anhvv200053 commited on
Commit
fe99a65
·
verified ·
1 Parent(s): 993d202

Upload 11 files

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vilm/vinallama-2.7b-chat
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
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vilm/vinallama-2.7b-chat",
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": 0.1,
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
+ "k_proj",
24
+ "v_proj",
25
+ "q_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5453cd380c9fac1bb563ae23f988362848bc222326feb24d9de3975e258d07a
3
+ size 323013288
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b033661b80368b18ccc9906a9c1f00543ee04294a80f931fe2d5d020c19768ed
3
+ size 646160890
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8dbef056e0c29c6f7b5c80c56e6188effeae40a6463363cdfb8af9ea35a8d2
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7de8907e79c9f47fccf3aa89da8ca3d3d851fdb56e005195640f80ea9c8917
3
+ size 1064
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "46303": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "46304": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "46305": {
47
+ "content": "<|im_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ }
54
+ },
55
+ "bos_token": "<s>",
56
+ "clean_up_tokenization_spaces": false,
57
+ "eos_token": "<|im_end|>",
58
+ "legacy": false,
59
+ "max_length": 256,
60
+ "model_max_length": 1000000000000000019884624838656,
61
+ "pad_token": "<|im_end|>",
62
+ "sp_model_kwargs": {},
63
+ "stride": 0,
64
+ "tokenizer_class": "LlamaTokenizer",
65
+ "truncation_side": "right",
66
+ "truncation_strategy": "longest_first",
67
+ "unk_token": "<unk>",
68
+ "use_default_system_prompt": true,
69
+ "use_fast": true
70
+ }
trainer_state.json ADDED
@@ -0,0 +1,2133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.733952049497293,
5
+ "eval_steps": 500,
6
+ "global_step": 30000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.025779840164990978,
13
+ "grad_norm": 0.5347822308540344,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.4509,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.051559680329981955,
20
+ "grad_norm": 0.4712078273296356,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.1744,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.07733952049497293,
27
+ "grad_norm": 0.5031601786613464,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.096,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.10311936065996391,
34
+ "grad_norm": 0.49241065979003906,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.9847,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.12889920082495487,
41
+ "grad_norm": 0.9957050681114197,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.9928,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.15467904098994587,
48
+ "grad_norm": 0.38163048028945923,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.9008,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.18045888115493683,
55
+ "grad_norm": 0.4322434663772583,
56
+ "learning_rate": 0.0002,
57
+ "loss": 0.9108,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.20623872131992782,
62
+ "grad_norm": 0.4072737395763397,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.8713,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.23201856148491878,
69
+ "grad_norm": 0.5637839436531067,
70
+ "learning_rate": 0.0002,
71
+ "loss": 0.8538,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.25779840164990975,
76
+ "grad_norm": 0.6094131469726562,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.8154,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.28357824181490077,
83
+ "grad_norm": 0.4212701618671417,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.7897,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.30935808197989173,
90
+ "grad_norm": 0.4663824737071991,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.8021,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.3351379221448827,
97
+ "grad_norm": 0.3774861693382263,
98
+ "learning_rate": 0.0002,
99
+ "loss": 0.7452,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.36091776230987366,
104
+ "grad_norm": 0.19446992874145508,
105
+ "learning_rate": 0.0002,
106
+ "loss": 0.737,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.3866976024748647,
111
+ "grad_norm": 0.25984033942222595,
112
+ "learning_rate": 0.0002,
113
+ "loss": 0.6966,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.41247744263985564,
118
+ "grad_norm": 0.3495163023471832,
119
+ "learning_rate": 0.0002,
120
+ "loss": 0.7179,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.4382572828048466,
125
+ "grad_norm": 0.5092929601669312,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.7132,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.46403712296983757,
132
+ "grad_norm": 0.16095790266990662,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.6652,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.4898169631348286,
139
+ "grad_norm": 0.38502034544944763,
140
+ "learning_rate": 0.0002,
141
+ "loss": 0.6564,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.5155968032998195,
146
+ "grad_norm": 0.3100506067276001,
147
+ "learning_rate": 0.0002,
148
+ "loss": 0.6082,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.5413766434648105,
153
+ "grad_norm": 0.4585016965866089,
154
+ "learning_rate": 0.0002,
155
+ "loss": 0.6491,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.5671564836298015,
160
+ "grad_norm": 0.35394927859306335,
161
+ "learning_rate": 0.0002,
162
+ "loss": 0.6136,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.5929363237947924,
167
+ "grad_norm": 0.4828909933567047,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.5639,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.6187161639597835,
174
+ "grad_norm": 0.7377568483352661,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.5998,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.6444960041247745,
181
+ "grad_norm": 0.33992356061935425,
182
+ "learning_rate": 0.0002,
183
+ "loss": 0.5535,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.6702758442897654,
188
+ "grad_norm": 0.40880173444747925,
189
+ "learning_rate": 0.0002,
190
+ "loss": 0.5839,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.6960556844547564,
195
+ "grad_norm": 0.6135886907577515,
196
+ "learning_rate": 0.0002,
197
+ "loss": 0.5697,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.7218355246197473,
202
+ "grad_norm": 0.14242181181907654,
203
+ "learning_rate": 0.0002,
204
+ "loss": 0.562,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.7476153647847383,
209
