BoburAmirov commited on
Commit
9f0f12c
1 Parent(s): 507f66d

upload model

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Llama-2-7b-chat-hf
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
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
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9edabf78265a73047112e538330e8aed34efc6dfbccc79cbae028a3e4d810633
3
+ size 134235048
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfcfd1dc6ea07b5fc22accb2456b490bb4a922d89a6214fbbfc09ed614688b4
3
+ size 268515002
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e29ccbc9c8625a33220ed543bb5e48fe335096cfdec234f7ceccc2c1a452da0
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ef9b5765263cd51042a755ae529d23e5d6fd529baa4b159cb9626532b6340d
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "</s>",
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": false
48
+ }
trainer_state.json ADDED
@@ -0,0 +1,2343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 13.2,
5
+ "eval_steps": 500,
6
+ "global_step": 33000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 1.1794846057891846,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.9634,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "grad_norm": 0.9956796169281006,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.5897,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.12,
27
+ "grad_norm": 0.7088788747787476,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.3967,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.16,
34
+ "grad_norm": 0.8429712057113647,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.403,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.2,
41
+ "grad_norm": 0.7503288388252258,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.3169,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "grad_norm": 0.6073698401451111,
49
+ "learning_rate": 0.0002,
50
+ "loss": 2.2718,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.28,
55
+ "grad_norm": 0.6131550073623657,
56
+ "learning_rate": 0.0002,
57
+ "loss": 2.1968,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.32,
62
+ "grad_norm": 1.0864523649215698,
63
+ "learning_rate": 0.0002,
64
+ "loss": 2.2322,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.36,
69
+ "grad_norm": 0.7630054950714111,
70
+ "learning_rate": 0.0002,
71
+ "loss": 2.2196,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.4,
76
+ "grad_norm": 0.8388053178787231,
77
+ "learning_rate": 0.0002,
78
+ "loss": 2.2967,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.44,
83
+ "grad_norm": 0.7474327087402344,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.222,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.48,
90
+ "grad_norm": 0.7345255613327026,
91
+ "learning_rate": 0.0002,
92
+ "loss": 2.0606,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.52,
97
+ "grad_norm": 0.5666030049324036,
98
+ "learning_rate": 0.0002,
99
+ "loss": 2.1423,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.56,
104
+ "grad_norm": 0.7595005631446838,
105
+ "learning_rate": 0.0002,
106
+ "loss": 2.1629,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.6,
111
+ "grad_norm": 0.5787087678909302,
112
+ "learning_rate": 0.0002,
113
+ "loss": 2.1169,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.64,
118
+ "grad_norm": 0.9300134778022766,
119
+ "learning_rate": 0.0002,
120
+ "loss": 2.0647,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.68,
125
+ "grad_norm": 0.6892948746681213,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.0773,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.72,
132
+ "grad_norm": 0.5084001421928406,
133
+ "learning_rate": 0.0002,
134
+ "loss": 2.1002,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.76,
139
+ "grad_norm": 0.470070481300354,
140
+ "learning_rate": 0.0002,
141
+ "loss": 2.0381,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.8,
146
+ "grad_norm": 0.6220455169677734,
147
+ "learning_rate": 0.0002,
148
+ "loss": 2.0517,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.84,
153
+ "grad_norm": 0.8656258583068848,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.9672,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.88,
160
+ "grad_norm": 0.7517567873001099,
161
+ "learning_rate": 0.0002,
162
+ "loss": 2.0848,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.92,
167
+ "grad_norm": 0.7987684011459351,
168
+ "learning_rate": 0.0002,
169
+ "loss": 2.0362,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.96,
174
+ "grad_norm": 0.6208759546279907,
175
+ "learning_rate": 0.0002,
176
+ "loss": 2.0221,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "grad_norm": 0.5592771768569946,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.9436,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 1.04,
188
+ "grad_norm": 0.8733409643173218,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.9028,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 1.08,
195
+ "grad_norm": 0.6601306200027466,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.9403,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 1.12,
202
+ "grad_norm": 0.7789013385772705,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8257,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 1.16,
209
+ "grad_norm": 0.5855867862701416,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.9351,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 1.2,
216
+ "grad_norm": 0.5030935406684875,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.9253,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 1.24,
223
+ "grad_norm": 0.6684442758560181,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.9153,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 1.28,
230
+ "grad_norm": 0.6724442839622498,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8726,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 1.32,
237
+ "grad_norm": 0.48911118507385254,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.9423,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 1.3599999999999999,
244
+ "grad_norm": 0.7769139409065247,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.7886,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 1.4,
251
+ "grad_norm": 0.639460027217865,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.9118,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 1.44,
258
+ "grad_norm": 0.5745570659637451,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8423,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 1.48,
265
+ "grad_norm": 0.6319829225540161,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.8893,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 1.52,
