manojbalaji1 commited on
Commit
395bc16
·
verified ·
1 Parent(s): 9197f00

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/phi-4
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/phi-4
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- 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. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ 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).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.18.0
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/phi-4",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 16,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
+ "qalora_group_size": 16,
32
+ "r": 16,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "o_proj",
37
+ "down_proj",
38
+ "v_proj",
39
+ "up_proj",
40
+ "q_proj",
41
+ "k_proj",
42
+ "gate_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89afd1c14c36ece1191cd7ea6498714ba013e28b76a5c261718c4c8cb0e56a9f
3
+ size 262219392
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93fe68502709f80dce7333494f48d0f26331a1dc25cf27deece73ebe753726e
3
+ size 524761587
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d0bc73f6a0196614398565ea2629ba85da708c447d04a84da26b5ab03582b6
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccc5f5bc18867063fd11889a931acbabe4e064fc5fea17c0c7a32aa6c051537
3
+ size 14917
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a4038642da45dbbbd64d023f9dea7e4e8c1735c39edf584d0936ab114a27a7
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "�",
17
+ "unk_token": {
18
+ "content": "�",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,790 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "5809": {
5
+ "content": "�",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100256": {
13
+ "content": "<|dummy_0|>",
14
+ "lstrip": true,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100257": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": true,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100258": {
29
+ "content": "<|fim_prefix|>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100259": {
37
+ "content": "<|fim_middle|>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100260": {
45
+ "content": "<|fim_suffix|>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100261": {
53
+ "content": "<|dummy_1|>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100262": {
61
+ "content": "<|dummy_2|>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100263": {
69
+ "content": "<|dummy_3|>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100264": {
77
+ "content": "<|im_start|>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100265": {
85
+ "content": "<|im_end|>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100266": {
93
+ "content": "<|im_sep|>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100267": {
101
+ "content": "<|dummy_4|>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100268": {
109
+ "content": "<|dummy_5|>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100269": {
117
+ "content": "<|dummy_6|>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100270": {
125
+ "content": "<|dummy_7|>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100271": {
133
+ "content": "<|dummy_8|>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100272": {
141
+ "content": "<|dummy_9|>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100273": {
149
+ "content": "<|dummy_10|>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100274": {
157
+ "content": "<|dummy_11|>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100275": {
165
+ "content": "<|dummy_12|>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100276": {
173
+ "content": "<|endofprompt|>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100277": {
181
+ "content": "<|dummy_13|>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "100278": {
189
+ "content": "<|dummy_14|>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "100279": {
197
+ "content": "<|dummy_15|>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "100280": {
205
+ "content": "<|dummy_16|>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "100281": {
213
+ "content": "<|dummy_17|>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "100282": {
221
+ "content": "<|dummy_18|>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "100283": {
229
+ "content": "<|dummy_19|>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "100284": {
237
+ "content": "<|dummy_20|>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "100285": {
245
+ "content": "<|dummy_21|>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "100286": {
253
+ "content": "<|dummy_22|>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "100287": {
261
+ "content": "<|dummy_23|>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "100288": {
269
+ "content": "<|dummy_24|>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "100289": {
277
+ "content": "<|dummy_25|>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "100290": {
285
+ "content": "<|dummy_26|>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "100291": {
293
+ "content": "<|dummy_27|>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "100292": {
301
+ "content": "<|dummy_28|>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "100293": {
309
+ "content": "<|dummy_29|>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "100294": {
317
+ "content": "<|dummy_30|>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "100295": {
325
+ "content": "<|dummy_31|>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "100296": {
333
+ "content": "<|dummy_32|>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "100297": {
341
+ "content": "<|dummy_33|>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "100298": {
349
+ "content": "<|dummy_34|>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "100299": {
357
+ "content": "<|dummy_35|>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "100300": {
365
+ "content": "<|dummy_36|>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "100301": {
373
+ "content": "<|dummy_37|>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "100302": {
381
+ "content": "<|dummy_38|>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "100303": {
389
+ "content": "<|dummy_39|>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "100304": {
397
+ "content": "<|dummy_40|>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "100305": {
405
+ "content": "<|dummy_41|>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "100306": {
413
+ "content": "<|dummy_42|>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "100307": {
421
+ "content": "<|dummy_43|>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "100308": {
429
+ "content": "<|dummy_44|>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "100309": {
437
+ "content": "<|dummy_45|>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "100310": {
445
+ "content": "<|dummy_46|>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "100311": {
453
+ "content": "<|dummy_47|>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "100312": {
461
+ "content": "<|dummy_48|>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "100313": {
469
+ "content": "<|dummy_49|>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "100314": {
477
+ "content": "<|dummy_50|>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "100315": {
485
+ "content": "<|dummy_51|>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "100316": {
493
+ "content": "<|dummy_52|>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "100317": {
501
+ "content": "<|dummy_53|>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "100318": {
509
+ "content": "<|dummy_54|>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "100319": {
517
+ "content": "<|dummy_55|>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "100320": {
525
+ "content": "<|dummy_56|>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "100321": {
533
+ "content": "<|dummy_57|>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "100322": {
541
+ "content": "<|dummy_58|>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "100323": {
