rsh-raj commited on
Commit
e2100de
·
verified ·
1 Parent(s): bd38c05

Upload 8 files

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codellama-7b-bnb-4bit
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codellama-7b-bnb-4bit",
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": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
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
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj",
30
+ "o_proj",
31
+ "q_proj",
32
+ "v_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b483877b74c3198556e3dcb2976d2c708ebd7f4c13cf76d6c4080ffe0a98de7
3
+ size 639691872
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "unk_token": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32007": {
30
+ "content": "▁<PRE>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32008": {
38
+ "content": "▁<SUF>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32009": {
46
+ "content": "▁<MID>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32010": {
54
+ "content": "▁<EOT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "▁<PRE>",
64
+ "▁<MID>",
65
+ "▁<SUF>",
66
+ "▁<EOT>",
67
+ "▁<PRE>",
68
+ "▁<MID>",
69
+ "▁<SUF>",
70
+ "▁<EOT>"
71
+ ],
72
+ "bos_token": "<s>",
73
+ "clean_up_tokenization_spaces": false,
74
+ "eos_token": "</s>",
75
+ "eot_token": "▁<EOT>",
76
+ "extra_special_tokens": {},
77
+ "fill_token": "<FILL_ME>",
78
+ "legacy": null,
79
+ "middle_token": "▁<MID>",
80
+ "model_max_length": 16384,
81
+ "pad_token": "<unk>",
82
+ "padding_side": "right",
83
+ "prefix_token": "▁<PRE>",
84
+ "sp_model_kwargs": {},
85
+ "suffix_token": "▁<SUF>",
86
+ "tokenizer_class": "CodeLlamaTokenizer",
87
+ "unk_token": "<unk>",
88
+ "use_default_system_prompt": false
89
+ }
trainer_state.json ADDED
@@ -0,0 +1,1209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1680,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03571428571428571,
13
+ "grad_norm": 0.2544403374195099,
14
+ "learning_rate": 9.970149253731344e-05,
15
+ "loss": 1.4916,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07142857142857142,
20
+ "grad_norm": 0.17301955819129944,
21
+ "learning_rate": 9.91044776119403e-05,
22
+ "loss": 0.908,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10714285714285714,
27
+ "grad_norm": 0.11398938298225403,
28
+ "learning_rate": 9.850746268656717e-05,
29
+ "loss": 0.4285,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.14285714285714285,
34
+ "grad_norm": 0.08889368921518326,
35
+ "learning_rate": 9.791044776119404e-05,
36
+ "loss": 0.3305,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.17857142857142858,
41
+ "grad_norm": 0.07145170122385025,
42
+ "learning_rate": 9.731343283582089e-05,
43
+ "loss": 0.3709,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.21428571428571427,
48
+ "grad_norm": 0.08652878552675247,
49
+ "learning_rate": 9.671641791044777e-05,
50
+ "loss": 0.3822,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.25,
55
+ "grad_norm": 0.0885363519191742,
56
+ "learning_rate": 9.611940298507464e-05,
57
+ "loss": 0.3799,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2857142857142857,
62
+ "grad_norm": 0.07026822865009308,
63
+ "learning_rate": 9.552238805970149e-05,
64
+ "loss": 0.4085,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.32142857142857145,
69
+ "grad_norm": 0.07123386859893799,
70
+ "learning_rate": 9.492537313432837e-05,
71
+ "loss": 0.2925,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.35714285714285715,
76
+ "grad_norm": 0.07839447259902954,
77
+ "learning_rate": 9.432835820895522e-05,
78
+ "loss": 0.3455,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.39285714285714285,
83
+ "grad_norm": 0.0755082443356514,
84
+ "learning_rate": 9.373134328358209e-05,
85
+ "loss": 0.3406,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.42857142857142855,
90
+ "grad_norm": 0.0823201835155487,
91
+ "learning_rate": 9.313432835820896e-05,
92
+ "loss": 0.3259,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4642857142857143,
97
