vantaa32 commited on
Commit
993710d
·
verified ·
1 Parent(s): bb064b0

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-7b-hf
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16.0,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.01,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916af11d0703123ba667e1f3fb7f7f309d584a8ed4448932d2908e2c7e88013c
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 sha256:4f6b06f28f0388c0b61c7bbd24012e36baa3d39a961dee7d0dc03afab6d4b891
3
+ size 268543610
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f358ea43734a8aa857e087131b9d0f2bff0982e036a1d94a0e12dd14813682e
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aeb274e69529baf3171d7a61d2d553638f67c2ed841e18f0520c827a83b052a
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<s>",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "</s>",
42
+ "extra_special_tokens": {},
43
+ "legacy": false,
44
+ "model_max_length": 512,
45
+ "pad_token": "[PAD]",
46
+ "padding_side": "right",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "tokenizer_class": "LlamaTokenizer",
50
+ "unk_token": "<unk>",
51
+ "use_default_system_prompt": false
52
+ }
trainer_state.json ADDED
@@ -0,0 +1,1727 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.996599690880989,
5
+ "eval_steps": 500,
6
+ "global_step": 2424,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012364760432766615,
13
+ "grad_norm": 0.04875350371003151,
14
+ "learning_rate": 0.00029876237623762373,
15
+ "loss": 1.0085,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.02472952086553323,
20
+ "grad_norm": 0.03758955001831055,
21
+ "learning_rate": 0.0002975247524752475,
22
+ "loss": 0.9611,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.03709428129829984,
27
+ "grad_norm": 0.036796920001506805,
28
+ "learning_rate": 0.00029628712871287126,
29
+ "loss": 0.9033,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.04945904173106646,
34
+ "grad_norm": 0.04110224172472954,
35
+ "learning_rate": 0.000295049504950495,
36
+ "loss": 0.9154,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.061823802163833076,
41
+ "grad_norm": 0.03811247646808624,
42
+ "learning_rate": 0.0002938118811881188,
43
+ "loss": 0.9001,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07418856259659969,
48
+ "grad_norm": 0.0396280363202095,
49
+ "learning_rate": 0.00029257425742574254,
50
+ "loss": 0.9069,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0865533230293663,
55
+ "grad_norm": 0.036311160773038864,
56
+ "learning_rate": 0.0002913366336633663,
57
+ "loss": 0.8905,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.09891808346213292,
62
+ "grad_norm": 0.04230085760354996,
63
+ "learning_rate": 0.00029009900990099006,
64
+ "loss": 0.928,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.11128284389489954,
69
+ "grad_norm": 0.03857972100377083,
70
+ "learning_rate": 0.0002888613861386138,
71
+ "loss": 0.9122,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.12364760432766615,
76
+ "grad_norm": 0.043333932757377625,
77
+ "learning_rate": 0.0002876237623762376,
78
+ "loss": 0.8921,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.13601236476043277,
83
+ "grad_norm": 0.03789997100830078,
84
+ "learning_rate": 0.00028638613861386135,
85
+ "loss": 0.8988,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.14837712519319937,
90
+ "grad_norm": 0.03549322113394737,
91
+ "learning_rate": 0.0002851485148514851,
92
+ "loss": 0.899,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.160741885625966,
97
+ "grad_norm": 0.04001789167523384,
98
+ "learning_rate": 0.00028391089108910887,
99
+ "loss": 0.8937,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.1731066460587326,
104
+ "grad_norm": 0.04051420837640762,
105
+ "learning_rate": 0.00028267326732673263,
106
+ "loss": 0.8941,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.18547140649149924,
111
+ "grad_norm": 0.03879082202911377,
112
+ "learning_rate": 0.0002814356435643564,
113
+ "loss": 0.9086,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.19783616692426584,
118
+ "grad_norm": 0.03938911855220795,
119
+ "learning_rate": 0.00028019801980198015,
120
+ "loss": 0.908,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.21020092735703247,
125
+ "grad_norm": 0.04576217010617256,
126
+ "learning_rate": 0.0002789603960396039,
127
+ "loss": 0.9058,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.22256568778979907,
132
+ "grad_norm": 0.05652037635445595,
133
+ "learning_rate": 0.00027772277227722773,
134
+ "loss": 0.8718,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.23493044822256567,
139
+ "grad_norm": 0.04269680753350258,
140
+ "learning_rate": 0.00027648514851485144,
141
+ "loss": 0.9102,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2472952086553323,
146
+ "grad_norm": 0.046770963817834854,
147
+ "learning_rate": 0.0002752475247524752,
148
+ "loss": 0.8893,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2596599690880989,
153
+ "grad_norm": 0.0391731895506382,
154
+ "learning_rate": 0.000274009900990099,
155
+ "loss": 0.8858,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.27202472952086554,
160
+ "grad_norm": 0.04302387312054634,
161
+ "learning_rate": 0.0002727722772277227,
162
+ "loss": 0.8967,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.28438948995363217,
167
+ "grad_norm": 0.04622489586472511,
168
+ "learning_rate": 0.0002715346534653465,
169
+ "loss": 0.8919,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.29675425038639874,
174
+ "grad_norm": 0.04950324073433876,
175
+ "learning_rate": 0.0002702970297029703,
176
+ "loss": 0.8898,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.3091190108191654,
181
+ "grad_norm": 0.047146428376436234,
182
+ "learning_rate": 0.000269059405940594,