+ "grad_norm": 0.1636349856853485,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.5301,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.7733952049497294,
216
+ "grad_norm": 0.5300703644752502,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.5428,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.7991750451147203,
223
+ "grad_norm": 0.2816906273365021,
224
+ "learning_rate": 0.0002,
225
+ "loss": 0.5319,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.8249548852797113,
230
+ "grad_norm": 0.4165875315666199,
231
+ "learning_rate": 0.0002,
232
+ "loss": 0.5073,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.8507347254447022,
237
+ "grad_norm": 0.46957316994667053,
238
+ "learning_rate": 0.0002,
239
+ "loss": 0.4973,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.8765145656096932,
244
+ "grad_norm": 0.22382797300815582,
245
+ "learning_rate": 0.0002,
246
+ "loss": 0.5091,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.9022944057746842,
251
+ "grad_norm": 0.517814576625824,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.4879,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.9280742459396751,
258
+ "grad_norm": 0.44171011447906494,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.4711,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.9538540861046662,
265
+ "grad_norm": 0.3107047379016876,
266
+ "learning_rate": 0.0002,
267
+ "loss": 0.465,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.9796339262696572,
272
+ "grad_norm": 0.09984863549470901,
273
+ "learning_rate": 0.0002,
274
+ "loss": 0.4485,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 1.005413766434648,
279
+ "grad_norm": 0.43100592494010925,
280
+ "learning_rate": 0.0002,
281
+ "loss": 0.4752,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 1.031193606599639,
286
+ "grad_norm": 0.5259262919425964,
287
+ "learning_rate": 0.0002,
288
+ "loss": 0.3621,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 1.0569734467646301,
293
+ "grad_norm": 0.47033509612083435,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.3569,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 1.082753286929621,
300
+ "grad_norm": 0.5318751931190491,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.3512,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 1.108533127094612,
307
+ "grad_norm": 0.5434057116508484,
308
+ "learning_rate": 0.0002,
309
+ "loss": 0.3504,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 1.134312967259603,
314
+ "grad_norm": 0.47843560576438904,
315
+ "learning_rate": 0.0002,
316
+ "loss": 0.3712,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 1.160092807424594,
321
+ "grad_norm": 0.5956776142120361,
322
+ "learning_rate": 0.0002,
323
+ "loss": 0.3511,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 1.1858726475895849,
328
+ "grad_norm": 0.5072950720787048,
329
+ "learning_rate": 0.0002,
330
+ "loss": 0.3445,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 1.211652487754576,
335
+ "grad_norm": 0.5608052611351013,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.3377,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 1.237432327919567,
342
+ "grad_norm": 0.474223256111145,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.3276,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 1.2632121680845578,
349
+ "grad_norm": 0.5215118527412415,
350
+ "learning_rate": 0.0002,
351
+ "loss": 0.3375,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 1.288992008249549,
356
+ "grad_norm": 0.3922516405582428,
357
+ "learning_rate": 0.0002,
358
+ "loss": 0.342,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 1.3147718484145399,
363
+ "grad_norm": 0.4958643615245819,
364
+ "learning_rate": 0.0002,
365
+ "loss": 0.3553,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 1.3405516885795308,
370
+ "grad_norm": 0.564983069896698,
371
+ "learning_rate": 0.0002,
372
+ "loss": 0.3389,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 1.3663315287445217,
377
+ "grad_norm": 0.5662856698036194,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.3382,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 1.3921113689095128,
384
+ "grad_norm": 0.5040738582611084,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.3408,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 1.4178912090745037,
391
+ "grad_norm": 0.27346768975257874,
392
+ "learning_rate": 0.0002,
393
+ "loss": 0.3266,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 1.4436710492394949,
398
+ "grad_norm": 0.5055024027824402,
399
+ "learning_rate": 0.0002,
400
+ "loss": 0.3561,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 1.4694508894044858,
405
+ "grad_norm": 0.5442714691162109,
406
+ "learning_rate": 0.0002,
407
+ "loss": 0.3241,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 1.4952307295694767,
412
+ "grad_norm": 0.4862806499004364,
413
+ "learning_rate": 0.0002,
414
+ "loss": 0.344,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 1.5210105697344676,
419
+ "grad_norm": 0.6346714496612549,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.3195,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 1.5467904098994585,
426
+ "grad_norm": 0.5846338272094727,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.3232,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 1.5725702500644496,
433
+ "grad_norm": 0.41255345940589905,
434
+ "learning_rate": 0.0002,
435
+ "loss": 0.3379,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 1.5983500902294405,
440
+ "grad_norm": 0.6396617293357849,
441
+ "learning_rate": 0.0002,
442
+ "loss": 0.3099,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 1.6241299303944317,
447
+ "grad_norm": 0.3450670540332794,
448
+ "learning_rate": 0.0002,
449
+ "loss": 0.3129,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 1.6499097705594226,
454
+ "grad_norm": 0.30461055040359497,
455
+ "learning_rate": 0.0002,
456
+ "loss": 0.2978,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 1.6756896107244135,
461
+ "grad_norm": 0.4209739863872528,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.3323,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 1.7014694508894044,
468
+ "grad_norm": 0.3296062648296356,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.3047,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 1.7272492910543955,
475
+ "grad_norm": 0.9009484648704529,
476
+ "learning_rate": 0.0002,
477
+ "loss": 0.3046,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 1.7530291312193864,
482
+ "grad_norm": 0.7505986094474792,
483
+ "learning_rate": 0.0002,
484
+ "loss": 0.3123,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 1.7788089713843775,
489