+ "grad_norm": 0.08403510600328445,
98
+ "learning_rate": 9.253731343283582e-05,
99
+ "loss": 0.3017,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5,
104
+ "grad_norm": 0.10145727545022964,
105
+ "learning_rate": 9.194029850746269e-05,
106
+ "loss": 0.3473,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5357142857142857,
111
+ "grad_norm": 0.07516448199748993,
112
+ "learning_rate": 9.134328358208956e-05,
113
+ "loss": 0.2865,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5714285714285714,
118
+ "grad_norm": 0.07223515212535858,
119
+ "learning_rate": 9.074626865671642e-05,
120
+ "loss": 0.3045,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6071428571428571,
125
+ "grad_norm": 0.07799769937992096,
126
+ "learning_rate": 9.014925373134329e-05,
127
+ "loss": 0.3306,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6428571428571429,
132
+ "grad_norm": 0.08388201892375946,
133
+ "learning_rate": 8.955223880597016e-05,
134
+ "loss": 0.309,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6785714285714286,
139
+ "grad_norm": 0.0838930755853653,
140
+ "learning_rate": 8.895522388059702e-05,
141
+ "loss": 0.3356,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7142857142857143,
146
+ "grad_norm": 0.07891852408647537,
147
+ "learning_rate": 8.835820895522389e-05,
148
+ "loss": 0.3048,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.75,
153
+ "grad_norm": 0.07239601761102676,
154
+ "learning_rate": 8.776119402985074e-05,
155
+ "loss": 0.3601,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7857142857142857,
160
+ "grad_norm": 0.07549150288105011,
161
+ "learning_rate": 8.716417910447762e-05,
162
+ "loss": 0.3415,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8214285714285714,
167
+ "grad_norm": 0.08595260232686996,
168
+ "learning_rate": 8.656716417910447e-05,
169
+ "loss": 0.3521,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8571428571428571,
174
+ "grad_norm": 0.08356776833534241,
175
+ "learning_rate": 8.597014925373134e-05,
176
+ "loss": 0.2898,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8928571428571429,
181
+ "grad_norm": 0.07699938863515854,
182
+ "learning_rate": 8.537313432835822e-05,
183
+ "loss": 0.3038,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9285714285714286,
188
+ "grad_norm": 0.07691926509141922,
189
+ "learning_rate": 8.477611940298507e-05,
190
+ "loss": 0.3403,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9642857142857143,
195
+ "grad_norm": 0.07808340340852737,
196
+ "learning_rate": 8.417910447761194e-05,
197
+ "loss": 0.3164,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.0,
202
+ "grad_norm": 0.07639653235673904,
203
+ "learning_rate": 8.358208955223881e-05,
204
+ "loss": 0.2872,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.0357142857142858,
209
+ "grad_norm": 0.07973363250494003,
210
+ "learning_rate": 8.298507462686567e-05,
211
+ "loss": 0.3111,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.0714285714285714,
216
+ "grad_norm": 0.08878948539495468,
217
+ "learning_rate": 8.238805970149254e-05,
218
+ "loss": 0.317,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 1.1071428571428572,
223
+ "grad_norm": 0.07322458922863007,
224
+ "learning_rate": 8.179104477611941e-05,
225
+ "loss": 0.2999,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.1428571428571428,
230
+ "grad_norm": 0.08571141958236694,
231
+ "learning_rate": 8.119402985074627e-05,
232
+ "loss": 0.2642,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.1785714285714286,
237
+ "grad_norm": 0.10807636380195618,
238
+ "learning_rate": 8.059701492537314e-05,
239
+ "loss": 0.3024,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 1.2142857142857142,
244
+ "grad_norm": 0.1146746426820755,
245
+ "learning_rate": 8e-05,
246
+ "loss": 0.2788,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 1.25,
251
+ "grad_norm": 0.10096397995948792,
252
+ "learning_rate": 7.940298507462687e-05,
253
+ "loss": 0.278,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 1.2857142857142856,
258
+ "grad_norm": 0.08820641040802002,