183
+ "loss": 0.8941,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.321483771251932,
188
+ "grad_norm": 0.04186677187681198,
189
+ "learning_rate": 0.00026782178217821777,
190
+ "loss": 0.892,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.33384853168469864,
195
+ "grad_norm": 0.04358995333313942,
196
+ "learning_rate": 0.0002665841584158416,
197
+ "loss": 0.8813,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3462132921174652,
202
+ "grad_norm": 0.03836526349186897,
203
+ "learning_rate": 0.00026534653465346534,
204
+ "loss": 0.8883,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.35857805255023184,
209
+ "grad_norm": 0.04279692843556404,
210
+ "learning_rate": 0.00026410891089108905,
211
+ "loss": 0.8964,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.37094281298299847,
216
+ "grad_norm": 0.04259683936834335,
217
+ "learning_rate": 0.00026287128712871287,
218
+ "loss": 0.8864,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.38330757341576505,
223
+ "grad_norm": 0.04212690517306328,
224
+ "learning_rate": 0.00026163366336633663,
225
+ "loss": 0.8937,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.3956723338485317,
230
+ "grad_norm": 0.04193605110049248,
231
+ "learning_rate": 0.00026039603960396033,
232
+ "loss": 0.8743,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.4080370942812983,
237
+ "grad_norm": 0.043696388602256775,
238
+ "learning_rate": 0.00025915841584158415,
239
+ "loss": 0.8919,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.42040185471406494,
244
+ "grad_norm": 0.04463732987642288,
245
+ "learning_rate": 0.0002579207920792079,
246
+ "loss": 0.8791,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.4327666151468315,
251
+ "grad_norm": 0.042219433933496475,
252
+ "learning_rate": 0.0002566831683168316,
253
+ "loss": 0.8886,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.44513137557959814,
258
+ "grad_norm": 0.04634915664792061,
259
+ "learning_rate": 0.00025544554455445543,
260
+ "loss": 0.8798,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.4574961360123648,
265
+ "grad_norm": 0.03766421601176262,
266
+ "learning_rate": 0.0002542079207920792,
267
+ "loss": 0.8809,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.46986089644513135,
272
+ "grad_norm": 0.04153716191649437,
273
+ "learning_rate": 0.00025297029702970296,
274
+ "loss": 0.8921,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.482225656877898,
279
+ "grad_norm": 0.04694748297333717,
280
+ "learning_rate": 0.0002517326732673267,
281
+ "loss": 0.895,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.4945904173106646,
286
+ "grad_norm": 0.05713290721178055,
287
+ "learning_rate": 0.0002504950495049505,
288
+ "loss": 0.8774,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5069551777434312,
293
+ "grad_norm": 0.0414641909301281,
294
+ "learning_rate": 0.00024925742574257424,
295
+ "loss": 0.8908,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.5193199381761978,
300
+ "grad_norm": 0.04552585631608963,
301
+ "learning_rate": 0.000248019801980198,
302
+ "loss": 0.8843,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5316846986089645,
307
+ "grad_norm": 0.04167173057794571,
308
+ "learning_rate": 0.00024678217821782176,
309
+ "loss": 0.8583,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5440494590417311,
314
+ "grad_norm": 0.04508620873093605,
315
+ "learning_rate": 0.0002455445544554455,
316
+ "loss": 0.9205,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5564142194744977,
321
+ "grad_norm": 0.04546656087040901,
322
+ "learning_rate": 0.0002443069306930693,
323
+ "loss": 0.8857,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.5687789799072643,
328
+ "grad_norm": 0.046972740441560745,
329
+ "learning_rate": 0.00024306930693069305,
330
+ "loss": 0.8788,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.5811437403400309,
335
+ "grad_norm": 0.03991515189409256,
336
+ "learning_rate": 0.0002418316831683168,
337
+ "loss": 0.8731,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.5935085007727975,
342
+ "grad_norm": 0.047520458698272705,
343
+ "learning_rate": 0.0002405940594059406,
344
+ "loss": 0.8986,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6058732612055642,
349
+ "grad_norm": 0.04166582226753235,
350
+ "learning_rate": 0.00023935643564356433,
351
+ "loss": 0.8865,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6182380216383307,
356
+ "grad_norm": 0.043145373463630676,
357
+ "learning_rate": 0.0002381188118811881,
358
+ "loss": 0.8738,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6306027820710973,
363
+ "grad_norm": 0.04514694958925247,
364
+ "learning_rate": 0.00023688118811881188,
365
+ "loss": 0.8976,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.642967542503864,
370
+ "grad_norm": 0.03927430510520935,
371
+ "learning_rate": 0.00023564356435643561,
372
+ "loss": 0.8953,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6553323029366306,
377
+ "grad_norm": 0.048136577010154724,
378
+ "learning_rate": 0.00023440594059405938,
379
+ "loss": 0.8979,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.6676970633693973,
384
+ "grad_norm": 0.043889183551073074,
385
+ "learning_rate": 0.00023316831683168316,
386
+ "loss": 0.9065,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.6800618238021638,
391
+ "grad_norm": 0.05049331858754158,
392
+ "learning_rate": 0.0002319306930693069,
393
+ "loss": 0.8941,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.6924265842349304,
398
+ "grad_norm": 0.04710015654563904,
399
+ "learning_rate": 0.00023069306930693066,
400
+ "loss": 0.8716,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7047913446676971,
405
+ "grad_norm": 0.04900379851460457,
406
+ "learning_rate": 0.00022945544554455445,