+ "grad_norm": 0.3542492389678955,
490
+ "learning_rate": 0.0002,
491
+ "loss": 0.3259,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 1.8045888115493685,
496
+ "grad_norm": 0.4935378432273865,
497
+ "learning_rate": 0.0002,
498
+ "loss": 0.3262,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 1.8303686517143594,
503
+ "grad_norm": 0.3000539541244507,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.2887,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 1.8561484918793503,
510
+ "grad_norm": 0.2680779695510864,
511
+ "learning_rate": 0.0002,
512
+ "loss": 0.3108,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 1.8819283320443412,
517
+ "grad_norm": 0.5922934412956238,
518
+ "learning_rate": 0.0002,
519
+ "loss": 0.3211,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 1.9077081722093323,
524
+ "grad_norm": 0.38349688053131104,
525
+ "learning_rate": 0.0002,
526
+ "loss": 0.316,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 1.9334880123743234,
531
+ "grad_norm": 0.7654793858528137,
532
+ "learning_rate": 0.0002,
533
+ "loss": 0.3111,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 1.9592678525393143,
538
+ "grad_norm": 0.2399352639913559,
539
+ "learning_rate": 0.0002,
540
+ "loss": 0.3042,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 1.9850476927043053,
545
+ "grad_norm": 0.42787912487983704,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.2928,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 2.010827532869296,
552
+ "grad_norm": 0.4771544933319092,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.2487,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 2.036607373034287,
559
+ "grad_norm": 0.6133277416229248,
560
+ "learning_rate": 0.0002,
561
+ "loss": 0.2219,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 2.062387213199278,
566
+ "grad_norm": 0.43137651681900024,
567
+ "learning_rate": 0.0002,
568
+ "loss": 0.2158,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 2.0881670533642693,
573
+ "grad_norm": 0.41038885712623596,
574
+ "learning_rate": 0.0002,
575
+ "loss": 0.2127,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 2.1139468935292602,
580
+ "grad_norm": 0.351235568523407,
581
+ "learning_rate": 0.0002,
582
+ "loss": 0.2185,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 2.139726733694251,
587
+ "grad_norm": 0.41089433431625366,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.2346,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 2.165506573859242,
594
+ "grad_norm": 0.3464137613773346,
595
+ "learning_rate": 0.0002,
596
+ "loss": 0.2273,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 2.191286414024233,
601
+ "grad_norm": 0.2753762900829315,
602
+ "learning_rate": 0.0002,
603
+ "loss": 0.2359,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 2.217066254189224,
608
+ "grad_norm": 0.3630015552043915,
609
+ "learning_rate": 0.0002,
610
+ "loss": 0.2351,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 2.2428460943542152,
615
+ "grad_norm": 0.5501378178596497,
616
+ "learning_rate": 0.0002,
617
+ "loss": 0.2273,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 2.268625934519206,
622
+ "grad_norm": 0.31958362460136414,
623
+ "learning_rate": 0.0002,
624
+ "loss": 0.2306,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 2.294405774684197,
629
+ "grad_norm": 0.4495809078216553,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.2283,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 2.320185614849188,
636
+ "grad_norm": 0.45789313316345215,
637
+ "learning_rate": 0.0002,
638
+ "loss": 0.2191,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 2.345965455014179,
643
+ "grad_norm": 0.2430783361196518,
644
+ "learning_rate": 0.0002,
645
+ "loss": 0.2266,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 2.3717452951791698,
650
+ "grad_norm": 0.512585461139679,
651
+ "learning_rate": 0.0002,
652
+ "loss": 0.2293,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 2.3975251353441607,
657
+ "grad_norm": 0.42088598012924194,
658
+ "learning_rate": 0.0002,
659
+ "loss": 0.2388,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 2.423304975509152,
664
+ "grad_norm": 0.4196650981903076,
665
+ "learning_rate": 0.0002,
666
+ "loss": 0.2305,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 2.449084815674143,
671
+ "grad_norm": 0.45856234431266785,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.2294,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 2.474864655839134,
678
+ "grad_norm": 0.5690295100212097,
679
+ "learning_rate": 0.0002,
680
+ "loss": 0.2237,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 2.5006444960041248,
685
+ "grad_norm": 0.5325428247451782,
686
+ "learning_rate": 0.0002,
687
+ "loss": 0.2125,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 2.5264243361691157,
692
+ "grad_norm": 0.4254339933395386,
693
+ "learning_rate": 0.0002,
694
+ "loss": 0.2335,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 2.5522041763341066,
699
+ "grad_norm": 0.44463545083999634,
700
+ "learning_rate": 0.0002,
701
+ "loss": 0.2247,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 2.577984016499098,
706
+ "grad_norm": 0.4192294776439667,
707
+ "learning_rate": 0.0002,
708
+ "loss": 0.2328,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 2.603763856664089,
713
+ "grad_norm": 0.39080777764320374,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.2229,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 2.6295436968290797,
720
+ "grad_norm": 0.3375299870967865,
721
+ "learning_rate": 0.0002,
722
+ "loss": 0.2374,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 2.6553235369940706,
727
+ "grad_norm": 0.6126553416252136,
728
+ "learning_rate": 0.0002,
729
+ "loss": 0.2283,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 2.6811033771590616,
734
+ "grad_norm": 0.21654823422431946,
735
+ "learning_rate": 0.0002,
736
+ "loss": 0.2265,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 2.7068832173240525,
741
+ "grad_norm": 0.41668832302093506,
742
+ "learning_rate": 0.0002,
743
+ "loss": 0.2267,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 2.7326630574890434,
748
+ "grad_norm": 0.5655872225761414,
749
+ "learning_rate": 0.0002,
750
+ "loss": 0.2331,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 2.7584428976540343,
755
+ "grad_norm": 0.49956533312797546,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.2323,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 2.7842227378190256,
762
+ "grad_norm": 0.4230547547340393,
763
+ "learning_rate": 0.0002,
764
+ "loss": 0.2157,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 2.8100025779840165,
769
+ "grad_norm": 0.5253151655197144,
