AdithyaSK commited on
Commit
ff71004
·
verified ·
1 Parent(s): 0ab2947

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Llama-2-7b-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 0.9.0
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 256,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "up_proj",
26
+ "v_proj",
27
+ "gate_proj",
28
+ "down_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:adadcf21d4682bd65e146aa45b0113da5a9436e2c85696a3b84df33e917857a8
3
+ size 2558587064
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692821d5c3911ab190d565d9093a0df73deff248e73be37a2c1b0045aeb6f22c
3
+ size 1282290004
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbb40ce992670fb616d9b8f9adb153ecaa93849d405319102e1c8af86942c08
3
+ size 14512
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb93c64d5291ab1cb420ea7d1d20c3876eee37246869e4b0836acc38ddbe4b8
3
+ size 14512
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232ed0aa36eba0b49bab9f931603d38429aa7f1a42e67f5469c47983616a34cf
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,1890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.30042194092827,
5
+ "eval_steps": 500,
6
+ "global_step": 267,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.33328112959861755,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.9029,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 0.341234415769577,
21
+ "learning_rate": 4e-05,
22
+ "loss": 0.9276,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 0.3182106614112854,
28
+ "learning_rate": 6e-05,
29
+ "loss": 0.9148,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 0.22865141928195953,
35
+ "learning_rate": 8e-05,
36
+ "loss": 0.8421,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 0.29670122265815735,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.7984,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "grad_norm": 0.28762516379356384,
49
+ "learning_rate": 0.00012,
50
+ "loss": 0.7625,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "grad_norm": 0.23907965421676636,
56
+ "learning_rate": 0.00014,
57
+ "loss": 0.7226,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01,
62
+ "grad_norm": 0.19532263278961182,
63
+ "learning_rate": 0.00016,
64
+ "loss": 0.7043,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "grad_norm": 0.1425202488899231,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.6784,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.01,
76
+ "grad_norm": 0.10882167518138885,
77
+ "learning_rate": 0.0002,
78
+ "loss": 0.6579,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "grad_norm": 0.11275648325681686,
84
+ "learning_rate": 0.00019999935985220405,
85
+ "loss": 0.6592,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "grad_norm": 0.10155748575925827,
91
+ "learning_rate": 0.00019999743941701188,
92
+ "loss": 0.6554,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "grad_norm": 0.0845816433429718,
98
+ "learning_rate": 0.0001999942387190108,
99
+ "loss": 0.6513,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02,
104
+ "grad_norm": 0.09046202898025513,
105
+ "learning_rate": 0.0001999897577991792,
106
+ "loss": 0.6267,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.02,
111
+ "grad_norm": 0.08296829462051392,
112
+ "learning_rate": 0.00019998399671488612,
113
+ "loss": 0.6434,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.02,
118
+ "grad_norm": 0.07594181597232819,
119
+ "learning_rate": 0.00019997695553989042,
120
+ "loss": 0.6096,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.02,
125
+ "grad_norm": 0.0683172270655632,
126
+ "learning_rate": 0.00019996863436433997,
127
+ "loss": 0.6143,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "grad_norm": 0.05627186596393585,
133
+ "learning_rate": 0.0001999590332947704,
134
+ "loss": 0.6024,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "grad_norm": 0.05644279345870018,
140
+ "learning_rate": 0.00019994815245410384,
141
+ "loss": 0.595,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.02,
146
+ "grad_norm": 0.05661479011178017,
147
+ "learning_rate": 0.00019993599198164715,
148
+ "loss": 0.5759,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.02,
153
+ "grad_norm": 0.04077177122235298,
154
+ "learning_rate": 0.00019992255203309033,
155
+ "loss": 0.582,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.02,
160
+ "grad_norm": 0.04510512948036194,
161
+ "learning_rate": 0.00019990783278050448,
162
+ "loss": 0.5751,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.03,
167
+ "grad_norm": 0.0470162108540535,
168
+ "learning_rate": 0.00019989183441233952,
169
+ "loss": 0.5716,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "grad_norm": 0.04402562975883484,
175
+ "learning_rate": 0.00019987455713342187,
176
+ "loss": 0.564,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.03,
181
+ "grad_norm": 0.045594893395900726,
182
+ "learning_rate": 0.00019985600116495173,
183
+ "loss": 0.5657,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.03,
188
+ "grad_norm": 0.037670280784368515,
189
+ "learning_rate": 0.0001998361667445004,
190
+ "loss": 0.5619,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.03,
195
+ "grad_norm": 0.034366946667432785,
196
+ "learning_rate": 0.00019981505412600706,
197
+ "loss": 0.554,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03,
202
+ "grad_norm": 0.044084370136260986,
203
+ "learning_rate": 0.00019979266357977564,
204
+ "loss": 0.5527,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.03,
209
+ "grad_norm": 0.04839107394218445,
210
+ "learning_rate": 0.0001997689953924713,
211
+ "loss": 0.5534,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.03,
216
+ "grad_norm": 0.04943666234612465,
217
