satyanayak commited on
Commit
0865df8
·
verified ·
1 Parent(s): 8743186

upload all model files

Browse files

Extracted all the model files and uploaded.

README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-2
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-2",
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": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "dense"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763c81136d99820ca248ef4597c67d6d78c449007aea88b62cfe8f16135dcc5d
3
+ size 41977360
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
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 sha256:646d4f487a71c50f3db1aa3bd8e5a736341897f5adeb09a078de540ef56ab17c
3
+ size 84037562
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc09d9fb1f403f1b24fee3d70d6cfe9af0fd6cd9ff28cb259765762c8823e53
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488341b84be4d141b80ff7a3c415a5379e4f119b97bd41cb6c25814f1435efa8
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2392011c84b4f34c297237910f29d1ca5210b6cae19a9f6405857d131d112c9a
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
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 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "extra_special_tokens": {},
321
+ "model_max_length": 2048,
322
+ "pad_token": "<|endoftext|>",
323
+ "return_token_type_ids": false,
324
+ "tokenizer_class": "CodeGenTokenizer",
325
+ "unk_token": "<|endoftext|>"
326
+ }
trainer_state.json ADDED
@@ -0,0 +1,1993 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9998981773750127,
5
+ "eval_steps": 500,
6
+ "global_step": 2455,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004072904999490887,
13
+ "grad_norm": 0.7094523906707764,
14
+ "learning_rate": 2.702702702702703e-05,
15
+ "loss": 1.8961,
16
+ "mean_token_accuracy": 0.5438283555209636,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.008145809998981774,
21
+ "grad_norm": 0.4965726137161255,
22
+ "learning_rate": 5.405405405405406e-05,
23
+ "loss": 2.0135,
24
+ "mean_token_accuracy": 0.5206024497747421,
25
+ "step": 20
26
+ },
27
+ {
28
+ "epoch": 0.01221871499847266,
29
+ "grad_norm": 0.5204955339431763,
30
+ "learning_rate": 8.108108108108109e-05,
31
+ "loss": 1.7338,
32
+ "mean_token_accuracy": 0.5830004885792732,
33
+ "step": 30
34
+ },
35
+ {
36
+ "epoch": 0.01629161999796355,
37
+ "grad_norm": 0.4678299129009247,
38
+ "learning_rate": 0.00010810810810810812,
39
+ "loss": 1.7561,
40
+ "mean_token_accuracy": 0.5730855345726014,
41
+ "step": 40
42
+ },
43
+ {
44
+ "epoch": 0.020364524997454433,
45
+ "grad_norm": 0.439376562833786,
46
+ "learning_rate": 0.00013513513513513514,
47
+ "loss": 1.7277,
48
+ "mean_token_accuracy": 0.5785414174199104,
49
+ "step": 50
50
+ },
51
+ {
52
+ "epoch": 0.02443742999694532,
53
+ "grad_norm": 0.5652154684066772,
54
+ "learning_rate": 0.00016216216216216218,
55
+ "loss": 1.5663,
56
+ "mean_token_accuracy": 0.6036677993834019,
57
+ "step": 60
58
+ },
59
+ {
60
+ "epoch": 0.02851033499643621,
61
+ "grad_norm": 0.5163070559501648,
62
+ "learning_rate": 0.0001891891891891892,
63
+ "loss": 1.8259,
64
+ "mean_token_accuracy": 0.5530456639826298,
65
+ "step": 70
66
+ },
67
+ {
68
+ "epoch": 0.0325832399959271,
69
+ "grad_norm": 0.41974571347236633,
70
+ "learning_rate": 0.00019999686634492516,
71
+ "loss": 1.6554,
72
+ "mean_token_accuracy": 0.6073097884654999,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.03665614499541798,
77