770
+ "learning_rate": 0.0002,
771
+ "loss": 0.2189,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 2.8357824181490074,
776
+ "grad_norm": 0.3807348906993866,
777
+ "learning_rate": 0.0002,
778
+ "loss": 0.2285,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 2.8615622583139984,
783
+ "grad_norm": 0.6454833149909973,
784
+ "learning_rate": 0.0002,
785
+ "loss": 0.228,
786
+ "step": 11100
787
+ },
788
+ {
789
+ "epoch": 2.8873420984789897,
790
+ "grad_norm": 0.2508118450641632,
791
+ "learning_rate": 0.0002,
792
+ "loss": 0.2139,
793
+ "step": 11200
794
+ },
795
+ {
796
+ "epoch": 2.9131219386439806,
797
+ "grad_norm": 0.32768428325653076,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.2206,
800
+ "step": 11300
801
+ },
802
+ {
803
+ "epoch": 2.9389017788089715,
804
+ "grad_norm": 0.4850573241710663,
805
+ "learning_rate": 0.0002,
806
+ "loss": 0.2235,
807
+ "step": 11400
808
+ },
809
+ {
810
+ "epoch": 2.9646816189739624,
811
+ "grad_norm": 0.6089478135108948,
812
+ "learning_rate": 0.0002,
813
+ "loss": 0.2081,
814
+ "step": 11500
815
+ },
816
+ {
817
+ "epoch": 2.9904614591389533,
818
+ "grad_norm": 0.47153401374816895,
819
+ "learning_rate": 0.0002,
820
+ "loss": 0.2463,
821
+ "step": 11600
822
+ },
823
+ {
824
+ "epoch": 3.0162412993039442,
825
+ "grad_norm": 0.3843853771686554,
826
+ "learning_rate": 0.0002,
827
+ "loss": 0.1911,
828
+ "step": 11700
829
+ },
830
+ {
831
+ "epoch": 3.042021139468935,
832
+ "grad_norm": 0.21224769949913025,
833
+ "learning_rate": 0.0002,
834
+ "loss": 0.1753,
835
+ "step": 11800
836
+ },
837
+ {
838
+ "epoch": 3.067800979633926,
839
+ "grad_norm": 0.3223534822463989,
840
+ "learning_rate": 0.0002,
841
+ "loss": 0.1799,
842
+ "step": 11900
843
+ },
844
+ {
845
+ "epoch": 3.0935808197989174,
846
+ "grad_norm": 0.399443656206131,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.1755,
849
+ "step": 12000
850
+ },
851
+ {
852
+ "epoch": 3.1193606599639083,
853
+ "grad_norm": 0.253034770488739,
854
+ "learning_rate": 0.0002,
855
+ "loss": 0.177,
856
+ "step": 12100
857
+ },
858
+ {
859
+ "epoch": 3.1451405001288992,
860
+ "grad_norm": 0.318568617105484,
861
+ "learning_rate": 0.0002,
862
+ "loss": 0.1772,
863
+ "step": 12200
864
+ },
865
+ {
866
+ "epoch": 3.17092034029389,
867
+ "grad_norm": 0.2624630928039551,
868
+ "learning_rate": 0.0002,
869
+ "loss": 0.1876,
870
+ "step": 12300
871
+ },
872
+ {
873
+ "epoch": 3.196700180458881,
874
+ "grad_norm": 0.46422523260116577,
875
+ "learning_rate": 0.0002,
876
+ "loss": 0.1717,
877
+ "step": 12400
878
+ },
879
+ {
880
+ "epoch": 3.222480020623872,
881
+ "grad_norm": 0.4504973888397217,
882
+ "learning_rate": 0.0002,
883
+ "loss": 0.1862,
884
+ "step": 12500
885
+ },
886
+ {
887
+ "epoch": 3.2482598607888633,
888
+ "grad_norm": 0.44676682353019714,
889
+ "learning_rate": 0.0002,
890
+ "loss": 0.1865,
891
+ "step": 12600
892
+ },
893
+ {
894
+ "epoch": 3.274039700953854,
895
+ "grad_norm": 0.44682949781417847,
896
+ "learning_rate": 0.0002,
897
+ "loss": 0.1797,
898
+ "step": 12700
899
+ },
900
+ {
901
+ "epoch": 3.299819541118845,
902
+ "grad_norm": 0.22240401804447174,
903
+ "learning_rate": 0.0002,
904
+ "loss": 0.1823,
905
+ "step": 12800
906
+ },
907
+ {
908
+ "epoch": 3.325599381283836,
909
+ "grad_norm": 0.3457636535167694,
910
+ "learning_rate": 0.0002,
911
+ "loss": 0.1839,
912
+ "step": 12900
913
+ },
914
+ {
915
+ "epoch": 3.351379221448827,
916
+ "grad_norm": 0.5065191388130188,
917
+ "learning_rate": 0.0002,
918
+ "loss": 0.1823,
919
+ "step": 13000
920
+ },
921
+ {
922
+ "epoch": 3.377159061613818,
923
+ "grad_norm": 0.516930341720581,
924
+ "learning_rate": 0.0002,
925
+ "loss": 0.1812,
926
+ "step": 13100
927
+ },
928
+ {
929
+ "epoch": 3.4029389017788088,
930
+ "grad_norm": 0.5823391079902649,
931
+ "learning_rate": 0.0002,
932
+ "loss": 0.1851,
933
+ "step": 13200
934
+ },
935
+ {
936
+ "epoch": 3.4287187419438,
937
+ "grad_norm": 0.4604497253894806,
938
+ "learning_rate": 0.0002,
939
+ "loss": 0.1897,
940
+ "step": 13300
941
+ },
942
+ {
943
+ "epoch": 3.454498582108791,
944
+ "grad_norm": 0.3871957063674927,
945
+ "learning_rate": 0.0002,
946
+ "loss": 0.1778,
947
+ "step": 13400
948
+ },
949
+ {
950
+ "epoch": 3.480278422273782,
951
+ "grad_norm": 0.40806278586387634,
952
+ "learning_rate": 0.0002,
953
+ "loss": 0.1854,
954
+ "step": 13500
955
+ },
956
+ {
957
+ "epoch": 3.506058262438773,
958
+ "grad_norm": 0.24849525094032288,
959
+ "learning_rate": 0.0002,
960
+ "loss": 0.1825,
961
+ "step": 13600
962
+ },
963
+ {
964
+ "epoch": 3.5318381026037637,
965
+ "grad_norm": 0.28265008330345154,
966
+ "learning_rate": 0.0002,
967
+ "loss": 0.1914,
968
+ "step": 13700
969
+ },
970
+ {
971
+ "epoch": 3.557617942768755,
972
+ "grad_norm": 0.18643364310264587,
973
+ "learning_rate": 0.0002,
974
+ "loss": 0.1728,
975
+ "step": 13800
976
+ },
977
+ {
978
+ "epoch": 3.583397782933746,
979
+ "grad_norm": 0.36125150322914124,
980
+ "learning_rate": 0.0002,
981
+ "loss": 0.184,
982
+ "step": 13900
983
+ },
984
+ {
985
+ "epoch": 3.609177623098737,
986
+ "grad_norm": 0.35003572702407837,
987
+ "learning_rate": 0.0002,
988
+ "loss": 0.1834,
989
+ "step": 14000
990
+ },
991
+ {
992
+ "epoch": 3.634957463263728,
993
+ "grad_norm": 0.29175901412963867,
994
+ "learning_rate": 0.0002,
995
+ "loss": 0.1845,
996
+ "step": 14100
997
+ },
998
+ {
999
+ "epoch": 3.6607373034287187,
1000
+ "grad_norm": 0.37868496775627136,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 0.1893,
1003
+ "step": 14200
1004
+ },
1005
+ {
1006
+ "epoch": 3.6865171435937096,
1007
+ "grad_norm": 0.3279033899307251,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 0.1908,
1010
+ "step": 14300
1011
+ },
1012
+ {
1013
+ "epoch": 3.7122969837587005,
1014
+ "grad_norm": 0.31007370352745056,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 0.1832,
1017
+ "step": 14400
1018
+ },
1019
+ {
1020
+ "epoch": 3.7380768239236914,
1021
+ "grad_norm": 0.298289030790329,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 0.1948,
1024
+ "step": 14500
1025
+ },
1026
+ {
1027
+ "epoch": 3.763856664088683,
1028
+ "grad_norm": 0.6039551496505737,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 0.1828,
1031
+ "step": 14600
1032
+ },
1033
+ {
1034
+ "epoch": 3.7896365042536737,
1035
+ "grad_norm": 0.449587345123291,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 0.1891,
1038
+ "step": 14700
1039
+ },
1040
+ {
1041
+ "epoch": 3.8154163444186646,
1042
+ "grad_norm": 0.6465901136398315,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 0.1895,
1045
+ "step": 14800
1046
+ },
1047
+ {
1048
+ "epoch": 3.8411961845836555,
1049