259
+ "learning_rate": 7.880597014925374e-05,
260
+ "loss": 0.3123,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 1.3214285714285714,
265
+ "grad_norm": 0.09731289744377136,
266
+ "learning_rate": 7.820895522388059e-05,
267
+ "loss": 0.2962,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 1.3571428571428572,
272
+ "grad_norm": 0.09726134687662125,
273
+ "learning_rate": 7.761194029850747e-05,
274
+ "loss": 0.2723,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 1.3928571428571428,
279
+ "grad_norm": 0.1366291046142578,
280
+ "learning_rate": 7.701492537313433e-05,
281
+ "loss": 0.2549,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 1.4285714285714286,
286
+ "grad_norm": 0.09392824023962021,
287
+ "learning_rate": 7.641791044776119e-05,
288
+ "loss": 0.2785,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 1.4642857142857144,
293
+ "grad_norm": 0.10537943243980408,
294
+ "learning_rate": 7.582089552238806e-05,
295
+ "loss": 0.2692,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 1.5,
300
+ "grad_norm": 0.11430277675390244,
301
+ "learning_rate": 7.522388059701493e-05,
302
+ "loss": 0.2787,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 1.5357142857142856,
307
+ "grad_norm": 0.1093386635184288,
308
+ "learning_rate": 7.46268656716418e-05,
309
+ "loss": 0.2953,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 1.5714285714285714,
314
+ "grad_norm": 0.10960441827774048,
315
+ "learning_rate": 7.402985074626866e-05,
316
+ "loss": 0.2906,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.6071428571428572,
321
+ "grad_norm": 0.11768423765897751,
322
+ "learning_rate": 7.343283582089552e-05,
323
+ "loss": 0.3433,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.6428571428571428,
328
+ "grad_norm": 0.10420206189155579,
329
+ "learning_rate": 7.283582089552239e-05,
330
+ "loss": 0.2769,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.6785714285714286,
335
+ "grad_norm": 0.090525321662426,
336
+ "learning_rate": 7.223880597014926e-05,
337
+ "loss": 0.2859,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.7142857142857144,
342
+ "grad_norm": 0.11874176561832428,
343
+ "learning_rate": 7.164179104477612e-05,
344
+ "loss": 0.3243,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.75,
349
+ "grad_norm": 0.08634401112794876,
350
+ "learning_rate": 7.104477611940299e-05,
351
+ "loss": 0.2398,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.7857142857142856,
356
+ "grad_norm": 0.10205753147602081,
357
+ "learning_rate": 7.044776119402984e-05,
358
+ "loss": 0.3725,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.8214285714285714,
363
+ "grad_norm": 0.09119073301553726,
364
+ "learning_rate": 6.985074626865672e-05,
365
+ "loss": 0.2374,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 1.8571428571428572,
370
+ "grad_norm": 0.11212314665317535,
371
+ "learning_rate": 6.925373134328359e-05,
372
+ "loss": 0.2958,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 1.8928571428571428,
377
+ "grad_norm": 0.11491134017705917,
378
+ "learning_rate": 6.865671641791044e-05,
379
+ "loss": 0.291,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 1.9285714285714286,
384
+ "grad_norm": 0.11586255580186844,
385
+ "learning_rate": 6.805970149253732e-05,
386
+ "loss": 0.3222,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 1.9642857142857144,
391
+ "grad_norm": 0.10049410909414291,
392
+ "learning_rate": 6.746268656716418e-05,
393
+ "loss": 0.2914,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 2.0,
398
+ "grad_norm": 0.08521942794322968,
399
+ "learning_rate": 6.686567164179106e-05,
400
+ "loss": 0.2999,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 2.0357142857142856,
405
+ "grad_norm": 0.11586008220911026,
406
+ "learning_rate": 6.626865671641791e-05,
407
+ "loss": 0.2531,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 2.0714285714285716,
412
+ "grad_norm": 0.1241249069571495,
413
+ "learning_rate": 6.567164179104478e-05,
414
+ "loss": 0.2422,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 2.107142857142857,