+ "grad_norm": 0.5097134709358215,
78
+ "learning_rate": 0.00019997771694180204,
79
+ "loss": 1.7208,
80
+ "mean_token_accuracy": 0.5835812106728554,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 0.04072904999490887,
85
+ "grad_norm": 0.3469955623149872,
86
+ "learning_rate": 0.00019994116238472668,
87
+ "loss": 1.7954,
88
+ "mean_token_accuracy": 0.5794057920575142,
89
+ "step": 100
90
+ },
91
+ {
92
+ "epoch": 0.044801954994399755,
93
+ "grad_norm": 0.5898286700248718,
94
+ "learning_rate": 0.0001998872090374941,
95
+ "loss": 1.8089,
96
+ "mean_token_accuracy": 0.5614037178456783,
97
+ "step": 110
98
+ },
99
+ {
100
+ "epoch": 0.04887485999389064,
101
+ "grad_norm": 0.3150334656238556,
102
+ "learning_rate": 0.0001998158662928604,
103
+ "loss": 1.5827,
104
+ "mean_token_accuracy": 0.5801003761589527,
105
+ "step": 120
106
+ },
107
+ {
108
+ "epoch": 0.05294776499338153,
109
+ "grad_norm": 0.3100312352180481,
110
+ "learning_rate": 0.00019972714657090772,
111
+ "loss": 1.6712,
112
+ "mean_token_accuracy": 0.5900266923010349,
113
+ "step": 130
114
+ },
115
+ {
116
+ "epoch": 0.05702066999287242,
117
+ "grad_norm": 0.30420345067977905,
118
+ "learning_rate": 0.0001996210653168819,
119
+ "loss": 1.646,
120
+ "mean_token_accuracy": 0.5839473098516464,
121
+ "step": 140
122
+ },
123
+ {
124
+ "epoch": 0.0610935749923633,
125
+ "grad_norm": 0.454593688249588,
126
+ "learning_rate": 0.0001994976409985037,
127
+ "loss": 1.7184,
128
+ "mean_token_accuracy": 0.566600239276886,
129
+ "step": 150
130
+ },
131
+ {
132
+ "epoch": 0.0651664799918542,
133
+ "grad_norm": 0.35688647627830505,
134
+ "learning_rate": 0.0001993568951027537,
135
+ "loss": 1.6766,
136
+ "mean_token_accuracy": 0.5824202686548233,
137
+ "step": 160
138
+ },
139
+ {
140
+ "epoch": 0.06923938499134508,
141
+ "grad_norm": 0.3199939727783203,
142
+ "learning_rate": 0.0001991988521321317,
143
+ "loss": 1.542,
144
+ "mean_token_accuracy": 0.6095141984522343,
145
+ "step": 170
146
+ },
147
+ {
148
+ "epoch": 0.07331228999083596,
149
+ "grad_norm": 0.5523242950439453,
150
+ "learning_rate": 0.00019902353960039087,
151
+ "loss": 1.7218,
152
+ "mean_token_accuracy": 0.5745485998690129,
153
+ "step": 180
154
+ },
155
+ {
156
+ "epoch": 0.07738519499032685,
157
+ "grad_norm": 0.3872721493244171,
158
+ "learning_rate": 0.00019883098802774812,
159
+ "loss": 1.7306,
160
+ "mean_token_accuracy": 0.5514535710215569,
161
+ "step": 190
162
+ },
163
+ {
164
+ "epoch": 0.08145809998981773,
165
+ "grad_norm": 0.2679811120033264,
166
+ "learning_rate": 0.0001986212309355707,
167
+ "loss": 1.6524,
168
+ "mean_token_accuracy": 0.5822832569479942,
169
+ "step": 200
170
+ },
171
+ {
172
+ "epoch": 0.08553100498930863,
173
+ "grad_norm": 0.5167363882064819,
174
+ "learning_rate": 0.00019839430484054046,
175
+ "loss": 1.6964,
176
+ "mean_token_accuracy": 0.573430598527193,
177
+ "step": 210
178
+ },
179
+ {
180
+ "epoch": 0.08960390998879951,
181
+ "grad_norm": 0.4363399147987366,
182
+ "learning_rate": 0.0001981502492482967,
183
+ "loss": 1.7296,
184
+ "mean_token_accuracy": 0.5835007324814796,
185
+ "step": 220
186
+ },
187
+ {
188
+ "epoch": 0.0936768149882904,
189
+ "grad_norm": 0.4052150845527649,
190
+ "learning_rate": 0.00019788910664655848,
191
+ "loss": 1.5772,
192
+ "mean_token_accuracy": 0.5771500714123249,
193
+ "step": 230
194
+ },
195
+ {
196
+ "epoch": 0.09774971998778129,
197
+ "grad_norm": 0.34224212169647217,
198
+ "learning_rate": 0.0001976109224977281,
199
+ "loss": 1.6263,