+ "grad_norm": 0.5226249098777771,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 0.1767,
1052
+ "step": 14900
1053
+ },
1054
+ {
1055
+ "epoch": 3.8669760247486464,
1056
+ "grad_norm": 0.29470816254615784,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 0.1958,
1059
+ "step": 15000
1060
+ },
1061
+ {
1062
+ "epoch": 3.892755864913638,
1063
+ "grad_norm": 0.4997386336326599,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 0.1984,
1066
+ "step": 15100
1067
+ },
1068
+ {
1069
+ "epoch": 3.9185357050786287,
1070
+ "grad_norm": 0.35381177067756653,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 0.1839,
1073
+ "step": 15200
1074
+ },
1075
+ {
1076
+ "epoch": 3.9443155452436196,
1077
+ "grad_norm": 0.29231759905815125,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 0.1812,
1080
+ "step": 15300
1081
+ },
1082
+ {
1083
+ "epoch": 3.9700953854086105,
1084
+ "grad_norm": 0.40497833490371704,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 0.1798,
1087
+ "step": 15400
1088
+ },
1089
+ {
1090
+ "epoch": 3.9958752255736014,
1091
+ "grad_norm": 0.1775328516960144,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 0.1931,
1094
+ "step": 15500
1095
+ },
1096
+ {
1097
+ "epoch": 4.021655065738592,
1098
+ "grad_norm": 0.2625548243522644,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 0.1513,
1101
+ "step": 15600
1102
+ },
1103
+ {
1104
+ "epoch": 4.047434905903583,
1105
+ "grad_norm": 0.47476592659950256,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 0.1607,
1108
+ "step": 15700
1109
+ },
1110
+ {
1111
+ "epoch": 4.073214746068574,
1112
+ "grad_norm": 0.4454491138458252,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 0.1529,
1115
+ "step": 15800
1116
+ },
1117
+ {
1118
+ "epoch": 4.098994586233565,
1119
+ "grad_norm": 0.12239188700914383,
1120
+ "learning_rate": 0.0002,
1121
+ "loss": 0.1539,
1122
+ "step": 15900
1123
+ },
1124
+ {
1125
+ "epoch": 4.124774426398556,
1126
+ "grad_norm": 0.2339598536491394,
1127
+ "learning_rate": 0.0002,
1128
+ "loss": 0.1572,
1129
+ "step": 16000
1130
+ },
1131
+ {
1132
+ "epoch": 4.150554266563548,
1133
+ "grad_norm": 0.19658803939819336,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.1571,
1136
+ "step": 16100
1137
+ },
1138
+ {
1139
+ "epoch": 4.176334106728539,
1140
+ "grad_norm": 0.25842776894569397,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 0.155,
1143
+ "step": 16200
1144
+ },
1145
+ {
1146
+ "epoch": 4.20211394689353,
1147
+ "grad_norm": 0.4655442535877228,
1148
+ "learning_rate": 0.0002,
1149
+ "loss": 0.1584,
1150
+ "step": 16300
1151
+ },
1152
+ {
1153
+ "epoch": 4.2278937870585205,
1154
+ "grad_norm": 0.3778013586997986,
1155
+ "learning_rate": 0.0002,
1156
+ "loss": 0.1587,
1157
+ "step": 16400
1158
+ },
1159
+ {
1160
+ "epoch": 4.253673627223511,
1161
+ "grad_norm": 0.22199797630310059,
1162
+ "learning_rate": 0.0002,
1163
+ "loss": 0.1573,
1164
+ "step": 16500
1165
+ },
1166
+ {
1167
+ "epoch": 4.279453467388502,
1168
+ "grad_norm": 0.23724961280822754,
1169
+ "learning_rate": 0.0002,
1170
+ "loss": 0.1649,
1171
+ "step": 16600
1172
+ },
1173
+ {
1174
+ "epoch": 4.305233307553493,
1175
+ "grad_norm": 0.4558769166469574,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 0.1633,
1178
+ "step": 16700
1179
+ },
1180
+ {
1181
+ "epoch": 4.331013147718484,
1182
+ "grad_norm": 0.27720391750335693,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 0.1613,
1185
+ "step": 16800
1186
+ },
1187
+ {
1188
+ "epoch": 4.356792987883475,
1189
+ "grad_norm": 0.3628349304199219,
1190
+ "learning_rate": 0.0002,
1191
+ "loss": 0.16,
1192
+ "step": 16900
1193
+ },
1194
+ {
1195
+ "epoch": 4.382572828048466,
1196
+ "grad_norm": 0.6290438175201416,
1197
+ "learning_rate": 0.0002,
1198
+ "loss": 0.1658,
1199
+ "step": 17000
1200
+ },
1201
+ {
1202
+ "epoch": 4.408352668213457,
1203
+ "grad_norm": 0.14983007311820984,
1204
+ "learning_rate": 0.0002,
1205
+ "loss": 0.1629,
1206
+ "step": 17100
1207
+ },
1208
+ {
1209
+ "epoch": 4.434132508378448,
1210
+ "grad_norm": 0.30865323543548584,
1211
+ "learning_rate": 0.0002,
1212
+ "loss": 0.1603,
1213
+ "step": 17200
1214
+ },
1215
+ {
1216
+ "epoch": 4.459912348543439,
1217
+ "grad_norm": 0.5674950480461121,
1218
+ "learning_rate": 0.0002,
1219
+ "loss": 0.1674,
1220
+ "step": 17300
1221
+ },
1222
+ {
1223
+ "epoch": 4.4856921887084305,
1224
+ "grad_norm": 0.40429455041885376,
1225
+ "learning_rate": 0.0002,
1226
+ "loss": 0.1677,
1227
+ "step": 17400
1228
+ },
1229
+ {
1230
+ "epoch": 4.511472028873421,
1231
+ "grad_norm": 0.27213749289512634,
1232
+ "learning_rate": 0.0002,
1233
+ "loss": 0.1642,
1234
+ "step": 17500
1235
+ },
1236
+ {
1237
+ "epoch": 4.537251869038412,
1238
+ "grad_norm": 0.40964949131011963,
1239
+ "learning_rate": 0.0002,
1240
+ "loss": 0.1626,
1241
+ "step": 17600
1242
+ },
1243
+ {
1244
+ "epoch": 4.563031709203403,
1245
+ "grad_norm": 0.3955250382423401,
1246
+ "learning_rate": 0.0002,
1247
+ "loss": 0.1564,
1248
+ "step": 17700
1249
+ },
1250
+ {
1251
+ "epoch": 4.588811549368394,
1252
+ "grad_norm": 0.3900775611400604,
1253
+ "learning_rate": 0.0002,
1254
+ "loss": 0.1605,
1255
+ "step": 17800
1256
+ },
1257
+ {
1258
+ "epoch": 4.614591389533385,
1259
+ "grad_norm": 0.2436327487230301,
1260
+ "learning_rate": 0.0002,
1261
+ "loss": 0.1603,
1262
+ "step": 17900
1263
+ },
1264
+ {
1265
+ "epoch": 4.640371229698376,
1266
+ "grad_norm": 0.4188991189002991,
1267
+ "learning_rate": 0.0002,
1268
+ "loss": 0.163,
1269
+ "step": 18000
1270
+ },
1271
+ {
1272
+ "epoch": 4.666151069863367,
1273
+ "grad_norm": 0.15686850249767303,
1274
+ "learning_rate": 0.0002,
1275
+ "loss": 0.1656,
1276
+ "step": 18100
1277
+ },
1278
+ {
1279
+ "epoch": 4.691930910028358,
1280
+ "grad_norm": 0.30334389209747314,
1281
+ "learning_rate": 0.0002,
1282
+ "loss": 0.1612,
1283
+ "step": 18200
1284
+ },
1285
+ {
1286
+ "epoch": 4.717710750193349,
1287
+ "grad_norm": 0.33619073033332825,
1288
+ "learning_rate": 0.0002,
1289
+ "loss": 0.1626,
1290
+ "step": 18300
1291
+ },
1292
+ {
1293
+ "epoch": 4.7434905903583395,
1294
+ "grad_norm": 0.20497629046440125,
1295
+ "learning_rate": 0.0002,
1296
+ "loss": 0.1647,
1297
+ "step": 18400
1298
+ },
1299
+ {
1300
+ "epoch": 4.76927043052333,
1301
+ "grad_norm": 0.20428726077079773,
1302
+ "learning_rate": 0.0002,
1303
+ "loss": 0.1726,
1304
+ "step": 18500
1305
+ },
1306
+ {
1307
+ "epoch": 4.795050270688321,
1308
+ "grad_norm": 0.3606746196746826,
1309
+ "learning_rate": 0.0002,
1310
+ "loss": 0.1638,
1311
+ "step": 18600
1312
+ },
1313
+ {
1314
+ "epoch": 4.820830110853313,
1315
+ "grad_norm": 0.3441687226295471,
1316
+ "learning_rate": 0.0002,
1317
+ "loss": 0.1676,
1318
+ "step": 18700
1319
+ },