272
+ "grad_norm": 0.5839726328849792,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8506,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 1.56,
279
+ "grad_norm": 0.7453562617301941,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8698,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 1.6,
286
+ "grad_norm": 0.7091575264930725,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.8367,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 1.6400000000000001,
293
+ "grad_norm": 0.722655177116394,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.8939,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 1.6800000000000002,
300
+ "grad_norm": 0.566392183303833,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7557,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 1.72,
307
+ "grad_norm": 0.564018189907074,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.72,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 1.76,
314
+ "grad_norm": 0.7120116949081421,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7436,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 1.8,
321
+ "grad_norm": 0.7515490651130676,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.83,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 1.8399999999999999,
328
+ "grad_norm": 0.6733573079109192,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.8012,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 1.88,
335
+ "grad_norm": 1.0119801759719849,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.8833,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 1.92,
342
+ "grad_norm": 0.73843914270401,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8012,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 1.96,
349
+ "grad_norm": 0.5831142067909241,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.768,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 2.0,
356
+ "grad_norm": 0.5329481959342957,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8615,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 2.04,
363
+ "grad_norm": 0.5874722599983215,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.6998,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 2.08,
370
+ "grad_norm": 0.5984659194946289,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.7303,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 2.12,
377
+ "grad_norm": 0.7614981532096863,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.6637,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 2.16,
384
+ "grad_norm": 0.8689171671867371,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 2.2,
391
+ "grad_norm": 0.8071489334106445,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.6588,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 2.24,
398
+ "grad_norm": 0.7306439280509949,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.7062,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 2.2800000000000002,
405
+ "grad_norm": 0.483328253030777,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.705,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 2.32,
412
+ "grad_norm": 0.9662113189697266,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.6375,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 2.36,
419
+ "grad_norm": 0.6570947766304016,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.6495,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 2.4,
426
+ "grad_norm": 0.6682040691375732,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.6971,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 2.44,
433
+ "grad_norm": 0.6937342286109924,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.6179,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 2.48,
440
+ "grad_norm": 0.6113543510437012,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.6769,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 2.52,
447
+ "grad_norm": 0.6734089851379395,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.6866,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 2.56,
454
+ "grad_norm": 0.6203577518463135,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.6999,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 2.6,
461
+ "grad_norm": 0.8067578077316284,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.6294,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 2.64,
468
+ "grad_norm": 0.7386764883995056,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.6841,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 2.68,
475
+ "grad_norm": 0.9529528617858887,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.665,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 2.7199999999999998,
482
+ "grad_norm": 0.5639382600784302,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.6756,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 2.76,
489
+ "grad_norm": 0.8711239695549011,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.5953,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 2.8,
496
+ "grad_norm": 0.6677307486534119,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.6708,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 2.84,
503
+ "grad_norm": 0.6820212006568909,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.6722,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 2.88,
510
+ "grad_norm": 0.6516992449760437,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.6407,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 2.92,
517
+ "grad_norm": 0.6071237325668335,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.6273,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 2.96,
524
+ "grad_norm": 0.6759991645812988,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.6218,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 3.0,
531
+ "grad_norm": 0.6260673403739929,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.7184,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 3.04,
538
+ "grad_norm": 0.6020120978355408,
539
+ "learning_rate": 0.0002,
540
+ "loss": 1.4686,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 3.08,
545
+ "grad_norm": 0.9953874945640564,
546
+ "learning_rate": 0.0002,
547
+ "loss": 1.5124,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 3.12,
552
+ "grad_norm": 0.7787545323371887,
553
+ "learning_rate": 0.0002,
554
+ "loss": 1.5184,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 3.16,
559
+ "grad_norm": 0.9334218502044678,
560
+ "learning_rate": 0.0002,
561
+ "loss": 1.5031,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 3.2,
566
+ "grad_norm": 0.9822279214859009,