+ "learning_rate": 0.0001997440498671168,
218
+ "loss": 0.5357,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.03,
223
+ "grad_norm": 0.05644814297556877,
224
+ "learning_rate": 0.00019971782732308867,
225
+ "loss": 0.5388,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.04,
230
+ "grad_norm": 0.05796538665890694,
231
+ "learning_rate": 0.00019969032809611287,
232
+ "loss": 0.5327,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.04,
237
+ "grad_norm": 0.05399211496114731,
238
+ "learning_rate": 0.0001996615525382609,
239
+ "loss": 0.5447,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.04,
244
+ "grad_norm": 0.03574652597308159,
245
+ "learning_rate": 0.0001996315010179449,
246
+ "loss": 0.5213,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.04,
251
+ "grad_norm": 0.04394914582371712,
252
+ "learning_rate": 0.00019960017391991314,
253
+ "loss": 0.5247,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04,
258
+ "grad_norm": 0.05197073519229889,
259
+ "learning_rate": 0.00019956757164524516,
260
+ "loss": 0.5253,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04,
265
+ "grad_norm": 0.05605654790997505,
266
+ "learning_rate": 0.00019953369461134634,
267
+ "loss": 0.5289,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.04,
272
+ "grad_norm": 0.05167644843459129,
273
+ "learning_rate": 0.00019949854325194294,
274
+ "loss": 0.5223,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.04,
279
+ "grad_norm": 0.04118728265166283,
280
+ "learning_rate": 0.0001994621180170762,
281
+ "loss": 0.52,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.05,
286
+ "grad_norm": 0.0373263917863369,
287
+ "learning_rate": 0.00019942441937309684,
288
+ "loss": 0.5076,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.05,
293
+ "grad_norm": 0.04870600998401642,
294
+ "learning_rate": 0.0001993854478026589,
295
+ "loss": 0.5287,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.05,
300
+ "grad_norm": 0.05014103651046753,
301
+ "learning_rate": 0.00019934520380471372,
302
+ "loss": 0.5048,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.05,
307
+ "grad_norm": 0.04807833209633827,
308
+ "learning_rate": 0.0001993036878945034,
309
+ "loss": 0.5075,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.05,
314
+ "grad_norm": 0.040045421570539474,
315
+ "learning_rate": 0.0001992609006035543,
316
+ "loss": 0.4954,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05,
321
+ "grad_norm": 0.04202349856495857,
322
+ "learning_rate": 0.00019921684247967028,
323
+ "loss": 0.4953,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.05,
328
+ "grad_norm": 0.041629109531641006,
329
+ "learning_rate": 0.0001991715140869255,
330
+ "loss": 0.501,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.05,
335
+ "grad_norm": 0.04767894372344017,
336
+ "learning_rate": 0.0001991249160056574,
337
+ "loss": 0.4878,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.05,
342
+ "grad_norm": 0.05395263060927391,
343
+ "learning_rate": 0.00019907704883245916,
344
+ "loss": 0.5014,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.06,
349
+ "grad_norm": 0.06040235981345177,
350
+ "learning_rate": 0.00019902791318017205,
351
+ "loss": 0.5043,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.06,
356
+ "grad_norm": 0.06749273091554642,
357
+ "learning_rate": 0.0001989775096778777,
358
+ "loss": 0.4931,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.06,
363
+ "grad_norm": 0.06482889503240585,
364
+ "learning_rate": 0.00019892583897088994,
365
+ "loss": 0.4869,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.06,
370
+ "grad_norm": 0.045358914881944656,
371
+ "learning_rate": 0.0001988729017207465,
372
+ "loss": 0.479,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.06,
377
+ "grad_norm": 0.043360061943531036,
378
+ "learning_rate": 0.00019881869860520073,
379
+ "loss": 0.4953,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.06,
384
+ "grad_norm": 0.060205183923244476,
385
+ "learning_rate": 0.00019876323031821266,
386
+ "loss": 0.4705,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06,
391
+ "grad_norm": 0.05729120969772339,
392
+ "learning_rate": 0.00019870649756994037,
393
+ "loss": 0.4887,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.06,
398
+ "grad_norm": 0.03843148052692413,
399
+ "learning_rate": 0.00019864850108673073,
400
+ "loss": 0.4737,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.06,
405
+ "grad_norm": 0.053673889487981796,
406
+ "learning_rate": 0.00019858924161111015,
407
+ "loss": 0.4817,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.07,
412
+ "grad_norm": 0.05148368701338768,
413
+ "learning_rate": 0.00019852871990177503,
414
+ "loss": 0.4763,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.07,
419
+ "grad_norm": 0.05371672287583351,
420
+ "learning_rate": 0.00019846693673358226,
421
+ "loss": 0.4751,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.07,
426
+ "grad_norm": 0.05490916967391968,
427
+ "learning_rate": 0.00019840389289753896,
428
+ "loss": 0.457,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.07,
433
+ "grad_norm": 0.04629400372505188,
434
+ "learning_rate": 0.00019833958920079255,
435
+ "loss": 0.4692,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.07,
440
+ "grad_norm": 0.051137253642082214,
441
+ "learning_rate": 0.00019827402646662047,
442
+ "loss": 0.4614,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07,
447
+ "grad_norm": 0.051790811121463776,
448
+ "learning_rate": 0.0001982072055344195,
449
+ "loss": 0.4594,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.07,
454
+ "grad_norm": 0.0445956289768219,
455
+ "learning_rate": 0.00019813912725969509,
456
+ "loss": 0.4601,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.07,
461