549
+ "content": "<|dummy_59|>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "100324": {
557
+ "content": "<|dummy_60|>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "100325": {
565
+ "content": "<|dummy_61|>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "100326": {
573
+ "content": "<|dummy_62|>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "100327": {
581
+ "content": "<|dummy_63|>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "100328": {
589
+ "content": "<|dummy_64|>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "100329": {
597
+ "content": "<|dummy_65|>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "100330": {
605
+ "content": "<|dummy_66|>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "100331": {
613
+ "content": "<|dummy_67|>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "100332": {
621
+ "content": "<|dummy_68|>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "100333": {
629
+ "content": "<|dummy_69|>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "100334": {
637
+ "content": "<|dummy_70|>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "100335": {
645
+ "content": "<|dummy_71|>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "100336": {
653
+ "content": "<|dummy_72|>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "100337": {
661
+ "content": "<|dummy_73|>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "100338": {
669
+ "content": "<|dummy_74|>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "100339": {
677
+ "content": "<|dummy_75|>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "100340": {
685
+ "content": "<|dummy_76|>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "100341": {
693
+ "content": "<|dummy_77|>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "100342": {
701
+ "content": "<|dummy_78|>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "100343": {
709
+ "content": "<|dummy_79|>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "100344": {
717
+ "content": "<|dummy_80|>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "100345": {
725
+ "content": "<|dummy_81|>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "100346": {
733
+ "content": "<|dummy_82|>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "100347": {
741
+ "content": "<|dummy_83|>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "100348": {
749
+ "content": "<|dummy_84|>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "100349": {
757
+ "content": "<|dummy_85|>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "100350": {
765
+ "content": "<|dummy_86|>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "100351": {
773
+ "content": "<|dummy_87|>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ }
780
+ },
781
+ "bos_token": "<|endoftext|>",
782
+ "clean_up_tokenization_spaces": false,
783
+ "eos_token": "<|im_end|>",
784
+ "extra_special_tokens": {},
785
+ "model_max_length": 16384,
786
+ "pad_token": "�",
787
+ "padding_side": "right",
788
+ "tokenizer_class": "GPT2Tokenizer",
789
+ "unk_token": "�"
790
+ }
trainer_state.json ADDED
@@ -0,0 +1,2071 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 260,
3
+ "best_metric": 2.055561065673828,
4
+ "best_model_checkpoint": "training_checkpoints_response/checkpoint-260",
5
+ "epoch": 2.0,
6
+ "eval_steps": 10,
7
+ "global_step": 260,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007705273296412232,
14
+ "grad_norm": 2.017982244491577,
15
+ "learning_rate": 0.0,
16
+ "loss": 5.6166,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.015410546592824464,
21
+ "grad_norm": 2.01672101020813,
22
+ "learning_rate": 4e-05,
23
+ "loss": 5.5572,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.023115819889236697,
28
+ "grad_norm": 1.8205599784851074,
29
+ "learning_rate": 8e-05,
30
+ "loss": 5.4484,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.030821093185648928,
35
+ "grad_norm": 2.033153772354126,
36
+ "learning_rate": 0.00012,
37
+ "loss": 4.9237,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.03852636648206116,
42
+ "grad_norm": 0.9784541726112366,
43
+ "learning_rate": 0.00016,
44
+ "loss": 4.265,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.046231639778473395,
49
+ "grad_norm": 1.331294059753418,
50
+ "learning_rate": 0.0002,
51
+ "loss": 4.0517,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.05393691307488562,
56
+ "grad_norm": 0.9355050325393677,
57
+ "learning_rate": 0.0001999997057408339,
58
+ "loss": 3.8557,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.061642186371297855,
63
+ "grad_norm": 0.9015745520591736,
64
+ "learning_rate": 0.00019999882296506738,
65
+ "loss": 3.748,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0693474596677101,
70
+ "grad_norm": 1.2373126745224,
71
+ "learning_rate": 0.00019999735167789567,
72
+ "loss": 3.6541,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.07705273296412232,
77
+ "grad_norm": 1.0876531600952148,
78
+ "learning_rate": 0.00019999529188797764,
79
+ "loss": 3.6214,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.07705273296412232,
84
+ "eval_loss": 3.5308990478515625,
85
+ "eval_runtime": 106.7512,
86
+ "eval_samples_per_second": 13.311,
87
+ "eval_steps_per_second": 6.66,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.08475800626053455,
92
+ "grad_norm": 0.777705729007721,
93
+ "learning_rate": 0.0001999926436074355,
94
+ "loss": 3.48,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.09246327955694679,
99
+ "grad_norm": 0.8222021460533142,
100
+ "learning_rate": 0.00019998940685185489,
101
+ "loss": 3.496,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.10016855285335902,
106
+ "grad_norm": 0.6591089367866516,
107
+ "learning_rate": 0.00019998558164028465,
108
+ "loss": 3.4495,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.10787382614977124,
113
+ "grad_norm": 0.7974819540977478,
114
+ "learning_rate": 0.00019998116799523693,
115
+ "loss": 3.4051,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.11557909944618348,
120
+ "grad_norm": 0.7156230211257935,
121
+ "learning_rate": 0.00019997616594268677,
122
+ "loss": 3.1975,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.12328437274259571,
127
+ "grad_norm": 0.7960515022277832,
128
+ "learning_rate": 0.00019997057551207221,
129
+ "loss": 3.3313,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.13098964603900795,
134
+ "grad_norm": 0.8480799198150635,
135
+ "learning_rate": 0.00019996439673629395,
136
+ "loss": 3.2139,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.1386949193354202,
141
+ "grad_norm": 0.7401062250137329,
142
+ "learning_rate": 0.00019995762965171522,
143
+ "loss": 3.1781,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.1464001926318324,
148
+ "grad_norm": 0.9942293167114258,
149
+ "learning_rate": 0.00019995027429816156,
150
+ "loss": 3.156,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.15410546592824464,
155
+ "grad_norm": 1.0390517711639404,
156
+ "learning_rate": 0.00019994233071892056,
157
+ "loss": 3.1887,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.15410546592824464,
162
+ "eval_loss": 3.1240084171295166,
163
+ "eval_runtime": 105.7457,
164
+ "eval_samples_per_second": 13.438,
165
+ "eval_steps_per_second": 6.724,
166
+ "step": 20
167
+ },
168
+ {
169
+ "epoch": 0.16181073922465689,
170
+ "grad_norm": 0.7464455962181091,
171
+ "learning_rate": 0.0001999337989607416,
172
+ "loss": 3.2054,
173
+ "step": 21
174
+ },
175
+ {
176
+ "epoch": 0.1695160125210691,
177
+ "grad_norm": 0.7927932739257812,
178
+ "learning_rate": 0.00019992467907383572,
179
+ "loss": 3.0757,
180
+ "step": 22
181
+ },
182
+ {
183
+ "epoch": 0.17722128581748134,
184
+ "grad_norm": 0.9063711762428284,
185
+ "learning_rate": 0.00019991497111187506,
186
+ "loss": 2.9577,
187
+ "step": 23
188
+ },
189
+ {
190
+ "epoch": 0.18492655911389358,
191
+ "grad_norm": 0.8212271332740784,
192
+ "learning_rate": 0.00019990467513199283,
193
+ "loss": 2.9703,
194
+ "step": 24
195
+ },
196
+ {
197
+ "epoch": 0.1926318324103058,
198
+ "grad_norm": 0.9584224224090576,
199
+ "learning_rate": 0.00019989379119478268,
200
+ "loss": 3.0312,
201
+ "step": 25
202