567
+ "learning_rate": 0.0002,
568
+ "loss": 1.504,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 3.24,
573
+ "grad_norm": 0.8602248430252075,
574
+ "learning_rate": 0.0002,
575
+ "loss": 1.5348,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 3.2800000000000002,
580
+ "grad_norm": 0.88422691822052,
581
+ "learning_rate": 0.0002,
582
+ "loss": 1.4788,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 3.32,
587
+ "grad_norm": 0.8250532746315002,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.5258,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 3.36,
594
+ "grad_norm": 1.3689357042312622,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.53,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 3.4,
601
+ "grad_norm": 1.0472410917282104,
602
+ "learning_rate": 0.0002,
603
+ "loss": 1.5347,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 3.44,
608
+ "grad_norm": 0.7986043095588684,
609
+ "learning_rate": 0.0002,
610
+ "loss": 1.4467,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 3.48,
615
+ "grad_norm": 0.8166589736938477,
616
+ "learning_rate": 0.0002,
617
+ "loss": 1.6207,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 3.52,
622
+ "grad_norm": 0.7566811442375183,
623
+ "learning_rate": 0.0002,
624
+ "loss": 1.5238,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 3.56,
629
+ "grad_norm": 0.9338216185569763,
630
+ "learning_rate": 0.0002,
631
+ "loss": 1.5801,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 3.6,
636
+ "grad_norm": 0.9602301716804504,
637
+ "learning_rate": 0.0002,
638
+ "loss": 1.4506,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 3.64,
643
+ "grad_norm": 0.9274515509605408,
644
+ "learning_rate": 0.0002,
645
+ "loss": 1.5574,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 3.68,
650
+ "grad_norm": 1.6966444253921509,
651
+ "learning_rate": 0.0002,
652
+ "loss": 1.4391,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 3.7199999999999998,
657
+ "grad_norm": 0.9805380702018738,
658
+ "learning_rate": 0.0002,
659
+ "loss": 1.5071,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 3.76,
664
+ "grad_norm": 1.1102324724197388,
665
+ "learning_rate": 0.0002,
666
+ "loss": 1.5041,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 3.8,
671
+ "grad_norm": 1.1052135229110718,
672
+ "learning_rate": 0.0002,
673
+ "loss": 1.504,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 3.84,
678
+ "grad_norm": 0.8187786936759949,
679
+ "learning_rate": 0.0002,
680
+ "loss": 1.5444,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 3.88,
685
+ "grad_norm": 1.5404032468795776,
686
+ "learning_rate": 0.0002,
687
+ "loss": 1.5627,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 3.92,
692
+ "grad_norm": 0.7880242466926575,
693
+ "learning_rate": 0.0002,
694
+ "loss": 1.508,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 3.96,
699
+ "grad_norm": 1.2433679103851318,
700
+ "learning_rate": 0.0002,
701
+ "loss": 1.5252,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 4.0,
706
+ "grad_norm": NaN,
707
+ "learning_rate": 0.0002,
708
+ "loss": 1.5194,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 4.04,
713
+ "grad_norm": 0.9061052799224854,
714
+ "learning_rate": 0.0002,
715
+ "loss": 1.3939,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 4.08,
720
+ "grad_norm": 0.9826890230178833,
721
+ "learning_rate": 0.0002,
722
+ "loss": 1.3602,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 4.12,
727
+ "grad_norm": 1.1164418458938599,
728
+ "learning_rate": 0.0002,
729
+ "loss": 1.4036,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 4.16,
734
+ "grad_norm": 1.2371020317077637,
735
+ "learning_rate": 0.0002,
736
+ "loss": 1.4325,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 4.2,
741
+ "grad_norm": 0.9281136393547058,
742
+ "learning_rate": 0.0002,
743
+ "loss": 1.3633,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 4.24,
748
+ "grad_norm": 1.5267653465270996,
749
+ "learning_rate": 0.0002,
750
+ "loss": 1.3531,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 4.28,
755
+ "grad_norm": 0.9372194409370422,
756
+ "learning_rate": 0.0002,
757
+ "loss": 1.387,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 4.32,
762
+ "grad_norm": 1.9180704355239868,
763
+ "learning_rate": 0.0002,
764
+ "loss": 1.4049,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 4.36,
769
+ "grad_norm": 0.9102849960327148,
770
+ "learning_rate": 0.0002,
771
+ "loss": 1.3481,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 4.4,
776
+ "grad_norm": 1.3661117553710938,
777
+ "learning_rate": 0.0002,
778
+ "loss": 1.3171,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 4.44,
783
+ "grad_norm": 0.6796606183052063,
784
+ "learning_rate": 0.0002,
785
+ "loss": 1.3776,
786
+ "step": 11100
787
+ },
788
+ {
789
+ "epoch": 4.48,
790
+ "grad_norm": 1.2240846157073975,
791
+ "learning_rate": 0.0002,
792
+ "loss": 1.3756,
793
+ "step": 11200
794
+ },
795
+ {
796
+ "epoch": 4.52,
797
+ "grad_norm": 0.7911117672920227,
798
+ "learning_rate": 0.0002,
799
+ "loss": 1.3484,
800
+ "step": 11300
801
+ },
802
+ {
803
+ "epoch": 4.5600000000000005,
804
+ "grad_norm": 0.6849353313446045,
805
+ "learning_rate": 0.0002,
806
+ "loss": 1.3985,
807
+ "step": 11400
808
+ },
809
+ {
810
+ "epoch": 4.6,
811
+ "grad_norm": 1.292270541191101,
812
+ "learning_rate": 0.0002,
813
+ "loss": 1.3338,
814
+ "step": 11500
815
+ },
816
+ {
817
+ "epoch": 4.64,
818
+ "grad_norm": 1.0751451253890991,
819
+ "learning_rate": 0.0002,
820
+ "loss": 1.4044,
821
+ "step": 11600
822
+ },
823
+ {
824
+ "epoch": 4.68,
825
+ "grad_norm": 1.391108512878418,
826
+ "learning_rate": 0.0002,
827
+ "loss": 1.4003,
828
+ "step": 11700
829
+ },
830
+ {
831
+ "epoch": 4.72,
832
+ "grad_norm": 0.8339885473251343,
833
+ "learning_rate": 0.0002,
834
+ "loss": 1.389,
835
+ "step": 11800
836
+ },
837
+ {
838
+ "epoch": 4.76,
839
+ "grad_norm": 0.9836968779563904,
840
+ "learning_rate": 0.0002,
841
+ "loss": 1.3732,
842
+ "step": 11900
843
+ },
844
+ {
845
+ "epoch": 4.8,
846
+ "grad_norm": 1.3942408561706543,
847
+ "learning_rate": 0.0002,
848
+ "loss": 1.3763,
849
+ "step": 12000
850
+ },
851
+ {
852
+ "epoch": 4.84,
853
+ "grad_norm": 0.8473936915397644,
854
+ "learning_rate": 0.0002,
855
+ "loss": 1.3675,
856
+ "step": 12100
857
+ },
858
+ {
859
+ "epoch": 4.88,
860
+ "grad_norm": 1.1180263757705688,
861
+ "learning_rate": 0.0002,
862
+ "loss": 1.3018,
863
+ "step": 12200
864
+ },
865
+ {
866
+ "epoch": 4.92,
867
+ "grad_norm": 1.0825896263122559,
868
+ "learning_rate": 0.0002,
869
+ "loss": 1.3935,
870
+ "step": 12300
871
+ },
872
+ {
873
+ "epoch": 4.96,
874