407
+ "loss": 0.9017,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7171561051004637,
412
+ "grad_norm": 0.0502135343849659,
413
+ "learning_rate": 0.0002282178217821782,
414
+ "loss": 0.8774,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7295208655332303,
419
+ "grad_norm": 0.047438524663448334,
420
+ "learning_rate": 0.00022698019801980194,
421
+ "loss": 0.8815,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7418856259659969,
426
+ "grad_norm": 0.04633660241961479,
427
+ "learning_rate": 0.00022574257425742573,
428
+ "loss": 0.8746,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.7542503863987635,
433
+ "grad_norm": 0.04724352806806564,
434
+ "learning_rate": 0.0002245049504950495,
435
+ "loss": 0.9005,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.7666151468315301,
440
+ "grad_norm": 0.04557831212878227,
441
+ "learning_rate": 0.00022326732673267323,
442
+ "loss": 0.8798,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.7789799072642968,
447
+ "grad_norm": 0.047848157584667206,
448
+ "learning_rate": 0.00022202970297029702,
449
+ "loss": 0.893,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.7913446676970634,
454
+ "grad_norm": 0.04449377954006195,
455
+ "learning_rate": 0.00022079207920792078,
456
+ "loss": 0.8851,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.80370942812983,
461
+ "grad_norm": 0.04431360587477684,
462
+ "learning_rate": 0.0002195544554455445,
463
+ "loss": 0.8876,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8160741885625966,
468
+ "grad_norm": 0.04388862103223801,
469
+ "learning_rate": 0.0002183168316831683,
470
+ "loss": 0.8886,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8284389489953632,
475
+ "grad_norm": 0.04719037562608719,
476
+ "learning_rate": 0.00021707920792079206,
477
+ "loss": 0.9011,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8408037094281299,
482
+ "grad_norm": 0.04291271045804024,
483
+ "learning_rate": 0.00021584158415841585,
484
+ "loss": 0.8738,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.8531684698608965,
489
+ "grad_norm": 0.04412473365664482,
490
+ "learning_rate": 0.00021460396039603958,
491
+ "loss": 0.8738,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.865533230293663,
496
+ "grad_norm": 0.046331875026226044,
497
+ "learning_rate": 0.00021336633663366334,
498
+ "loss": 0.8899,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.8778979907264297,
503
+ "grad_norm": 0.04418357461690903,
504
+ "learning_rate": 0.00021212871287128713,
505
+ "loss": 0.889,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.8902627511591963,
510
+ "grad_norm": 0.04221678525209427,
511
+ "learning_rate": 0.00021089108910891087,
512
+ "loss": 0.8751,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9026275115919629,
517
+ "grad_norm": 0.04472072795033455,
518
+ "learning_rate": 0.00020965346534653463,
519
+ "loss": 0.8775,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9149922720247295,
524
+ "grad_norm": 0.04348697140812874,
525
+ "learning_rate": 0.00020841584158415842,
526
+ "loss": 0.8751,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.9273570324574961,
531
+ "grad_norm": 0.04851846024394035,
532
+ "learning_rate": 0.00020717821782178215,
533
+ "loss": 0.8951,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.9397217928902627,
538
+ "grad_norm": 0.04079887643456459,
539
+ "learning_rate": 0.0002059405940594059,
540
+ "loss": 0.9028,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.9520865533230294,
545
+ "grad_norm": 0.04408387467265129,
546
+ "learning_rate": 0.0002047029702970297,
547
+ "loss": 0.8842,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.964451313755796,
552
+ "grad_norm": 0.04127747192978859,
553
+ "learning_rate": 0.00020346534653465346,
554
+ "loss": 0.876,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.9768160741885626,
559
+ "grad_norm": 0.05341732129454613,
560
+ "learning_rate": 0.0002022277227722772,
561
+ "loss": 0.8843,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.9891808346213292,
566
+ "grad_norm": 0.04694453999400139,
567
+ "learning_rate": 0.00020099009900990098,
568
+ "loss": 0.8815,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.0012364760432766,
573
+ "grad_norm": 0.05160349979996681,
574
+ "learning_rate": 0.00019975247524752475,
575
+ "loss": 0.8857,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.0136012364760432,
580
+ "grad_norm": 0.0415058434009552,
581
+ "learning_rate": 0.00019851485148514848,
582
+ "loss": 0.8461,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.02596599690881,
587
+ "grad_norm": 0.04516944661736488,
588
+ "learning_rate": 0.00019727722772277227,
589
+ "loss": 0.8548,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.0383307573415765,
594
+ "grad_norm": 0.04707406461238861,
595
+ "learning_rate": 0.00019603960396039603,
596
+ "loss": 0.8503,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.0506955177743431,
601
+ "grad_norm": 0.049354761838912964,
602
+ "learning_rate": 0.00019480198019801976,
603
+ "loss": 0.8584,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.0630602782071097,
608
+ "grad_norm": 0.04959525167942047,
609
+ "learning_rate": 0.00019356435643564355,
610
+ "loss": 0.8788,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.0754250386398763,
615
+ "grad_norm": 0.048685044050216675,
616
+ "learning_rate": 0.0001923267326732673,
617
+ "loss": 0.873,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.087789799072643,
622
+ "grad_norm": 0.045906998217105865,
623
+ "learning_rate": 0.00019108910891089107,
624
+ "loss": 0.8775,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.1001545595054096,
629
+ "grad_norm": 0.04486127197742462,
630
+ "learning_rate": 0.00018985148514851484,
631