+ },
203
+ {
204
+ "epoch": 0.20033710570671803,
205
+ "grad_norm": 0.8282833695411682,
206
+ "learning_rate": 0.00019988231936429865,
207
+ "loss": 2.9714,
208
+ "step": 26
209
+ },
210
+ {
211
+ "epoch": 0.20804237900313027,
212
+ "grad_norm": 0.9134896397590637,
213
+ "learning_rate": 0.00019987025970805448,
214
+ "loss": 3.0278,
215
+ "step": 27
216
+ },
217
+ {
218
+ "epoch": 0.2157476522995425,
219
+ "grad_norm": 1.1262270212173462,
220
+ "learning_rate": 0.00019985761229702353,
221
+ "loss": 2.9815,
222
+ "step": 28
223
+ },
224
+ {
225
+ "epoch": 0.22345292559595473,
226
+ "grad_norm": 0.8728867173194885,
227
+ "learning_rate": 0.0001998443772056381,
228
+ "loss": 2.9337,
229
+ "step": 29
230
+ },
231
+ {
232
+ "epoch": 0.23115819889236697,
233
+ "grad_norm": 0.9984097480773926,
234
+ "learning_rate": 0.00019983055451178915,
235
+ "loss": 2.9111,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 0.23115819889236697,
240
+ "eval_loss": 2.9105160236358643,
241
+ "eval_runtime": 105.9725,
242
+ "eval_samples_per_second": 13.409,
243
+ "eval_steps_per_second": 6.709,
244
+ "step": 30
245
+ },
246
+ {
247
+ "epoch": 0.2388634721887792,
248
+ "grad_norm": 0.878777027130127,
249
+ "learning_rate": 0.00019981614429682575,
250
+ "loss": 2.9316,
251
+ "step": 31
252
+ },
253
+ {
254
+ "epoch": 0.24656874548519142,
255
+ "grad_norm": 0.9172009229660034,
256
+ "learning_rate": 0.00019980114664555463,
257
+ "loss": 2.7396,
258
+ "step": 32
259
+ },
260
+ {
261
+ "epoch": 0.25427401878160366,
262
+ "grad_norm": 0.7860124707221985,
263
+ "learning_rate": 0.00019978556164623976,
264
+ "loss": 2.7795,
265
+ "step": 33
266
+ },
267
+ {
268
+ "epoch": 0.2619792920780159,
269
+ "grad_norm": 0.9437300562858582,
270
+ "learning_rate": 0.00019976938939060172,
271
+ "loss": 2.9493,
272
+ "step": 34
273
+ },
274
+ {
275
+ "epoch": 0.26968456537442814,
276
+ "grad_norm": 0.8502227067947388,
277
+ "learning_rate": 0.00019975262997381718,
278
+ "loss": 2.8353,
279
+ "step": 35
280
+ },
281
+ {
282
+ "epoch": 0.2773898386708404,
283
+ "grad_norm": 1.125998616218567,
284
+ "learning_rate": 0.00019973528349451837,
285
+ "loss": 2.8016,
286
+ "step": 36
287
+ },
288
+ {
289
+ "epoch": 0.28509511196725257,
290
+ "grad_norm": 0.8806775212287903,
291
+ "learning_rate": 0.00019971735005479252,
292
+ "loss": 2.8202,
293
+ "step": 37
294
+ },
295
+ {
296
+ "epoch": 0.2928003852636648,
297
+ "grad_norm": 1.1541495323181152,
298
+ "learning_rate": 0.00019969882976018122,
299
+ "loss": 2.9782,
300
+ "step": 38
301
+ },
302
+ {
303
+ "epoch": 0.30050565856007705,
304
+ "grad_norm": 0.8781335353851318,
305
+ "learning_rate": 0.00019967972271967978,
306
+ "loss": 2.9002,
307
+ "step": 39
308
+ },
309
+ {
310
+ "epoch": 0.3082109318564893,
311
+ "grad_norm": 0.8811110258102417,
312
+ "learning_rate": 0.00019966002904573662,
313
+ "loss": 2.7621,
314
+ "step": 40
315
+ },
316
+ {
317
+ "epoch": 0.3082109318564893,
318
+ "eval_loss": 2.7593281269073486,
319
+ "eval_runtime": 105.5836,
320
+ "eval_samples_per_second": 13.459,
321
+ "eval_steps_per_second": 6.734,
322
+ "step": 40
323
+ },
324
+ {
325
+ "epoch": 0.31591620515290153,
326
+ "grad_norm": 0.918214738368988,
327
+ "learning_rate": 0.00019963974885425266,
328
+ "loss": 2.7196,
329
+ "step": 41
330
+ },
331
+ {
332
+ "epoch": 0.32362147844931377,
333
+ "grad_norm": 0.8387148976325989,
334
+ "learning_rate": 0.00019961888226458052,
335
+ "loss": 2.7425,
336
+ "step": 42
337
+ },
338
+ {
339
+ "epoch": 0.33132675174572596,
340
+ "grad_norm": 0.8574619293212891,
341
+ "learning_rate": 0.00019959742939952392,
342
+ "loss": 2.6934,
343
+ "step": 43
344
+ },
345
+ {
346
+ "epoch": 0.3390320250421382,
347
+ "grad_norm": 0.8649158477783203,
348
+ "learning_rate": 0.0001995753903853369,
349
+ "loss": 2.6884,
350
+ "step": 44
351
+ },
352
+ {
353
+ "epoch": 0.34673729833855044,
354
+ "grad_norm": 0.8105392456054688,
355
+ "learning_rate": 0.00019955276535172308,
356
+ "loss": 2.5697,
357
+ "step": 45
358
+ },
359
+ {
360
+ "epoch": 0.3544425716349627,
361
+ "grad_norm": 0.9031375646591187,
362
+ "learning_rate": 0.0001995295544318349,
363
+ "loss": 2.7052,
364
+ "step": 46
365
+ },
366
+ {
367
+ "epoch": 0.3621478449313749,
368
+ "grad_norm": 0.915088415145874,
369
+ "learning_rate": 0.00019950575776227298,
370
+ "loss": 2.6312,
371
+ "step": 47
372
+ },
373
+ {
374
+ "epoch": 0.36985311822778716,
375
+ "grad_norm": 0.8281115293502808,
376
+ "learning_rate": 0.00019948137548308502,
377
+ "loss": 2.6221,
378
+ "step": 48
379
+ },
380
+ {
381
+ "epoch": 0.3775583915241994,
382
+ "grad_norm": 0.8810791373252869,
383
+ "learning_rate": 0.00019945640773776522,
384
+ "loss": 2.794,
385
+ "step": 49
386
+ },
387
+ {
388
+ "epoch": 0.3852636648206116,
389
+ "grad_norm": 0.8257634043693542,
390
+ "learning_rate": 0.00019943085467325332,
391
+ "loss": 2.6968,
392
+ "step": 50
393
+ },
394
+ {
395
+ "epoch": 0.3852636648206116,
396
+ "eval_loss": 2.6551294326782227,
397
+ "eval_runtime": 105.8223,
398
+ "eval_samples_per_second": 13.428,
399
+ "eval_steps_per_second": 6.719,
400
+ "step": 50
401
+ },
402
+ {
403
+ "epoch": 0.3929689381170238,
404
+ "grad_norm": 0.9086642265319824,
405
+ "learning_rate": 0.0001994047164399338,
406
+ "loss": 2.5626,
407
+ "step": 51
408
+ },
409
+ {
410
+ "epoch": 0.40067421141343607,
411
+ "grad_norm": 0.9169562458992004,
412
+ "learning_rate": 0.0001993779931916349,
413
+ "loss": 2.6817,
414
+ "step": 52
415
+ },
416
+ {
417
+ "epoch": 0.4083794847098483,
418
+ "grad_norm": 0.8974910974502563,
419
+ "learning_rate": 0.00019935068508562792,
420
+ "loss": 2.6238,
421
+ "step": 53
422
+ },
423
+ {
424
+ "epoch": 0.41608475800626055,
425
+ "grad_norm": 0.9639973640441895,
426
+ "learning_rate": 0.00019932279228262608,
427
+ "loss": 2.593,
428
+ "step": 54
429
+ },
430
+ {
431
+ "epoch": 0.4237900313026728,
432
+ "grad_norm": 0.8378269076347351,
433
+ "learning_rate": 0.00019929431494678356,
434
+ "loss": 2.5429,
435
+ "step": 55
436
+ },
437
+ {
438
+ "epoch": 0.431495304599085,
439
+ "grad_norm": 0.8850448727607727,
440
+ "learning_rate": 0.00019926525324569472,
441
+ "loss": 2.6811,
442
+ "step": 56
443
+ },
444
+ {
445
+ "epoch": 0.4392005778954972,
446
+ "grad_norm": 0.8458334803581238,
447
+ "learning_rate": 0.000199235607350393,
448
+ "loss": 2.4878,
449
+ "step": 57
450
+ },
451
+ {
452
+ "epoch": 0.44690585119190945,
453
+ "grad_norm": 0.9009547233581543,
454
+ "learning_rate": 0.00019920537743535,
455
+ "loss": 2.7239,
456
+ "step": 58
457
+ },
458
+ {
459
+ "epoch": 0.4546111244883217,
460
+ "grad_norm": 0.8072719573974609,
461
+ "learning_rate": 0.00019917456367847422,
462
+ "loss": 2.5281,
463
+ "step": 59
464
+ },
465
+ {
466
+ "epoch": 0.46231639778473393,
467
+ "grad_norm": 0.8849979639053345,
468
+ "learning_rate": 0.00019914316626111034,
469
+ "loss": 2.621,
470
+ "step": 60
471
+ },
472
+ {
473
+ "epoch": 0.46231639778473393,
474
+ "eval_loss": 2.5811991691589355,
475
+ "eval_runtime": 105.8628,
476
+ "eval_samples_per_second": 13.423,
477
+ "eval_steps_per_second": 6.716,
478
+ "step": 60
479
+ },
480
+ {
481
+ "epoch": 0.4700216710811462,
482
+ "grad_norm": 0.8845431804656982,
483
+ "learning_rate": 0.00019911118536803787,
484
+ "loss": 2.4806,
485
+ "step": 61
486
+ },
487
+ {
488
+ "epoch": 0.4777269443775584,
489
+ "grad_norm": 0.9649096727371216,
490
+ "learning_rate": 0.00019907862118747022,
491
+ "loss": 2.6962,
492
+ "step": 62
493
+ },
494
+ {
495
+ "epoch": 0.4854322176739706,
496
+ "grad_norm": 0.9057343602180481,
497
+ "learning_rate": 0.00019904547391105356,
498
+ "loss": 2.5838,
499
+ "step": 63
500
+ },
501
+ {
502
+ "epoch": 0.49313749097038284,
503
+ "grad_norm": 1.025192141532898,
504
+ "learning_rate": 0.00019901174373386575,
505
+ "loss": 2.5524,
506
+ "step": 64
507
+ },
508
+ {
509
+ "epoch": 0.5008427642667951,
510
+ "grad_norm": 0.8533208966255188,
511
+ "learning_rate": 0.00019897743085441506,
512
+ "loss": 2.6436,
513
+ "step": 65
514
+ },
515
+ {
516
+ "epoch": 0.5085480375632073,
517
+ "grad_norm": 1.1548839807510376,
518
+ "learning_rate": 0.00019894253547463896,
519
+ "loss": 2.6098,
520
+ "step": 66
521
+ },
522