+ "grad_norm": 1.7957453727722168,
875
+ "learning_rate": 0.0002,
876
+ "loss": 1.4167,
877
+ "step": 12400
878
+ },
879
+ {
880
+ "epoch": 5.0,
881
+ "grad_norm": 1.4984807968139648,
882
+ "learning_rate": 0.0002,
883
+ "loss": 1.3562,
884
+ "step": 12500
885
+ },
886
+ {
887
+ "epoch": 5.04,
888
+ "grad_norm": 1.2871723175048828,
889
+ "learning_rate": 0.0002,
890
+ "loss": 1.2327,
891
+ "step": 12600
892
+ },
893
+ {
894
+ "epoch": 5.08,
895
+ "grad_norm": 0.5957996249198914,
896
+ "learning_rate": 0.0002,
897
+ "loss": 1.1613,
898
+ "step": 12700
899
+ },
900
+ {
901
+ "epoch": 5.12,
902
+ "grad_norm": 1.0731712579727173,
903
+ "learning_rate": 0.0002,
904
+ "loss": 1.2683,
905
+ "step": 12800
906
+ },
907
+ {
908
+ "epoch": 5.16,
909
+ "grad_norm": 1.2785401344299316,
910
+ "learning_rate": 0.0002,
911
+ "loss": 1.2215,
912
+ "step": 12900
913
+ },
914
+ {
915
+ "epoch": 5.2,
916
+ "grad_norm": 0.6945757269859314,
917
+ "learning_rate": 0.0002,
918
+ "loss": 1.2665,
919
+ "step": 13000
920
+ },
921
+ {
922
+ "epoch": 5.24,
923
+ "grad_norm": 0.8779969215393066,
924
+ "learning_rate": 0.0002,
925
+ "loss": 1.2028,
926
+ "step": 13100
927
+ },
928
+ {
929
+ "epoch": 5.28,
930
+ "grad_norm": 0.9905422329902649,
931
+ "learning_rate": 0.0002,
932
+ "loss": 1.2691,
933
+ "step": 13200
934
+ },
935
+ {
936
+ "epoch": 5.32,
937
+ "grad_norm": 0.7267619967460632,
938
+ "learning_rate": 0.0002,
939
+ "loss": 1.2794,
940
+ "step": 13300
941
+ },
942
+ {
943
+ "epoch": 5.36,
944
+ "grad_norm": 1.1280577182769775,
945
+ "learning_rate": 0.0002,
946
+ "loss": 1.2608,
947
+ "step": 13400
948
+ },
949
+ {
950
+ "epoch": 5.4,
951
+ "grad_norm": 1.3053045272827148,
952
+ "learning_rate": 0.0002,
953
+ "loss": 1.253,
954
+ "step": 13500
955
+ },
956
+ {
957
+ "epoch": 5.44,
958
+ "grad_norm": 1.1373580694198608,
959
+ "learning_rate": 0.0002,
960
+ "loss": 1.2236,
961
+ "step": 13600
962
+ },
963
+ {
964
+ "epoch": 5.48,
965
+ "grad_norm": 0.9823132753372192,
966
+ "learning_rate": 0.0002,
967
+ "loss": 1.2841,
968
+ "step": 13700
969
+ },
970
+ {
971
+ "epoch": 5.52,
972
+ "grad_norm": 1.0225436687469482,
973
+ "learning_rate": 0.0002,
974
+ "loss": 1.2052,
975
+ "step": 13800
976
+ },
977
+ {
978
+ "epoch": 5.5600000000000005,
979
+ "grad_norm": 1.6617635488510132,
980
+ "learning_rate": 0.0002,
981
+ "loss": 1.2314,
982
+ "step": 13900
983
+ },
984
+ {
985
+ "epoch": 5.6,
986
+ "grad_norm": 1.0195096731185913,
987
+ "learning_rate": 0.0002,
988
+ "loss": 1.2959,
989
+ "step": 14000
990
+ },
991
+ {
992
+ "epoch": 5.64,
993
+ "grad_norm": 1.3563017845153809,
994
+ "learning_rate": 0.0002,
995
+ "loss": 1.2683,
996
+ "step": 14100
997
+ },
998
+ {
999
+ "epoch": 5.68,
1000
+ "grad_norm": 2.1966164112091064,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 1.2247,
1003
+ "step": 14200
1004
+ },
1005
+ {
1006
+ "epoch": 5.72,
1007
+ "grad_norm": 1.057099461555481,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 1.2577,
1010
+ "step": 14300
1011
+ },
1012
+ {
1013
+ "epoch": 5.76,
1014
+ "grad_norm": 1.2523263692855835,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 1.2865,
1017
+ "step": 14400
1018
+ },
1019
+ {
1020
+ "epoch": 5.8,
1021
+ "grad_norm": 1.7607208490371704,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 1.2205,
1024
+ "step": 14500
1025
+ },
1026
+ {
1027
+ "epoch": 5.84,
1028
+ "grad_norm": 1.9455257654190063,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 1.2829,
1031
+ "step": 14600
1032
+ },
1033
+ {
1034
+ "epoch": 5.88,
1035
+ "grad_norm": 1.0618771314620972,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 1.3037,
1038
+ "step": 14700
1039
+ },
1040
+ {
1041
+ "epoch": 5.92,
1042
+ "grad_norm": 1.0242942571640015,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 1.2165,
1045
+ "step": 14800
1046
+ },
1047
+ {
1048
+ "epoch": 5.96,
1049
+ "grad_norm": 1.2692897319793701,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 1.2873,
1052
+ "step": 14900
1053
+ },
1054
+ {
1055
+ "epoch": 6.0,
1056
+ "grad_norm": 1.0533056259155273,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 1.2528,
1059
+ "step": 15000
1060
+ },
1061
+ {
1062
+ "epoch": 6.04,
1063
+ "grad_norm": 0.8311458230018616,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 1.0705,
1066
+ "step": 15100
1067
+ },
1068
+ {
1069
+ "epoch": 6.08,
1070
+ "grad_norm": 1.0614266395568848,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 1.0803,
1073
+ "step": 15200
1074
+ },
1075
+ {
1076
+ "epoch": 6.12,
1077
+ "grad_norm": 1.4157719612121582,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 1.0864,
1080
+ "step": 15300
1081
+ },
1082
+ {
1083
+ "epoch": 6.16,
1084
+ "grad_norm": 1.0785095691680908,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 1.1076,
1087
+ "step": 15400
1088
+ },
1089
+ {
1090
+ "epoch": 6.2,
1091
+ "grad_norm": 1.3798463344573975,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 1.1038,
1094
+ "step": 15500
1095
+ },
1096
+ {
1097
+ "epoch": 6.24,
1098
+ "grad_norm": 0.9821926355361938,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 1.1482,
1101
+ "step": 15600
1102
+ },
1103
+ {
1104
+ "epoch": 6.28,
1105
+ "grad_norm": 2.189770221710205,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 1.1154,
1108
+ "step": 15700
1109
+ },
1110
+ {
1111
+ "epoch": 6.32,
1112
+ "grad_norm": 5.5393500328063965,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 1.1186,
1115
+ "step": 15800
1116
+ },
1117
+ {
1118
+ "epoch": 6.36,
1119
+ "grad_norm": 1.2127723693847656,
1120
+ "learning_rate": 0.0002,
1121
+ "loss": 1.1888,
1122
+ "step": 15900
1123
+ },
1124
+ {
1125
+ "epoch": 6.4,
1126
+ "grad_norm": 2.876635789871216,
1127
+ "learning_rate": 0.0002,
1128
+ "loss": 1.1029,
1129
+ "step": 16000
1130
+ },
1131
+ {
1132
+ "epoch": 6.44,
1133
+ "grad_norm": 1.3155653476715088,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 1.1092,
1136
+ "step": 16100
1137
+ },
1138
+ {
1139
+ "epoch": 6.48,
1140
+ "grad_norm": 1.1871975660324097,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 1.1488,
1143
+ "step": 16200
1144
+ },
1145
+ {
1146
+ "epoch": 6.52,
1147
+ "grad_norm": 1.6706851720809937,
1148
+ "learning_rate": 0.0002,
1149
+ "loss": 1.153,
1150
+ "step": 16300
1151
+ },
1152
+ {
1153
+ "epoch": 6.5600000000000005,
1154
+ "grad_norm": 2.3989503383636475,
1155
+ "learning_rate": 0.0002,
1156
+ "loss": 1.1049,
1157
+ "step": 16400
1158
+ },
1159
+ {
1160
+ "epoch": 6.6,
1161
+ "grad_norm": 1.0962737798690796,
1162
+ "learning_rate": 0.0002,
1163
+ "loss": 1.182,
1164
+ "step": 16500
1165
+ },
1166
+ {
1167
+ "epoch": 6.64,
1168
+ "grad_norm": 1.2321207523345947,
1169