1320
+ {
1321
+ "epoch": 4.846609951018304,
1322
+ "grad_norm": 0.3479159474372864,
1323
+ "learning_rate": 0.0002,
1324
+ "loss": 0.1654,
1325
+ "step": 18800
1326
+ },
1327
+ {
1328
+ "epoch": 4.872389791183295,
1329
+ "grad_norm": 0.39751461148262024,
1330
+ "learning_rate": 0.0002,
1331
+ "loss": 0.1592,
1332
+ "step": 18900
1333
+ },
1334
+ {
1335
+ "epoch": 4.898169631348286,
1336
+ "grad_norm": 0.1793346256017685,
1337
+ "learning_rate": 0.0002,
1338
+ "loss": 0.1683,
1339
+ "step": 19000
1340
+ },
1341
+ {
1342
+ "epoch": 4.923949471513277,
1343
+ "grad_norm": 0.100714772939682,
1344
+ "learning_rate": 0.0002,
1345
+ "loss": 0.1592,
1346
+ "step": 19100
1347
+ },
1348
+ {
1349
+ "epoch": 4.949729311678268,
1350
+ "grad_norm": 0.6268895864486694,
1351
+ "learning_rate": 0.0002,
1352
+ "loss": 0.1667,
1353
+ "step": 19200
1354
+ },
1355
+ {
1356
+ "epoch": 4.975509151843259,
1357
+ "grad_norm": 0.32232895493507385,
1358
+ "learning_rate": 0.0002,
1359
+ "loss": 0.1615,
1360
+ "step": 19300
1361
+ },
1362
+ {
1363
+ "epoch": 5.0012889920082495,
1364
+ "grad_norm": 0.3094789683818817,
1365
+ "learning_rate": 0.0002,
1366
+ "loss": 0.1648,
1367
+ "step": 19400
1368
+ },
1369
+ {
1370
+ "epoch": 5.02706883217324,
1371
+ "grad_norm": 0.3806459307670593,
1372
+ "learning_rate": 0.0002,
1373
+ "loss": 0.149,
1374
+ "step": 19500
1375
+ },
1376
+ {
1377
+ "epoch": 5.052848672338231,
1378
+ "grad_norm": 0.28195375204086304,
1379
+ "learning_rate": 0.0002,
1380
+ "loss": 0.1409,
1381
+ "step": 19600
1382
+ },
1383
+ {
1384
+ "epoch": 5.078628512503222,
1385
+ "grad_norm": 0.1819002479314804,
1386
+ "learning_rate": 0.0002,
1387
+ "loss": 0.1403,
1388
+ "step": 19700
1389
+ },
1390
+ {
1391
+ "epoch": 5.104408352668213,
1392
+ "grad_norm": 0.27728572487831116,
1393
+ "learning_rate": 0.0002,
1394
+ "loss": 0.1426,
1395
+ "step": 19800
1396
+ },
1397
+ {
1398
+ "epoch": 5.130188192833204,
1399
+ "grad_norm": 0.21889761090278625,
1400
+ "learning_rate": 0.0002,
1401
+ "loss": 0.1499,
1402
+ "step": 19900
1403
+ },
1404
+ {
1405
+ "epoch": 5.155968032998196,
1406
+ "grad_norm": 0.3974555432796478,
1407
+ "learning_rate": 0.0002,
1408
+ "loss": 0.1427,
1409
+ "step": 20000
1410
+ },
1411
+ {
1412
+ "epoch": 5.181747873163187,
1413
+ "grad_norm": 0.48159608244895935,
1414
+ "learning_rate": 0.0002,
1415
+ "loss": 0.1477,
1416
+ "step": 20100
1417
+ },
1418
+ {
1419
+ "epoch": 5.207527713328178,
1420
+ "grad_norm": 0.3865210711956024,
1421
+ "learning_rate": 0.0002,
1422
+ "loss": 0.1424,
1423
+ "step": 20200
1424
+ },
1425
+ {
1426
+ "epoch": 5.233307553493169,
1427
+ "grad_norm": 0.26485195755958557,
1428
+ "learning_rate": 0.0002,
1429
+ "loss": 0.1486,
1430
+ "step": 20300
1431
+ },
1432
+ {
1433
+ "epoch": 5.2590873936581595,
1434
+ "grad_norm": 0.41939619183540344,
1435
+ "learning_rate": 0.0002,
1436
+ "loss": 0.151,
1437
+ "step": 20400
1438
+ },
1439
+ {
1440
+ "epoch": 5.28486723382315,
1441
+ "grad_norm": 0.3483380973339081,
1442
+ "learning_rate": 0.0002,
1443
+ "loss": 0.1475,
1444
+ "step": 20500
1445
+ },
1446
+ {
1447
+ "epoch": 5.310647073988141,
1448
+ "grad_norm": 0.40975695848464966,
1449
+ "learning_rate": 0.0002,
1450
+ "loss": 0.1461,
1451
+ "step": 20600
1452
+ },
1453
+ {
1454
+ "epoch": 5.336426914153132,
1455
+ "grad_norm": 0.27101436257362366,
1456
+ "learning_rate": 0.0002,
1457
+ "loss": 0.1528,
1458
+ "step": 20700
1459
+ },
1460
+ {
1461
+ "epoch": 5.362206754318123,
1462
+ "grad_norm": 0.27852606773376465,
1463
+ "learning_rate": 0.0002,
1464
+ "loss": 0.1484,
1465
+ "step": 20800
1466
+ },
1467
+ {
1468
+ "epoch": 5.387986594483114,
1469
+ "grad_norm": 0.4176689684391022,
1470
+ "learning_rate": 0.0002,
1471
+ "loss": 0.1485,
1472
+ "step": 20900
1473
+ },
1474
+ {
1475
+ "epoch": 5.413766434648105,
1476
+ "grad_norm": 0.4901387691497803,
1477
+ "learning_rate": 0.0002,
1478
+ "loss": 0.1479,
1479
+ "step": 21000
1480
+ },
1481
+ {
1482
+ "epoch": 5.439546274813096,
1483
+ "grad_norm": 0.33768975734710693,
1484
+ "learning_rate": 0.0002,
1485
+ "loss": 0.15,
1486
+ "step": 21100
1487
+ },
1488
+ {
1489
+ "epoch": 5.465326114978087,
1490
+ "grad_norm": 0.5349870324134827,
1491
+ "learning_rate": 0.0002,
1492
+ "loss": 0.1485,
1493
+ "step": 21200
1494
+ },
1495
+ {
1496
+ "epoch": 5.4911059551430785,
1497
+ "grad_norm": 0.24405865371227264,
1498
+ "learning_rate": 0.0002,
1499
+ "loss": 0.146,
1500
+ "step": 21300
1501
+ },
1502
+ {
1503
+ "epoch": 5.516885795308069,
1504
+ "grad_norm": 0.2870001494884491,
1505
+ "learning_rate": 0.0002,
1506
+ "loss": 0.1482,
1507
+ "step": 21400
1508
+ },
1509
+ {
1510
+ "epoch": 5.54266563547306,
1511
+ "grad_norm": 0.34606364369392395,
1512
+ "learning_rate": 0.0002,
1513
+ "loss": 0.1535,
1514
+ "step": 21500
1515
+ },
1516
+ {
1517
+ "epoch": 5.568445475638051,
1518
+ "grad_norm": 0.4999238848686218,
1519
+ "learning_rate": 0.0002,
1520
+ "loss": 0.1523,
1521
+ "step": 21600
1522
+ },
1523
+ {
1524
+ "epoch": 5.594225315803042,
1525
+ "grad_norm": 0.2526559829711914,
1526
+ "learning_rate": 0.0002,
1527
+ "loss": 0.1524,
1528
+ "step": 21700
1529
+ },
1530
+ {
1531
+ "epoch": 5.620005155968033,
1532
+ "grad_norm": 0.270786315202713,
1533
+ "learning_rate": 0.0002,
1534
+ "loss": 0.1511,
1535
+ "step": 21800
1536
+ },
1537
+ {
1538
+ "epoch": 5.645784996133024,
1539
+ "grad_norm": 0.4440493881702423,
1540
+ "learning_rate": 0.0002,
1541
+ "loss": 0.1539,
1542
+ "step": 21900
1543
+ },
1544
+ {
1545
+ "epoch": 5.671564836298015,
1546
+ "grad_norm": 0.4871107041835785,
1547
+ "learning_rate": 0.0002,
1548
+ "loss": 0.1505,
1549
+ "step": 22000
1550
+ },
1551
+ {
1552
+ "epoch": 5.697344676463006,
1553
+ "grad_norm": 0.40973493456840515,
1554
+ "learning_rate": 0.0002,
1555
+ "loss": 0.1553,
1556
+ "step": 22100
1557
+ },
1558
+ {
1559
+ "epoch": 5.723124516627997,
1560
+ "grad_norm": 0.4365851581096649,
1561
+ "learning_rate": 0.0002,
1562
+ "loss": 0.1502,
1563
+ "step": 22200
1564
+ },
1565
+ {
1566
+ "epoch": 5.748904356792988,
1567
+ "grad_norm": 0.5478639602661133,
1568
+ "learning_rate": 0.0002,
1569
+ "loss": 0.1611,
1570
+ "step": 22300
1571
+ },
1572
+ {
1573
+ "epoch": 5.7746841969579785,
1574
+ "grad_norm": 0.29485803842544556,
1575
+ "learning_rate": 0.0002,
1576
+ "loss": 0.157,
1577
+ "step": 22400
1578
+ },
1579
+ {
1580
+ "epoch": 5.800464037122969,
1581
+ "grad_norm": 0.20778502523899078,
1582
+ "learning_rate": 0.0002,
1583
+ "loss": 0.1489,
1584
+ "step": 22500
1585
+ },
1586
+ {
1587
+ "epoch": 5.826243877287961,
1588
+ "grad_norm": 0.1795939952135086,
1589
+ "learning_rate": 0.0002,
1590
+ "loss": 0.1517,
1591
+ "step": 22600
1592
+ },
1593
+ {
1594