200
+ "mean_token_accuracy": 0.5942870646715164,
201
+ "step": 240
202
+ },
203
+ {
204
+ "epoch": 0.10182262498727217,
205
+ "grad_norm": 0.4852873980998993,
206
+ "learning_rate": 0.00019731574523097647,
207
+ "loss": 1.5731,
208
+ "mean_token_accuracy": 0.5886094763875007,
209
+ "step": 250
210
+ },
211
+ {
212
+ "epoch": 0.10589552998676306,
213
+ "grad_norm": 0.30241233110427856,
214
+ "learning_rate": 0.00019700362623381197,
215
+ "loss": 1.8311,
216
+ "mean_token_accuracy": 0.5616028495132923,
217
+ "step": 260
218
+ },
219
+ {
220
+ "epoch": 0.10996843498625394,
221
+ "grad_norm": 0.38147303462028503,
222
+ "learning_rate": 0.00019667461984313448,
223
+ "loss": 1.652,
224
+ "mean_token_accuracy": 0.5836799181997776,
225
+ "step": 270
226
+ },
227
+ {
228
+ "epoch": 0.11404133998574484,
229
+ "grad_norm": 0.3174324333667755,
230
+ "learning_rate": 0.00019632878333577592,
231
+ "loss": 1.6831,
232
+ "mean_token_accuracy": 0.5850063987076283,
233
+ "step": 280
234
+ },
235
+ {
236
+ "epoch": 0.11811424498523572,
237
+ "grad_norm": 0.350323349237442,
238
+ "learning_rate": 0.00019596617691852863,
239
+ "loss": 1.6644,
240
+ "mean_token_accuracy": 0.5841067053377629,
241
+ "step": 290
242
+ },
243
+ {
244
+ "epoch": 0.1221871499847266,
245
+ "grad_norm": 0.30346542596817017,
246
+ "learning_rate": 0.0001955868637176643,
247
+ "loss": 1.656,
248
+ "mean_token_accuracy": 0.584677055478096,
249
+ "step": 300
250
+ },
251
+ {
252
+ "epoch": 0.1262600549842175,
253
+ "grad_norm": 0.2639765739440918,
254
+ "learning_rate": 0.00019519090976794406,
255
+ "loss": 1.7454,
256
+ "mean_token_accuracy": 0.5678185373544693,
257
+ "step": 310
258
+ },
259
+ {
260
+ "epoch": 0.1303329599837084,
261
+ "grad_norm": 0.3039887547492981,
262
+ "learning_rate": 0.00019477838400112254,
263
+ "loss": 1.754,
264
+ "mean_token_accuracy": 0.5744720883667469,
265
+ "step": 320
266
+ },
267
+ {
268
+ "epoch": 0.13440586498319926,
269
+ "grad_norm": 0.35102295875549316,
270
+ "learning_rate": 0.00019434935823394746,
271
+ "loss": 1.6665,
272
+ "mean_token_accuracy": 0.5876846723258495,
273
+ "step": 330
274
+ },
275
+ {
276
+ "epoch": 0.13847876998269015,
277
+ "grad_norm": 0.3325759470462799,
278
+ "learning_rate": 0.00019390390715565725,
279
+ "loss": 1.6773,
280
+ "mean_token_accuracy": 0.5869172632694244,
281
+ "step": 340
282
+ },
283
+ {
284
+ "epoch": 0.14255167498218105,
285
+ "grad_norm": 0.37209993600845337,
286
+ "learning_rate": 0.000193442108314978,
287
+ "loss": 1.6328,
288
+ "mean_token_accuracy": 0.5927142709493637,
289
+ "step": 350
290
+ },
291
+ {
292
+ "epoch": 0.14662457998167192,
293
+ "grad_norm": 0.2964717149734497,
294
+ "learning_rate": 0.00019296404210662331,
295
+ "loss": 1.5659,
296
+ "mean_token_accuracy": 0.60322862342,
297
+ "step": 360
298
+ },
299
+ {
300
+ "epoch": 0.1506974849811628,
301
+ "grad_norm": 0.29879456758499146,
302
+ "learning_rate": 0.00019246979175729822,
303
+ "loss": 1.7083,
304
+ "mean_token_accuracy": 0.5893984287977219,
305
+ "step": 370
306
+ },
307
+ {
308
+ "epoch": 0.1547703899806537,
309
+ "grad_norm": 0.3726056218147278,
310
+ "learning_rate": 0.00019195944331121015,
311
+ "loss": 1.6854,
312
+ "mean_token_accuracy": 0.5761750474572181,
313
+ "step": 380
314
+ },
315
+ {
316
+ "epoch": 0.1588432949801446,
317
+ "grad_norm": 0.517816424369812,
318
+ "learning_rate": 0.0001914330856150897,
319
+ "loss": 1.7282,
320
+ "mean_token_accuracy": 0.5854727104306221,
321