+ "grad_norm": 0.04766576737165451,
462
+ "learning_rate": 0.0001980697925140504,
463
+ "loss": 0.4631,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.07,
468
+ "grad_norm": 0.04839074984192848,
469
+ "learning_rate": 0.0001979992021851751,
470
+ "loss": 0.4605,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.08,
475
+ "grad_norm": 0.04736727103590965,
476
+ "learning_rate": 0.0001979273571768341,
477
+ "loss": 0.4617,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.08,
482
+ "grad_norm": 0.057293377816677094,
483
+ "learning_rate": 0.0001978542584088558,
484
+ "loss": 0.4621,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.08,
489
+ "grad_norm": 0.05025665834546089,
490
+ "learning_rate": 0.0001977799068171206,
491
+ "loss": 0.4671,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.08,
496
+ "grad_norm": 0.057366687804460526,
497
+ "learning_rate": 0.0001977043033535486,
498
+ "loss": 0.4521,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.08,
503
+ "grad_norm": 0.07595837116241455,
504
+ "learning_rate": 0.00019762744898608762,
505
+ "loss": 0.4671,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08,
510
+ "grad_norm": 0.07574213296175003,
511
+ "learning_rate": 0.0001975493446987007,
512
+ "loss": 0.4664,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.08,
517
+ "grad_norm": 0.06472938507795334,
518
+ "learning_rate": 0.00019746999149135362,
519
+ "loss": 0.456,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.08,
524
+ "grad_norm": 0.05983012542128563,
525
+ "learning_rate": 0.00019738939038000205,
526
+ "loss": 0.4459,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.08,
531
+ "grad_norm": 0.05136057734489441,
532
+ "learning_rate": 0.00019730754239657842,
533
+ "loss": 0.4486,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.09,
538
+ "grad_norm": 0.06191498041152954,
539
+ "learning_rate": 0.00019722444858897878,
540
+ "loss": 0.4424,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.09,
545
+ "grad_norm": 0.06742191314697266,
546
+ "learning_rate": 0.0001971401100210496,
547
+ "loss": 0.458,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.09,
552
+ "grad_norm": 0.06019548326730728,
553
+ "learning_rate": 0.00019705452777257377,
554
+ "loss": 0.4423,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.09,
559
+ "grad_norm": 0.05012982338666916,
560
+ "learning_rate": 0.0001969677029392571,
561
+ "loss": 0.4466,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.09,
566
+ "grad_norm": 0.0552060566842556,
567
+ "learning_rate": 0.00019687963663271409,
568
+ "loss": 0.4534,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.09,
573
+ "grad_norm": 0.05883748456835747,
574
+ "learning_rate": 0.00019679032998045376,
575
+ "loss": 0.4409,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.09,
580
+ "grad_norm": 0.07146705687046051,
581
+ "learning_rate": 0.00019669978412586528,
582
+ "loss": 0.4582,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.09,
587
+ "grad_norm": 0.054095230996608734,
588
+ "learning_rate": 0.00019660800022820317,
589
+ "loss": 0.4487,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.09,
594
+ "grad_norm": 0.04927053675055504,
595
+ "learning_rate": 0.00019651497946257266,
596
+ "loss": 0.4429,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1,
601
+ "grad_norm": 0.06037526577711105,
602
+ "learning_rate": 0.00019642072301991455,
603
+ "loss": 0.4456,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.1,
608
+ "grad_norm": 0.05555957555770874,
609
+ "learning_rate": 0.00019632523210698987,
610
+ "loss": 0.4382,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1,
615
+ "grad_norm": 0.04606284573674202,
616
+ "learning_rate": 0.00019622850794636455,
617
+ "loss": 0.4411,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1,
622
+ "grad_norm": 0.04605920985341072,
623
+ "learning_rate": 0.00019613055177639384,
624
+ "loss": 0.4326,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.1,
629
+ "grad_norm": 0.050325632095336914,
630
+ "learning_rate": 0.0001960313648512062,
631
+ "loss": 0.4338,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.1,
636
+ "grad_norm": 0.04921424016356468,
637
+ "learning_rate": 0.00019593094844068748,
638
+ "loss": 0.4316,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.1,
643
+ "grad_norm": 0.04333706200122833,
644
+ "learning_rate": 0.00019582930383046457,
645
+ "loss": 0.4441,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.1,
650
+ "grad_norm": 0.048454612493515015,
651
+ "learning_rate": 0.0001957264323218889,
652
+ "loss": 0.4382,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.1,
657
+ "grad_norm": 0.0541059784591198,
658
+ "learning_rate": 0.00019562233523201986,
659
+ "loss": 0.4328,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.11,
664
+ "grad_norm": 0.043696511536836624,
665
+ "learning_rate": 0.00019551701389360795,
666
+ "loss": 0.4335,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.11,
671
+ "grad_norm": 0.04407835751771927,
672
+ "learning_rate": 0.00019541046965507758,
673
+ "loss": 0.4327,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.11,
678
+ "grad_norm": 0.05477238819003105,
679
+ "learning_rate": 0.00019530270388050998,
680
+ "loss": 0.4294,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.11,
685
+ "grad_norm": 0.05609311908483505,
686
+ "learning_rate": 0.00019519371794962556,
687
+ "loss": 0.4305,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.11,
692
+ "grad_norm": 0.045145273208618164,
693
+ "learning_rate": 0.00019508351325776642,
694
+ "loss": 0.4395,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.11,
699
+ "grad_norm": 0.04475285857915878,
700
+ "learning_rate": 0.00019497209121587837,
701