419
+ "grad_norm": 0.15100309252738953,
420
+ "learning_rate": 6.507462686567164e-05,
421
+ "loss": 0.2177,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 2.142857142857143,
426
+ "grad_norm": 0.1219455674290657,
427
+ "learning_rate": 6.447761194029851e-05,
428
+ "loss": 0.2349,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 2.1785714285714284,
433
+ "grad_norm": 0.1460845172405243,
434
+ "learning_rate": 6.388059701492538e-05,
435
+ "loss": 0.2407,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 2.2142857142857144,
440
+ "grad_norm": 0.1512862741947174,
441
+ "learning_rate": 6.328358208955224e-05,
442
+ "loss": 0.284,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 2.25,
447
+ "grad_norm": 0.14087745547294617,
448
+ "learning_rate": 6.268656716417911e-05,
449
+ "loss": 0.2561,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 2.2857142857142856,
454
+ "grad_norm": 0.11492959409952164,
455
+ "learning_rate": 6.208955223880598e-05,
456
+ "loss": 0.2708,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 2.3214285714285716,
461
+ "grad_norm": 0.15090124309062958,
462
+ "learning_rate": 6.149253731343284e-05,
463
+ "loss": 0.2092,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 2.357142857142857,
468
+ "grad_norm": 0.1459421068429947,
469
+ "learning_rate": 6.08955223880597e-05,
470
+ "loss": 0.2442,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 2.392857142857143,
475
+ "grad_norm": 0.1471620351076126,
476
+ "learning_rate": 6.029850746268657e-05,
477
+ "loss": 0.267,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 2.4285714285714284,
482
+ "grad_norm": 0.1476091742515564,
483
+ "learning_rate": 5.970149253731343e-05,
484
+ "loss": 0.2867,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 2.4642857142857144,
489
+ "grad_norm": 0.15003158152103424,
490
+ "learning_rate": 5.91044776119403e-05,
491
+ "loss": 0.2711,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 2.5,
496
+ "grad_norm": 0.16726762056350708,
497
+ "learning_rate": 5.8507462686567175e-05,
498
+ "loss": 0.2398,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 2.5357142857142856,
503
+ "grad_norm": 0.1285712569952011,
504
+ "learning_rate": 5.7910447761194034e-05,
505
+ "loss": 0.2768,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 2.571428571428571,
510
+ "grad_norm": 0.13130241632461548,
511
+ "learning_rate": 5.73134328358209e-05,
512
+ "loss": 0.2486,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 2.607142857142857,
517
+ "grad_norm": 0.15794238448143005,
518
+ "learning_rate": 5.671641791044776e-05,
519
+ "loss": 0.2367,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 2.642857142857143,
524
+ "grad_norm": 0.16475516557693481,
525
+ "learning_rate": 5.6119402985074634e-05,
526
+ "loss": 0.2593,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 2.678571428571429,
531
+ "grad_norm": 0.14723050594329834,
532
+ "learning_rate": 5.5522388059701494e-05,
533
+ "loss": 0.2398,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 2.7142857142857144,
538
+ "grad_norm": 0.14579030871391296,
539
+ "learning_rate": 5.492537313432836e-05,
540
+ "loss": 0.2603,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 2.75,
545
+ "grad_norm": 0.14156433939933777,
546
+ "learning_rate": 5.432835820895522e-05,
547
+ "loss": 0.2241,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 2.7857142857142856,
552
+ "grad_norm": 0.1483439803123474,
553
+ "learning_rate": 5.373134328358209e-05,
554
+ "loss": 0.2514,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 2.821428571428571,
559
+ "grad_norm": 0.1641162484884262,
560
+ "learning_rate": 5.313432835820896e-05,
561
+ "loss": 0.2479,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 2.857142857142857,
566
+ "grad_norm": 0.1514202207326889,
567
+ "learning_rate": 5.253731343283582e-05,
568
+ "loss": 0.2317,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 2.892857142857143,
573
+ "grad_norm": 0.13422024250030518,
574
+ "learning_rate": 5.194029850746269e-05,
575