+ "learning_rate": 0.0002,
1170
+ "loss": 1.1196,
1171
+ "step": 16600
1172
+ },
1173
+ {
1174
+ "epoch": 6.68,
1175
+ "grad_norm": 1.6745890378952026,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 1.1776,
1178
+ "step": 16700
1179
+ },
1180
+ {
1181
+ "epoch": 6.72,
1182
+ "grad_norm": 3.3587148189544678,
1183
+ "learning_rate": 0.0002,
1184
+ "loss": 1.1335,
1185
+ "step": 16800
1186
+ },
1187
+ {
1188
+ "epoch": 6.76,
1189
+ "grad_norm": 1.2802035808563232,
1190
+ "learning_rate": 0.0002,
1191
+ "loss": 1.2144,
1192
+ "step": 16900
1193
+ },
1194
+ {
1195
+ "epoch": 6.8,
1196
+ "grad_norm": 1.5999842882156372,
1197
+ "learning_rate": 0.0002,
1198
+ "loss": 1.1143,
1199
+ "step": 17000
1200
+ },
1201
+ {
1202
+ "epoch": 6.84,
1203
+ "grad_norm": 1.5529465675354004,
1204
+ "learning_rate": 0.0002,
1205
+ "loss": 1.1503,
1206
+ "step": 17100
1207
+ },
1208
+ {
1209
+ "epoch": 6.88,
1210
+ "grad_norm": 0.9041572213172913,
1211
+ "learning_rate": 0.0002,
1212
+ "loss": 1.1681,
1213
+ "step": 17200
1214
+ },
1215
+ {
1216
+ "epoch": 6.92,
1217
+ "grad_norm": 1.2176377773284912,
1218
+ "learning_rate": 0.0002,
1219
+ "loss": 1.1284,
1220
+ "step": 17300
1221
+ },
1222
+ {
1223
+ "epoch": 6.96,
1224
+ "grad_norm": 1.1047685146331787,
1225
+ "learning_rate": 0.0002,
1226
+ "loss": 1.1622,
1227
+ "step": 17400
1228
+ },
1229
+ {
1230
+ "epoch": 7.0,
1231
+ "grad_norm": 2.3316566944122314,
1232
+ "learning_rate": 0.0002,
1233
+ "loss": 1.149,
1234
+ "step": 17500
1235
+ },
1236
+ {
1237
+ "epoch": 7.04,
1238
+ "grad_norm": 0.9057099223136902,
1239
+ "learning_rate": 0.0002,
1240
+ "loss": 0.9952,
1241
+ "step": 17600
1242
+ },
1243
+ {
1244
+ "epoch": 7.08,
1245
+ "grad_norm": 2.2556183338165283,
1246
+ "learning_rate": 0.0002,
1247
+ "loss": 0.9667,
1248
+ "step": 17700
1249
+ },
1250
+ {
1251
+ "epoch": 7.12,
1252
+ "grad_norm": 1.2181649208068848,
1253
+ "learning_rate": 0.0002,
1254
+ "loss": 0.9606,
1255
+ "step": 17800
1256
+ },
1257
+ {
1258
+ "epoch": 7.16,
1259
+ "grad_norm": 1.1756635904312134,
1260
+ "learning_rate": 0.0002,
1261
+ "loss": 1.0176,
1262
+ "step": 17900
1263
+ },
1264
+ {
1265
+ "epoch": 7.2,
1266
+ "grad_norm": 1.3955613374710083,
1267
+ "learning_rate": 0.0002,
1268
+ "loss": 1.0423,
1269
+ "step": 18000
1270
+ },
1271
+ {
1272
+ "epoch": 7.24,
1273
+ "grad_norm": 2.0451719760894775,
1274
+ "learning_rate": 0.0002,
1275
+ "loss": 1.0152,
1276
+ "step": 18100
1277
+ },
1278
+ {
1279
+ "epoch": 7.28,
1280
+ "grad_norm": 1.8395252227783203,
1281
+ "learning_rate": 0.0002,
1282
+ "loss": 0.9896,
1283
+ "step": 18200
1284
+ },
1285
+ {
1286
+ "epoch": 7.32,
1287
+ "grad_norm": 0.8587050437927246,
1288
+ "learning_rate": 0.0002,
1289
+ "loss": 0.9976,
1290
+ "step": 18300
1291
+ },
1292
+ {
1293
+ "epoch": 7.36,
1294
+ "grad_norm": 1.848895788192749,
1295
+ "learning_rate": 0.0002,
1296
+ "loss": 0.9711,
1297
+ "step": 18400
1298
+ },
1299
+ {
1300
+ "epoch": 7.4,
1301
+ "grad_norm": 0.8069963455200195,
1302
+ "learning_rate": 0.0002,
1303
+ "loss": 1.02,
1304
+ "step": 18500
1305
+ },
1306
+ {
1307
+ "epoch": 7.44,
1308
+ "grad_norm": 1.0655219554901123,
1309
+ "learning_rate": 0.0002,
1310
+ "loss": 1.0069,
1311
+ "step": 18600
1312
+ },
1313
+ {
1314
+ "epoch": 7.48,
1315
+ "grad_norm": 1.474328637123108,
1316
+ "learning_rate": 0.0002,
1317
+ "loss": 1.0311,
1318
+ "step": 18700
1319
+ },
1320
+ {
1321
+ "epoch": 7.52,
1322
+ "grad_norm": 1.3253296613693237,
1323
+ "learning_rate": 0.0002,
1324
+ "loss": 1.0158,
1325
+ "step": 18800
1326
+ },
1327
+ {
1328
+ "epoch": 7.5600000000000005,
1329
+ "grad_norm": 1.1345421075820923,
1330
+ "learning_rate": 0.0002,
1331
+ "loss": 1.0391,
1332
+ "step": 18900
1333
+ },
1334
+ {
1335
+ "epoch": 7.6,
1336
+ "grad_norm": 1.0736902952194214,
1337
+ "learning_rate": 0.0002,
1338
+ "loss": 1.0498,
1339
+ "step": 19000
1340
+ },
1341
+ {
1342
+ "epoch": 7.64,
1343
+ "grad_norm": 1.6537193059921265,
1344
+ "learning_rate": 0.0002,
1345
+ "loss": 1.0235,
1346
+ "step": 19100
1347
+ },
1348
+ {
1349
+ "epoch": 7.68,
1350
+ "grad_norm": 1.3010786771774292,
1351
+ "learning_rate": 0.0002,
1352
+ "loss": 1.0307,
1353
+ "step": 19200
1354
+ },
1355
+ {
1356
+ "epoch": 7.72,
1357
+ "grad_norm": 0.9209179282188416,
1358
+ "learning_rate": 0.0002,
1359
+ "loss": 1.0111,
1360
+ "step": 19300
1361
+ },
1362
+ {
1363
+ "epoch": 7.76,
1364
+ "grad_norm": 5.0836310386657715,
1365
+ "learning_rate": 0.0002,
1366
+ "loss": 1.059,
1367
+ "step": 19400
1368
+ },
1369
+ {
1370
+ "epoch": 7.8,
1371
+ "grad_norm": 1.7362360954284668,
1372
+ "learning_rate": 0.0002,
1373
+ "loss": 1.0704,
1374
+ "step": 19500
1375
+ },
1376
+ {
1377
+ "epoch": 7.84,
1378
+ "grad_norm": 1.692413330078125,
1379
+ "learning_rate": 0.0002,
1380
+ "loss": 1.0618,
1381
+ "step": 19600
1382
+ },
1383
+ {
1384
+ "epoch": 7.88,
1385
+ "grad_norm": 3.538470506668091,
1386
+ "learning_rate": 0.0002,
1387
+ "loss": 1.0778,
1388
+ "step": 19700
1389
+ },
1390
+ {
1391
+ "epoch": 7.92,
1392
+ "grad_norm": 2.578237533569336,
1393
+ "learning_rate": 0.0002,
1394
+ "loss": 1.1153,
1395
+ "step": 19800
1396
+ },
1397
+ {
1398
+ "epoch": 7.96,
1399
+ "grad_norm": 1.356609582901001,
1400
+ "learning_rate": 0.0002,
1401
+ "loss": 1.0597,
1402
+ "step": 19900
1403
+ },
1404
+ {
1405
+ "epoch": 8.0,
1406
+ "grad_norm": 0.89506995677948,
1407
+ "learning_rate": 0.0002,
1408
+ "loss": 1.0892,
1409
+ "step": 20000
1410
+ },
1411
+ {
1412
+ "epoch": 8.04,
1413
+ "grad_norm": 1.5506243705749512,
1414
+ "learning_rate": 0.0002,
1415
+ "loss": 0.8659,
1416
+ "step": 20100
1417
+ },
1418
+ {
1419
+ "epoch": 8.08,
1420
+ "grad_norm": 1.69996178150177,
1421
+ "learning_rate": 0.0002,
1422
+ "loss": 0.9142,
1423
+ "step": 20200
1424
+ },
1425
+ {
1426
+ "epoch": 8.12,
1427
+ "grad_norm": 2.0094783306121826,
1428
+ "learning_rate": 0.0002,
1429
+ "loss": 0.8807,
1430
+ "step": 20300
1431
+ },
1432
+ {
1433
+ "epoch": 8.16,
1434
+ "grad_norm": 1.6503652334213257,
1435
+ "learning_rate": 0.0002,
1436
+ "loss": 0.857,
1437
+ "step": 20400
1438
+ },
1439
+ {
1440
+ "epoch": 8.2,
1441
+ "grad_norm": 0.933527410030365,
1442
+ "learning_rate": 0.0002,
1443
+ "loss": 0.8855,
1444
+ "step": 20500
1445
+ },
1446
+ {
1447
+ "epoch": 8.24,
1448
+ "grad_norm": 1.6827526092529297,
1449
+ "learning_rate": 0.0002,
1450
+ "loss": 0.9295,
1451
+ "step": 20600
1452
+ },
1453
+ {
1454
+ "epoch": 8.28,
1455
+ "grad_norm": 2.89079213142395,
1456
+ "learning_rate": 0.0002,
1457
+ "loss": 0.9146,
1458
+ "step": 20700
1459
+ },
1460
+ {
1461
+ "epoch": 8.32,
1462
+ "grad_norm": 1.0603892803192139,
1463
+ "learning_rate": 0.0002,
1464
+ "loss": 0.9279,
1465