+ {
523
+ "epoch": 0.5162533108596196,
524
+ "grad_norm": 0.8191328644752502,
525
+ "learning_rate": 0.0001989070577999033,
526
+ "loss": 2.4753,
527
+ "step": 67
528
+ },
529
+ {
530
+ "epoch": 0.5239585841560318,
531
+ "grad_norm": 0.8318487405776978,
532
+ "learning_rate": 0.00019887099803900062,
533
+ "loss": 2.5462,
534
+ "step": 68
535
+ },
536
+ {
537
+ "epoch": 0.531663857452444,
538
+ "grad_norm": 0.9106600284576416,
539
+ "learning_rate": 0.00019883435640414922,
540
+ "loss": 2.5209,
541
+ "step": 69
542
+ },
543
+ {
544
+ "epoch": 0.5393691307488563,
545
+ "grad_norm": 0.8238663077354431,
546
+ "learning_rate": 0.00019879713311099192,
547
+ "loss": 2.5371,
548
+ "step": 70
549
+ },
550
+ {
551
+ "epoch": 0.5393691307488563,
552
+ "eval_loss": 2.5044679641723633,
553
+ "eval_runtime": 105.9687,
554
+ "eval_samples_per_second": 13.41,
555
+ "eval_steps_per_second": 6.71,
556
+ "step": 70
557
+ },
558
+ {
559
+ "epoch": 0.5470744040452685,
560
+ "grad_norm": 0.7846340537071228,
561
+ "learning_rate": 0.0001987593283785945,
562
+ "loss": 2.3816,
563
+ "step": 71
564
+ },
565
+ {
566
+ "epoch": 0.5547796773416808,
567
+ "grad_norm": 0.8555856347084045,
568
+ "learning_rate": 0.00019872094242944486,
569
+ "loss": 2.5142,
570
+ "step": 72
571
+ },
572
+ {
573
+ "epoch": 0.5624849506380929,
574
+ "grad_norm": 0.8151663541793823,
575
+ "learning_rate": 0.00019868197548945124,
576
+ "loss": 2.4673,
577
+ "step": 73
578
+ },
579
+ {
580
+ "epoch": 0.5701902239345051,
581
+ "grad_norm": 0.8196232914924622,
582
+ "learning_rate": 0.00019864242778794134,
583
+ "loss": 2.5647,
584
+ "step": 74
585
+ },
586
+ {
587
+ "epoch": 0.5778954972309174,
588
+ "grad_norm": 0.7875572443008423,
589
+ "learning_rate": 0.00019860229955766053,
590
+ "loss": 2.3415,
591
+ "step": 75
592
+ },
593
+ {
594
+ "epoch": 0.5856007705273296,
595
+ "grad_norm": 0.8158406615257263,
596
+ "learning_rate": 0.00019856159103477086,
597
+ "loss": 2.4969,
598
+ "step": 76
599
+ },
600
+ {
601
+ "epoch": 0.5933060438237419,
602
+ "grad_norm": 0.8049045205116272,
603
+ "learning_rate": 0.00019852030245884943,
604
+ "loss": 2.4275,
605
+ "step": 77
606
+ },
607
+ {
608
+ "epoch": 0.6010113171201541,
609
+ "grad_norm": 0.860619306564331,
610
+ "learning_rate": 0.0001984784340728871,
611
+ "loss": 2.5144,
612
+ "step": 78
613
+ },
614
+ {
615
+ "epoch": 0.6087165904165663,
616
+ "grad_norm": 0.8955098986625671,
617
+ "learning_rate": 0.00019843598612328696,
618
+ "loss": 2.5056,
619
+ "step": 79
620
+ },
621
+ {
622
+ "epoch": 0.6164218637129786,
623
+ "grad_norm": 0.8398386240005493,
624
+ "learning_rate": 0.00019839295885986296,
625
+ "loss": 2.5076,
626
+ "step": 80
627
+ },
628
+ {
629
+ "epoch": 0.6164218637129786,
630
+ "eval_loss": 2.448918581008911,
631
+ "eval_runtime": 106.0515,
632
+ "eval_samples_per_second": 13.399,
633
+ "eval_steps_per_second": 6.704,
634
+ "step": 80
635
+ },
636
+ {
637
+ "epoch": 0.6241271370093908,
638
+ "grad_norm": 0.7882781624794006,
639
+ "learning_rate": 0.0001983493525358385,
640
+ "loss": 2.4004,
641
+ "step": 81
642
+ },
643
+ {
644
+ "epoch": 0.6318324103058031,
645
+ "grad_norm": 0.9114618301391602,
646
+ "learning_rate": 0.0001983051674078448,
647
+ "loss": 2.4736,
648
+ "step": 82
649
+ },
650
+ {
651
+ "epoch": 0.6395376836022153,
652
+ "grad_norm": 0.848273754119873,
653
+ "learning_rate": 0.00019826040373591933,
654
+ "loss": 2.4109,
655
+ "step": 83
656
+ },
657
+ {
658
+ "epoch": 0.6472429568986275,
659
+ "grad_norm": 0.8459404110908508,
660
+ "learning_rate": 0.00019821506178350462,
661
+ "loss": 2.4403,
662
+ "step": 84
663
+ },
664
+ {
665
+ "epoch": 0.6549482301950398,
666
+ "grad_norm": 0.8759799599647522,
667
+ "learning_rate": 0.0001981691418174463,
668
+ "loss": 2.5644,
669
+ "step": 85
670
+ },
671
+ {
672
+ "epoch": 0.6626535034914519,
673
+ "grad_norm": 0.8305234313011169,
674
+ "learning_rate": 0.0001981226441079918,
675
+ "loss": 2.4926,
676
+ "step": 86
677
+ },
678
+ {
679
+ "epoch": 0.6703587767878642,
680
+ "grad_norm": 0.8062665462493896,
681
+ "learning_rate": 0.0001980755689287887,
682
+ "loss": 2.3749,
683
+ "step": 87
684
+ },
685
+ {
686
+ "epoch": 0.6780640500842764,
687
+ "grad_norm": 0.8252109289169312,
688
+ "learning_rate": 0.00019802791655688302,
689
+ "loss": 2.4395,
690
+ "step": 88
691
+ },
692
+ {
693
+ "epoch": 0.6857693233806886,
694
+ "grad_norm": 0.8706617951393127,
695
+ "learning_rate": 0.00019797968727271775,
696
+ "loss": 2.3723,
697
+ "step": 89
698
+ },
699
+ {
700
+ "epoch": 0.6934745966771009,
701
+ "grad_norm": 0.8899645209312439,
702
+ "learning_rate": 0.000197930881360131,
703
+ "loss": 2.4322,
704
+ "step": 90
705
+ },
706
+ {
707
+ "epoch": 0.6934745966771009,
708
+ "eval_loss": 2.4009482860565186,
709
+ "eval_runtime": 105.8795,
710
+ "eval_samples_per_second": 13.421,
711
+ "eval_steps_per_second": 6.715,
712
+ "step": 90
713
+ },
714
+ {
715
+ "epoch": 0.7011798699735131,
716
+ "grad_norm": 0.8663708567619324,
717
+ "learning_rate": 0.0001978814991063546,
718
+ "loss": 2.3818,
719
+ "step": 91
720
+ },
721
+ {
722
+ "epoch": 0.7088851432699254,
723
+ "grad_norm": 0.8973158597946167,
724
+ "learning_rate": 0.00019783154080201207,
725
+ "loss": 2.3594,
726
+ "step": 92
727
+ },
728
+ {
729
+ "epoch": 0.7165904165663376,
730
+ "grad_norm": 0.8583101630210876,
731
+ "learning_rate": 0.00019778100674111725,
732
+ "loss": 2.4124,
733
+ "step": 93
734
+ },
735
+ {
736
+ "epoch": 0.7242956898627498,
737
+ "grad_norm": 0.8070630431175232,
738
+ "learning_rate": 0.00019772989722107237,
739
+ "loss": 2.3592,
740
+ "step": 94
741
+ },
742
+ {
743
+ "epoch": 0.7320009631591621,
744
+ "grad_norm": 0.889661967754364,
745
+ "learning_rate": 0.0001976782125426663,
746
+ "loss": 2.3848,
747
+ "step": 95
748
+ },
749
+ {
750
+ "epoch": 0.7397062364555743,
751
+ "grad_norm": 0.8866454362869263,
752
+ "learning_rate": 0.00019762595301007281,
753
+ "loss": 2.4904,
754
+ "step": 96
755
+ },
756
+ {
757
+ "epoch": 0.7474115097519866,
758
+ "grad_norm": 0.7881627082824707,
759
+ "learning_rate": 0.00019757311893084885,
760
+ "loss": 2.2242,
761
+ "step": 97
762
+ },
763
+ {
764
+ "epoch": 0.7551167830483988,
765
+ "grad_norm": 0.9172340035438538,
766
+ "learning_rate": 0.0001975197106159327,
767
+ "loss": 2.4029,
768
+ "step": 98
769
+ },
770
+ {
771
+ "epoch": 0.7628220563448109,
772
+ "grad_norm": 0.9356191754341125,
773
+ "learning_rate": 0.00019746572837964205,
774
+ "loss": 2.3779,
775
+ "step": 99
776
+ },
777
+ {
778
+ "epoch": 0.7705273296412232,
779
+ "grad_norm": 0.8568073511123657,
780
+ "learning_rate": 0.00019741117253967229,
781
+ "loss": 2.3872,
782
+ "step": 100
783
+ },
784
+ {
785
+ "epoch": 0.7705273296412232,
786
+ "eval_loss": 2.368114709854126,
787
+ "eval_runtime": 105.7943,
788
+ "eval_samples_per_second": 13.432,
789
+ "eval_steps_per_second": 6.721,
790
+ "step": 100
791
+ },
792
+ {
793
+ "epoch": 0.7782326029376354,
794
+ "grad_norm": 0.8859056234359741,
795
+ "learning_rate": 0.00019735604341709448,
796
+ "loss": 2.3408,
797
+ "step": 101
798
+ },
799
+ {
800
+ "epoch": 0.7859378762340476,
801
+ "grad_norm": 0.9037278294563293,
802
+ "learning_rate": 0.00019730034133635366,
803
+ "loss": 2.4584,
804
+ "step": 102
805
+ },
806
+ {
807
+ "epoch": 0.7936431495304599,
808
+ "grad_norm": 0.8553995490074158,
809
+ "learning_rate": 0.00019724406662526678,
810
+ "loss": 2.3491,
811
+ "step": 103
812
+ },
813
+ {
814
+ "epoch": 0.8013484228268721,
815
+ "grad_norm": 0.7836203575134277,
816
+ "learning_rate": 0.0001971872196150208,
817
+ "loss": 2.2855,
818
+ "step": 104
819
+ },
820
+ {
821
+ "epoch": 0.8090536961232844,
822
+ "grad_norm": 0.8526378870010376,
823
+ "learning_rate": 0.00019712980064017085,
824
+ "loss": 2.2859,
825
+ "step": 105
826
+ },
827
+ {
828
+ "epoch": 0.8167589694196966,
829
+ "grad_norm": 0.8489184379577637,
830
+ "learning_rate": 0.00019707181003863808,
831
+ "loss": 2.2908,
832
+ "step": 106
833
+ },
834
+ {
835
+ "epoch": 0.8244642427161089,
836
+ "grad_norm": 0.8646358251571655,
837
+ "learning_rate": 0.00019701324815170785,
838
+ "loss": 2.1875,
839
+ "step": 107
840
+ },
841
+ {
842
+ "epoch": 0.8321695160125211,