+ "loss": 0.2639,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 2.928571428571429,
580
+ "grad_norm": 0.12607942521572113,
581
+ "learning_rate": 5.134328358208955e-05,
582
+ "loss": 0.2111,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 2.9642857142857144,
587
+ "grad_norm": 0.13523127138614655,
588
+ "learning_rate": 5.074626865671642e-05,
589
+ "loss": 0.2522,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 3.0,
594
+ "grad_norm": 0.17928624153137207,
595
+ "learning_rate": 5.014925373134328e-05,
596
+ "loss": 0.2688,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 3.0357142857142856,
601
+ "grad_norm": 0.15228058397769928,
602
+ "learning_rate": 4.955223880597015e-05,
603
+ "loss": 0.1855,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 3.0714285714285716,
608
+ "grad_norm": 0.15598702430725098,
609
+ "learning_rate": 4.895522388059702e-05,
610
+ "loss": 0.2103,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 3.107142857142857,
615
+ "grad_norm": 0.16875101625919342,
616
+ "learning_rate": 4.8358208955223885e-05,
617
+ "loss": 0.2006,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 3.142857142857143,
622
+ "grad_norm": 0.16867318749427795,
623
+ "learning_rate": 4.7761194029850745e-05,
624
+ "loss": 0.1751,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 3.1785714285714284,
629
+ "grad_norm": 0.17668938636779785,
630
+ "learning_rate": 4.716417910447761e-05,
631
+ "loss": 0.1818,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 3.2142857142857144,
636
+ "grad_norm": 0.19076865911483765,
637
+ "learning_rate": 4.656716417910448e-05,
638
+ "loss": 0.2115,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 3.25,
643
+ "grad_norm": 0.21991585195064545,
644
+ "learning_rate": 4.5970149253731345e-05,
645
+ "loss": 0.2076,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 3.2857142857142856,
650
+ "grad_norm": 0.1979696899652481,
651
+ "learning_rate": 4.537313432835821e-05,
652
+ "loss": 0.2359,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 3.3214285714285716,
657
+ "grad_norm": 0.20029081404209137,
658
+ "learning_rate": 4.477611940298508e-05,
659
+ "loss": 0.1868,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 3.357142857142857,
664
+ "grad_norm": 0.20280781388282776,
665
+ "learning_rate": 4.4179104477611944e-05,
666
+ "loss": 0.2117,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 3.392857142857143,
671
+ "grad_norm": 0.22452795505523682,
672
+ "learning_rate": 4.358208955223881e-05,
673
+ "loss": 0.2021,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 3.4285714285714284,
678
+ "grad_norm": 0.1844116449356079,
679
+ "learning_rate": 4.298507462686567e-05,
680
+ "loss": 0.2223,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 3.4642857142857144,
685
+ "grad_norm": 0.19978521764278412,
686
+ "learning_rate": 4.238805970149254e-05,
687
+ "loss": 0.1995,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 3.5,
692
+ "grad_norm": 0.19762808084487915,
693
+ "learning_rate": 4.1791044776119404e-05,
694
+ "loss": 0.1821,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 3.5357142857142856,
699
+ "grad_norm": 0.19516855478286743,
700
+ "learning_rate": 4.119402985074627e-05,
701
+ "loss": 0.1961,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 3.571428571428571,
706
+ "grad_norm": 0.1498711109161377,
707
+ "learning_rate": 4.059701492537314e-05,
708
+ "loss": 0.1688,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 3.607142857142857,
713
+ "grad_norm": 0.2100873589515686,
714
+ "learning_rate": 4e-05,
715
+ "loss": 0.2069,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 3.642857142857143,
720
+ "grad_norm": 0.19105233252048492,
721
+ "learning_rate": 3.940298507462687e-05,
722
+ "loss": 0.1784,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 3.678571428571429,
727
+ "grad_norm": 0.20961785316467285,
728
+ "learning_rate": 3.8805970149253736e-05,
729
+ "loss": 0.2109,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 3.7142857142857144,
734
+ "grad_norm": 0.2236211895942688,
735