+ "step": 390
322
+ },
323
+ {
324
+ "epoch": 0.16291619997963547,
325
+ "grad_norm": 0.25848233699798584,
326
+ "learning_rate": 0.00019089081030272296,
327
+ "loss": 1.5562,
328
+ "mean_token_accuracy": 0.6038706839084625,
329
+ "step": 400
330
+ },
331
+ {
332
+ "epoch": 0.16698910497912636,
333
+ "grad_norm": 0.3191607892513275,
334
+ "learning_rate": 0.00019033271177899922,
335
+ "loss": 1.6452,
336
+ "mean_token_accuracy": 0.5812859788537026,
337
+ "step": 410
338
+ },
339
+ {
340
+ "epoch": 0.17106200997861726,
341
+ "grad_norm": 0.3990655243396759,
342
+ "learning_rate": 0.0001897588872034758,
343
+ "loss": 1.626,
344
+ "mean_token_accuracy": 0.569889971613884,
345
+ "step": 420
346
+ },
347
+ {
348
+ "epoch": 0.17513491497810812,
349
+ "grad_norm": 0.346086323261261,
350
+ "learning_rate": 0.00018916943647346375,
351
+ "loss": 1.7451,
352
+ "mean_token_accuracy": 0.578500047326088,
353
+ "step": 430
354
+ },
355
+ {
356
+ "epoch": 0.17920781997759902,
357
+ "grad_norm": 0.36437422037124634,
358
+ "learning_rate": 0.0001885644622066364,
359
+ "loss": 1.846,
360
+ "mean_token_accuracy": 0.5627885892987251,
361
+ "step": 440
362
+ },
363
+ {
364
+ "epoch": 0.18328072497708991,
365
+ "grad_norm": 0.2968160808086395,
366
+ "learning_rate": 0.00018794406972316482,
367
+ "loss": 1.671,
368
+ "mean_token_accuracy": 0.5769762165844441,
369
+ "step": 450
370
+ },
371
+ {
372
+ "epoch": 0.1873536299765808,
373
+ "grad_norm": 0.2781198024749756,
374
+ "learning_rate": 0.00018730836702738257,
375
+ "loss": 1.4983,
376
+ "mean_token_accuracy": 0.613883113116026,
377
+ "step": 460
378
+ },
379
+ {
380
+ "epoch": 0.19142653497607168,
381
+ "grad_norm": 0.4645621180534363,
382
+ "learning_rate": 0.0001866574647889831,
383
+ "loss": 1.6776,
384
+ "mean_token_accuracy": 0.5890260674059391,
385
+ "step": 470
386
+ },
387
+ {
388
+ "epoch": 0.19549943997556257,
389
+ "grad_norm": 0.3920878767967224,
390
+ "learning_rate": 0.00018599147632375332,
391
+ "loss": 1.802,
392
+ "mean_token_accuracy": 0.568213502317667,
393
+ "step": 480
394
+ },
395
+ {
396
+ "epoch": 0.19957234497505347,
397
+ "grad_norm": 0.3473225235939026,
398
+ "learning_rate": 0.00018531051757384633,
399
+ "loss": 1.7161,
400
+ "mean_token_accuracy": 0.5727271348237991,
401
+ "step": 490
402
+ },
403
+ {
404
+ "epoch": 0.20364524997454433,
405
+ "grad_norm": 0.30091673135757446,
406
+ "learning_rate": 0.00018461470708759712,
407
+ "loss": 1.7042,
408
+ "mean_token_accuracy": 0.5763454169034958,
409
+ "step": 500
410
+ },
411
+ {
412
+ "epoch": 0.20771815497403523,
413
+ "grad_norm": 0.31175661087036133,
414
+ "learning_rate": 0.00018390416599888435,
415
+ "loss": 1.689,
416
+ "mean_token_accuracy": 0.5796464458107948,
417
+ "step": 510
418
+ },
419
+ {
420
+ "epoch": 0.21179105997352612,
421
+ "grad_norm": 0.3624255955219269,
422
+ "learning_rate": 0.0001831790180060422,
423
+ "loss": 1.5619,
424
+ "mean_token_accuracy": 0.6015763126313687,
425
+ "step": 520
426
+ },
427
+ {
428
+ "epoch": 0.215863964973017,
429
+ "grad_norm": 0.2667541205883026,
430
+ "learning_rate": 0.00018243938935032561,
431
+ "loss": 1.6877,
432
+ "mean_token_accuracy": 0.5839527539908886,
433
+ "step": 530
434
+ },
435
+ {
436
+ "epoch": 0.2199368699725079,
437
+ "grad_norm": 0.31019967794418335,
438
+ "learning_rate": 0.00018168540879393296,
439
+ "loss": 1.7831,
440
+ "mean_token_accuracy": 0.5688935197889805,
441
+ "step": 540
442
+ },
443
+ {
444
+ "epoch": 0.22400977497199878,
445