+ "step": 20800
1466
+ },
1467
+ {
1468
+ "epoch": 8.36,
1469
+ "grad_norm": 3.3014211654663086,
1470
+ "learning_rate": 0.0002,
1471
+ "loss": 0.9406,
1472
+ "step": 20900
1473
+ },
1474
+ {
1475
+ "epoch": 8.4,
1476
+ "grad_norm": 0.8049854040145874,
1477
+ "learning_rate": 0.0002,
1478
+ "loss": 0.907,
1479
+ "step": 21000
1480
+ },
1481
+ {
1482
+ "epoch": 8.44,
1483
+ "grad_norm": 2.991314649581909,
1484
+ "learning_rate": 0.0002,
1485
+ "loss": 0.9721,
1486
+ "step": 21100
1487
+ },
1488
+ {
1489
+ "epoch": 8.48,
1490
+ "grad_norm": 1.043578028678894,
1491
+ "learning_rate": 0.0002,
1492
+ "loss": 0.9557,
1493
+ "step": 21200
1494
+ },
1495
+ {
1496
+ "epoch": 8.52,
1497
+ "grad_norm": 1.6888822317123413,
1498
+ "learning_rate": 0.0002,
1499
+ "loss": 0.9477,
1500
+ "step": 21300
1501
+ },
1502
+ {
1503
+ "epoch": 8.56,
1504
+ "grad_norm": 1.4089540243148804,
1505
+ "learning_rate": 0.0002,
1506
+ "loss": 0.9424,
1507
+ "step": 21400
1508
+ },
1509
+ {
1510
+ "epoch": 8.6,
1511
+ "grad_norm": 7.123160362243652,
1512
+ "learning_rate": 0.0002,
1513
+ "loss": 0.9232,
1514
+ "step": 21500
1515
+ },
1516
+ {
1517
+ "epoch": 8.64,
1518
+ "grad_norm": 1.149699091911316,
1519
+ "learning_rate": 0.0002,
1520
+ "loss": 0.9189,
1521
+ "step": 21600
1522
+ },
1523
+ {
1524
+ "epoch": 8.68,
1525
+ "grad_norm": 1.3870540857315063,
1526
+ "learning_rate": 0.0002,
1527
+ "loss": 0.9318,
1528
+ "step": 21700
1529
+ },
1530
+ {
1531
+ "epoch": 8.72,
1532
+ "grad_norm": 1.4124248027801514,
1533
+ "learning_rate": 0.0002,
1534
+ "loss": 0.9657,
1535
+ "step": 21800
1536
+ },
1537
+ {
1538
+ "epoch": 8.76,
1539
+ "grad_norm": 0.6599737405776978,
1540
+ "learning_rate": 0.0002,
1541
+ "loss": 0.9493,
1542
+ "step": 21900
1543
+ },
1544
+ {
1545
+ "epoch": 8.8,
1546
+ "grad_norm": 1.0088489055633545,
1547
+ "learning_rate": 0.0002,
1548
+ "loss": 0.9739,
1549
+ "step": 22000
1550
+ },
1551
+ {
1552
+ "epoch": 8.84,
1553
+ "grad_norm": 0.7540724873542786,
1554
+ "learning_rate": 0.0002,
1555
+ "loss": 0.9492,
1556
+ "step": 22100
1557
+ },
1558
+ {
1559
+ "epoch": 8.88,
1560
+ "grad_norm": 1.0838185548782349,
1561
+ "learning_rate": 0.0002,
1562
+ "loss": 1.0105,
1563
+ "step": 22200
1564
+ },
1565
+ {
1566
+ "epoch": 8.92,
1567
+ "grad_norm": 0.8989962935447693,
1568
+ "learning_rate": 0.0002,
1569
+ "loss": 0.9256,
1570
+ "step": 22300
1571
+ },
1572
+ {
1573
+ "epoch": 8.96,
1574
+ "grad_norm": 0.9646226167678833,
1575
+ "learning_rate": 0.0002,
1576
+ "loss": 0.9766,
1577
+ "step": 22400
1578
+ },
1579
+ {
1580
+ "epoch": 9.0,
1581
+ "grad_norm": 1.0363638401031494,
1582
+ "learning_rate": 0.0002,
1583
+ "loss": 0.9676,
1584
+ "step": 22500
1585
+ },
1586
+ {
1587
+ "epoch": 9.04,
1588
+ "grad_norm": 1.2631175518035889,
1589
+ "learning_rate": 0.0002,
1590
+ "loss": 0.7845,
1591
+ "step": 22600
1592
+ },
1593
+ {
1594
+ "epoch": 9.08,
1595
+ "grad_norm": 1.2183212041854858,
1596
+ "learning_rate": 0.0002,
1597
+ "loss": 0.7785,
1598
+ "step": 22700
1599
+ },
1600
+ {
1601
+ "epoch": 9.12,
1602
+ "grad_norm": 1.4566229581832886,
1603
+ "learning_rate": 0.0002,
1604
+ "loss": 0.7972,
1605
+ "step": 22800
1606
+ },
1607
+ {
1608
+ "epoch": 9.16,
1609
+ "grad_norm": 1.2739365100860596,
1610
+ "learning_rate": 0.0002,
1611
+ "loss": 0.7729,
1612
+ "step": 22900
1613
+ },
1614
+ {
1615
+ "epoch": 9.2,
1616
+ "grad_norm": 1.4455575942993164,
1617
+ "learning_rate": 0.0002,
1618
+ "loss": 0.8359,
1619
+ "step": 23000
1620
+ },
1621
+ {
1622
+ "epoch": 9.24,
1623
+ "grad_norm": 1.1576048135757446,
1624
+ "learning_rate": 0.0002,
1625
+ "loss": 0.8324,
1626
+ "step": 23100
1627
+ },
1628
+ {
1629
+ "epoch": 9.28,
1630
+ "grad_norm": 1.3177443742752075,
1631
+ "learning_rate": 0.0002,
1632
+ "loss": 0.8223,
1633
+ "step": 23200
1634
+ },
1635
+ {
1636
+ "epoch": 9.32,
1637
+ "grad_norm": 4.67700719833374,
1638
+ "learning_rate": 0.0002,
1639
+ "loss": 0.8154,
1640
+ "step": 23300
1641
+ },
1642
+ {
1643
+ "epoch": 9.36,
1644
+ "grad_norm": 1.2279400825500488,
1645
+ "learning_rate": 0.0002,
1646
+ "loss": 0.8047,
1647
+ "step": 23400
1648
+ },
1649
+ {
1650
+ "epoch": 9.4,
1651
+ "grad_norm": 0.6378070712089539,
1652
+ "learning_rate": 0.0002,
1653
+ "loss": 0.8539,
1654
+ "step": 23500
1655
+ },
1656
+ {
1657
+ "epoch": 9.44,
1658
+ "grad_norm": 1.7342982292175293,
1659
+ "learning_rate": 0.0002,
1660
+ "loss": 0.8405,
1661
+ "step": 23600
1662
+ },
1663
+ {
1664
+ "epoch": 9.48,
1665
+ "grad_norm": 1.534493088722229,
1666
+ "learning_rate": 0.0002,
1667
+ "loss": 0.8493,
1668
+ "step": 23700
1669
+ },
1670
+ {
1671
+ "epoch": 9.52,
1672
+ "grad_norm": 1.0669933557510376,
1673
+ "learning_rate": 0.0002,
1674
+ "loss": 0.8931,
1675
+ "step": 23800
1676
+ },
1677
+ {
1678
+ "epoch": 9.56,
1679
+ "grad_norm": 1.2402708530426025,
1680
+ "learning_rate": 0.0002,
1681
+ "loss": 0.8689,
1682
+ "step": 23900
1683
+ },
1684
+ {
1685
+ "epoch": 9.6,
1686
+ "grad_norm": 1.2599835395812988,
1687
+ "learning_rate": 0.0002,
1688
+ "loss": 0.8733,
1689
+ "step": 24000
1690
+ },
1691
+ {
1692
+ "epoch": 9.64,
1693
+ "grad_norm": 2.5779175758361816,
1694
+ "learning_rate": 0.0002,
1695
+ "loss": 0.8934,
1696
+ "step": 24100
1697
+ },
1698
+ {
1699
+ "epoch": 9.68,
1700
+ "grad_norm": 1.8797070980072021,
1701
+ "learning_rate": 0.0002,
1702
+ "loss": 0.8536,
1703
+ "step": 24200
1704
+ },
1705
+ {
1706
+ "epoch": 9.72,
1707
+ "grad_norm": 1.3404995203018188,
1708
+ "learning_rate": 0.0002,
1709
+ "loss": 0.9191,
1710
+ "step": 24300
1711
+ },
1712
+ {
1713
+ "epoch": 9.76,
1714
+ "grad_norm": 1.4789234399795532,
1715
+ "learning_rate": 0.0002,
1716
+ "loss": 0.8198,
1717
+ "step": 24400
1718
+ },
1719
+ {
1720
+ "epoch": 9.8,
1721
+ "grad_norm": 0.6044953465461731,
1722
+ "learning_rate": 0.0002,
1723
+ "loss": 0.8304,
1724
+ "step": 24500
1725
+ },
1726
+ {
1727
+ "epoch": 9.84,
1728
+ "grad_norm": 1.2792354822158813,
1729
+ "learning_rate": 0.0002,
1730
+ "loss": 0.9196,
1731
+ "step": 24600
1732
+ },
1733
+ {
1734
+ "epoch": 9.88,
1735
+ "grad_norm": 2.047617197036743,
1736
+ "learning_rate": 0.0002,
1737
+ "loss": 0.9136,
1738
+ "step": 24700
1739
+ },
1740
+ {
1741
+ "epoch": 9.92,
1742
+ "grad_norm": 5.776161193847656,
1743
+ "learning_rate": 0.0002,
1744
+ "loss": 0.8715,
1745
+ "step": 24800
1746
+ },
1747
+ {
1748
+ "epoch": 9.96,
1749
+ "grad_norm": 1.9059360027313232,
1750
+ "learning_rate": 0.0002,
1751
+ "loss": 0.8712,
1752
+ "step": 24900
1753
+ },
1754
+ {
1755
+ "epoch": 10.0,
1756
+ "grad_norm": 1.1497496366500854,
1757
+ "learning_rate": 0.0002,
1758
+ "loss": 0.8607,
1759
+ "step": 25000
1760
+ },
1761
+ {
1762
+ "epoch": 10.04,