+ "learning_rate": 3.8208955223880596e-05,
736
+ "loss": 0.1971,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 3.75,
741
+ "grad_norm": 0.2324950248003006,
742
+ "learning_rate": 3.761194029850746e-05,
743
+ "loss": 0.2296,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 3.7857142857142856,
748
+ "grad_norm": 0.1860949546098709,
749
+ "learning_rate": 3.701492537313433e-05,
750
+ "loss": 0.1956,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 3.821428571428571,
755
+ "grad_norm": 0.18874789774417877,
756
+ "learning_rate": 3.6417910447761196e-05,
757
+ "loss": 0.1876,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 3.857142857142857,
762
+ "grad_norm": 0.20682772994041443,
763
+ "learning_rate": 3.582089552238806e-05,
764
+ "loss": 0.1775,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 3.892857142857143,
769
+ "grad_norm": 0.1853661686182022,
770
+ "learning_rate": 3.522388059701492e-05,
771
+ "loss": 0.2158,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 3.928571428571429,
776
+ "grad_norm": 0.2258283495903015,
777
+ "learning_rate": 3.4626865671641795e-05,
778
+ "loss": 0.2124,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 3.9642857142857144,
783
+ "grad_norm": 0.22331808507442474,
784
+ "learning_rate": 3.402985074626866e-05,
785
+ "loss": 0.197,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 4.0,
790
+ "grad_norm": 0.19635970890522003,
791
+ "learning_rate": 3.343283582089553e-05,
792
+ "loss": 0.2208,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 4.035714285714286,
797
+ "grad_norm": 0.23908133804798126,
798
+ "learning_rate": 3.283582089552239e-05,
799
+ "loss": 0.1415,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 4.071428571428571,
804
+ "grad_norm": 0.18970990180969238,
805
+ "learning_rate": 3.2238805970149255e-05,
806
+ "loss": 0.1568,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 4.107142857142857,
811
+ "grad_norm": 0.19420242309570312,
812
+ "learning_rate": 3.164179104477612e-05,
813
+ "loss": 0.1341,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 4.142857142857143,
818
+ "grad_norm": 0.23171567916870117,
819
+ "learning_rate": 3.104477611940299e-05,
820
+ "loss": 0.1501,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 4.178571428571429,
825
+ "grad_norm": 0.2723298668861389,
826
+ "learning_rate": 3.044776119402985e-05,
827
+ "loss": 0.1318,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 4.214285714285714,
832
+ "grad_norm": 0.23267976939678192,
833
+ "learning_rate": 2.9850746268656714e-05,
834
+ "loss": 0.1461,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 4.25,
839
+ "grad_norm": 0.1981896311044693,
840
+ "learning_rate": 2.9253731343283587e-05,
841
+ "loss": 0.1456,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 4.285714285714286,
846
+ "grad_norm": 0.23760183155536652,
847
+ "learning_rate": 2.865671641791045e-05,
848
+ "loss": 0.1363,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 4.321428571428571,
853
+ "grad_norm": 0.2675766348838806,
854
+ "learning_rate": 2.8059701492537317e-05,
855
+ "loss": 0.1682,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 4.357142857142857,
860
+ "grad_norm": 0.28035709261894226,
861
+ "learning_rate": 2.746268656716418e-05,
862
+ "loss": 0.1655,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 4.392857142857143,
867
+ "grad_norm": 0.25161004066467285,
868
+ "learning_rate": 2.6865671641791047e-05,
869
+ "loss": 0.1716,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 4.428571428571429,
874
+ "grad_norm": 0.22732681035995483,
875
+ "learning_rate": 2.626865671641791e-05,
876
+ "loss": 0.1834,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 4.464285714285714,
881
+ "grad_norm": 0.27060192823410034,
882
+ "learning_rate": 2.5671641791044776e-05,
883
+ "loss": 0.1746,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 4.5,
888
+ "grad_norm": 0.2511671185493469,
889
+ "learning_rate": 2.507462686567164e-05,
890
+ "loss": 0.138,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 4.535714285714286,