843
+ "grad_norm": 0.8263905048370361,
844
+ "learning_rate": 0.00019695411532402756,
845
+ "loss": 2.2223,
846
+ "step": 108
847
+ },
848
+ {
849
+ "epoch": 0.8398747893089333,
850
+ "grad_norm": 0.8620204925537109,
851
+ "learning_rate": 0.00019689441190360476,
852
+ "loss": 2.3383,
853
+ "step": 109
854
+ },
855
+ {
856
+ "epoch": 0.8475800626053456,
857
+ "grad_norm": 0.8234513401985168,
858
+ "learning_rate": 0.00019683413824180503,
859
+ "loss": 2.2424,
860
+ "step": 110
861
+ },
862
+ {
863
+ "epoch": 0.8475800626053456,
864
+ "eval_loss": 2.3261094093322754,
865
+ "eval_runtime": 105.4,
866
+ "eval_samples_per_second": 13.482,
867
+ "eval_steps_per_second": 6.746,
868
+ "step": 110
869
+ },
870
+ {
871
+ "epoch": 0.8552853359017578,
872
+ "grad_norm": 0.8316911458969116,
873
+ "learning_rate": 0.0001967732946933499,
874
+ "loss": 2.3706,
875
+ "step": 111
876
+ },
877
+ {
878
+ "epoch": 0.86299060919817,
879
+ "grad_norm": 0.8086533546447754,
880
+ "learning_rate": 0.0001967118816163148,
881
+ "loss": 2.2298,
882
+ "step": 112
883
+ },
884
+ {
885
+ "epoch": 0.8706958824945822,
886
+ "grad_norm": 0.7874895930290222,
887
+ "learning_rate": 0.00019664989937212698,
888
+ "loss": 2.3477,
889
+ "step": 113
890
+ },
891
+ {
892
+ "epoch": 0.8784011557909944,
893
+ "grad_norm": 0.7827970385551453,
894
+ "learning_rate": 0.00019658734832556332,
895
+ "loss": 2.2685,
896
+ "step": 114
897
+ },
898
+ {
899
+ "epoch": 0.8861064290874067,
900
+ "grad_norm": 0.837593674659729,
901
+ "learning_rate": 0.00019652422884474814,
902
+ "loss": 2.425,
903
+ "step": 115
904
+ },
905
+ {
906
+ "epoch": 0.8938117023838189,
907
+ "grad_norm": 0.8361220359802246,
908
+ "learning_rate": 0.0001964605413011512,
909
+ "loss": 2.245,
910
+ "step": 116
911
+ },
912
+ {
913
+ "epoch": 0.9015169756802311,
914
+ "grad_norm": 1.3296891450881958,
915
+ "learning_rate": 0.00019639628606958533,
916
+ "loss": 2.1907,
917
+ "step": 117
918
+ },
919
+ {
920
+ "epoch": 0.9092222489766434,
921
+ "grad_norm": 0.839888334274292,
922
+ "learning_rate": 0.0001963314635282044,
923
+ "loss": 2.3054,
924
+ "step": 118
925
+ },
926
+ {
927
+ "epoch": 0.9169275222730556,
928
+ "grad_norm": 0.8651548027992249,
929
+ "learning_rate": 0.0001962660740585009,
930
+ "loss": 2.3319,
931
+ "step": 119
932
+ },
933
+ {
934
+ "epoch": 0.9246327955694679,
935
+ "grad_norm": 0.9133594036102295,
936
+ "learning_rate": 0.0001962001180453039,
937
+ "loss": 2.4663,
938
+ "step": 120
939
+ },
940
+ {
941
+ "epoch": 0.9246327955694679,
942
+ "eval_loss": 2.287965774536133,
943
+ "eval_runtime": 105.1505,
944
+ "eval_samples_per_second": 13.514,
945
+ "eval_steps_per_second": 6.762,
946
+ "step": 120
947
+ },
948
+ {
949
+ "epoch": 0.9323380688658801,
950
+ "grad_norm": 0.8300138115882874,
951
+ "learning_rate": 0.00019613359587677658,
952
+ "loss": 2.3045,
953
+ "step": 121
954
+ },
955
+ {
956
+ "epoch": 0.9400433421622924,
957
+ "grad_norm": 0.8267295956611633,
958
+ "learning_rate": 0.0001960665079444141,
959
+ "loss": 2.1291,
960
+ "step": 122
961
+ },
962
+ {
963
+ "epoch": 0.9477486154587046,
964
+ "grad_norm": 0.8013430833816528,
965
+ "learning_rate": 0.00019599885464304128,
966
+ "loss": 2.254,
967
+ "step": 123
968
+ },
969
+ {
970
+ "epoch": 0.9554538887551168,
971
+ "grad_norm": 0.9202237129211426,
972
+ "learning_rate": 0.00019593063637081016,
973
+ "loss": 2.1937,
974
+ "step": 124
975
+ },
976
+ {
977
+ "epoch": 0.963159162051529,
978
+ "grad_norm": 0.8237356543540955,
979
+ "learning_rate": 0.0001958618535291978,
980
+ "loss": 2.3104,
981
+ "step": 125
982
+ },
983
+ {
984
+ "epoch": 0.9708644353479412,
985
+ "grad_norm": 0.7979533672332764,
986
+ "learning_rate": 0.0001957925065230038,
987
+ "loss": 2.1441,
988
+ "step": 126
989
+ },
990
+ {
991
+ "epoch": 0.9785697086443534,
992
+ "grad_norm": 0.8261020183563232,
993
+ "learning_rate": 0.00019572259576034807,
994
+ "loss": 2.2107,
995
+ "step": 127
996
+ },
997
+ {
998
+ "epoch": 0.9862749819407657,
999
+ "grad_norm": 0.8929041028022766,
1000
+ "learning_rate": 0.0001956521216526682,
1001
+ "loss": 2.3569,
1002
+ "step": 128
1003
+ },
1004
+ {
1005
+ "epoch": 0.9939802552371779,
1006
+ "grad_norm": 0.835917055606842,
1007
+ "learning_rate": 0.00019558108461471723,
1008
+ "loss": 2.1882,
1009
+ "step": 129
1010
+ },
1011
+ {
1012
+ "epoch": 1.0,
1013
+ "grad_norm": 0.9039733409881592,
1014
+ "learning_rate": 0.00019550948506456123,
1015
+ "loss": 2.1534,
1016
+ "step": 130
1017
+ },
1018
+ {
1019
+ "epoch": 1.0,
1020
+ "eval_loss": 2.2661569118499756,
1021
+ "eval_runtime": 104.9517,
1022
+ "eval_samples_per_second": 13.54,
1023
+ "eval_steps_per_second": 6.775,
1024
+ "step": 130
1025
+ },
1026
+ {
1027
+ "epoch": 1.0077052732964122,
1028
+ "grad_norm": 0.8830167055130005,
1029
+ "learning_rate": 0.00019543732342357662,
1030
+ "loss": 2.0627,
1031
+ "step": 131
1032
+ },
1033
+ {
1034
+ "epoch": 1.0154105465928245,
1035
+ "grad_norm": 0.7725016474723816,
1036
+ "learning_rate": 0.0001953646001164479,
1037
+ "loss": 1.8384,
1038
+ "step": 132
1039
+ },
1040
+ {
1041
+ "epoch": 1.0231158198892367,
1042
+ "grad_norm": 1.0426549911499023,
1043
+ "learning_rate": 0.00019529131557116504,
1044
+ "loss": 1.9797,
1045
+ "step": 133
1046
+ },
1047
+ {
1048
+ "epoch": 1.030821093185649,
1049
+ "grad_norm": 0.8179664611816406,
1050
+ "learning_rate": 0.00019521747021902103,
1051
+ "loss": 1.9345,
1052
+ "step": 134
1053
+ },
1054
+ {
1055
+ "epoch": 1.0385263664820612,
1056
+ "grad_norm": 0.9306544065475464,
1057
+ "learning_rate": 0.00019514306449460933,
1058
+ "loss": 1.9243,
1059
+ "step": 135
1060
+ },
1061
+ {
1062
+ "epoch": 1.0462316397784734,
1063
+ "grad_norm": 1.0536283254623413,
1064
+ "learning_rate": 0.00019506809883582124,
1065
+ "loss": 1.8673,
1066
+ "step": 136
1067
+ },
1068
+ {
1069
+ "epoch": 1.0539369130748857,
1070
+ "grad_norm": 0.9281775951385498,
1071
+ "learning_rate": 0.00019499257368384344,
1072
+ "loss": 1.8323,
1073
+ "step": 137
1074
+ },
1075
+ {
1076
+ "epoch": 1.061642186371298,
1077
+ "grad_norm": 1.1008800268173218,
1078
+ "learning_rate": 0.00019491648948315526,
1079
+ "loss": 1.8566,
1080
+ "step": 138
1081
+ },
1082
+ {
1083
+ "epoch": 1.0693474596677102,
1084
+ "grad_norm": 0.9318124651908875,
1085
+ "learning_rate": 0.00019483984668152617,
1086
+ "loss": 1.8207,
1087
+ "step": 139
1088
+ },
1089
+ {
1090
+ "epoch": 1.0770527329641224,
1091
+ "grad_norm": 0.9358550310134888,
1092
+ "learning_rate": 0.00019476264573001315,
1093
+ "loss": 1.8863,
1094
+ "step": 140
1095
+ },
1096
+ {
1097
+ "epoch": 1.0770527329641224,
1098
+ "eval_loss": 2.2706642150878906,
1099
+ "eval_runtime": 104.9728,
1100
+ "eval_samples_per_second": 13.537,
1101
+ "eval_steps_per_second": 6.773,
1102
+ "step": 140
1103
+ },
1104
+ {
1105
+ "epoch": 1.0847580062605346,
1106
+ "grad_norm": 0.9916208386421204,
1107
+ "learning_rate": 0.0001946848870829579,
1108
+ "loss": 1.9447,
1109
+ "step": 141
1110
+ },
1111
+ {
1112
+ "epoch": 1.0924632795569469,
1113
+ "grad_norm": 0.8726244568824768,
1114
+ "learning_rate": 0.00019460657119798436,
1115
+ "loss": 1.9505,
1116
+ "step": 142
1117
+ },
1118
+ {
1119
+ "epoch": 1.1001685528533591,
1120
+ "grad_norm": 0.9002631306648254,
1121
+ "learning_rate": 0.00019452769853599584,
1122
+ "loss": 1.9362,
1123
+ "step": 143
1124
+ },
1125
+ {
1126
+ "epoch": 1.1078738261497711,
1127
+ "grad_norm": 0.9998403787612915,
1128
+ "learning_rate": 0.0001944482695611724,
1129
+ "loss": 1.9402,
1130
+ "step": 144
1131
+ },
1132
+ {
1133
+ "epoch": 1.1155790994461834,
1134
+ "grad_norm": 0.8798266649246216,
1135
+ "learning_rate": 0.00019436828474096816,
1136
+ "loss": 1.9165,
1137
+ "step": 145
1138
+ },
1139
+ {
1140
+ "epoch": 1.1232843727425956,
1141
+ "grad_norm": 0.9074817299842834,
1142
+ "learning_rate": 0.00019428774454610843,
1143
+ "loss": 1.8952,
1144
+ "step": 146
1145
+ },
1146
+ {
1147
+ "epoch": 1.1309896460390079,
1148
+ "grad_norm": 0.9803466200828552,
1149
+ "learning_rate": 0.00019420664945058702,
1150
+ "loss": 2.0203,
1151
+ "step": 147
1152
+ },
1153
+ {
1154
+ "epoch": 1.13869491933542,
1155
+ "grad_norm": 0.8859460353851318,