+ "loss": 0.4284,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.11,
706
+ "grad_norm": 0.04405711591243744,
707
+ "learning_rate": 0.00019485945325049288,
708
+ "loss": 0.4214,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.11,
713
+ "grad_norm": 0.04461454227566719,
714
+ "learning_rate": 0.0001947456008037089,
715
+ "loss": 0.4154,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.11,
720
+ "grad_norm": 0.04791221395134926,
721
+ "learning_rate": 0.00019463053533317425,
722
+ "loss": 0.4248,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.12,
727
+ "grad_norm": 0.05543987452983856,
728
+ "learning_rate": 0.00019451425831206706,
729
+ "loss": 0.4303,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.12,
734
+ "grad_norm": 0.06330578774213791,
735
+ "learning_rate": 0.00019439677122907697,
736
+ "loss": 0.4274,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.12,
741
+ "grad_norm": 0.05569112300872803,
742
+ "learning_rate": 0.00019427807558838588,
743
+ "loss": 0.4234,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.12,
748
+ "grad_norm": 0.047680530697107315,
749
+ "learning_rate": 0.00019415817290964883,
750
+ "loss": 0.4155,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.12,
755
+ "grad_norm": 0.05214262008666992,
756
+ "learning_rate": 0.0001940370647279746,
757
+ "loss": 0.4224,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.12,
762
+ "grad_norm": 0.06332990527153015,
763
+ "learning_rate": 0.00019391475259390584,
764
+ "loss": 0.4233,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.12,
769
+ "grad_norm": 0.05726313218474388,
770
+ "learning_rate": 0.00019379123807339942,
771
+ "loss": 0.4118,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.12,
776
+ "grad_norm": 0.044936031103134155,
777
+ "learning_rate": 0.00019366652274780628,
778
+ "loss": 0.4296,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.12,
783
+ "grad_norm": 0.05117325484752655,
784
+ "learning_rate": 0.0001935406082138513,
785
+ "loss": 0.4287,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.13,
790
+ "grad_norm": 0.058542776852846146,
791
+ "learning_rate": 0.00019341349608361267,
792
+ "loss": 0.4213,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.13,
797
+ "grad_norm": 0.056066304445266724,
798
+ "learning_rate": 0.00019328518798450138,
799
+ "loss": 0.4174,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.13,
804
+ "grad_norm": 0.049762677401304245,
805
+ "learning_rate": 0.00019315568555924035,
806
+ "loss": 0.418,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.13,
811
+ "grad_norm": 0.043821126222610474,
812
+ "learning_rate": 0.00019302499046584348,
813
+ "loss": 0.4012,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.13,
818
+ "grad_norm": 0.05036221817135811,
819
+ "learning_rate": 0.00019289310437759427,
820
+ "loss": 0.4237,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.13,
825
+ "grad_norm": 0.050889529287815094,
826
+ "learning_rate": 0.00019276002898302447,
827
+ "loss": 0.4144,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.13,
832
+ "grad_norm": 0.04269757494330406,
833
+ "learning_rate": 0.0001926257659858925,
834
+ "loss": 0.4078,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.13,
839
+ "grad_norm": 0.04927165433764458,
840
+ "learning_rate": 0.00019249031710516162,
841
+ "loss": 0.4155,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.14,
846
+ "grad_norm": 0.05124311521649361,
847
+ "learning_rate": 0.00019235368407497788,
848
+ "loss": 0.3966,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.14,
853
+ "grad_norm": 0.04073040187358856,
854
+ "learning_rate": 0.00019221586864464786,
855
+ "loss": 0.4064,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.14,
860
+ "grad_norm": 0.04988453537225723,
861
+ "learning_rate": 0.00019207687257861655,
862
+ "loss": 0.4197,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.14,
867
+ "grad_norm": 0.05227258801460266,
868
+ "learning_rate": 0.0001919366976564444,
869
+ "loss": 0.414,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.14,
874
+ "grad_norm": 0.0466819666326046,
875
+ "learning_rate": 0.00019179534567278475,
876
+ "loss": 0.4173,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.14,
881
+ "grad_norm": 0.047633491456508636,
882
+ "learning_rate": 0.00019165281843736085,
883
+ "loss": 0.4085,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.14,
888
+ "grad_norm": 0.05280464142560959,
889
+ "learning_rate": 0.00019150911777494258,
890
+ "loss": 0.4051,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.14,
895
+ "grad_norm": 0.052302148193120956,
896
+ "learning_rate": 0.00019136424552532318,
897
+ "loss": 0.42,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.14,
902
+ "grad_norm": 0.04875241965055466,
903
+ "learning_rate": 0.00019121820354329577,
904
+ "loss": 0.4258,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.15,
909
+ "grad_norm": 0.04654408246278763,
910
+ "learning_rate": 0.0001910709936986293,
911
+ "loss": 0.409,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.15,
916
+ "grad_norm": 0.05745020881295204,
917
+ "learning_rate": 0.00019092261787604492,
918
+ "loss": 0.4059,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.15,
923
+ "grad_norm": 0.06945241987705231,
924
+ "learning_rate": 0.00019077307797519183,
925
+ "loss": 0.4038,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.15,
930
+ "grad_norm": 0.06346461176872253,
931
+ "learning_rate": 0.00019062237591062272,
932
+ "loss": 0.4031,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.15,
937
+ "grad_norm": 0.058026187121868134,
938
+ "learning_rate": 0.00019047051361176953,
939
+ "loss": 0.4126,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.15,
944
+ "grad_norm": 0.04755179584026337,