+ "epoch": 5.852023717452952,
1595
+ "grad_norm": 0.4165894687175751,
1596
+ "learning_rate": 0.0002,
1597
+ "loss": 0.1464,
1598
+ "step": 22700
1599
+ },
1600
+ {
1601
+ "epoch": 5.877803557617943,
1602
+ "grad_norm": 0.35076722502708435,
1603
+ "learning_rate": 0.0002,
1604
+ "loss": 0.1499,
1605
+ "step": 22800
1606
+ },
1607
+ {
1608
+ "epoch": 5.903583397782934,
1609
+ "grad_norm": 0.3190014362335205,
1610
+ "learning_rate": 0.0002,
1611
+ "loss": 0.1474,
1612
+ "step": 22900
1613
+ },
1614
+ {
1615
+ "epoch": 5.929363237947925,
1616
+ "grad_norm": 0.6232258081436157,
1617
+ "learning_rate": 0.0002,
1618
+ "loss": 0.1521,
1619
+ "step": 23000
1620
+ },
1621
+ {
1622
+ "epoch": 5.955143078112916,
1623
+ "grad_norm": 0.41889217495918274,
1624
+ "learning_rate": 0.0002,
1625
+ "loss": 0.1553,
1626
+ "step": 23100
1627
+ },
1628
+ {
1629
+ "epoch": 5.980922918277907,
1630
+ "grad_norm": 0.4977259635925293,
1631
+ "learning_rate": 0.0002,
1632
+ "loss": 0.1543,
1633
+ "step": 23200
1634
+ },
1635
+ {
1636
+ "epoch": 6.006702758442898,
1637
+ "grad_norm": 0.3092762231826782,
1638
+ "learning_rate": 0.0002,
1639
+ "loss": 0.145,
1640
+ "step": 23300
1641
+ },
1642
+ {
1643
+ "epoch": 6.0324825986078885,
1644
+ "grad_norm": 0.15745452046394348,
1645
+ "learning_rate": 0.0002,
1646
+ "loss": 0.138,
1647
+ "step": 23400
1648
+ },
1649
+ {
1650
+ "epoch": 6.058262438772879,
1651
+ "grad_norm": 0.10685788840055466,
1652
+ "learning_rate": 0.0002,
1653
+ "loss": 0.1345,
1654
+ "step": 23500
1655
+ },
1656
+ {
1657
+ "epoch": 6.08404227893787,
1658
+ "grad_norm": 0.41699907183647156,
1659
+ "learning_rate": 0.0002,
1660
+ "loss": 0.1379,
1661
+ "step": 23600
1662
+ },
1663
+ {
1664
+ "epoch": 6.109822119102861,
1665
+ "grad_norm": 0.18783129751682281,
1666
+ "learning_rate": 0.0002,
1667
+ "loss": 0.1306,
1668
+ "step": 23700
1669
+ },
1670
+ {
1671
+ "epoch": 6.135601959267852,
1672
+ "grad_norm": 0.15569710731506348,
1673
+ "learning_rate": 0.0002,
1674
+ "loss": 0.1372,
1675
+ "step": 23800
1676
+ },
1677
+ {
1678
+ "epoch": 6.161381799432844,
1679
+ "grad_norm": 0.4492259919643402,
1680
+ "learning_rate": 0.0002,
1681
+ "loss": 0.1414,
1682
+ "step": 23900
1683
+ },
1684
+ {
1685
+ "epoch": 6.187161639597835,
1686
+ "grad_norm": 0.1448894888162613,
1687
+ "learning_rate": 0.0002,
1688
+ "loss": 0.1376,
1689
+ "step": 24000
1690
+ },
1691
+ {
1692
+ "epoch": 6.212941479762826,
1693
+ "grad_norm": 0.2028491050004959,
1694
+ "learning_rate": 0.0002,
1695
+ "loss": 0.1349,
1696
+ "step": 24100
1697
+ },
1698
+ {
1699
+ "epoch": 6.238721319927817,
1700
+ "grad_norm": 0.19205012917518616,
1701
+ "learning_rate": 0.0002,
1702
+ "loss": 0.1396,
1703
+ "step": 24200
1704
+ },
1705
+ {
1706
+ "epoch": 6.2645011600928076,
1707
+ "grad_norm": 0.29885369539260864,
1708
+ "learning_rate": 0.0002,
1709
+ "loss": 0.1449,
1710
+ "step": 24300
1711
+ },
1712
+ {
1713
+ "epoch": 6.2902810002577985,
1714
+ "grad_norm": 0.15814617276191711,
1715
+ "learning_rate": 0.0002,
1716
+ "loss": 0.1438,
1717
+ "step": 24400
1718
+ },
1719
+ {
1720
+ "epoch": 6.316060840422789,
1721
+ "grad_norm": 0.2691551148891449,
1722
+ "learning_rate": 0.0002,
1723
+ "loss": 0.1406,
1724
+ "step": 24500
1725
+ },
1726
+ {
1727
+ "epoch": 6.34184068058778,
1728
+ "grad_norm": 0.543335497379303,
1729
+ "learning_rate": 0.0002,
1730
+ "loss": 0.1389,
1731
+ "step": 24600
1732
+ },
1733
+ {
1734
+ "epoch": 6.367620520752771,
1735
+ "grad_norm": 0.33116665482521057,
1736
+ "learning_rate": 0.0002,
1737
+ "loss": 0.1403,
1738
+ "step": 24700
1739
+ },
1740
+ {
1741
+ "epoch": 6.393400360917762,
1742
+ "grad_norm": 0.5159612894058228,
1743
+ "learning_rate": 0.0002,
1744
+ "loss": 0.1408,
1745
+ "step": 24800
1746
+ },
1747
+ {
1748
+ "epoch": 6.419180201082753,
1749
+ "grad_norm": 0.30205056071281433,
1750
+ "learning_rate": 0.0002,
1751
+ "loss": 0.1409,
1752
+ "step": 24900
1753
+ },
1754
+ {
1755
+ "epoch": 6.444960041247744,
1756
+ "grad_norm": 0.44916966557502747,
1757
+ "learning_rate": 0.0002,
1758
+ "loss": 0.1432,
1759
+ "step": 25000
1760
+ },
1761
+ {
1762
+ "epoch": 6.470739881412735,
1763
+ "grad_norm": 0.18665899336338043,
1764
+ "learning_rate": 0.0002,
1765
+ "loss": 0.1434,
1766
+ "step": 25100
1767
+ },
1768
+ {
1769
+ "epoch": 6.496519721577727,
1770
+ "grad_norm": 0.4078758656978607,
1771
+ "learning_rate": 0.0002,
1772
+ "loss": 0.1411,
1773
+ "step": 25200
1774
+ },
1775
+ {
1776
+ "epoch": 6.5222995617427175,
1777
+ "grad_norm": 0.39813536405563354,
1778
+ "learning_rate": 0.0002,
1779
+ "loss": 0.1445,
1780
+ "step": 25300
1781
+ },
1782
+ {
1783
+ "epoch": 6.548079401907708,
1784
+ "grad_norm": 0.2587377727031708,
1785
+ "learning_rate": 0.0002,
1786
+ "loss": 0.1463,
1787
+ "step": 25400
1788
+ },
1789
+ {
1790
+ "epoch": 6.573859242072699,
1791
+ "grad_norm": 0.41181057691574097,
1792
+ "learning_rate": 0.0002,
1793
+ "loss": 0.1487,
1794
+ "step": 25500
1795
+ },
1796
+ {
1797
+ "epoch": 6.59963908223769,
1798
+ "grad_norm": 0.3136518597602844,
1799
+ "learning_rate": 0.0002,
1800
+ "loss": 0.1414,
1801
+ "step": 25600
1802
+ },
1803
+ {
1804
+ "epoch": 6.625418922402681,
1805
+ "grad_norm": 0.4114777445793152,
1806
+ "learning_rate": 0.0002,
1807
+ "loss": 0.1434,
1808
+ "step": 25700
1809
+ },
1810
+ {
1811
+ "epoch": 6.651198762567672,
1812
+ "grad_norm": 0.17142866551876068,
1813
+ "learning_rate": 0.0002,
1814
+ "loss": 0.1411,
1815
+ "step": 25800
1816
+ },
1817
+ {
1818
+ "epoch": 6.676978602732663,
1819
+ "grad_norm": 0.5585296750068665,
1820
+ "learning_rate": 0.0002,
1821
+ "loss": 0.148,
1822
+ "step": 25900
1823
+ },
1824
+ {
1825
+ "epoch": 6.702758442897654,
1826
+ "grad_norm": 0.23773185908794403,
1827
+ "learning_rate": 0.0002,
1828
+ "loss": 0.1468,
1829
+ "step": 26000
1830
+ },
1831
+ {
1832
+ "epoch": 6.728538283062645,
1833
+ "grad_norm": 0.38246840238571167,
1834
+ "learning_rate": 0.0002,
1835
+ "loss": 0.1426,
1836
+ "step": 26100
1837
+ },
1838
+ {
1839
+ "epoch": 6.754318123227636,
1840
+ "grad_norm": 0.5393186807632446,
1841
+ "learning_rate": 0.0002,
1842
+ "loss": 0.1456,
1843
+ "step": 26200
1844
+ },
1845
+ {
1846
+ "epoch": 6.780097963392627,
1847
+ "grad_norm": 0.21433015167713165,
1848
+ "learning_rate": 0.0002,
1849
+ "loss": 0.1456,
1850
+ "step": 26300
1851
+ },
1852
+ {
1853
+ "epoch": 6.8058778035576175,
1854
+ "grad_norm": 0.4375258982181549,
1855
+ "learning_rate": 0.0002,
1856
+ "loss": 0.1461,
1857
+ "step": 26400
1858
+ },
1859
+ {
1860
+ "epoch": 6.831657643722609,
1861
+ "grad_norm": 0.515832781791687,
1862
+ "learning_rate": 0.0002,
1863
+ "loss": 0.1484,
1864
+ "step": 26500
1865
+ },
1866
+ {
1867