+ "grad_norm": 0.2726418673992157,
446
+ "learning_rate": 0.0001809172075975897,
447
+ "loss": 1.7288,
448
+ "mean_token_accuracy": 0.5798229008913041,
449
+ "step": 550
450
+ },
451
+ {
452
+ "epoch": 0.22808267997148968,
453
+ "grad_norm": 0.29514381289482117,
454
+ "learning_rate": 0.00018013491949769734,
455
+ "loss": 1.7188,
456
+ "mean_token_accuracy": 0.5756009854376316,
457
+ "step": 560
458
+ },
459
+ {
460
+ "epoch": 0.23215558497098054,
461
+ "grad_norm": 0.37964069843292236,
462
+ "learning_rate": 0.00017933868068305104,
463
+ "loss": 1.6244,
464
+ "mean_token_accuracy": 0.5932842157781124,
465
+ "step": 570
466
+ },
467
+ {
468
+ "epoch": 0.23622848997047144,
469
+ "grad_norm": 0.300620436668396,
470
+ "learning_rate": 0.0001785286297711305,
471
+ "loss": 1.5565,
472
+ "mean_token_accuracy": 0.5965760670602321,
473
+ "step": 580
474
+ },
475
+ {
476
+ "epoch": 0.24030139496996233,
477
+ "grad_norm": 0.5466737151145935,
478
+ "learning_rate": 0.00017770490778396808,
479
+ "loss": 1.6532,
480
+ "mean_token_accuracy": 0.5821332208812237,
481
+ "step": 590
482
+ },
483
+ {
484
+ "epoch": 0.2443742999694532,
485
+ "grad_norm": 0.3445660173892975,
486
+ "learning_rate": 0.00017686765812359808,
487
+ "loss": 1.7585,
488
+ "mean_token_accuracy": 0.5790032669901848,
489
+ "step": 600
490
+ },
491
+ {
492
+ "epoch": 0.2484472049689441,
493
+ "grad_norm": 0.3492606282234192,
494
+ "learning_rate": 0.0001760170265470921,
495
+ "loss": 1.6401,
496
+ "mean_token_accuracy": 0.6002471588551999,
497
+ "step": 610
498
+ },
499
+ {
500
+ "epoch": 0.252520109968435,
501
+ "grad_norm": 0.31294527649879456,
502
+ "learning_rate": 0.00017515316114118375,
503
+ "loss": 1.6915,
504
+ "mean_token_accuracy": 0.5570432722568512,
505
+ "step": 620
506
+ },
507
+ {
508
+ "epoch": 0.25659301496792586,
509
+ "grad_norm": 0.27257561683654785,
510
+ "learning_rate": 0.00017427621229648853,
511
+ "loss": 1.5666,
512
+ "mean_token_accuracy": 0.6028999522328377,
513
+ "step": 630
514
+ },
515
+ {
516
+ "epoch": 0.2606659199674168,
517
+ "grad_norm": 0.29818692803382874,
518
+ "learning_rate": 0.00017338633268132212,
519
+ "loss": 1.5926,
520
+ "mean_token_accuracy": 0.5965964362025261,
521
+ "step": 640
522
+ },
523
+ {
524
+ "epoch": 0.26473882496690765,
525
+ "grad_norm": 0.49210649728775024,
526
+ "learning_rate": 0.0001724836772151223,
527
+ "loss": 1.5925,
528
+ "mean_token_accuracy": 0.5952631443738937,
529
+ "step": 650
530
+ },
531
+ {
532
+ "epoch": 0.2688117299663985,
533
+ "grad_norm": 0.3807302713394165,
534
+ "learning_rate": 0.00017156840304147902,
535
+ "loss": 1.6237,
536
+ "mean_token_accuracy": 0.5884141281247139,
537
+ "step": 660
538
+ },
539
+ {
540
+ "epoch": 0.27288463496588944,
541
+ "grad_norm": 0.2621661126613617,
542
+ "learning_rate": 0.00017064066950077722,
543
+ "loss": 1.7356,
544
+ "mean_token_accuracy": 0.5827617473900318,
545
+ "step": 670
546
+ },
547
+ {
548
+ "epoch": 0.2769575399653803,
549
+ "grad_norm": 0.30957838892936707,
550
+ "learning_rate": 0.00016970063810245716,
551
+ "loss": 1.5585,
552
+ "mean_token_accuracy": 0.5888052701950073,
553
+ "step": 680
554
+ },
555
+ {
556
+ "epoch": 0.2810304449648712,
557
+ "grad_norm": 0.2501460611820221,
558
+ "learning_rate": 0.00016874847249689722,
559
+ "loss": 1.5913,
560
+ "mean_token_accuracy": 0.5886548452079297,
561
+ "step": 690
562
+ },
563
+ {
564
+ "epoch": 0.2851033499643621,
565
+ "grad_norm": 0.3207811415195465,
566