1156
+ "learning_rate": 0.0001941249999316634,
1157
+ "loss": 1.7384,
1158
+ "step": 148
1159
+ },
1160
+ {
1161
+ "epoch": 1.1464001926318323,
1162
+ "grad_norm": 0.9056553244590759,
1163
+ "learning_rate": 0.00019404279646986005,
1164
+ "loss": 1.9843,
1165
+ "step": 149
1166
+ },
1167
+ {
1168
+ "epoch": 1.1541054659282446,
1169
+ "grad_norm": 0.8923737406730652,
1170
+ "learning_rate": 0.00019396003954895932,
1171
+ "loss": 1.8566,
1172
+ "step": 150
1173
+ },
1174
+ {
1175
+ "epoch": 1.1541054659282446,
1176
+ "eval_loss": 2.2248008251190186,
1177
+ "eval_runtime": 104.7815,
1178
+ "eval_samples_per_second": 13.562,
1179
+ "eval_steps_per_second": 6.786,
1180
+ "step": 150
1181
+ },
1182
+ {
1183
+ "epoch": 1.1618107392246568,
1184
+ "grad_norm": 0.8597286939620972,
1185
+ "learning_rate": 0.00019387672965600087,
1186
+ "loss": 1.8025,
1187
+ "step": 151
1188
+ },
1189
+ {
1190
+ "epoch": 1.169516012521069,
1191
+ "grad_norm": 0.8409769535064697,
1192
+ "learning_rate": 0.00019379286728127875,
1193
+ "loss": 1.7198,
1194
+ "step": 152
1195
+ },
1196
+ {
1197
+ "epoch": 1.1772212858174813,
1198
+ "grad_norm": 0.8676941990852356,
1199
+ "learning_rate": 0.00019370845291833837,
1200
+ "loss": 1.8608,
1201
+ "step": 153
1202
+ },
1203
+ {
1204
+ "epoch": 1.1849265591138936,
1205
+ "grad_norm": 0.8940218687057495,
1206
+ "learning_rate": 0.00019362348706397373,
1207
+ "loss": 1.8922,
1208
+ "step": 154
1209
+ },
1210
+ {
1211
+ "epoch": 1.1926318324103058,
1212
+ "grad_norm": 0.8716734051704407,
1213
+ "learning_rate": 0.00019353797021822447,
1214
+ "loss": 1.9176,
1215
+ "step": 155
1216
+ },
1217
+ {
1218
+ "epoch": 1.200337105706718,
1219
+ "grad_norm": 0.9402107000350952,
1220
+ "learning_rate": 0.00019345190288437293,
1221
+ "loss": 1.9318,
1222
+ "step": 156
1223
+ },
1224
+ {
1225
+ "epoch": 1.2080423790031303,
1226
+ "grad_norm": 0.9611467719078064,
1227
+ "learning_rate": 0.00019336528556894106,
1228
+ "loss": 1.9521,
1229
+ "step": 157
1230
+ },
1231
+ {
1232
+ "epoch": 1.2157476522995425,
1233
+ "grad_norm": 0.8599668145179749,
1234
+ "learning_rate": 0.0001932781187816877,
1235
+ "loss": 1.8943,
1236
+ "step": 158
1237
+ },
1238
+ {
1239
+ "epoch": 1.2234529255959548,
1240
+ "grad_norm": 0.8738541007041931,
1241
+ "learning_rate": 0.00019319040303560542,
1242
+ "loss": 1.7769,
1243
+ "step": 159
1244
+ },
1245
+ {
1246
+ "epoch": 1.231158198892367,
1247
+ "grad_norm": 0.8689557313919067,
1248
+ "learning_rate": 0.0001931021388469174,
1249
+ "loss": 1.872,
1250
+ "step": 160
1251
+ },
1252
+ {
1253
+ "epoch": 1.231158198892367,
1254
+ "eval_loss": 2.224492311477661,
1255
+ "eval_runtime": 104.8175,
1256
+ "eval_samples_per_second": 13.557,
1257
+ "eval_steps_per_second": 6.783,
1258
+ "step": 160
1259
+ },
1260
+ {
1261
+ "epoch": 1.2388634721887792,
1262
+ "grad_norm": 0.8626556992530823,
1263
+ "learning_rate": 0.00019301332673507456,
1264
+ "loss": 1.7732,
1265
+ "step": 161
1266
+ },
1267
+ {
1268
+ "epoch": 1.2465687454851915,
1269
+ "grad_norm": 0.8939476013183594,
1270
+ "learning_rate": 0.00019292396722275253,
1271
+ "loss": 1.7973,
1272
+ "step": 162
1273
+ },
1274
+ {
1275
+ "epoch": 1.2542740187816037,
1276
+ "grad_norm": 0.970128059387207,
1277
+ "learning_rate": 0.00019283406083584834,
1278
+ "loss": 1.9681,
1279
+ "step": 163
1280
+ },
1281
+ {
1282
+ "epoch": 1.261979292078016,
1283
+ "grad_norm": 0.891115128993988,
1284
+ "learning_rate": 0.00019274360810347761,
1285
+ "loss": 1.8834,
1286
+ "step": 164
1287
+ },
1288
+ {
1289
+ "epoch": 1.2696845653744282,
1290
+ "grad_norm": 0.8977951407432556,
1291
+ "learning_rate": 0.00019265260955797126,
1292
+ "loss": 1.8711,
1293
+ "step": 165
1294
+ },
1295
+ {
1296
+ "epoch": 1.2773898386708404,
1297
+ "grad_norm": 0.9272082448005676,
1298
+ "learning_rate": 0.00019256106573487238,
1299
+ "loss": 1.9325,
1300
+ "step": 166
1301
+ },
1302
+ {
1303
+ "epoch": 1.2850951119672525,
1304
+ "grad_norm": 0.8868167400360107,
1305
+ "learning_rate": 0.00019246897717293315,
1306
+ "loss": 1.9478,
1307
+ "step": 167
1308
+ },
1309
+ {
1310
+ "epoch": 1.2928003852636647,
1311
+ "grad_norm": 0.9022207260131836,
1312
+ "learning_rate": 0.00019237634441411164,
1313
+ "loss": 1.915,
1314
+ "step": 168
1315
+ },
1316
+ {
1317
+ "epoch": 1.300505658560077,
1318
+ "grad_norm": 0.8826063275337219,
1319
+ "learning_rate": 0.00019228316800356867,
1320
+ "loss": 1.8847,
1321
+ "step": 169
1322
+ },
1323
+ {
1324
+ "epoch": 1.3082109318564892,
1325
+ "grad_norm": 1.0092695951461792,
1326
+ "learning_rate": 0.00019218944848966443,
1327
+ "loss": 1.9258,
1328
+ "step": 170
1329
+ },
1330
+ {
1331
+ "epoch": 1.3082109318564892,
1332
+ "eval_loss": 2.211585521697998,
1333
+ "eval_runtime": 104.5108,
1334
+ "eval_samples_per_second": 13.597,
1335
+ "eval_steps_per_second": 6.803,
1336
+ "step": 170
1337
+ },
1338
+ {
1339
+ "epoch": 1.3159162051529014,
1340
+ "grad_norm": 0.9667842984199524,
1341
+ "learning_rate": 0.00019209518642395547,
1342
+ "loss": 1.9539,
1343
+ "step": 171
1344
+ },
1345
+ {
1346
+ "epoch": 1.3236214784493137,
1347
+ "grad_norm": 0.9047468304634094,
1348
+ "learning_rate": 0.00019200038236119132,
1349
+ "loss": 1.8967,
1350
+ "step": 172
1351
+ },
1352
+ {
1353
+ "epoch": 1.331326751745726,
1354
+ "grad_norm": 0.8873062133789062,
1355
+ "learning_rate": 0.00019190503685931128,
1356
+ "loss": 1.8798,
1357
+ "step": 173
1358
+ },
1359
+ {
1360
+ "epoch": 1.3390320250421381,
1361
+ "grad_norm": 0.8417840003967285,
1362
+ "learning_rate": 0.00019180915047944112,
1363
+ "loss": 1.7452,
1364
+ "step": 174
1365
+ },
1366
+ {
1367
+ "epoch": 1.3467372983385504,
1368
+ "grad_norm": 0.8584864735603333,
1369
+ "learning_rate": 0.0001917127237858897,
1370
+ "loss": 1.8955,
1371
+ "step": 175
1372
+ },
1373
+ {
1374
+ "epoch": 1.3544425716349626,
1375
+ "grad_norm": 0.8773009777069092,
1376
+ "learning_rate": 0.00019161575734614585,
1377
+ "loss": 1.7692,
1378
+ "step": 176
1379
+ },
1380
+ {
1381
+ "epoch": 1.3621478449313749,
1382
+ "grad_norm": 0.9004015922546387,
1383
+ "learning_rate": 0.00019151825173087484,
1384
+ "loss": 1.9334,
1385
+ "step": 177
1386
+ },
1387
+ {
1388
+ "epoch": 1.369853118227787,
1389
+ "grad_norm": 0.8859035968780518,
1390
+ "learning_rate": 0.00019142020751391505,
1391
+ "loss": 1.8605,
1392
+ "step": 178
1393
+ },
1394
+ {
1395
+ "epoch": 1.3775583915241993,
1396
+ "grad_norm": 0.9315618872642517,
1397
+ "learning_rate": 0.0001913216252722747,
1398
+ "loss": 1.8103,
1399
+ "step": 179
1400
+ },
1401
+ {
1402
+ "epoch": 1.3852636648206116,
1403
+ "grad_norm": 1.6217914819717407,
1404
+ "learning_rate": 0.0001912225055861284,
1405
+ "loss": 1.9772,
1406
+ "step": 180
1407
+ },
1408
+ {
1409
+ "epoch": 1.3852636648206116,
1410
+ "eval_loss": 2.185598850250244,
1411
+ "eval_runtime": 104.5878,
1412
+ "eval_samples_per_second": 13.587,
1413
+ "eval_steps_per_second": 6.798,
1414
+ "step": 180
1415
+ },
1416
+ {
1417
+ "epoch": 1.3929689381170238,
1418
+ "grad_norm": 0.8966831564903259,
1419
+ "learning_rate": 0.0001911228490388136,
1420
+ "loss": 1.8413,
1421
+ "step": 181
1422
+ },
1423
+ {
1424
+ "epoch": 1.400674211413436,
1425
+ "grad_norm": 0.9048365354537964,
1426
+ "learning_rate": 0.00019102265621682735,
1427
+ "loss": 1.8856,
1428
+ "step": 182
1429
+ },
1430
+ {
1431
+ "epoch": 1.4083794847098483,
1432
+ "grad_norm": 0.9013424515724182,
1433
+ "learning_rate": 0.00019092192770982282,
1434
+ "loss": 1.8913,
1435
+ "step": 183
1436
+ },
1437
+ {
1438
+ "epoch": 1.4160847580062605,
1439
+ "grad_norm": 0.8626971244812012,
1440
+ "learning_rate": 0.00019082066411060572,
1441
+ "loss": 1.879,
1442
+ "step": 184
1443
+ },
1444
+ {
1445
+ "epoch": 1.4237900313026728,
1446
+ "grad_norm": 0.827437162399292,
1447
+ "learning_rate": 0.0001907188660151309,
1448
+ "loss": 1.764,
1449
+ "step": 185
1450
+ },
1451
+ {
1452
+ "epoch": 1.431495304599085,
1453
+ "grad_norm": 0.8971157670021057,
1454
+ "learning_rate": 0.00019061653402249878,
1455
+ "loss": 1.8373,
1456
+ "step": 186
1457
+ },
1458
+ {
1459
+ "epoch": 1.4392005778954973,
1460
+ "grad_norm": 0.8580353856086731,
1461
+ "learning_rate": 0.00019051366873495197,