+ "loss": 0.8647,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.1125193199381762,
636
+ "grad_norm": 0.05211256071925163,
637
+ "learning_rate": 0.0001886138613861386,
638
+ "loss": 0.8594,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 1.1248840803709428,
643
+ "grad_norm": 0.05048747360706329,
644
+ "learning_rate": 0.00018737623762376236,
645
+ "loss": 0.8564,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 1.1372488408037094,
650
+ "grad_norm": 0.04840526729822159,
651
+ "learning_rate": 0.00018613861386138612,
652
+ "loss": 0.8782,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 1.1496136012364762,
657
+ "grad_norm": 0.049940045922994614,
658
+ "learning_rate": 0.00018490099009900988,
659
+ "loss": 0.867,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 1.1619783616692427,
664
+ "grad_norm": 0.053729794919490814,
665
+ "learning_rate": 0.00018366336633663364,
666
+ "loss": 0.8585,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 1.1743431221020093,
671
+ "grad_norm": 0.05020948871970177,
672
+ "learning_rate": 0.0001824257425742574,
673
+ "loss": 0.8688,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 1.1867078825347759,
678
+ "grad_norm": 0.0517219677567482,
679
+ "learning_rate": 0.00018118811881188116,
680
+ "loss": 0.8731,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 1.1990726429675425,
685
+ "grad_norm": 0.04891285300254822,
686
+ "learning_rate": 0.00017995049504950493,
687
+ "loss": 0.8348,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.211437403400309,
692
+ "grad_norm": 0.051312196999788284,
693
+ "learning_rate": 0.00017871287128712871,
694
+ "loss": 0.8658,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 1.2238021638330758,
699
+ "grad_norm": 0.051922161132097244,
700
+ "learning_rate": 0.00017747524752475245,
701
+ "loss": 0.8542,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 1.2361669242658424,
706
+ "grad_norm": 0.0521603561937809,
707
+ "learning_rate": 0.0001762376237623762,
708
+ "loss": 0.8628,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 1.248531684698609,
713
+ "grad_norm": 0.05443425104022026,
714
+ "learning_rate": 0.000175,
715
+ "loss": 0.875,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 1.2608964451313756,
720
+ "grad_norm": 0.05506913363933563,
721
+ "learning_rate": 0.00017376237623762373,
722
+ "loss": 0.8704,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 1.2732612055641421,
727
+ "grad_norm": 0.05535837262868881,
728
+ "learning_rate": 0.00017252475247524752,
729
+ "loss": 0.8629,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 1.2856259659969087,
734
+ "grad_norm": 0.050953879952430725,
735
+ "learning_rate": 0.00017128712871287128,
736
+ "loss": 0.8386,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 1.2979907264296755,
741
+ "grad_norm": 0.047925543040037155,
742
+ "learning_rate": 0.00017004950495049502,
743
+ "loss": 0.8664,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 1.310355486862442,
748
+ "grad_norm": 0.054691240191459656,
749
+ "learning_rate": 0.0001688118811881188,
750
+ "loss": 0.8634,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 1.3227202472952087,
755
+ "grad_norm": 0.05087495222687721,
756
+ "learning_rate": 0.00016757425742574257,
757
+ "loss": 0.8482,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 1.3350850077279752,
762
+ "grad_norm": 0.051902078092098236,
763
+ "learning_rate": 0.00016633663366336633,
764
+ "loss": 0.8478,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 1.3474497681607418,
769
+ "grad_norm": 0.05033488944172859,
770
+ "learning_rate": 0.0001650990099009901,
771
+ "loss": 0.8572,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 1.3598145285935086,
776
+ "grad_norm": 0.05153260752558708,
777
+ "learning_rate": 0.00016386138613861385,
778
+ "loss": 0.8465,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 1.3721792890262752,
783
+ "grad_norm": 0.052806247025728226,
784
+ "learning_rate": 0.0001626237623762376,
785
+ "loss": 0.8707,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 1.3845440494590417,
790
+ "grad_norm": 0.05425600707530975,
791
+ "learning_rate": 0.00016138613861386137,
792
+ "loss": 0.858,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 1.3969088098918083,
797
+ "grad_norm": 0.05116913095116615,
798
+ "learning_rate": 0.00016014851485148513,
799
+ "loss": 0.867,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 1.409273570324575,
804
+ "grad_norm": 0.052799541503190994,
805
+ "learning_rate": 0.0001589108910891089,
806
+ "loss": 0.849,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 1.4216383307573417,
811
+ "grad_norm": 0.06275513023138046,
812
+ "learning_rate": 0.00015767326732673266,
813
+ "loss": 0.8577,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 1.4340030911901083,
818
+ "grad_norm": 0.051965054124593735,
819
+ "learning_rate": 0.00015643564356435642,
820
+ "loss": 0.853,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 1.4463678516228748,
825
+ "grad_norm": 0.05356529727578163,
826
+ "learning_rate": 0.00015519801980198018,
827
+ "loss": 0.8789,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 1.4587326120556414,
832
+ "grad_norm": 0.05566537007689476,
833
+ "learning_rate": 0.00015396039603960397,
834
+ "loss": 0.8716,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 1.471097372488408,
839
+ "grad_norm": 0.05320986732840538,
840
+ "learning_rate": 0.0001527227722772277,
841
+ "loss": 0.8736,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 1.4834621329211746,
846
+ "grad_norm": 0.049232013523578644,
847
+ "learning_rate": 0.00015148514851485146,
848
+ "loss": 0.849,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 1.4958268933539411,
853
+ "grad_norm": 0.058629848062992096,
854