+ "learning_rate": 0.00016778433844692397,
567
+ "loss": 1.6791,
568
+ "mean_token_accuracy": 0.5861249402165413,
569
+ "step": 700
570
+ },
571
+ {
572
+ "epoch": 0.28917625496385296,
573
+ "grad_norm": 0.45466601848602295,
574
+ "learning_rate": 0.0001668084037989544,
575
+ "loss": 1.5153,
576
+ "mean_token_accuracy": 0.5999807387590408,
577
+ "step": 710
578
+ },
579
+ {
580
+ "epoch": 0.29324915996334383,
581
+ "grad_norm": 0.34910282492637634,
582
+ "learning_rate": 0.00016582083845377552,
583
+ "loss": 1.6821,
584
+ "mean_token_accuracy": 0.5889992110431195,
585
+ "step": 720
586
+ },
587
+ {
588
+ "epoch": 0.29732206496283475,
589
+ "grad_norm": 0.4916020929813385,
590
+ "learning_rate": 0.00016482181433696643,
591
+ "loss": 1.8462,
592
+ "mean_token_accuracy": 0.5748938458040357,
593
+ "step": 730
594
+ },
595
+ {
596
+ "epoch": 0.3013949699623256,
597
+ "grad_norm": 0.2545833885669708,
598
+ "learning_rate": 0.00016381150536896736,
599
+ "loss": 1.5756,
600
+ "mean_token_accuracy": 0.6056667067110538,
601
+ "step": 740
602
+ },
603
+ {
604
+ "epoch": 0.3054678749618165,
605
+ "grad_norm": 0.30347147583961487,
606
+ "learning_rate": 0.0001627900874348022,
607
+ "loss": 1.6003,
608
+ "mean_token_accuracy": 0.5873342089354991,
609
+ "step": 750
610
+ },
611
+ {
612
+ "epoch": 0.3095407799613074,
613
+ "grad_norm": 0.37371426820755005,
614
+ "learning_rate": 0.0001617577383534584,
615
+ "loss": 1.6576,
616
+ "mean_token_accuracy": 0.5790071420371532,
617
+ "step": 760
618
+ },
619
+ {
620
+ "epoch": 0.3136136849607983,
621
+ "grad_norm": 0.41969504952430725,
622
+ "learning_rate": 0.00016071463784693045,
623
+ "loss": 1.6181,
624
+ "mean_token_accuracy": 0.5854876518249512,
625
+ "step": 770
626
+ },
627
+ {
628
+ "epoch": 0.3176865899602892,
629
+ "grad_norm": 0.17495319247245789,
630
+ "learning_rate": 0.00015966096750893197,
631
+ "loss": 1.5142,
632
+ "mean_token_accuracy": 0.6079291738569736,
633
+ "step": 780
634
+ },
635
+ {
636
+ "epoch": 0.32175949495978007,
637
+ "grad_norm": 0.30013784766197205,
638
+ "learning_rate": 0.00015859691077328215,
639
+ "loss": 1.6583,
640
+ "mean_token_accuracy": 0.581703095138073,
641
+ "step": 790
642
+ },
643
+ {
644
+ "epoch": 0.32583239995927094,
645
+ "grad_norm": 0.3358050584793091,
646
+ "learning_rate": 0.00015752265288197155,
647
+ "loss": 1.6468,
648
+ "mean_token_accuracy": 0.6049091577529907,
649
+ "step": 800
650
+ },
651
+ {
652
+ "epoch": 0.32990530495876186,
653
+ "grad_norm": 0.3690403699874878,
654
+ "learning_rate": 0.00015643838085291323,
655
+ "loss": 1.8431,
656
+ "mean_token_accuracy": 0.5602408707141876,
657
+ "step": 810
658
+ },
659
+ {
660
+ "epoch": 0.3339782099582527,
661
+ "grad_norm": 0.34296655654907227,
662
+ "learning_rate": 0.00015534428344738505,
663
+ "loss": 1.7042,
664
+ "mean_token_accuracy": 0.5799131192266941,
665
+ "step": 820
666
+ },
667
+ {
668
+ "epoch": 0.3380511149577436,
669
+ "grad_norm": 0.2764555513858795,
670
+ "learning_rate": 0.00015424055113716763,
671
+ "loss": 1.5479,
672
+ "mean_token_accuracy": 0.5909703068435193,
673
+ "step": 830
674
+ },
675
+ {
676
+ "epoch": 0.3421240199572345,
677
+ "grad_norm": 0.26227012276649475,
678
+ "learning_rate": 0.0001531273760713855,
679
+ "loss": 1.5303,
680
+ "mean_token_accuracy": 0.5910052061080933,
681
+ "step": 840
682
+ },
683
+ {
684
+ "epoch": 0.3461969249567254,
685
+ "grad_norm": 0.3656936585903168,
686
+ "learning_rate": 0.00015200495204305574,
687
+ "loss": 1.5586,
688