895
+ "grad_norm": 0.2796226441860199,
896
+ "learning_rate": 2.447761194029851e-05,
897
+ "loss": 0.1491,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 4.571428571428571,
902
+ "grad_norm": 0.2223314791917801,
903
+ "learning_rate": 2.3880597014925373e-05,
904
+ "loss": 0.1608,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 4.607142857142857,
909
+ "grad_norm": 0.36256590485572815,
910
+ "learning_rate": 2.328358208955224e-05,
911
+ "loss": 0.1617,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 4.642857142857143,
916
+ "grad_norm": 0.2692199647426605,
917
+ "learning_rate": 2.2686567164179106e-05,
918
+ "loss": 0.1569,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 4.678571428571429,
923
+ "grad_norm": 0.24237553775310516,
924
+ "learning_rate": 2.2089552238805972e-05,
925
+ "loss": 0.1464,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 4.714285714285714,
930
+ "grad_norm": 0.3302353024482727,
931
+ "learning_rate": 2.1492537313432835e-05,
932
+ "loss": 0.152,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 4.75,
937
+ "grad_norm": 0.30900838971138,
938
+ "learning_rate": 2.0895522388059702e-05,
939
+ "loss": 0.1583,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 4.785714285714286,
944
+ "grad_norm": 0.24671396613121033,
945
+ "learning_rate": 2.029850746268657e-05,
946
+ "loss": 0.173,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 4.821428571428571,
951
+ "grad_norm": 0.24723851680755615,
952
+ "learning_rate": 1.9701492537313435e-05,
953
+ "loss": 0.1596,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 4.857142857142857,
958
+ "grad_norm": 0.25336161255836487,
959
+ "learning_rate": 1.9104477611940298e-05,
960
+ "loss": 0.1502,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 4.892857142857143,
965
+ "grad_norm": 0.31974342465400696,
966
+ "learning_rate": 1.8507462686567165e-05,
967
+ "loss": 0.168,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 4.928571428571429,
972
+ "grad_norm": 0.26496830582618713,
973
+ "learning_rate": 1.791044776119403e-05,
974
+ "loss": 0.1679,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 4.964285714285714,
979
+ "grad_norm": 0.258620947599411,
980
+ "learning_rate": 1.7313432835820898e-05,
981
+ "loss": 0.147,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 5.0,
986
+ "grad_norm": 0.23998712003231049,
987
+ "learning_rate": 1.6716417910447764e-05,
988
+ "loss": 0.1307,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 5.035714285714286,
993
+ "grad_norm": 0.23837468028068542,
994
+ "learning_rate": 1.6119402985074627e-05,
995
+ "loss": 0.1111,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 5.071428571428571,
1000
+ "grad_norm": 0.25923416018486023,
1001
+ "learning_rate": 1.5522388059701494e-05,
1002
+ "loss": 0.1247,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 5.107142857142857,
1007
+ "grad_norm": 0.28286945819854736,
1008
+ "learning_rate": 1.4925373134328357e-05,
1009
+ "loss": 0.1243,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 5.142857142857143,
1014
+ "grad_norm": 0.2576877772808075,
1015
+ "learning_rate": 1.4328358208955225e-05,
1016
+ "loss": 0.1196,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 5.178571428571429,
1021
+ "grad_norm": 0.25924208760261536,
1022
+ "learning_rate": 1.373134328358209e-05,
1023
+ "loss": 0.1039,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 5.214285714285714,
1028
+ "grad_norm": 0.24316276609897614,
1029
+ "learning_rate": 1.3134328358208955e-05,
1030
+ "loss": 0.1308,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 5.25,
1035
+ "grad_norm": 0.43592455983161926,
1036
+ "learning_rate": 1.253731343283582e-05,
1037
+ "loss": 0.1185,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 5.285714285714286,
1042
+ "grad_norm": 0.23961405456066132,
1043
+ "learning_rate": 1.1940298507462686e-05,
1044
+ "loss": 0.1278,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 5.321428571428571,
1049
+ "grad_norm": 0.3024062514305115,
1050
+ "learning_rate": 1.1343283582089553e-05,
1051