945
+ "learning_rate": 0.0001903174930229185,
946
+ "loss": 0.4209,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.15,
951
+ "grad_norm": 0.05765068158507347,
952
+ "learning_rate": 0.0001901633161031856,
953
+ "loss": 0.4067,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.15,
958
+ "grad_norm": 0.05687811225652695,
959
+ "learning_rate": 0.000190007984826491,
960
+ "loss": 0.3975,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.15,
965
+ "grad_norm": 0.04930473491549492,
966
+ "learning_rate": 0.0001898515011815343,
967
+ "loss": 0.4146,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.16,
972
+ "grad_norm": 0.05147051811218262,
973
+ "learning_rate": 0.0001896938671717687,
974
+ "loss": 0.4035,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.16,
979
+ "grad_norm": 0.05680418014526367,
980
+ "learning_rate": 0.0001895350848153754,
981
+ "loss": 0.4049,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.16,
986
+ "grad_norm": 0.0444297268986702,
987
+ "learning_rate": 0.00018937515614523797,
988
+ "loss": 0.4085,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.16,
993
+ "grad_norm": 0.05083802342414856,
994
+ "learning_rate": 0.00018921408320891612,
995
+ "loss": 0.4036,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.16,
1000
+ "grad_norm": 0.04978756606578827,
1001
+ "learning_rate": 0.00018905186806861957,
1002
+ "loss": 0.4058,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.16,
1007
+ "grad_norm": 0.04963681101799011,
1008
+ "learning_rate": 0.00018888851280118155,
1009
+ "loss": 0.3977,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.16,
1014
+ "grad_norm": 0.0466095507144928,
1015
+ "learning_rate": 0.00018872401949803237,
1016
+ "loss": 0.3945,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.16,
1021
+ "grad_norm": 0.04972768574953079,
1022
+ "learning_rate": 0.00018855839026517257,
1023
+ "loss": 0.4151,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.16,
1028
+ "grad_norm": 0.054370637983083725,
1029
+ "learning_rate": 0.0001883916272231459,
1030
+ "loss": 0.3944,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.17,
1035
+ "grad_norm": 0.054699357599020004,
1036
+ "learning_rate": 0.00018822373250701224,
1037
+ "loss": 0.3989,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.17,
1042
+ "grad_norm": 0.054452769458293915,
1043
+ "learning_rate": 0.00018805470826632024,
1044
+ "loss": 0.3984,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.17,
1049
+ "grad_norm": 0.04596908017992973,
1050
+ "learning_rate": 0.00018788455666507981,
1051
+ "loss": 0.4018,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.17,
1056
+ "grad_norm": 0.054354868829250336,
1057
+ "learning_rate": 0.00018771327988173435,
1058
+ "loss": 0.3985,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.17,
1063
+ "grad_norm": 0.05570242181420326,
1064
+ "learning_rate": 0.00018754088010913304,
1065
+ "loss": 0.3818,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.17,
1070
+ "grad_norm": 0.054722048342227936,
1071
+ "learning_rate": 0.00018736735955450251,
1072
+ "loss": 0.4111,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.17,
1077
+ "grad_norm": 0.04620000347495079,
1078
+ "learning_rate": 0.00018719272043941882,
1079
+ "loss": 0.3949,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.17,
1084
+ "grad_norm": 0.048443205654621124,
1085
+ "learning_rate": 0.00018701696499977884,
1086
+ "loss": 0.3856,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.17,
1091
+ "grad_norm": 0.06628945469856262,
1092
+ "learning_rate": 0.00018684009548577168,
1093
+ "loss": 0.4048,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.18,
1098
+ "grad_norm": 0.05339967459440231,
1099
+ "learning_rate": 0.00018666211416184999,
1100
+ "loss": 0.3894,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.18,
1105
+ "grad_norm": 0.04650304839015007,
1106
+ "learning_rate": 0.00018648302330670082,
1107
+ "loss": 0.4004,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.18,
1112
+ "grad_norm": 0.05634591728448868,
1113
+ "learning_rate": 0.00018630282521321645,
1114
+ "loss": 0.4033,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.18,
1119
+ "grad_norm": 0.048666685819625854,
1120
+ "learning_rate": 0.00018612152218846513,
1121
+ "loss": 0.399,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.18,
1126
+ "grad_norm": 0.04597772657871246,
1127
+ "learning_rate": 0.0001859391165536615,
1128
+ "loss": 0.3931,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.18,
1133
+ "grad_norm": 0.0526028610765934,
1134
+ "learning_rate": 0.00018575561064413689,
1135
+ "loss": 0.3879,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.18,
1140
+ "grad_norm": 0.05867009237408638,
1141
+ "learning_rate": 0.00018557100680930937,
1142
+ "loss": 0.3905,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.18,
1147
+ "grad_norm": 0.05077454075217247,
1148
+ "learning_rate": 0.00018538530741265364,
1149
+ "loss": 0.395,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.18,
1154
+ "grad_norm": 0.0461389385163784,
1155
+ "learning_rate": 0.00018519851483167097,
1156
+ "loss": 0.4016,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.19,
1161
+ "grad_norm": 0.059010252356529236,
1162
+ "learning_rate": 0.00018501063145785846,
1163
+ "loss": 0.3823,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.19,
1168
+ "grad_norm": 0.06437338888645172,
1169
+ "learning_rate": 0.00018482165969667874,
1170
+ "loss": 0.3918,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.19,
1175
+ "grad_norm": 0.04585932940244675,
1176
+ "learning_rate": 0.00018463160196752887,
1177
+ "loss": 0.3808,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.19,
1182
+ "grad_norm": 0.05361521616578102,
1183
