,
1855
+ "grad_norm": 3.6738593578338623,
1856
+ "learning_rate": 0.00017658472408248551,
1857
+ "loss": 6.0577,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 0.23006535947712417,
1862
+ "grad_norm": 3.147831439971924,
1863
+ "learning_rate": 0.0001764069179870055,
1864
+ "loss": 5.8112,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 0.23093681917211328,
1869
+ "grad_norm": 3.1304612159729004,
1870
+ "learning_rate": 0.00017622852959040273,
1871
+ "loss": 6.0289,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 0.2318082788671024,
1876
+ "grad_norm": 3.5180559158325195,
1877
+ "learning_rate": 0.0001760495602521847,
1878
+ "loss": 6.1329,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 0.2326797385620915,
1883
+ "grad_norm": 2.9736528396606445,
1884
+ "learning_rate": 0.00017587001133628592,
1885
+ "loss": 5.8546,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 0.23355119825708062,
1890
+ "grad_norm": 2.9651129245758057,
1891
+ "learning_rate": 0.0001756898842110582,
1892
+ "loss": 6.4554,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 0.2344226579520697,
1897
+ "grad_norm": 4.1373515129089355,
1898
+ "learning_rate": 0.0001755091802492597,
1899
+ "loss": 6.0014,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 0.23529411764705882,
1904
+ "grad_norm": 3.086876630783081,
1905
+ "learning_rate": 0.0001753279008280449,
1906
+ "loss": 6.4445,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 0.23616557734204793,
1911
+ "grad_norm": 3.251668930053711,
1912
+ "learning_rate": 0.00017514604732895363,
1913
+ "loss": 6.9109,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 0.23703703703703705,
1918
+ "grad_norm": 3.4233386516571045,
1919
+ "learning_rate": 0.000174963621137901,
1920
+ "loss": 6.6209,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 0.23790849673202613,
1925
+ "grad_norm": 3.802621603012085,
1926
+ "learning_rate": 0.0001747806236451666,
1927
+ "loss": 7.2266,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 0.23877995642701524,
1932
+ "grad_norm": 3.2463502883911133,
1933
+ "learning_rate": 0.00017459705624538383,
1934
+ "loss": 6.7707,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 0.23965141612200436,
1939
+ "grad_norm": 2.789658784866333,
1940
+ "learning_rate": 0.00017441292033752948,
1941
+ "loss": 6.0205,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 0.24052287581699347,
1946
+ "grad_norm": 3.016808271408081,
1947
+ "learning_rate": 0.00017422821732491293,
1948
+ "loss": 5.7279,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 0.24139433551198258,
1953
+ "grad_norm": 3.44633150100708,
1954
+ "learning_rate": 0.00017404294861516557,
1955
+ "loss": 6.5382,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 0.24226579520697167,
1960
+ "grad_norm": 3.792668342590332,
1961
+ "learning_rate": 0.00017385711562022986,
1962
+ "loss": 7.1705,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 0.24313725490196078,
1967
+ "grad_norm": 3.15065860748291,
1968
+ "learning_rate": 0.00017367071975634882,
1969
+ "loss": 5.6286,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 0.2440087145969499,
1974
+ "grad_norm": 3.124851703643799,
1975
+ "learning_rate": 0.00017348376244405512,
1976
+ "loss": 5.9117,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 0.244880174291939,
1981
+ "grad_norm": 3.9259023666381836,
1982
+ "learning_rate": 0.00017329624510816017,
1983
+ "loss": 6.4439,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 0.2457516339869281,
1988
+ "grad_norm": 3.3216142654418945,
1989
+ "learning_rate": 0.00017310816917774343,
1990
+ "loss": 6.8465,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 0.2466230936819172,
1995
+ "grad_norm": 4.405170917510986,
1996
+ "learning_rate": 0.0001729195360861414,
1997
+ "loss": 6.1221,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 0.24749455337690632,
2002
+ "grad_norm": 3.6341638565063477,
2003
+ "learning_rate": 0.0001727303472709368,
2004
+ "loss": 6.5787,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 0.24836601307189543,
2009
+ "grad_norm": 3.294029712677002,
2010
+ "learning_rate": 0.00017254060417394741,
2011
+ "loss": 6.3653,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 0.24923747276688454,
2016
+ "grad_norm": 3.6027772426605225,
2017
+ "learning_rate": 0.00017235030824121542,
2018
+ "loss": 5.6906,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 0.25010893246187366,
2023
+ "grad_norm": 3.3305227756500244,
2024
+ "learning_rate": 0.000172159460922996,
2025
+ "loss": 6.9769,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 0.25010893246187366,
2030
+ "eval_loss": 1.5338541269302368,
2031
+ "eval_runtime": 35.2309,
2032
+ "eval_samples_per_second": 13.738,
2033
+ "eval_steps_per_second": 6.869,
2034
+ "step": 287
2035
+ }
2036
+ ],
2037
+ "logging_steps": 1,
2038
+ "max_steps": 1148,
2039
+ "num_input_tokens_seen": 0,
2040
+ "num_train_epochs": 2,
2041
+ "save_steps": 287,
2042
+ "stateful_callbacks": {
2043
+ "TrainerControl": {
2044
+ "args": {
2045
+ "should_epoch_stop": false,
2046
+ "should_evaluate": false,
2047
+ "should_log": false,
2048
+ "should_save": true,
2049
+ "should_training_stop": false
2050
+ },
2051
+ "attributes": {}
2052
+ }
2053
+ },
2054
+ "total_flos": 1.6808219391295488e+17,
2055
+ "train_batch_size": 2,
2056
+ "trial_name": null,
2057
+ "trial_params": null
2058
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4454205bc92d9a440191e9e761ee29bb14a11c1317d3e3bb449f2b8b391d7d4
3
+ size 6776