+ "mean_token_accuracy": 0.5943005800247192,
689
+ "step": 850
690
+ },
691
+ {
692
+ "epoch": 0.35026982995621625,
693
+ "grad_norm": 0.29997819662094116,
694
+ "learning_rate": 0.00015087347445535013,
695
+ "loss": 1.8219,
696
+ "mean_token_accuracy": 0.5533552631735802,
697
+ "step": 860
698
+ },
699
+ {
700
+ "epoch": 0.3543427349557072,
701
+ "grad_norm": 0.290685772895813,
702
+ "learning_rate": 0.00014973314028757787,
703
+ "loss": 1.7261,
704
+ "mean_token_accuracy": 0.5844682581722737,
705
+ "step": 870
706
+ },
707
+ {
708
+ "epoch": 0.35841563995519804,
709
+ "grad_norm": 0.34553012251853943,
710
+ "learning_rate": 0.00014858414806089295,
711
+ "loss": 1.6982,
712
+ "mean_token_accuracy": 0.5762835793197155,
713
+ "step": 880
714
+ },
715
+ {
716
+ "epoch": 0.3624885449546889,
717
+ "grad_norm": 0.2141156941652298,
718
+ "learning_rate": 0.0001474266978037338,
719
+ "loss": 1.5318,
720
+ "mean_token_accuracy": 0.6048024773597718,
721
+ "step": 890
722
+ },
723
+ {
724
+ "epoch": 0.36656144995417983,
725
+ "grad_norm": 0.30456602573394775,
726
+ "learning_rate": 0.00014626099101700018,
727
+ "loss": 1.7901,
728
+ "mean_token_accuracy": 0.5763920709490776,
729
+ "step": 900
730
+ },
731
+ {
732
+ "epoch": 0.3706343549536707,
733
+ "grad_norm": 0.26921945810317993,
734
+ "learning_rate": 0.00014508723063897376,
735
+ "loss": 1.4936,
736
+ "mean_token_accuracy": 0.6303243085741996,
737
+ "step": 910
738
+ },
739
+ {
740
+ "epoch": 0.3747072599531616,
741
+ "grad_norm": 0.28455570340156555,
742
+ "learning_rate": 0.00014390562100998868,
743
+ "loss": 1.5804,
744
+ "mean_token_accuracy": 0.6074232332408428,
745
+ "step": 920
746
+ },
747
+ {
748
+ "epoch": 0.3787801649526525,
749
+ "grad_norm": 0.3388415575027466,
750
+ "learning_rate": 0.00014271636783685777,
751
+ "loss": 1.6731,
752
+ "mean_token_accuracy": 0.5768752813339233,
753
+ "step": 930
754
+ },
755
+ {
756
+ "epoch": 0.38285306995214335,
757
+ "grad_norm": 0.4311608076095581,
758
+ "learning_rate": 0.00014151967815706091,
759
+ "loss": 1.7237,
760
+ "mean_token_accuracy": 0.5706497602164745,
761
+ "step": 940
762
+ },
763
+ {
764
+ "epoch": 0.3869259749516343,
765
+ "grad_norm": 0.35940027236938477,
766
+ "learning_rate": 0.00014031576030270202,
767
+ "loss": 1.5355,
768
+ "mean_token_accuracy": 0.5908183179795742,
769
+ "step": 950
770
+ },
771
+ {
772
+ "epoch": 0.39099887995112514,
773
+ "grad_norm": 0.34071287512779236,
774
+ "learning_rate": 0.00013910482386424023,
775
+ "loss": 1.7247,
776
+ "mean_token_accuracy": 0.5757749699056148,
777
+ "step": 960
778
+ },
779
+ {
780
+ "epoch": 0.395071784950616,
781
+ "grad_norm": 0.413870245218277,
782
+ "learning_rate": 0.00013788707965400236,
783
+ "loss": 1.6796,
784
+ "mean_token_accuracy": 0.592286454886198,
785
+ "step": 970
786
+ },
787
+ {
788
+ "epoch": 0.39914468995010693,
789
+ "grad_norm": 0.2649496793746948,
790
+ "learning_rate": 0.00013666273966948252,
791
+ "loss": 1.5955,
792
+ "mean_token_accuracy": 0.5936679825186729,
793
+ "step": 980
794
+ },
795
+ {
796
+ "epoch": 0.4032175949495978,
797
+ "grad_norm": 0.3525199294090271,
798
+ "learning_rate": 0.00013543201705643526,
799
+ "loss": 1.647,
800
+ "mean_token_accuracy": 0.5950982637703419,
801
+ "step": 990
802
+ },
803
+ {
804
+ "epoch": 0.40729049994908867,
805
+ "grad_norm": 0.33436283469200134,
806
+ "learning_rate": 0.00013419512607176914,
807
+ "loss": 1.7161,
808
+ "mean_token_accuracy": 0.574284989386797,
809
+ "step": 1000