+ "learning_rate": 0.00018444046070370963,
1184
+ "loss": 0.3858,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.19,
1189
+ "grad_norm": 0.05653822794556618,
1190
+ "learning_rate": 0.00018424823835239417,
1191
+ "loss": 0.3785,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.19,
1196
+ "grad_norm": 0.04439689964056015,
1197
+ "learning_rate": 0.0001840549373745968,
1198
+ "loss": 0.3894,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.19,
1203
+ "grad_norm": 0.05564529448747635,
1204
+ "learning_rate": 0.00018386056024514137,
1205
+ "loss": 0.3883,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.19,
1210
+ "grad_norm": 0.06035888195037842,
1211
+ "learning_rate": 0.00018366510945262972,
1212
+ "loss": 0.3855,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.19,
1217
+ "grad_norm": 0.044238511472940445,
1218
+ "learning_rate": 0.0001834685874994098,
1219
+ "loss": 0.3934,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.2,
1224
+ "grad_norm": 0.050235260277986526,
1225
+ "learning_rate": 0.00018327099690154344,
1226
+ "loss": 0.3819,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.2,
1231
+ "grad_norm": 0.051336683332920074,
1232
+ "learning_rate": 0.00018307234018877434,
1233
+ "loss": 0.3897,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.2,
1238
+ "grad_norm": 0.045052576810121536,
1239
+ "learning_rate": 0.0001828726199044957,
1240
+ "loss": 0.3822,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.2,
1245
+ "grad_norm": 0.05162283405661583,
1246
+ "learning_rate": 0.00018267183860571753,
1247
+ "loss": 0.4047,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.2,
1252
+ "grad_norm": 0.0488157793879509,
1253
+ "learning_rate": 0.00018246999886303383,
1254
+ "loss": 0.3947,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.2,
1259
+ "grad_norm": 0.04454487934708595,
1260
+ "learning_rate": 0.00018226710326059006,
1261
+ "loss": 0.3942,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.2,
1266
+ "grad_norm": 0.0500001423060894,
1267
+ "learning_rate": 0.0001820631543960496,
1268
+ "loss": 0.3826,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.2,
1273
+ "grad_norm": 0.04919865354895592,
1274
+ "learning_rate": 0.00018185815488056076,
1275
+ "loss": 0.3791,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.2,
1280
+ "grad_norm": 0.04547140747308731,
1281
+ "learning_rate": 0.00018165210733872336,
1282
+ "loss": 0.3879,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.21,
1287
+ "grad_norm": 0.044622063636779785,
1288
+ "learning_rate": 0.00018144501440855496,
1289
+ "loss": 0.3778,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.21,
1294
+ "grad_norm": 0.04467932507395744,
1295
+ "learning_rate": 0.00018123687874145721,
1296
+ "loss": 0.3994,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.21,
1301
+ "grad_norm": 0.04281982406973839,
1302
+ "learning_rate": 0.0001810277030021819,
1303
+ "loss": 0.3817,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.21,
1308
+ "grad_norm": 0.05303504317998886,
1309
+ "learning_rate": 0.00018081748986879679,
1310
+ "loss": 0.3749,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.21,
1315
+ "grad_norm": 0.046573616564273834,
1316
+ "learning_rate": 0.00018060624203265134,
1317
+ "loss": 0.3866,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.21,
1322
+ "grad_norm": 0.044320229440927505,
1323
+ "learning_rate": 0.00018039396219834237,
1324
+ "loss": 0.3732,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.21,
1329
+ "grad_norm": 0.05708359181880951,
1330
+ "learning_rate": 0.00018018065308367912,
1331
+ "loss": 0.3863,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.21,
1336
+ "grad_norm": 0.045029208064079285,
1337
+ "learning_rate": 0.00017996631741964888,
1338
+ "loss": 0.3862,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.21,
1343
+ "grad_norm": 0.055195923894643784,
1344
+ "learning_rate": 0.00017975095795038165,
1345
+ "loss": 0.3835,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.22,
1350
+ "grad_norm": 0.048293352127075195,
1351
+ "learning_rate": 0.00017953457743311523,
1352
+ "loss": 0.374,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.22,
1357
+ "grad_norm": 0.04677055403590202,
1358
+ "learning_rate": 0.00017931717863815987,
1359
+ "loss": 0.377,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.22,
1364
+ "grad_norm": 0.04955766722559929,
1365
+ "learning_rate": 0.00017909876434886273,
1366
+ "loss": 0.3808,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.22,
1371
+ "grad_norm": 0.04526973515748978,
1372
+ "learning_rate": 0.00017887933736157233,
1373
+ "loss": 0.3796,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.22,
1378
+ "grad_norm": 0.043622203171253204,
1379
+ "learning_rate": 0.00017865890048560277,
1380
+ "loss": 0.376,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.22,
1385
+ "grad_norm": 0.046581387519836426,
1386
+ "learning_rate": 0.0001784374565431976,
1387
+ "loss": 0.3716,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.22,
1392
+ "grad_norm": 0.04433497413992882,
1393
+ "learning_rate": 0.00017821500836949386,
1394
+ "loss": 0.3715,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.22,
1399
+ "grad_norm": 0.04146367311477661,
1400
+ "learning_rate": 0.00017799155881248572,
1401
+ "loss": 0.3809,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.23,
1406
+ "grad_norm": 0.045288585126399994,
1407
+ "learning_rate": 0.000177767110732988,
1408
+ "loss": 0.3885,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.23,
1413
+ "grad_norm": 0.04070120304822922,
1414
+ "learning_rate": 0.00017754166700459958,
1415
+ "loss": 0.3713,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.23,
1420
+ "grad_norm": 0.042820919305086136,
1421