1763
+ "grad_norm": 0.6882659792900085,
1764
+ "learning_rate": 0.0002,
1765
+ "loss": 0.7556,
1766
+ "step": 25100
1767
+ },
1768
+ {
1769
+ "epoch": 10.08,
1770
+ "grad_norm": 0.9709841012954712,
1771
+ "learning_rate": 0.0002,
1772
+ "loss": 0.787,
1773
+ "step": 25200
1774
+ },
1775
+ {
1776
+ "epoch": 10.12,
1777
+ "grad_norm": 0.9609636664390564,
1778
+ "learning_rate": 0.0002,
1779
+ "loss": 0.701,
1780
+ "step": 25300
1781
+ },
1782
+ {
1783
+ "epoch": 10.16,
1784
+ "grad_norm": 1.397544026374817,
1785
+ "learning_rate": 0.0002,
1786
+ "loss": 0.7548,
1787
+ "step": 25400
1788
+ },
1789
+ {
1790
+ "epoch": 10.2,
1791
+ "grad_norm": 2.043348550796509,
1792
+ "learning_rate": 0.0002,
1793
+ "loss": 0.7357,
1794
+ "step": 25500
1795
+ },
1796
+ {
1797
+ "epoch": 10.24,
1798
+ "grad_norm": 0.7744215726852417,
1799
+ "learning_rate": 0.0002,
1800
+ "loss": 0.7481,
1801
+ "step": 25600
1802
+ },
1803
+ {
1804
+ "epoch": 10.28,
1805
+ "grad_norm": 0.7471018433570862,
1806
+ "learning_rate": 0.0002,
1807
+ "loss": 0.7206,
1808
+ "step": 25700
1809
+ },
1810
+ {
1811
+ "epoch": 10.32,
1812
+ "grad_norm": 1.5226207971572876,
1813
+ "learning_rate": 0.0002,
1814
+ "loss": 0.7199,
1815
+ "step": 25800
1816
+ },
1817
+ {
1818
+ "epoch": 10.36,
1819
+ "grad_norm": 0.9229708313941956,
1820
+ "learning_rate": 0.0002,
1821
+ "loss": 0.7449,
1822
+ "step": 25900
1823
+ },
1824
+ {
1825
+ "epoch": 10.4,
1826
+ "grad_norm": 0.8783457279205322,
1827
+ "learning_rate": 0.0002,
1828
+ "loss": 0.8026,
1829
+ "step": 26000
1830
+ },
1831
+ {
1832
+ "epoch": 10.44,
1833
+ "grad_norm": 1.858168125152588,
1834
+ "learning_rate": 0.0002,
1835
+ "loss": 0.758,
1836
+ "step": 26100
1837
+ },
1838
+ {
1839
+ "epoch": 10.48,
1840
+ "grad_norm": 9.689515113830566,
1841
+ "learning_rate": 0.0002,
1842
+ "loss": 0.7394,
1843
+ "step": 26200
1844
+ },
1845
+ {
1846
+ "epoch": 10.52,
1847
+ "grad_norm": 1.7214679718017578,
1848
+ "learning_rate": 0.0002,
1849
+ "loss": 0.7704,
1850
+ "step": 26300
1851
+ },
1852
+ {
1853
+ "epoch": 10.56,
1854
+ "grad_norm": 4.615940570831299,
1855
+ "learning_rate": 0.0002,
1856
+ "loss": 0.7957,
1857
+ "step": 26400
1858
+ },
1859
+ {
1860
+ "epoch": 10.6,
1861
+ "grad_norm": 1.4114075899124146,
1862
+ "learning_rate": 0.0002,
1863
+ "loss": 0.7613,
1864
+ "step": 26500
1865
+ },
1866
+ {
1867
+ "epoch": 10.64,
1868
+ "grad_norm": 1.1253297328948975,
1869
+ "learning_rate": 0.0002,
1870
+ "loss": 0.8119,
1871
+ "step": 26600
1872
+ },
1873
+ {
1874
+ "epoch": 10.68,
1875
+ "grad_norm": 1.9775581359863281,
1876
+ "learning_rate": 0.0002,
1877
+ "loss": 0.8083,
1878
+ "step": 26700
1879
+ },
1880
+ {
1881
+ "epoch": 10.72,
1882
+ "grad_norm": 0.6344081163406372,
1883
+ "learning_rate": 0.0002,
1884
+ "loss": 0.8078,
1885
+ "step": 26800
1886
+ },
1887
+ {
1888
+ "epoch": 10.76,
1889
+ "grad_norm": 1.287255048751831,
1890
+ "learning_rate": 0.0002,
1891
+ "loss": 0.7732,
1892
+ "step": 26900
1893
+ },
1894
+ {
1895
+ "epoch": 10.8,
1896
+ "grad_norm": 0.826394259929657,
1897
+ "learning_rate": 0.0002,
1898
+ "loss": 0.7874,
1899
+ "step": 27000
1900
+ },
1901
+ {
1902
+ "epoch": 10.84,
1903
+ "grad_norm": 1.9858311414718628,
1904
+ "learning_rate": 0.0002,
1905
+ "loss": 0.7672,
1906
+ "step": 27100
1907
+ },
1908
+ {
1909
+ "epoch": 10.88,
1910
+ "grad_norm": 2.411587715148926,
1911
+ "learning_rate": 0.0002,
1912
+ "loss": 0.7926,
1913
+ "step": 27200
1914
+ },
1915
+ {
1916
+ "epoch": 10.92,
1917
+ "grad_norm": 1.1117106676101685,
1918
+ "learning_rate": 0.0002,
1919
+ "loss": 0.8031,
1920
+ "step": 27300
1921
+ },
1922
+ {
1923
+ "epoch": 10.96,
1924
+ "grad_norm": 0.9955012798309326,
1925
+ "learning_rate": 0.0002,
1926
+ "loss": 0.8018,
1927
+ "step": 27400
1928
+ },
1929
+ {
1930
+ "epoch": 11.0,
1931
+ "grad_norm": 6.443946838378906,
1932
+ "learning_rate": 0.0002,
1933
+ "loss": 0.7974,
1934
+ "step": 27500
1935
+ },
1936
+ {
1937
+ "epoch": 11.04,
1938
+ "grad_norm": 0.9066771864891052,
1939
+ "learning_rate": 0.0002,
1940
+ "loss": 0.6354,
1941
+ "step": 27600
1942
+ },
1943
+ {
1944
+ "epoch": 11.08,
1945
+ "grad_norm": 1.2832303047180176,
1946
+ "learning_rate": 0.0002,
1947
+ "loss": 0.6669,
1948
+ "step": 27700
1949
+ },
1950
+ {
1951
+ "epoch": 11.12,
1952
+ "grad_norm": 1.3047817945480347,
1953
+ "learning_rate": 0.0002,
1954
+ "loss": 0.6408,
1955
+ "step": 27800
1956
+ },
1957
+ {
1958
+ "epoch": 11.16,
1959
+ "grad_norm": 1.2970690727233887,
1960
+ "learning_rate": 0.0002,
1961
+ "loss": 0.6777,
1962
+ "step": 27900
1963
+ },
1964
+ {
1965
+ "epoch": 11.2,
1966
+ "grad_norm": 1.2775633335113525,
1967
+ "learning_rate": 0.0002,
1968
+ "loss": 0.6366,
1969
+ "step": 28000
1970
+ },
1971
+ {
1972
+ "epoch": 11.24,
1973
+ "grad_norm": 1.1797577142715454,
1974
+ "learning_rate": 0.0002,
1975
+ "loss": 0.6618,
1976
+ "step": 28100
1977
+ },
1978
+ {
1979
+ "epoch": 11.28,
1980
+ "grad_norm": 0.4641984701156616,
1981
+ "learning_rate": 0.0002,
1982
+ "loss": 0.714,
1983
+ "step": 28200
1984
+ },
1985
+ {
1986
+ "epoch": 11.32,
1987
+ "grad_norm": 5.440238952636719,
1988
+ "learning_rate": 0.0002,
1989
+ "loss": 0.707,
1990
+ "step": 28300
1991
+ },
1992
+ {
1993
+ "epoch": 11.36,
1994
+ "grad_norm": 2.7342915534973145,
1995
+ "learning_rate": 0.0002,
1996
+ "loss": 0.7155,
1997
+ "step": 28400
1998
+ },
1999
+ {
2000
+ "epoch": 11.4,
2001
+ "grad_norm": 1.025922179222107,
2002
+ "learning_rate": 0.0002,
2003
+ "loss": 0.6761,
2004
+ "step": 28500
2005
+ },
2006
+ {
2007
+ "epoch": 11.44,
2008
+ "grad_norm": 1.4162850379943848,
2009
+ "learning_rate": 0.0002,
2010
+ "loss": 0.7079,
2011
+ "step": 28600
2012
+ },
2013
+ {
2014
+ "epoch": 11.48,
2015
+ "grad_norm": 1.673281192779541,
2016
+ "learning_rate": 0.0002,
2017
+ "loss": 0.6957,
2018
+ "step": 28700
2019
+ },
2020
+ {
2021
+ "epoch": 11.52,
2022
+ "grad_norm": 1.6640900373458862,
2023
+ "learning_rate": 0.0002,
2024
+ "loss": 0.7616,
2025
+ "step": 28800
2026
+ },
2027
+ {
2028
+ "epoch": 11.56,
2029
+ "grad_norm": 0.5658434629440308,
2030
+ "learning_rate": 0.0002,
2031
+ "loss": 0.6939,
2032
+ "step": 28900
2033
+ },
2034
+ {
2035
+ "epoch": 11.6,
2036
+ "grad_norm": 0.6061828136444092,
2037
+ "learning_rate": 0.0002,
2038
+ "loss": 0.7162,
2039
+ "step": 29000
2040
+ },
2041
+ {
2042
+ "epoch": 11.64,
2043
+ "grad_norm": 1.6504275798797607,
2044
+ "learning_rate": 0.0002,
2045
+ "loss": 0.7266,
2046
+ "step": 29100
2047
+ },
2048
+ {
2049
+ "epoch": 11.68,
2050
+ "grad_norm": 2.936732530593872,
2051
+ "learning_rate": 0.0002,
2052
+ "loss": 0.7053,
2053
+ "step": 29200
2054
+ },
2055
+ {
2056
+ "epoch": 11.72,
2057
+ "grad_norm": 1.2476632595062256,