+ "learning_rate": 0.00015024752475247525,
855
+ "loss": 0.8732,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 1.508191653786708,
860
+ "grad_norm": 0.055390194058418274,
861
+ "learning_rate": 0.000149009900990099,
862
+ "loss": 0.8678,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 1.5205564142194745,
867
+ "grad_norm": 0.05527270585298538,
868
+ "learning_rate": 0.00014777227722772275,
869
+ "loss": 0.8643,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 1.532921174652241,
874
+ "grad_norm": 0.04652067646384239,
875
+ "learning_rate": 0.00014653465346534653,
876
+ "loss": 0.8429,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 1.545285935085008,
881
+ "grad_norm": 0.05379781499505043,
882
+ "learning_rate": 0.0001452970297029703,
883
+ "loss": 0.8492,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 1.5576506955177742,
888
+ "grad_norm": 0.05249844118952751,
889
+ "learning_rate": 0.00014405940594059403,
890
+ "loss": 0.8447,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 1.570015455950541,
895
+ "grad_norm": 0.049639806151390076,
896
+ "learning_rate": 0.00014282178217821782,
897
+ "loss": 0.8667,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 1.5823802163833076,
902
+ "grad_norm": 0.052679967135190964,
903
+ "learning_rate": 0.00014158415841584158,
904
+ "loss": 0.8739,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 1.5947449768160742,
909
+ "grad_norm": 0.05990573391318321,
910
+ "learning_rate": 0.00014034653465346534,
911
+ "loss": 0.8824,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 1.6071097372488408,
916
+ "grad_norm": 0.052240803837776184,
917
+ "learning_rate": 0.0001391089108910891,
918
+ "loss": 0.868,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 1.6194744976816073,
923
+ "grad_norm": 0.05380776897072792,
924
+ "learning_rate": 0.00013787128712871286,
925
+ "loss": 0.8442,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 1.6318392581143741,
930
+ "grad_norm": 0.05081896856427193,
931
+ "learning_rate": 0.00013663366336633662,
932
+ "loss": 0.8515,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 1.6442040185471405,
937
+ "grad_norm": 0.04869316518306732,
938
+ "learning_rate": 0.00013539603960396039,
939
+ "loss": 0.8339,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 1.6565687789799073,
944
+ "grad_norm": 0.056119490414857864,
945
+ "learning_rate": 0.00013415841584158415,
946
+ "loss": 0.8483,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 1.6689335394126739,
951
+ "grad_norm": 0.05742491036653519,
952
+ "learning_rate": 0.0001329207920792079,
953
+ "loss": 0.8494,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 1.6812982998454404,
958
+ "grad_norm": 0.055017951875925064,
959
+ "learning_rate": 0.00013168316831683167,
960
+ "loss": 0.8563,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 1.6936630602782072,
965
+ "grad_norm": 0.04963842034339905,
966
+ "learning_rate": 0.00013044554455445543,
967
+ "loss": 0.8405,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 1.7060278207109736,
972
+ "grad_norm": 0.05574873462319374,
973
+ "learning_rate": 0.0001292079207920792,
974
+ "loss": 0.8557,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 1.7183925811437404,
979
+ "grad_norm": 0.05482814088463783,
980
+ "learning_rate": 0.00012797029702970295,
981
+ "loss": 0.8559,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 1.730757341576507,
986
+ "grad_norm": 0.06040499359369278,
987
+ "learning_rate": 0.00012673267326732672,
988
+ "loss": 0.8638,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 1.7431221020092735,
993
+ "grad_norm": 0.05430367961525917,
994
+ "learning_rate": 0.00012549504950495048,
995
+ "loss": 0.8473,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 1.7554868624420403,
1000
+ "grad_norm": 0.048315104097127914,
1001
+ "learning_rate": 0.00012425742574257426,
1002
+ "loss": 0.845,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 1.7678516228748067,
1007
+ "grad_norm": 0.05943458899855614,
1008
+ "learning_rate": 0.000123019801980198,
1009
+ "loss": 0.853,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 1.7802163833075735,
1014
+ "grad_norm": 0.05744357407093048,
1015
+ "learning_rate": 0.00012178217821782177,
1016
+ "loss": 0.8562,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 1.79258114374034,
1021
+ "grad_norm": 0.06155743822455406,
1022
+ "learning_rate": 0.00012054455445544554,
1023
+ "loss": 0.8404,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 1.8049459041731066,
1028
+ "grad_norm": 0.04887942224740982,
1029
+ "learning_rate": 0.0001193069306930693,
1030
+ "loss": 0.8477,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 1.8173106646058734,
1035
+ "grad_norm": 0.05377992242574692,
1036
+ "learning_rate": 0.00011806930693069306,
1037
+ "loss": 0.8765,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 1.8296754250386398,
1042
+ "grad_norm": 0.0468844473361969,
1043
+ "learning_rate": 0.00011683168316831682,
1044
+ "loss": 0.8151,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 1.8420401854714066,
1049
+ "grad_norm": 0.05763052776455879,
1050
+ "learning_rate": 0.0001155940594059406,
1051
+ "loss": 0.8539,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 1.8544049459041732,
1056
+ "grad_norm": 0.054946307092905045,
1057
+ "learning_rate": 0.00011435643564356434,
1058
+ "loss": 0.8564,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 1.8667697063369397,
1063
+ "grad_norm": 0.060760248452425,
1064
+ "learning_rate": 0.0001131188118811881,
1065
+ "loss": 0.8498,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 1.8791344667697063,
1070
+ "grad_norm": 0.058039598166942596,
1071
+ "learning_rate": 0.00011188118811881188,
1072