+ "learning_rate": 0.00017731523051366658,
1422
+ "loss": 0.3839,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.23,
1427
+ "grad_norm": 0.04416365176439285,
1428
+ "learning_rate": 0.00017708780415924539,
1429
+ "loss": 0.3728,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.23,
1434
+ "grad_norm": 0.04461952671408653,
1435
+ "learning_rate": 0.00017685939085306562,
1436
+ "loss": 0.373,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.23,
1441
+ "grad_norm": 0.04675828292965889,
1442
+ "learning_rate": 0.00017662999351949278,
1443
+ "loss": 0.3711,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.23,
1448
+ "grad_norm": 0.04258272796869278,
1449
+ "learning_rate": 0.00017639961509549078,
1450
+ "loss": 0.3782,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.23,
1455
+ "grad_norm": 0.04638506844639778,
1456
+ "learning_rate": 0.00017616825853058443,
1457
+ "loss": 0.3592,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.23,
1462
+ "grad_norm": 0.04781416058540344,
1463
+ "learning_rate": 0.00017593592678682166,
1464
+ "loss": 0.383,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.24,
1469
+ "grad_norm": 0.04813629388809204,
1470
+ "learning_rate": 0.00017570262283873552,
1471
+ "loss": 0.3775,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.24,
1476
+ "grad_norm": 0.046996332705020905,
1477
+ "learning_rate": 0.00017546834967330617,
1478
+ "loss": 0.3815,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.24,
1483
+ "grad_norm": 0.04889595881104469,
1484
+ "learning_rate": 0.00017523311028992268,
1485
+ "loss": 0.3636,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.24,
1490
+ "grad_norm": 0.04298345744609833,
1491
+ "learning_rate": 0.00017499690770034443,
1492
+ "loss": 0.3672,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.24,
1497
+ "grad_norm": 0.04219110682606697,
1498
+ "learning_rate": 0.00017475974492866278,
1499
+ "loss": 0.3801,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.24,
1504
+ "grad_norm": 0.051573265343904495,
1505
+ "learning_rate": 0.00017452162501126227,
1506
+ "loss": 0.3778,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.24,
1511
+ "grad_norm": 0.048954349011182785,
1512
+ "learning_rate": 0.00017428255099678167,
1513
+ "loss": 0.3849,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.24,
1518
+ "grad_norm": 0.042610183358192444,
1519
+ "learning_rate": 0.0001740425259460751,
1520
+ "loss": 0.3682,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.24,
1525
+ "grad_norm": 0.04517417773604393,
1526
+ "learning_rate": 0.00017380155293217264,
1527
+ "loss": 0.3827,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.25,
1532
+ "grad_norm": 0.04968888312578201,
1533
+ "learning_rate": 0.00017355963504024123,
1534
+ "loss": 0.3821,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.25,
1539
+ "grad_norm": 0.051313381642103195,
1540
+ "learning_rate": 0.0001733167753675449,
1541
+ "loss": 0.381,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.25,
1546
+ "grad_norm": 0.044351302087306976,
1547
+ "learning_rate": 0.0001730729770234054,
1548
+ "loss": 0.381,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.25,
1553
+ "grad_norm": 0.03970547392964363,
1554
+ "learning_rate": 0.00017282824312916218,
1555
+ "loss": 0.3698,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.25,
1560
+ "grad_norm": 0.04822370782494545,
1561
+ "learning_rate": 0.00017258257681813244,
1562
+ "loss": 0.3838,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.25,
1567
+ "grad_norm": 0.045927174389362335,
1568
+ "learning_rate": 0.0001723359812355712,
1569
+ "loss": 0.3662,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.25,
1574
+ "grad_norm": 0.042983219027519226,
1575
+ "learning_rate": 0.00017208845953863076,
1576
+ "loss": 0.3574,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.25,
1581
+ "grad_norm": 0.0422198586165905,
1582
+ "learning_rate": 0.0001718400148963206,
1583
+ "loss": 0.3559,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.25,
1588
+ "grad_norm": 0.042307570576667786,
1589
+ "learning_rate": 0.00017159065048946644,
1590
+ "loss": 0.3834,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.26,
1595
+ "grad_norm": 0.04701109230518341,
1596
+ "learning_rate": 0.0001713403695106698,
1597
+ "loss": 0.3718,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.26,
1602
+ "grad_norm": 0.04007503017783165,
1603
+ "learning_rate": 0.00017108917516426704,
1604
+ "loss": 0.3785,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.26,
1609
+ "grad_norm": 0.04560061916708946,
1610
+ "learning_rate": 0.00017083707066628832,
1611
+ "loss": 0.3713,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.26,
1616
+ "grad_norm": 0.04315731301903725,
1617
+ "learning_rate": 0.00017058405924441636,
1618
+ "loss": 0.3702,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.26,
1623
+ "grad_norm": 0.040260497480630875,
1624
+ "learning_rate": 0.0001703301441379453,
1625
+ "loss": 0.367,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.26,
1630
+ "grad_norm": 0.04882992431521416,
1631
+ "learning_rate": 0.000170075328597739,
1632
+ "loss": 0.3737,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.26,
1637
+ "grad_norm": 0.04410382732748985,
1638
+ "learning_rate": 0.0001698196158861896,
1639
+ "loss": 0.3625,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.26,
1644
+ "grad_norm": 0.04889338091015816,
1645
+ "learning_rate": 0.00016956300927717575,
1646
+ "loss": 0.3697,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.26,
1651
+ "grad_norm": 0.044603537768125534,
1652
+ "learning_rate": 0.00016930551205602043,
1653
+ "loss": 0.3729,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.27,
1658
+ "grad_norm": 0.0539550743997097,
1659