1462
+ "loss": 1.7123,
1463
+ "step": 187
1464
+ },
1465
+ {
1466
+ "epoch": 1.4469058511919095,
1467
+ "grad_norm": 0.8921018242835999,
1468
+ "learning_rate": 0.0001904102707578715,
1469
+ "loss": 1.7801,
1470
+ "step": 188
1471
+ },
1472
+ {
1473
+ "epoch": 1.4546111244883217,
1474
+ "grad_norm": 0.9258955121040344,
1475
+ "learning_rate": 0.00019030634069977338,
1476
+ "loss": 1.7388,
1477
+ "step": 189
1478
+ },
1479
+ {
1480
+ "epoch": 1.462316397784734,
1481
+ "grad_norm": 0.9307748079299927,
1482
+ "learning_rate": 0.0001902018791723051,
1483
+ "loss": 1.8279,
1484
+ "step": 190
1485
+ },
1486
+ {
1487
+ "epoch": 1.462316397784734,
1488
+ "eval_loss": 2.1763482093811035,
1489
+ "eval_runtime": 104.5816,
1490
+ "eval_samples_per_second": 13.587,
1491
+ "eval_steps_per_second": 6.799,
1492
+ "step": 190
1493
+ },
1494
+ {
1495
+ "epoch": 1.4700216710811462,
1496
+ "grad_norm": 0.9665712118148804,
1497
+ "learning_rate": 0.0001900968867902419,
1498
+ "loss": 1.8146,
1499
+ "step": 191
1500
+ },
1501
+ {
1502
+ "epoch": 1.4777269443775585,
1503
+ "grad_norm": 0.9362412095069885,
1504
+ "learning_rate": 0.00018999136417148323,
1505
+ "loss": 1.8572,
1506
+ "step": 192
1507
+ },
1508
+ {
1509
+ "epoch": 1.4854322176739707,
1510
+ "grad_norm": 0.8829795718193054,
1511
+ "learning_rate": 0.00018988531193704896,
1512
+ "loss": 1.8021,
1513
+ "step": 193
1514
+ },
1515
+ {
1516
+ "epoch": 1.493137490970383,
1517
+ "grad_norm": 0.8836817741394043,
1518
+ "learning_rate": 0.00018977873071107602,
1519
+ "loss": 1.9409,
1520
+ "step": 194
1521
+ },
1522
+ {
1523
+ "epoch": 1.5008427642667952,
1524
+ "grad_norm": 0.8436566591262817,
1525
+ "learning_rate": 0.00018967162112081438,
1526
+ "loss": 1.7496,
1527
+ "step": 195
1528
+ },
1529
+ {
1530
+ "epoch": 1.5085480375632074,
1531
+ "grad_norm": 0.8727232813835144,
1532
+ "learning_rate": 0.00018956398379662366,
1533
+ "loss": 1.809,
1534
+ "step": 196
1535
+ },
1536
+ {
1537
+ "epoch": 1.5162533108596197,
1538
+ "grad_norm": 0.9147477746009827,
1539
+ "learning_rate": 0.00018945581937196928,
1540
+ "loss": 1.7946,
1541
+ "step": 197
1542
+ },
1543
+ {
1544
+ "epoch": 1.523958584156032,
1545
+ "grad_norm": 0.9350097179412842,
1546
+ "learning_rate": 0.00018934712848341862,
1547
+ "loss": 1.8442,
1548
+ "step": 198
1549
+ },
1550
+ {
1551
+ "epoch": 1.5316638574524442,
1552
+ "grad_norm": 0.9377596974372864,
1553
+ "learning_rate": 0.00018923791177063756,
1554
+ "loss": 1.892,
1555
+ "step": 199
1556
+ },
1557
+ {
1558
+ "epoch": 1.5393691307488564,
1559
+ "grad_norm": 0.9386144280433655,
1560
+ "learning_rate": 0.00018912816987638645,
1561
+ "loss": 1.7704,
1562
+ "step": 200
1563
+ },
1564
+ {
1565
+ "epoch": 1.5393691307488564,
1566
+ "eval_loss": 2.165375232696533,
1567
+ "eval_runtime": 104.3086,
1568
+ "eval_samples_per_second": 13.623,
1569
+ "eval_steps_per_second": 6.816,
1570
+ "step": 200
1571
+ },
1572
+ {
1573
+ "epoch": 1.5470744040452686,
1574
+ "grad_norm": 0.9634820818901062,
1575
+ "learning_rate": 0.00018901790344651645,
1576
+ "loss": 1.8675,
1577
+ "step": 201
1578
+ },
1579
+ {
1580
+ "epoch": 1.5547796773416809,
1581
+ "grad_norm": 0.8905439376831055,
1582
+ "learning_rate": 0.0001889071131299657,
1583
+ "loss": 1.6538,
1584
+ "step": 202
1585
+ },
1586
+ {
1587
+ "epoch": 1.562484950638093,
1588
+ "grad_norm": 0.915834367275238,
1589
+ "learning_rate": 0.00018879579957875557,
1590
+ "loss": 1.9346,
1591
+ "step": 203
1592
+ },
1593
+ {
1594
+ "epoch": 1.5701902239345051,
1595
+ "grad_norm": 0.8621256351470947,
1596
+ "learning_rate": 0.00018868396344798668,
1597
+ "loss": 1.8841,
1598
+ "step": 204
1599
+ },
1600
+ {
1601
+ "epoch": 1.5778954972309174,
1602
+ "grad_norm": 0.900134265422821,
1603
+ "learning_rate": 0.0001885716053958352,
1604
+ "loss": 1.9718,
1605
+ "step": 205
1606
+ },
1607
+ {
1608
+ "epoch": 1.5856007705273296,
1609
+ "grad_norm": 0.9604853987693787,
1610
+ "learning_rate": 0.00018845872608354877,
1611
+ "loss": 1.8563,
1612
+ "step": 206
1613
+ },
1614
+ {
1615
+ "epoch": 1.5933060438237419,
1616
+ "grad_norm": 0.9031288623809814,
1617
+ "learning_rate": 0.00018834532617544296,
1618
+ "loss": 1.896,
1619
+ "step": 207
1620
+ },
1621
+ {
1622
+ "epoch": 1.601011317120154,
1623
+ "grad_norm": 1.0020586252212524,
1624
+ "learning_rate": 0.00018823140633889693,
1625
+ "loss": 1.8468,
1626
+ "step": 208
1627
+ },
1628
+ {
1629
+ "epoch": 1.6087165904165663,
1630
+ "grad_norm": 0.9199175834655762,
1631
+ "learning_rate": 0.00018811696724434983,
1632
+ "loss": 1.938,
1633
+ "step": 209
1634
+ },
1635
+ {
1636
+ "epoch": 1.6164218637129786,
1637
+ "grad_norm": 0.9412999749183655,
1638
+ "learning_rate": 0.0001880020095652967,
1639
+ "loss": 1.8204,
1640
+ "step": 210
1641
+ },
1642
+ {
1643
+ "epoch": 1.6164218637129786,
1644
+ "eval_loss": 2.136986017227173,
1645
+ "eval_runtime": 104.2848,
1646
+ "eval_samples_per_second": 13.626,
1647
+ "eval_steps_per_second": 6.818,
1648
+ "step": 210
1649
+ },
1650
+ {
1651
+ "epoch": 1.6241271370093908,
1652
+ "grad_norm": 0.8906149864196777,
1653
+ "learning_rate": 0.0001878865339782846,
1654
+ "loss": 1.8224,
1655
+ "step": 211
1656
+ },
1657
+ {
1658
+ "epoch": 1.631832410305803,
1659
+ "grad_norm": 0.928481936454773,
1660
+ "learning_rate": 0.00018777054116290846,
1661
+ "loss": 1.9321,
1662
+ "step": 212
1663
+ },
1664
+ {
1665
+ "epoch": 1.6395376836022153,
1666
+ "grad_norm": 0.8027057647705078,
1667
+ "learning_rate": 0.00018765403180180732,
1668
+ "loss": 1.6184,
1669
+ "step": 213
1670
+ },
1671
+ {
1672
+ "epoch": 1.6472429568986275,
1673
+ "grad_norm": 0.8844785094261169,
1674
+ "learning_rate": 0.00018753700658066008,
1675
+ "loss": 1.8004,
1676
+ "step": 214
1677
+ },
1678
+ {
1679
+ "epoch": 1.6549482301950398,
1680
+ "grad_norm": 0.8914289474487305,
1681
+ "learning_rate": 0.00018741946618818167,
1682
+ "loss": 1.9124,
1683
+ "step": 215
1684
+ },
1685
+ {
1686
+ "epoch": 1.6626535034914518,
1687
+ "grad_norm": 0.8590049743652344,
1688
+ "learning_rate": 0.00018730141131611882,
1689
+ "loss": 1.7388,
1690
+ "step": 216
1691
+ },
1692
+ {
1693
+ "epoch": 1.670358776787864,
1694
+ "grad_norm": 0.8608388900756836,
1695
+ "learning_rate": 0.0001871828426592461,
1696
+ "loss": 1.7499,
1697
+ "step": 217
1698
+ },
1699
+ {
1700
+ "epoch": 1.6780640500842763,
1701
+ "grad_norm": 0.9073550701141357,
1702
+ "learning_rate": 0.0001870637609153618,
1703
+ "loss": 1.8785,
1704
+ "step": 218
1705
+ },
1706
+ {
1707
+ "epoch": 1.6857693233806885,
1708
+ "grad_norm": 0.8661384582519531,
1709
+ "learning_rate": 0.00018694416678528378,
1710
+ "loss": 1.6824,
1711
+ "step": 219
1712
+ },
1713
+ {
1714
+ "epoch": 1.6934745966771008,
1715
+ "grad_norm": 0.8858973979949951,
1716
+ "learning_rate": 0.00018682406097284546,
1717
+ "loss": 1.7412,
1718
+ "step": 220
1719
+ },
1720
+ {
1721
+ "epoch": 1.6934745966771008,
1722
+ "eval_loss": 2.126521110534668,
1723
+ "eval_runtime": 104.1601,
1724
+ "eval_samples_per_second": 13.642,
1725
+ "eval_steps_per_second": 6.826,
1726
+ "step": 220
1727
+ },
1728
+ {
1729
+ "epoch": 1.701179869973513,
1730
+ "grad_norm": 0.9170217514038086,
1731
+ "learning_rate": 0.0001867034441848915,
1732
+ "loss": 1.7153,
1733
+ "step": 221
1734
+ },
1735
+ {
1736
+ "epoch": 1.7088851432699252,
1737
+ "grad_norm": 0.8762798309326172,
1738
+ "learning_rate": 0.00018658231713127393,
1739
+ "loss": 1.7609,
1740
+ "step": 222
1741
+ },
1742
+ {
1743
+ "epoch": 1.7165904165663375,
1744
+ "grad_norm": 0.8702017068862915,
1745
+ "learning_rate": 0.00018646068052484755,
1746
+ "loss": 1.7763,
1747
+ "step": 223
1748
+ },
1749
+ {
1750
+ "epoch": 1.7242956898627497,
1751
+ "grad_norm": 0.8977987766265869,
1752
+ "learning_rate": 0.00018633853508146615,
1753
+ "loss": 1.907,
1754
+ "step": 224
1755
+ },
1756
+ {
1757
+ "epoch": 1.732000963159162,
1758
+ "grad_norm": 0.8923841118812561,
1759
+ "learning_rate": 0.00018621588151997802,
1760
+ "loss": 1.8091,
1761
+ "step": 225
1762
+ },
1763
+ {
1764
+ "epoch": 1.7397062364555742,
1765
+ "grad_norm": 0.8536685705184937,
1766
+ "learning_rate": 0.00018609272056222188,
1767
+ "loss": 1.8238,
1768
+ "step": 226
1769
+ },