+ "epoch": 6.8574374838876,
1868
+ "grad_norm": 0.496559739112854,
1869
+ "learning_rate": 0.0002,
1870
+ "loss": 0.1461,
1871
+ "step": 26600
1872
+ },
1873
+ {
1874
+ "epoch": 6.883217324052591,
1875
+ "grad_norm": 0.30182015895843506,
1876
+ "learning_rate": 0.0002,
1877
+ "loss": 0.1471,
1878
+ "step": 26700
1879
+ },
1880
+ {
1881
+ "epoch": 6.908997164217582,
1882
+ "grad_norm": 0.3858971893787384,
1883
+ "learning_rate": 0.0002,
1884
+ "loss": 0.1469,
1885
+ "step": 26800
1886
+ },
1887
+ {
1888
+ "epoch": 6.934777004382573,
1889
+ "grad_norm": 0.30368533730506897,
1890
+ "learning_rate": 0.0002,
1891
+ "loss": 0.1466,
1892
+ "step": 26900
1893
+ },
1894
+ {
1895
+ "epoch": 6.960556844547564,
1896
+ "grad_norm": 0.29557520151138306,
1897
+ "learning_rate": 0.0002,
1898
+ "loss": 0.1446,
1899
+ "step": 27000
1900
+ },
1901
+ {
1902
+ "epoch": 6.986336684712555,
1903
+ "grad_norm": 0.34702664613723755,
1904
+ "learning_rate": 0.0002,
1905
+ "loss": 0.143,
1906
+ "step": 27100
1907
+ },
1908
+ {
1909
+ "epoch": 7.012116524877546,
1910
+ "grad_norm": 0.18182627856731415,
1911
+ "learning_rate": 0.0002,
1912
+ "loss": 0.1467,
1913
+ "step": 27200
1914
+ },
1915
+ {
1916
+ "epoch": 7.037896365042537,
1917
+ "grad_norm": 0.48641154170036316,
1918
+ "learning_rate": 0.0002,
1919
+ "loss": 0.1337,
1920
+ "step": 27300
1921
+ },
1922
+ {
1923
+ "epoch": 7.0636762052075275,
1924
+ "grad_norm": 0.5797538757324219,
1925
+ "learning_rate": 0.0002,
1926
+ "loss": 0.1291,
1927
+ "step": 27400
1928
+ },
1929
+ {
1930
+ "epoch": 7.089456045372518,
1931
+ "grad_norm": 0.20399855077266693,
1932
+ "learning_rate": 0.0002,
1933
+ "loss": 0.1372,
1934
+ "step": 27500
1935
+ },
1936
+ {
1937
+ "epoch": 7.115235885537509,
1938
+ "grad_norm": 0.12141354382038116,
1939
+ "learning_rate": 0.0002,
1940
+ "loss": 0.1359,
1941
+ "step": 27600
1942
+ },
1943
+ {
1944
+ "epoch": 7.1410157257025,
1945
+ "grad_norm": 0.13764117658138275,
1946
+ "learning_rate": 0.0002,
1947
+ "loss": 0.1276,
1948
+ "step": 27700
1949
+ },
1950
+ {
1951
+ "epoch": 7.166795565867492,
1952
+ "grad_norm": 0.21888123452663422,
1953
+ "learning_rate": 0.0002,
1954
+ "loss": 0.1337,
1955
+ "step": 27800
1956
+ },
1957
+ {
1958
+ "epoch": 7.192575406032483,
1959
+ "grad_norm": 0.1562834531068802,
1960
+ "learning_rate": 0.0002,
1961
+ "loss": 0.133,
1962
+ "step": 27900
1963
+ },
1964
+ {
1965
+ "epoch": 7.218355246197474,
1966
+ "grad_norm": 0.3367880880832672,
1967
+ "learning_rate": 0.0002,
1968
+ "loss": 0.1335,
1969
+ "step": 28000
1970
+ },
1971
+ {
1972
+ "epoch": 7.244135086362465,
1973
+ "grad_norm": 0.1075579896569252,
1974
+ "learning_rate": 0.0002,
1975
+ "loss": 0.1334,
1976
+ "step": 28100
1977
+ },
1978
+ {
1979
+ "epoch": 7.269914926527456,
1980
+ "grad_norm": 0.11283877491950989,
1981
+ "learning_rate": 0.0002,
1982
+ "loss": 0.1356,
1983
+ "step": 28200
1984
+ },
1985
+ {
1986
+ "epoch": 7.2956947666924465,
1987
+ "grad_norm": 0.24768362939357758,
1988
+ "learning_rate": 0.0002,
1989
+ "loss": 0.1374,
1990
+ "step": 28300
1991
+ },
1992
+ {
1993
+ "epoch": 7.3214746068574375,
1994
+ "grad_norm": 0.22776305675506592,
1995
+ "learning_rate": 0.0002,
1996
+ "loss": 0.1307,
1997
+ "step": 28400
1998
+ },
1999
+ {
2000
+ "epoch": 7.347254447022428,
2001
+ "grad_norm": 0.13827867805957794,
2002
+ "learning_rate": 0.0002,
2003
+ "loss": 0.1396,
2004
+ "step": 28500
2005
+ },
2006
+ {
2007
+ "epoch": 7.373034287187419,
2008
+ "grad_norm": 0.2935916781425476,
2009
+ "learning_rate": 0.0002,
2010
+ "loss": 0.1355,
2011
+ "step": 28600
2012
+ },
2013
+ {
2014
+ "epoch": 7.39881412735241,
2015
+ "grad_norm": 0.10991048812866211,
2016
+ "learning_rate": 0.0002,
2017
+ "loss": 0.1349,
2018
+ "step": 28700
2019
+ },
2020
+ {
2021
+ "epoch": 7.424593967517401,
2022
+ "grad_norm": 0.30149704217910767,
2023
+ "learning_rate": 0.0002,
2024
+ "loss": 0.1374,
2025
+ "step": 28800
2026
+ },
2027
+ {
2028
+ "epoch": 7.450373807682392,
2029
+ "grad_norm": 0.13918708264827728,
2030
+ "learning_rate": 0.0002,
2031
+ "loss": 0.141,
2032
+ "step": 28900
2033
+ },
2034
+ {
2035
+ "epoch": 7.476153647847383,
2036
+ "grad_norm": 0.13292869925498962,
2037
+ "learning_rate": 0.0002,
2038
+ "loss": 0.1386,
2039
+ "step": 29000
2040
+ },
2041
+ {
2042
+ "epoch": 7.501933488012375,
2043
+ "grad_norm": 0.5602275729179382,
2044
+ "learning_rate": 0.0002,
2045
+ "loss": 0.1421,
2046
+ "step": 29100
2047
+ },
2048
+ {
2049
+ "epoch": 7.527713328177366,
2050
+ "grad_norm": 0.12204320728778839,
2051
+ "learning_rate": 0.0002,
2052
+ "loss": 0.1334,
2053
+ "step": 29200
2054
+ },
2055
+ {
2056
+ "epoch": 7.5534931683423565,
2057
+ "grad_norm": 0.17424637079238892,
2058
+ "learning_rate": 0.0002,
2059
+ "loss": 0.1372,
2060
+ "step": 29300
2061
+ },
2062
+ {
2063
+ "epoch": 7.579273008507347,
2064
+ "grad_norm": 0.4190254509449005,
2065
+ "learning_rate": 0.0002,
2066
+ "loss": 0.1458,
2067
+ "step": 29400
2068
+ },
2069
+ {
2070
+ "epoch": 7.605052848672338,
2071
+ "grad_norm": 0.13242638111114502,
2072
+ "learning_rate": 0.0002,
2073
+ "loss": 0.1421,
2074
+ "step": 29500
2075
+ },
2076
+ {
2077
+ "epoch": 7.630832688837329,
2078
+ "grad_norm": 0.23242244124412537,
2079
+ "learning_rate": 0.0002,
2080
+ "loss": 0.1429,
2081
+ "step": 29600
2082
+ },
2083
+ {
2084
+ "epoch": 7.65661252900232,
2085
+ "grad_norm": 0.4323575794696808,
2086
+ "learning_rate": 0.0002,
2087
+ "loss": 0.1402,
2088
+ "step": 29700
2089
+ },
2090
+ {
2091
+ "epoch": 7.682392369167311,
2092
+ "grad_norm": 0.1595413088798523,
2093
+ "learning_rate": 0.0002,
2094
+ "loss": 0.1403,
2095
+ "step": 29800
2096
+ },
2097
+ {
2098
+ "epoch": 7.708172209332302,
2099
+ "grad_norm": 0.1448589414358139,
2100
+ "learning_rate": 0.0002,
2101
+ "loss": 0.136,
2102
+ "step": 29900
2103
+ },
2104
+ {
2105
+ "epoch": 7.733952049497293,
2106
+ "grad_norm": 0.5433810353279114,
2107
+ "learning_rate": 0.0002,
2108
+ "loss": 0.139,
2109
+ "step": 30000
2110
+ }
2111
+ ],
2112
+ "logging_steps": 100,
2113
+ "max_steps": 31032,
2114
+ "num_input_tokens_seen": 0,
2115
+ "num_train_epochs": 8,
2116
+ "save_steps": 3000,
2117
+ "stateful_callbacks": {
2118
+ "TrainerControl": {
2119
+ "args": {
2120
+ "should_epoch_stop": false,
2121
+ "should_evaluate": false,
2122
+ "should_log": false,
2123
+ "should_save": true,
2124
+ "should_training_stop": false
2125
+ },
2126
+ "attributes": {}
2127
+ }
2128
+ },
2129
+ "total_flos": 2.186321886206116e+17,
2130
+ "train_batch_size": 2,
2131
+ "trial_name": null,
2132
+ "trial_params": null
2133
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb43f92398ef10cb2bcf7e1ee38c45391bd6c835dd3c9b264b5a740a5b0d28b
3
+ size 5496