+ "loss": 0.8647,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 1.8914992272024729,
1077
+ "grad_norm": 0.05479070916771889,
1078
+ "learning_rate": 0.00011064356435643564,
1079
+ "loss": 0.8625,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 1.9038639876352397,
1084
+ "grad_norm": 0.0583939254283905,
1085
+ "learning_rate": 0.00010940594059405939,
1086
+ "loss": 0.8695,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 1.916228748068006,
1091
+ "grad_norm": 0.058852337300777435,
1092
+ "learning_rate": 0.00010816831683168316,
1093
+ "loss": 0.8443,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 1.9285935085007728,
1098
+ "grad_norm": 0.05506705492734909,
1099
+ "learning_rate": 0.00010693069306930692,
1100
+ "loss": 0.8544,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 1.9409582689335394,
1105
+ "grad_norm": 0.05682089179754257,
1106
+ "learning_rate": 0.00010569306930693068,
1107
+ "loss": 0.8718,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 1.953323029366306,
1112
+ "grad_norm": 0.05604562535881996,
1113
+ "learning_rate": 0.00010445544554455445,
1114
+ "loss": 0.857,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 1.9656877897990728,
1119
+ "grad_norm": 0.058413226157426834,
1120
+ "learning_rate": 0.0001032178217821782,
1121
+ "loss": 0.8558,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 1.9780525502318391,
1126
+ "grad_norm": 0.054590627551078796,
1127
+ "learning_rate": 0.00010198019801980197,
1128
+ "loss": 0.8443,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 1.990417310664606,
1133
+ "grad_norm": 0.05447821691632271,
1134
+ "learning_rate": 0.00010074257425742573,
1135
+ "loss": 0.8672,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 2.002472952086553,
1140
+ "grad_norm": 0.05398769676685333,
1141
+ "learning_rate": 9.95049504950495e-05,
1142
+ "loss": 0.8582,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 2.01483771251932,
1147
+ "grad_norm": 0.057375263422727585,
1148
+ "learning_rate": 9.826732673267325e-05,
1149
+ "loss": 0.8418,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 2.0272024729520863,
1154
+ "grad_norm": 0.054974183440208435,
1155
+ "learning_rate": 9.702970297029701e-05,
1156
+ "loss": 0.8224,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 2.039567233384853,
1161
+ "grad_norm": 0.06044444069266319,
1162
+ "learning_rate": 9.579207920792079e-05,
1163
+ "loss": 0.8373,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 2.05193199381762,
1168
+ "grad_norm": 0.06379813700914383,
1169
+ "learning_rate": 9.455445544554454e-05,
1170
+ "loss": 0.8311,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 2.0642967542503863,
1175
+ "grad_norm": 0.05604099482297897,
1176
+ "learning_rate": 9.331683168316831e-05,
1177
+ "loss": 0.8586,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 2.076661514683153,
1182
+ "grad_norm": 0.05408864468336105,
1183
+ "learning_rate": 9.207920792079207e-05,
1184
+ "loss": 0.8385,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 2.0890262751159194,
1189
+ "grad_norm": 0.06171610206365585,
1190
+ "learning_rate": 9.084158415841582e-05,
1191
+ "loss": 0.836,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 2.1013910355486862,
1196
+ "grad_norm": 0.05357811599969864,
1197
+ "learning_rate": 8.96039603960396e-05,
1198
+ "loss": 0.8365,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 2.113755795981453,
1203
+ "grad_norm": 0.059701114892959595,
1204
+ "learning_rate": 8.836633663366336e-05,
1205
+ "loss": 0.8168,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 2.1261205564142194,
1210
+ "grad_norm": 0.05693197622895241,
1211
+ "learning_rate": 8.712871287128713e-05,
1212
+ "loss": 0.8588,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 2.138485316846986,
1217
+ "grad_norm": 0.06465724855661392,
1218
+ "learning_rate": 8.589108910891088e-05,
1219
+ "loss": 0.8342,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 2.1508500772797525,
1224
+ "grad_norm": 0.06339121609926224,
1225
+ "learning_rate": 8.465346534653464e-05,
1226
+ "loss": 0.8338,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 2.1632148377125193,
1231
+ "grad_norm": 0.05768771097064018,
1232
+ "learning_rate": 8.341584158415841e-05,
1233
+ "loss": 0.8321,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 2.175579598145286,
1238
+ "grad_norm": 0.05351224169135094,
1239
+ "learning_rate": 8.217821782178216e-05,
1240
+ "loss": 0.8426,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 2.1879443585780525,
1245
+ "grad_norm": 0.06381036341190338,
1246
+ "learning_rate": 8.094059405940594e-05,
1247
+ "loss": 0.8531,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 2.2003091190108193,
1252
+ "grad_norm": 0.057617682963609695,
1253
+ "learning_rate": 7.97029702970297e-05,
1254
+ "loss": 0.8263,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 2.2126738794435856,
1259
+ "grad_norm": 0.06280315667390823,
1260
+ "learning_rate": 7.846534653465345e-05,
1261
+ "loss": 0.8073,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 2.2250386398763524,
1266
+ "grad_norm": 0.06251993030309677,
1267
+ "learning_rate": 7.722772277227722e-05,
1268
+ "loss": 0.8285,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 2.237403400309119,
1273
+ "grad_norm": 0.05487222224473953,
1274
+ "learning_rate": 7.599009900990098e-05,
1275
+ "loss": 0.8389,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 2.2497681607418856,
1280
+ "grad_norm": 0.06212658807635307,
1281
+ "learning_rate": 7.475247524752474e-05,
1282
+ "loss": 0.819,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 2.2621329211746524,
1287
+ "grad_norm": 0.06791824847459793,
1288
+ "learning_rate": 7.35148514851485e-05,
1289
+ "loss": 0.823,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 2.2744976816074187,
1294