+ "learning_rate": 0.00016904712751944931,
1660
+ "loss": 0.3625,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.27,
1665
+ "grad_norm": 0.04753349721431732,
1666
+ "learning_rate": 0.00016878785897554818,
1667
+ "loss": 0.3662,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.27,
1672
+ "grad_norm": 0.04425463080406189,
1673
+ "learning_rate": 0.0001685277097437208,
1674
+ "loss": 0.3595,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.27,
1679
+ "grad_norm": 0.04160892590880394,
1680
+ "learning_rate": 0.0001682666831546463,
1681
+ "loss": 0.3679,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.27,
1686
+ "grad_norm": 0.04600003361701965,
1687
+ "learning_rate": 0.0001680047825502366,
1688
+ "loss": 0.3702,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.27,
1693
+ "grad_norm": 0.03887678310275078,
1694
+ "learning_rate": 0.00016774201128359357,
1695
+ "loss": 0.3633,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.27,
1700
+ "grad_norm": 0.0477156862616539,
1701
+ "learning_rate": 0.00016747837271896622,
1702
+ "loss": 0.3702,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.27,
1707
+ "grad_norm": 0.04244072362780571,
1708
+ "learning_rate": 0.00016721387023170737,
1709
+ "loss": 0.3668,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.27,
1714
+ "grad_norm": 0.04049496725201607,
1715
+ "learning_rate": 0.0001669485072082308,
1716
+ "loss": 0.3785,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.28,
1721
+ "grad_norm": 0.04432998597621918,
1722
+ "learning_rate": 0.00016668228704596756,
1723
+ "loss": 0.3703,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.28,
1728
+ "grad_norm": 0.0432085320353508,
1729
+ "learning_rate": 0.00016641521315332265,
1730
+ "loss": 0.3615,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.28,
1735
+ "grad_norm": 0.03820549696683884,
1736
+ "learning_rate": 0.00016614728894963135,
1737
+ "loss": 0.3483,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.28,
1742
+ "grad_norm": 0.04436295107007027,
1743
+ "learning_rate": 0.00016587851786511543,
1744
+ "loss": 0.3661,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.28,
1749
+ "grad_norm": 0.04371733218431473,
1750
+ "learning_rate": 0.00016560890334083926,
1751
+ "loss": 0.3503,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.28,
1756
+ "grad_norm": 0.039205193519592285,
1757
+ "learning_rate": 0.00016533844882866568,
1758
+ "loss": 0.3482,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.28,
1763
+ "grad_norm": 0.04308384284377098,
1764
+ "learning_rate": 0.00016506715779121187,
1765
+ "loss": 0.373,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.28,
1770
+ "grad_norm": 0.040143441408872604,
1771
+ "learning_rate": 0.00016479503370180507,
1772
+ "loss": 0.3609,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.28,
1777
+ "grad_norm": 0.03845199570059776,
1778
+ "learning_rate": 0.000164522080044438,
1779
+ "loss": 0.3644,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.29,
1784
+ "grad_norm": 0.039730221033096313,
1785
+ "learning_rate": 0.00016424830031372425,
1786
+ "loss": 0.3514,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.29,
1791
+ "grad_norm": 0.04021477699279785,
1792
+ "learning_rate": 0.00016397369801485366,
1793
+ "loss": 0.3566,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.29,
1798
+ "grad_norm": 0.03929613530635834,
1799
+ "learning_rate": 0.00016369827666354745,
1800
+ "loss": 0.3649,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.29,
1805
+ "grad_norm": 0.040966227650642395,
1806
+ "learning_rate": 0.0001634220397860129,
1807
+ "loss": 0.3661,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.29,
1812
+ "grad_norm": 0.036787159740924835,
1813
+ "learning_rate": 0.0001631449909188987,
1814
+ "loss": 0.3572,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.29,
1819
+ "grad_norm": 0.039864350110292435,
1820
+ "learning_rate": 0.00016286713360924918,
1821
+ "loss": 0.3593,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.29,
1826
+ "grad_norm": 0.039622630923986435,
1827
+ "learning_rate": 0.00016258847141445928,
1828
+ "loss": 0.3711,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.29,
1833
+ "grad_norm": 0.03840857744216919,
1834
+ "learning_rate": 0.00016230900790222878,
1835
+ "loss": 0.3537,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.29,
1840
+ "grad_norm": 0.03800921142101288,
1841
+ "learning_rate": 0.00016202874665051674,
1842
+ "loss": 0.3662,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.3,
1847
+ "grad_norm": 0.03894530236721039,
1848
+ "learning_rate": 0.0001617476912474956,
1849
+ "loss": 0.3633,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.3,
1854
+ "grad_norm": 0.04486812278628349,
1855
+ "learning_rate": 0.00016146584529150526,
1856
+ "loss": 0.3594,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.3,
1861
+ "grad_norm": 0.0394977331161499,
1862
+ "learning_rate": 0.00016118321239100712,
1863
+ "loss": 0.3473,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.3,
1868
+ "grad_norm": 0.03960977867245674,
1869
+ "learning_rate": 0.0001608997961645377,
1870
+ "loss": 0.363,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.3,
1875
+ "grad_norm": 0.04547852650284767,
1876
+ "learning_rate": 0.00016061560024066248,
1877
+ "loss": 0.3698,
1878
+ "step": 267
1879
+ }
1880
+ ],
1881
+ "logging_steps": 1,
1882
+ "max_steps": 888,
1883
+ "num_input_tokens_seen": 0,
1884
+ "num_train_epochs": 1,
1885
+ "save_steps": 89,
1886
+ "total_flos": 5.32595180788777e+18,
1887
+ "train_batch_size": 14,
1888
+ "trial_name": null,
1889
+ "trial_params": null
1890
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0441fddfec498f33a86d551b67802f8f8fbf45a9463d322464e8ee1ed737775
3
+ size 5688