2058
+ "learning_rate": 0.0002,
2059
+ "loss": 0.6966,
2060
+ "step": 29300
2061
+ },
2062
+ {
2063
+ "epoch": 11.76,
2064
+ "grad_norm": 0.8274354934692383,
2065
+ "learning_rate": 0.0002,
2066
+ "loss": 0.6928,
2067
+ "step": 29400
2068
+ },
2069
+ {
2070
+ "epoch": 11.8,
2071
+ "grad_norm": 1.6214333772659302,
2072
+ "learning_rate": 0.0002,
2073
+ "loss": 0.7288,
2074
+ "step": 29500
2075
+ },
2076
+ {
2077
+ "epoch": 11.84,
2078
+ "grad_norm": 1.2420477867126465,
2079
+ "learning_rate": 0.0002,
2080
+ "loss": 0.7501,
2081
+ "step": 29600
2082
+ },
2083
+ {
2084
+ "epoch": 11.88,
2085
+ "grad_norm": 1.3407083749771118,
2086
+ "learning_rate": 0.0002,
2087
+ "loss": 0.7472,
2088
+ "step": 29700
2089
+ },
2090
+ {
2091
+ "epoch": 11.92,
2092
+ "grad_norm": 2.469486951828003,
2093
+ "learning_rate": 0.0002,
2094
+ "loss": 0.7077,
2095
+ "step": 29800
2096
+ },
2097
+ {
2098
+ "epoch": 11.96,
2099
+ "grad_norm": 2.422231912612915,
2100
+ "learning_rate": 0.0002,
2101
+ "loss": 0.7587,
2102
+ "step": 29900
2103
+ },
2104
+ {
2105
+ "epoch": 12.0,
2106
+ "grad_norm": 2.655271053314209,
2107
+ "learning_rate": 0.0002,
2108
+ "loss": 0.734,
2109
+ "step": 30000
2110
+ },
2111
+ {
2112
+ "epoch": 12.04,
2113
+ "grad_norm": 3.5966265201568604,
2114
+ "learning_rate": 0.0002,
2115
+ "loss": 0.5812,
2116
+ "step": 30100
2117
+ },
2118
+ {
2119
+ "epoch": 12.08,
2120
+ "grad_norm": 0.46480792760849,
2121
+ "learning_rate": 0.0002,
2122
+ "loss": 0.589,
2123
+ "step": 30200
2124
+ },
2125
+ {
2126
+ "epoch": 12.12,
2127
+ "grad_norm": 0.8438324928283691,
2128
+ "learning_rate": 0.0002,
2129
+ "loss": 0.6005,
2130
+ "step": 30300
2131
+ },
2132
+ {
2133
+ "epoch": 12.16,
2134
+ "grad_norm": 1.9844694137573242,
2135
+ "learning_rate": 0.0002,
2136
+ "loss": 0.6312,
2137
+ "step": 30400
2138
+ },
2139
+ {
2140
+ "epoch": 12.2,
2141
+ "grad_norm": 1.1500381231307983,
2142
+ "learning_rate": 0.0002,
2143
+ "loss": 0.621,
2144
+ "step": 30500
2145
+ },
2146
+ {
2147
+ "epoch": 12.24,
2148
+ "grad_norm": 1.3909460306167603,
2149
+ "learning_rate": 0.0002,
2150
+ "loss": 0.6353,
2151
+ "step": 30600
2152
+ },
2153
+ {
2154
+ "epoch": 12.28,
2155
+ "grad_norm": 3.504803419113159,
2156
+ "learning_rate": 0.0002,
2157
+ "loss": 0.6191,
2158
+ "step": 30700
2159
+ },
2160
+ {
2161
+ "epoch": 12.32,
2162
+ "grad_norm": 1.116080641746521,
2163
+ "learning_rate": 0.0002,
2164
+ "loss": 0.628,
2165
+ "step": 30800
2166
+ },
2167
+ {
2168
+ "epoch": 12.36,
2169
+ "grad_norm": 0.9176204800605774,
2170
+ "learning_rate": 0.0002,
2171
+ "loss": 0.6314,
2172
+ "step": 30900
2173
+ },
2174
+ {
2175
+ "epoch": 12.4,
2176
+ "grad_norm": 1.0510369539260864,
2177
+ "learning_rate": 0.0002,
2178
+ "loss": 0.6532,
2179
+ "step": 31000
2180
+ },
2181
+ {
2182
+ "epoch": 12.44,
2183
+ "grad_norm": 0.5242018103599548,
2184
+ "learning_rate": 0.0002,
2185
+ "loss": 0.6422,
2186
+ "step": 31100
2187
+ },
2188
+ {
2189
+ "epoch": 12.48,
2190
+ "grad_norm": 5.052489280700684,
2191
+ "learning_rate": 0.0002,
2192
+ "loss": 0.64,
2193
+ "step": 31200
2194
+ },
2195
+ {
2196
+ "epoch": 12.52,
2197
+ "grad_norm": 0.5426860451698303,
2198
+ "learning_rate": 0.0002,
2199
+ "loss": 0.6488,
2200
+ "step": 31300
2201
+ },
2202
+ {
2203
+ "epoch": 12.56,
2204
+ "grad_norm": 0.7503352165222168,
2205
+ "learning_rate": 0.0002,
2206
+ "loss": 0.6764,
2207
+ "step": 31400
2208
+ },
2209
+ {
2210
+ "epoch": 12.6,
2211
+ "grad_norm": 2.2711548805236816,
2212
+ "learning_rate": 0.0002,
2213
+ "loss": 0.6177,
2214
+ "step": 31500
2215
+ },
2216
+ {
2217
+ "epoch": 12.64,
2218
+ "grad_norm": 1.3384021520614624,
2219
+ "learning_rate": 0.0002,
2220
+ "loss": 0.6425,
2221
+ "step": 31600
2222
+ },
2223
+ {
2224
+ "epoch": 12.68,
2225
+ "grad_norm": 1.098314642906189,
2226
+ "learning_rate": 0.0002,
2227
+ "loss": 0.6453,
2228
+ "step": 31700
2229
+ },
2230
+ {
2231
+ "epoch": 12.72,
2232
+ "grad_norm": 0.8752951622009277,
2233
+ "learning_rate": 0.0002,
2234
+ "loss": 0.6724,
2235
+ "step": 31800
2236
+ },
2237
+ {
2238
+ "epoch": 12.76,
2239
+ "grad_norm": 1.700907826423645,
2240
+ "learning_rate": 0.0002,
2241
+ "loss": 0.6707,
2242
+ "step": 31900
2243
+ },
2244
+ {
2245
+ "epoch": 12.8,
2246
+ "grad_norm": 2.7010860443115234,
2247
+ "learning_rate": 0.0002,
2248
+ "loss": 0.6551,
2249
+ "step": 32000
2250
+ },
2251
+ {
2252
+ "epoch": 12.84,
2253
+ "grad_norm": 0.9509829878807068,
2254
+ "learning_rate": 0.0002,
2255
+ "loss": 0.6766,
2256
+ "step": 32100
2257
+ },
2258
+ {
2259
+ "epoch": 12.88,
2260
+ "grad_norm": 1.8936227560043335,
2261
+ "learning_rate": 0.0002,
2262
+ "loss": 0.6889,
2263
+ "step": 32200
2264
+ },
2265
+ {
2266
+ "epoch": 12.92,
2267
+ "grad_norm": 3.870959997177124,
2268
+ "learning_rate": 0.0002,
2269
+ "loss": 0.6526,
2270
+ "step": 32300
2271
+ },
2272
+ {
2273
+ "epoch": 12.96,
2274
+ "grad_norm": 0.8048538565635681,
2275
+ "learning_rate": 0.0002,
2276
+ "loss": 0.6658,
2277
+ "step": 32400
2278
+ },
2279
+ {
2280
+ "epoch": 13.0,
2281
+ "grad_norm": 3.0256259441375732,
2282
+ "learning_rate": 0.0002,
2283
+ "loss": 0.6521,
2284
+ "step": 32500
2285
+ },
2286
+ {
2287
+ "epoch": 13.04,
2288
+ "grad_norm": 0.5219417810440063,
2289
+ "learning_rate": 0.0002,
2290
+ "loss": 0.5415,
2291
+ "step": 32600
2292
+ },
2293
+ {
2294
+ "epoch": 13.08,
2295
+ "grad_norm": 0.6729668378829956,
2296
+ "learning_rate": 0.0002,
2297
+ "loss": 0.5442,
2298
+ "step": 32700
2299
+ },
2300
+ {
2301
+ "epoch": 13.12,
2302
+ "grad_norm": 5.041486740112305,
2303
+ "learning_rate": 0.0002,
2304
+ "loss": 0.5794,
2305
+ "step": 32800
2306
+ },
2307
+ {
2308
+ "epoch": 13.16,
2309
+ "grad_norm": 0.7740932106971741,
2310
+ "learning_rate": 0.0002,
2311
+ "loss": 0.5739,
2312
+ "step": 32900
2313
+ },
2314
+ {
2315
+ "epoch": 13.2,
2316
+ "grad_norm": 2.4038619995117188,
2317
+ "learning_rate": 0.0002,
2318
+ "loss": 0.5527,
2319
+ "step": 33000
2320
+ }
2321
+ ],
2322
+ "logging_steps": 100,
2323
+ "max_steps": 125000,
2324
+ "num_input_tokens_seen": 0,
2325
+ "num_train_epochs": 50,
2326
+ "save_steps": 1000,
2327
+ "stateful_callbacks": {
2328
+ "TrainerControl": {
2329
+ "args": {
2330
+ "should_epoch_stop": false,
2331
+ "should_evaluate": false,
2332
+ "should_log": false,
2333
+ "should_save": true,
2334
+ "should_training_stop": false
2335
+ },
2336
+ "attributes": {}
2337
+ }
2338
+ },
2339
+ "total_flos": 8.330326307619963e+17,
2340
+ "train_batch_size": 1,
2341
+ "trial_name": null,
2342
+ "trial_params": null
2343
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac982738137bca95e983e2664b44706868ba9f325f35c6d86a395d9ee7674069
3
+ size 5368