+ "grad_norm": 0.06564588844776154,
1295
+ "learning_rate": 7.227722772277227e-05,
1296
+ "loss": 0.8399,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 2.2868624420401855,
1301
+ "grad_norm": 0.07918984442949295,
1302
+ "learning_rate": 7.103960396039604e-05,
1303
+ "loss": 0.8441,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 2.2992272024729523,
1308
+ "grad_norm": 0.06684021651744843,
1309
+ "learning_rate": 6.98019801980198e-05,
1310
+ "loss": 0.8213,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 2.3115919629057187,
1315
+ "grad_norm": 0.05864300578832626,
1316
+ "learning_rate": 6.856435643564355e-05,
1317
+ "loss": 0.8238,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 2.3239567233384855,
1322
+ "grad_norm": 0.05827944353222847,
1323
+ "learning_rate": 6.732673267326732e-05,
1324
+ "loss": 0.8438,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 2.336321483771252,
1329
+ "grad_norm": 0.05539786070585251,
1330
+ "learning_rate": 6.608910891089109e-05,
1331
+ "loss": 0.8173,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 2.3486862442040186,
1336
+ "grad_norm": 0.06571885198354721,
1337
+ "learning_rate": 6.485148514851485e-05,
1338
+ "loss": 0.8262,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 2.361051004636785,
1343
+ "grad_norm": 0.06220625340938568,
1344
+ "learning_rate": 6.361386138613861e-05,
1345
+ "loss": 0.8576,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 2.3734157650695518,
1350
+ "grad_norm": 0.0579352080821991,
1351
+ "learning_rate": 6.237623762376237e-05,
1352
+ "loss": 0.8227,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 2.3857805255023186,
1357
+ "grad_norm": 0.06193961948156357,
1358
+ "learning_rate": 6.113861386138613e-05,
1359
+ "loss": 0.8414,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 2.398145285935085,
1364
+ "grad_norm": 0.061364226043224335,
1365
+ "learning_rate": 5.99009900990099e-05,
1366
+ "loss": 0.8387,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 2.4105100463678517,
1371
+ "grad_norm": 0.05785266309976578,
1372
+ "learning_rate": 5.866336633663366e-05,
1373
+ "loss": 0.8284,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 2.422874806800618,
1378
+ "grad_norm": 0.057832520455121994,
1379
+ "learning_rate": 5.742574257425742e-05,
1380
+ "loss": 0.8197,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 2.435239567233385,
1385
+ "grad_norm": 0.06421726942062378,
1386
+ "learning_rate": 5.618811881188118e-05,
1387
+ "loss": 0.8402,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 2.4476043276661517,
1392
+ "grad_norm": 0.06815137714147568,
1393
+ "learning_rate": 5.4950495049504944e-05,
1394
+ "loss": 0.8389,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 2.459969088098918,
1399
+ "grad_norm": 0.06730205565690994,
1400
+ "learning_rate": 5.371287128712871e-05,
1401
+ "loss": 0.8604,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 2.472333848531685,
1406
+ "grad_norm": 0.05876993387937546,
1407
+ "learning_rate": 5.247524752475247e-05,
1408
+ "loss": 0.8254,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 2.484698608964451,
1413
+ "grad_norm": 0.06757384538650513,
1414
+ "learning_rate": 5.1237623762376234e-05,
1415
+ "loss": 0.8292,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 2.497063369397218,
1420
+ "grad_norm": 0.06531625986099243,
1421
+ "learning_rate": 4.9999999999999996e-05,
1422
+ "loss": 0.8321,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 2.5094281298299848,
1427
+ "grad_norm": 0.060086678713560104,
1428
+ "learning_rate": 4.876237623762376e-05,
1429
+ "loss": 0.8459,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 2.521792890262751,
1434
+ "grad_norm": 0.06336929649114609,
1435
+ "learning_rate": 4.752475247524752e-05,
1436
+ "loss": 0.82,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 2.534157650695518,
1441
+ "grad_norm": 0.06393607705831528,
1442
+ "learning_rate": 4.6287128712871286e-05,
1443
+ "loss": 0.8313,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 2.5465224111282843,
1448
+ "grad_norm": 0.06480514258146286,
1449
+ "learning_rate": 4.504950495049505e-05,
1450
+ "loss": 0.8442,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 2.558887171561051,
1455
+ "grad_norm": 0.07233238965272903,
1456
+ "learning_rate": 4.38118811881188e-05,
1457
+ "loss": 0.8256,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 2.5712519319938174,
1462
+ "grad_norm": 0.06636520475149155,
1463
+ "learning_rate": 4.257425742574257e-05,
1464
+ "loss": 0.8284,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 2.583616692426584,
1469
+ "grad_norm": 0.07016933709383011,
1470
+ "learning_rate": 4.133663366336633e-05,
1471
+ "loss": 0.8378,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 2.595981452859351,
1476
+ "grad_norm": 0.06668656319379807,
1477
+ "learning_rate": 4.00990099009901e-05,
1478
+ "loss": 0.8461,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 2.6083462132921174,
1483
+ "grad_norm": 0.07296927273273468,
1484
+ "learning_rate": 3.886138613861386e-05,
1485
+ "loss": 0.8432,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 2.620710973724884,
1490
+ "grad_norm": 0.06670273840427399,
1491
+ "learning_rate": 3.7623762376237615e-05,
1492
+ "loss": 0.819,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 2.633075734157651,
1497
+ "grad_norm": 0.060203880071640015,
1498
+ "learning_rate": 3.638613861386138e-05,
1499
+ "loss": 0.8063,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 2.6454404945904173,
1504
+ "grad_norm": 0.06635984778404236,
1505
+ "learning_rate": 3.5148514851485144e-05,
1506
+ "loss": 0.8364,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 2.6578052550231837,
1511
+ "grad_norm": 0.060412149876356125,
1512