+ "loss": 0.1082,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 5.357142857142857,
1056
+ "grad_norm": 0.22534772753715515,
1057
+ "learning_rate": 1.0746268656716418e-05,
1058
+ "loss": 0.1055,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 5.392857142857143,
1063
+ "grad_norm": 0.27198487520217896,
1064
+ "learning_rate": 1.0149253731343284e-05,
1065
+ "loss": 0.1244,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 5.428571428571429,
1070
+ "grad_norm": 0.3203181326389313,
1071
+ "learning_rate": 9.552238805970149e-06,
1072
+ "loss": 0.152,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 5.464285714285714,
1077
+ "grad_norm": 0.26531946659088135,
1078
+ "learning_rate": 8.955223880597016e-06,
1079
+ "loss": 0.1159,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 5.5,
1084
+ "grad_norm": 0.3129872977733612,
1085
+ "learning_rate": 8.358208955223882e-06,
1086
+ "loss": 0.0963,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 5.535714285714286,
1091
+ "grad_norm": 0.25911077857017517,
1092
+ "learning_rate": 7.761194029850747e-06,
1093
+ "loss": 0.1187,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 5.571428571428571,
1098
+ "grad_norm": 0.2714295983314514,
1099
+ "learning_rate": 7.164179104477613e-06,
1100
+ "loss": 0.1168,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 5.607142857142857,
1105
+ "grad_norm": 0.3102964460849762,
1106
+ "learning_rate": 6.5671641791044775e-06,
1107
+ "loss": 0.1029,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 5.642857142857143,
1112
+ "grad_norm": 0.25025418400764465,
1113
+ "learning_rate": 5.970149253731343e-06,
1114
+ "loss": 0.1193,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 5.678571428571429,
1119
+ "grad_norm": 0.30030593276023865,
1120
+ "learning_rate": 5.373134328358209e-06,
1121
+ "loss": 0.1278,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 5.714285714285714,
1126
+ "grad_norm": 0.2856218218803406,
1127
+ "learning_rate": 4.7761194029850745e-06,
1128
+ "loss": 0.1197,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 5.75,
1133
+ "grad_norm": 0.29614830017089844,
1134
+ "learning_rate": 4.179104477611941e-06,
1135
+ "loss": 0.1144,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 5.785714285714286,
1140
+ "grad_norm": 0.2907536029815674,
1141
+ "learning_rate": 3.5820895522388063e-06,
1142
+ "loss": 0.1026,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 5.821428571428571,
1147
+ "grad_norm": 0.29087764024734497,
1148
+ "learning_rate": 2.9850746268656716e-06,
1149
+ "loss": 0.1133,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 5.857142857142857,
1154
+ "grad_norm": 0.29417696595191956,
1155
+ "learning_rate": 2.3880597014925373e-06,
1156
+ "loss": 0.1063,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 5.892857142857143,
1161
+ "grad_norm": 0.2516196370124817,
1162
+ "learning_rate": 1.7910447761194032e-06,
1163
+ "loss": 0.1214,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 5.928571428571429,
1168
+ "grad_norm": 0.2914963364601135,
1169
+ "learning_rate": 1.1940298507462686e-06,
1170
+ "loss": 0.1352,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 5.964285714285714,
1175
+ "grad_norm": 0.28471362590789795,
1176
+ "learning_rate": 5.970149253731343e-07,
1177
+ "loss": 0.1096,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 6.0,
1182
+ "grad_norm": 0.26661351323127747,
1183
+ "learning_rate": 0.0,
1184
+ "loss": 0.108,
1185
+ "step": 1680
1186
+ }
1187
+ ],
1188
+ "logging_steps": 10,
1189
+ "max_steps": 1680,
1190
+ "num_input_tokens_seen": 0,
1191
+ "num_train_epochs": 6,
1192
+ "save_steps": 500,
1193
+ "stateful_callbacks": {
1194
+ "TrainerControl": {
1195
+ "args": {
1196
+ "should_epoch_stop": false,
1197
+ "should_evaluate": false,
1198
+ "should_log": false,
1199
+ "should_save": true,
1200
+ "should_training_stop": true
1201
+ },
1202
+ "attributes": {}
1203
+ }
1204
+ },
1205
+ "total_flos": 3.58674567892992e+17,
1206
+ "train_batch_size": 5,
1207
+ "trial_name": null,
1208
+ "trial_params": null
1209
+ }