1770
+ {
1771
+ "epoch": 1.7474115097519864,
1772
+ "grad_norm": 0.9035041332244873,
1773
+ "learning_rate": 0.00018596905293302252,
1774
+ "loss": 1.8405,
1775
+ "step": 227
1776
+ },
1777
+ {
1778
+ "epoch": 1.7551167830483987,
1779
+ "grad_norm": 0.8790361881256104,
1780
+ "learning_rate": 0.00018584487936018661,
1781
+ "loss": 1.863,
1782
+ "step": 228
1783
+ },
1784
+ {
1785
+ "epoch": 1.762822056344811,
1786
+ "grad_norm": 0.9027377963066101,
1787
+ "learning_rate": 0.00018572020057449845,
1788
+ "loss": 1.8408,
1789
+ "step": 229
1790
+ },
1791
+ {
1792
+ "epoch": 1.7705273296412232,
1793
+ "grad_norm": 0.8394613265991211,
1794
+ "learning_rate": 0.00018559501730971544,
1795
+ "loss": 1.8159,
1796
+ "step": 230
1797
+ },
1798
+ {
1799
+ "epoch": 1.7705273296412232,
1800
+ "eval_loss": 2.0943915843963623,
1801
+ "eval_runtime": 104.4027,
1802
+ "eval_samples_per_second": 13.611,
1803
+ "eval_steps_per_second": 6.81,
1804
+ "step": 230
1805
+ },
1806
+ {
1807
+ "epoch": 1.7782326029376354,
1808
+ "grad_norm": 0.8502392768859863,
1809
+ "learning_rate": 0.00018546933030256417,
1810
+ "loss": 1.8635,
1811
+ "step": 231
1812
+ },
1813
+ {
1814
+ "epoch": 1.7859378762340476,
1815
+ "grad_norm": 0.8786526918411255,
1816
+ "learning_rate": 0.0001853431402927356,
1817
+ "loss": 1.7904,
1818
+ "step": 232
1819
+ },
1820
+ {
1821
+ "epoch": 1.79364314953046,
1822
+ "grad_norm": 0.8435688018798828,
1823
+ "learning_rate": 0.00018521644802288117,
1824
+ "loss": 1.7378,
1825
+ "step": 233
1826
+ },
1827
+ {
1828
+ "epoch": 1.8013484228268721,
1829
+ "grad_norm": 0.8533286452293396,
1830
+ "learning_rate": 0.00018508925423860805,
1831
+ "loss": 1.764,
1832
+ "step": 234
1833
+ },
1834
+ {
1835
+ "epoch": 1.8090536961232844,
1836
+ "grad_norm": 0.8472200036048889,
1837
+ "learning_rate": 0.00018496155968847496,
1838
+ "loss": 1.7098,
1839
+ "step": 235
1840
+ },
1841
+ {
1842
+ "epoch": 1.8167589694196966,
1843
+ "grad_norm": 0.8728060126304626,
1844
+ "learning_rate": 0.00018483336512398784,
1845
+ "loss": 1.7495,
1846
+ "step": 236
1847
+ },
1848
+ {
1849
+ "epoch": 1.8244642427161089,
1850
+ "grad_norm": 0.9004346132278442,
1851
+ "learning_rate": 0.0001847046712995951,
1852
+ "loss": 1.7832,
1853
+ "step": 237
1854
+ },
1855
+ {
1856
+ "epoch": 1.832169516012521,
1857
+ "grad_norm": 0.9028909802436829,
1858
+ "learning_rate": 0.00018457547897268354,
1859
+ "loss": 1.7123,
1860
+ "step": 238
1861
+ },
1862
+ {
1863
+ "epoch": 1.8398747893089333,
1864
+ "grad_norm": 0.9071741104125977,
1865
+ "learning_rate": 0.00018444578890357364,
1866
+ "loss": 1.8654,
1867
+ "step": 239
1868
+ },
1869
+ {
1870
+ "epoch": 1.8475800626053456,
1871
+ "grad_norm": 0.9161725640296936,
1872
+ "learning_rate": 0.0001843156018555153,
1873
+ "loss": 1.7549,
1874
+ "step": 240
1875
+ },
1876
+ {
1877
+ "epoch": 1.8475800626053456,
1878
+ "eval_loss": 2.0773444175720215,
1879
+ "eval_runtime": 104.335,
1880
+ "eval_samples_per_second": 13.62,
1881
+ "eval_steps_per_second": 6.815,
1882
+ "step": 240
1883
+ },
1884
+ {
1885
+ "epoch": 1.8552853359017578,
1886
+ "grad_norm": 0.8834810853004456,
1887
+ "learning_rate": 0.00018418491859468312,
1888
+ "loss": 1.7304,
1889
+ "step": 241
1890
+ },
1891
+ {
1892
+ "epoch": 1.86299060919817,
1893
+ "grad_norm": 0.8890105485916138,
1894
+ "learning_rate": 0.00018405373989017205,
1895
+ "loss": 1.7053,
1896
+ "step": 242
1897
+ },
1898
+ {
1899
+ "epoch": 1.8706958824945823,
1900
+ "grad_norm": 0.8263651132583618,
1901
+ "learning_rate": 0.0001839220665139928,
1902
+ "loss": 1.7864,
1903
+ "step": 243
1904
+ },
1905
+ {
1906
+ "epoch": 1.8784011557909945,
1907
+ "grad_norm": 0.8346523642539978,
1908
+ "learning_rate": 0.00018378989924106736,
1909
+ "loss": 1.7313,
1910
+ "step": 244
1911
+ },
1912
+ {
1913
+ "epoch": 1.8861064290874068,
1914
+ "grad_norm": 0.8848766684532166,
1915
+ "learning_rate": 0.00018365723884922435,
1916
+ "loss": 1.81,
1917
+ "step": 245
1918
+ },
1919
+ {
1920
+ "epoch": 1.893811702383819,
1921
+ "grad_norm": 0.9062768220901489,
1922
+ "learning_rate": 0.00018352408611919453,
1923
+ "loss": 1.819,
1924
+ "step": 246
1925
+ },
1926
+ {
1927
+ "epoch": 1.9015169756802313,
1928
+ "grad_norm": 0.8580806851387024,
1929
+ "learning_rate": 0.00018339044183460603,
1930
+ "loss": 1.7978,
1931
+ "step": 247
1932
+ },
1933
+ {
1934
+ "epoch": 1.9092222489766435,
1935
+ "grad_norm": 0.8717938661575317,
1936
+ "learning_rate": 0.00018325630678198005,
1937
+ "loss": 1.7062,
1938
+ "step": 248
1939
+ },
1940
+ {
1941
+ "epoch": 1.9169275222730557,
1942
+ "grad_norm": 0.8965945243835449,
1943
+ "learning_rate": 0.00018312168175072592,
1944
+ "loss": 1.8668,
1945
+ "step": 249
1946
+ },
1947
+ {
1948
+ "epoch": 1.924632795569468,
1949
+ "grad_norm": 0.8601094484329224,
1950
+ "learning_rate": 0.00018298656753313667,
1951
+ "loss": 1.733,
1952
+ "step": 250
1953
+ },
1954
+ {
1955
+ "epoch": 1.924632795569468,
1956
+ "eval_loss": 2.0676074028015137,
1957
+ "eval_runtime": 104.4942,
1958
+ "eval_samples_per_second": 13.599,
1959
+ "eval_steps_per_second": 6.804,
1960
+ "step": 250
1961
+ },
1962
+ {
1963
+ "epoch": 1.9323380688658802,
1964
+ "grad_norm": 0.9133442044258118,
1965
+ "learning_rate": 0.00018285096492438424,
1966
+ "loss": 1.8647,
1967
+ "step": 251
1968
+ },
1969
+ {
1970
+ "epoch": 1.9400433421622925,
1971
+ "grad_norm": 0.8821327686309814,
1972
+ "learning_rate": 0.00018271487472251477,
1973
+ "loss": 1.9081,
1974
+ "step": 252
1975
+ },
1976
+ {
1977
+ "epoch": 1.9477486154587047,
1978
+ "grad_norm": 0.8632904291152954,
1979
+ "learning_rate": 0.00018257829772844414,
1980
+ "loss": 1.8125,
1981
+ "step": 253
1982
+ },
1983
+ {
1984
+ "epoch": 1.955453888755117,
1985
+ "grad_norm": 0.8215700387954712,
1986
+ "learning_rate": 0.00018244123474595288,
1987
+ "loss": 1.7112,
1988
+ "step": 254
1989
+ },
1990
+ {
1991
+ "epoch": 1.963159162051529,
1992
+ "grad_norm": 0.8658733367919922,
1993
+ "learning_rate": 0.00018230368658168192,
1994
+ "loss": 1.7901,
1995
+ "step": 255
1996
+ },
1997
+ {
1998
+ "epoch": 1.9708644353479412,
1999
+ "grad_norm": 0.8564244508743286,
2000
+ "learning_rate": 0.0001821656540451273,
2001
+ "loss": 1.7651,
2002
+ "step": 256
2003
+ },
2004
+ {
2005
+ "epoch": 1.9785697086443534,
2006
+ "grad_norm": 0.896857738494873,
2007
+ "learning_rate": 0.00018202713794863586,
2008
+ "loss": 1.7607,
2009
+ "step": 257
2010
+ },
2011
+ {
2012
+ "epoch": 1.9862749819407657,
2013
+ "grad_norm": 0.9321516752243042,
2014
+ "learning_rate": 0.0001818881391074002,
2015
+ "loss": 1.8388,
2016
+ "step": 258
2017
+ },
2018
+ {
2019
+ "epoch": 1.993980255237178,
2020
+ "grad_norm": 0.9047143459320068,
2021
+ "learning_rate": 0.000181748658339454,
2022
+ "loss": 1.7978,
2023
+ "step": 259
2024
+ },
2025
+ {
2026
+ "epoch": 2.0,
2027
+ "grad_norm": 0.9801378846168518,
2028
+ "learning_rate": 0.00018160869646566713,
2029
+ "loss": 1.7296,
2030
+ "step": 260
2031
+ },
2032
+ {
2033
+ "epoch": 2.0,
2034
+ "eval_loss": 2.055561065673828,
2035
+ "eval_runtime": 104.4419,
2036
+ "eval_samples_per_second": 13.606,
2037
+ "eval_steps_per_second": 6.808,
2038
+ "step": 260
2039
+ }
2040
+ ],
2041
+ "logging_steps": 1,
2042
+ "max_steps": 1300,
2043
+ "num_input_tokens_seen": 0,
2044
+ "num_train_epochs": 10,
2045
+ "save_steps": 10,
2046
+ "stateful_callbacks": {
2047
+ "EarlyStoppingCallback": {
2048
+ "args": {
2049
+ "early_stopping_patience": 2,
2050
+ "early_stopping_threshold": 0.001
2051
+ },
2052
+ "attributes": {
2053
+ "early_stopping_patience_counter": 0
2054
+ }
2055
+ },
2056
+ "TrainerControl": {
2057
+ "args": {
2058
+ "should_epoch_stop": false,
2059
+ "should_evaluate": false,
2060
+ "should_log": false,
2061
+ "should_save": true,
2062
+ "should_training_stop": false
2063
+ },
2064
+ "attributes": {}
2065
+ }
2066
+ },
2067
+ "total_flos": 5.5500716906643456e+17,
2068
+ "train_batch_size": 1,
2069
+ "trial_name": null,
2070
+ "trial_params": null
2071
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc0bc4705482e359d4ec2f22c50ecf4daa9cc8c679ecab9d4a3867898407f82
3
+ size 6353
vocab.json ADDED
The diff for this file is too large to render. See raw diff