+ "learning_rate": 3.3910891089108906e-05,
1513
+ "loss": 0.827,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 2.6701700154559505,
1518
+ "grad_norm": 0.05948295816779137,
1519
+ "learning_rate": 3.267326732673267e-05,
1520
+ "loss": 0.802,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 2.6825347758887172,
1525
+ "grad_norm": 0.06251130253076553,
1526
+ "learning_rate": 3.1435643564356435e-05,
1527
+ "loss": 0.8302,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 2.6948995363214836,
1532
+ "grad_norm": 0.06650058180093765,
1533
+ "learning_rate": 3.0198019801980193e-05,
1534
+ "loss": 0.8386,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 2.7072642967542504,
1539
+ "grad_norm": 0.07029715925455093,
1540
+ "learning_rate": 2.8960396039603958e-05,
1541
+ "loss": 0.8421,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 2.719629057187017,
1546
+ "grad_norm": 0.06135771796107292,
1547
+ "learning_rate": 2.772277227722772e-05,
1548
+ "loss": 0.829,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 2.7319938176197835,
1553
+ "grad_norm": 0.06303984671831131,
1554
+ "learning_rate": 2.6485148514851484e-05,
1555
+ "loss": 0.8408,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 2.7443585780525503,
1560
+ "grad_norm": 0.06396885961294174,
1561
+ "learning_rate": 2.5247524752475248e-05,
1562
+ "loss": 0.817,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 2.7567233384853167,
1567
+ "grad_norm": 0.05814013257622719,
1568
+ "learning_rate": 2.4009900990099006e-05,
1569
+ "loss": 0.8384,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 2.7690880989180835,
1574
+ "grad_norm": 0.07185972481966019,
1575
+ "learning_rate": 2.277227722772277e-05,
1576
+ "loss": 0.8143,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 2.78145285935085,
1581
+ "grad_norm": 0.06624460965394974,
1582
+ "learning_rate": 2.1534653465346532e-05,
1583
+ "loss": 0.8296,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 2.7938176197836166,
1588
+ "grad_norm": 0.06510159373283386,
1589
+ "learning_rate": 2.0297029702970297e-05,
1590
+ "loss": 0.8302,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 2.8061823802163834,
1595
+ "grad_norm": 0.06376007944345474,
1596
+ "learning_rate": 1.9059405940594058e-05,
1597
+ "loss": 0.8173,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 2.81854714064915,
1602
+ "grad_norm": 0.0644875094294548,
1603
+ "learning_rate": 1.782178217821782e-05,
1604
+ "loss": 0.8358,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 2.8309119010819166,
1609
+ "grad_norm": 0.05571649968624115,
1610
+ "learning_rate": 1.6584158415841584e-05,
1611
+ "loss": 0.8139,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 2.8432766615146834,
1616
+ "grad_norm": 0.06556589901447296,
1617
+ "learning_rate": 1.5346534653465345e-05,
1618
+ "loss": 0.8241,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 2.8556414219474497,
1623
+ "grad_norm": 0.06124770641326904,
1624
+ "learning_rate": 1.4108910891089108e-05,
1625
+ "loss": 0.8184,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 2.8680061823802165,
1630
+ "grad_norm": 0.06707081943750381,
1631
+ "learning_rate": 1.287128712871287e-05,
1632
+ "loss": 0.8194,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 2.880370942812983,
1637
+ "grad_norm": 0.06600210070610046,
1638
+ "learning_rate": 1.1633663366336632e-05,
1639
+ "loss": 0.8614,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 2.8927357032457497,
1644
+ "grad_norm": 0.06310021132230759,
1645
+ "learning_rate": 1.0396039603960395e-05,
1646
+ "loss": 0.8485,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 2.905100463678516,
1651
+ "grad_norm": 0.06110014021396637,
1652
+ "learning_rate": 9.158415841584158e-06,
1653
+ "loss": 0.8171,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 2.917465224111283,
1658
+ "grad_norm": 0.07767624408006668,
1659
+ "learning_rate": 7.92079207920792e-06,
1660
+ "loss": 0.8403,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 2.9298299845440496,
1665
+ "grad_norm": 0.07363846898078918,
1666
+ "learning_rate": 6.683168316831683e-06,
1667
+ "loss": 0.8453,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 2.942194744976816,
1672
+ "grad_norm": 0.06242545694112778,
1673
+ "learning_rate": 5.445544554455446e-06,
1674
+ "loss": 0.8448,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 2.954559505409583,
1679
+ "grad_norm": 0.06873054057359695,
1680
+ "learning_rate": 4.207920792079208e-06,
1681
+ "loss": 0.8412,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 2.966924265842349,
1686
+ "grad_norm": 0.06264466792345047,
1687
+ "learning_rate": 2.97029702970297e-06,
1688
+ "loss": 0.8426,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 2.979289026275116,
1693
+ "grad_norm": 0.06905832886695862,
1694
+ "learning_rate": 1.7326732673267324e-06,
1695
+ "loss": 0.8469,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 2.9916537867078823,
1700
+ "grad_norm": 0.061685774475336075,
1701
+ "learning_rate": 4.95049504950495e-07,
1702
+ "loss": 0.8339,
1703
+ "step": 2420
1704
+ }
1705
+ ],
1706
+ "logging_steps": 10,
1707
+ "max_steps": 2424,
1708
+ "num_input_tokens_seen": 0,
1709
+ "num_train_epochs": 3,
1710
+ "save_steps": 500,
1711
+ "stateful_callbacks": {
1712
+ "TrainerControl": {
1713
+ "args": {
1714
+ "should_epoch_stop": false,
1715
+ "should_evaluate": false,
1716
+ "should_log": false,
1717
+ "should_save": true,
1718
+ "should_training_stop": true
1719
+ },
1720
+ "attributes": {}
1721
+ }
1722
+ },
1723
+ "total_flos": 2.723183421298311e+18,
1724
+ "train_batch_size": 8,
1725
+ "trial_name": null,
1726
+ "trial_params": null
1727
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916d7fb58500db212016cbc23cab8f6e9cc2c103f69a6804826e7bb07c43a797
3
+ size 5496