810
+ },
811
+ {
812
+ "epoch": 0.4113634049485796,
813
+ "grad_norm": 0.46867313981056213,
814
+ "learning_rate": 0.00013295228204624648,
815
+ "loss": 1.544,
816
+ "mean_token_accuracy": 0.6102774910628795,
817
+ "step": 1010
818
+ },
819
+ {
820
+ "epoch": 0.41543630994807046,
821
+ "grad_norm": 0.30373555421829224,
822
+ "learning_rate": 0.00013170370134699653,
823
+ "loss": 1.6287,
824
+ "mean_token_accuracy": 0.5843084178864956,
825
+ "step": 1020
826
+ },
827
+ {
828
+ "epoch": 0.4195092149475613,
829
+ "grad_norm": 0.2981624901294708,
830
+ "learning_rate": 0.00013044960133984804,
831
+ "loss": 1.6858,
832
+ "mean_token_accuracy": 0.5856122255325318,
833
+ "step": 1030
834
+ },
835
+ {
836
+ "epoch": 0.42358211994705225,
837
+ "grad_norm": 0.3545626997947693,
838
+ "learning_rate": 0.00012919020035148776,
839
+ "loss": 1.7392,
840
+ "mean_token_accuracy": 0.5841099888086319,
841
+ "step": 1040
842
+ },
843
+ {
844
+ "epoch": 0.4276550249465431,
845
+ "grad_norm": 0.2896677553653717,
846
+ "learning_rate": 0.0001279257176314521,
847
+ "loss": 1.5007,
848
+ "mean_token_accuracy": 0.573243772238493,
849
+ "step": 1050
850
+ },
851
+ {
852
+ "epoch": 0.431727929946034,
853
+ "grad_norm": 0.36384209990501404,
854
+ "learning_rate": 0.00012665637331395785,
855
+ "loss": 1.487,
856
+ "mean_token_accuracy": 0.6025885075330735,
857
+ "step": 1060
858
+ },
859
+ {
860
+ "epoch": 0.4358008349455249,
861
+ "grad_norm": 0.3681187033653259,
862
+ "learning_rate": 0.00012538238837957882,
863
+ "loss": 1.4913,
864
+ "mean_token_accuracy": 0.5982382036745548,
865
+ "step": 1070
866
+ },
867
+ {
868
+ "epoch": 0.4398737399450158,
869
+ "grad_norm": 0.2680988311767578,
870
+ "learning_rate": 0.00012410398461677554,
871
+ "loss": 1.6263,
872
+ "mean_token_accuracy": 0.5956345148384571,
873
+ "step": 1080
874
+ },
875
+ {
876
+ "epoch": 0.4439466449445067,
877
+ "grad_norm": 0.23174384236335754,
878
+ "learning_rate": 0.00012282138458328358,
879
+ "loss": 1.7378,
880
+ "mean_token_accuracy": 0.590882021188736,
881
+ "step": 1090
882
+ },
883
+ {
884
+ "epoch": 0.44801954994399756,
885
+ "grad_norm": 0.34088292717933655,
886
+ "learning_rate": 0.00012153481156736892,
887
+ "loss": 1.7385,
888
+ "mean_token_accuracy": 0.5994494572281838,
889
+ "step": 1100
890
+ },
891
+ {
892
+ "epoch": 0.45209245494348843,
893
+ "grad_norm": 0.24563632905483246,
894
+ "learning_rate": 0.00012024448954895522,
895
+ "loss": 1.5212,
896
+ "mean_token_accuracy": 0.6165470741689205,
897
+ "step": 1110
898
+ },
899
+ {
900
+ "epoch": 0.45616535994297935,
901
+ "grad_norm": 0.26980966329574585,
902
+ "learning_rate": 0.00011895064316063127,
903
+ "loss": 1.5254,
904
+ "mean_token_accuracy": 0.5898841544985771,
905
+ "step": 1120
906
+ },
907
+ {
908
+ "epoch": 0.4602382649424702,
909
+ "grad_norm": 0.32573202252388,
910
+ "learning_rate": 0.00011765349764854461,
911
+ "loss": 1.5704,
912
+ "mean_token_accuracy": 0.6047514051198959,
913
+ "step": 1130
914
+ },
915
+ {
916
+ "epoch": 0.4643111699419611,
917
+ "grad_norm": 0.3137454390525818,
918
+ "learning_rate": 0.00011635327883318831,
919
+ "loss": 1.5893,
920
+ "mean_token_accuracy": 0.5792985640466213,
921
+ "step": 1140
922
+ },
923
+ {
924
+ "epoch": 0.468384074941452,
925
+ "grad_norm": 0.368747353553772,
926
+ "learning_rate": 0.00011505021307008785,
927
+ "loss": 1.6388,
928
+ "mean_token_accuracy": 0.5851111486554146,
929
+ "step": 1150
930
+ },
931
+ {
932
+ "epoch": 0.4724569799409429,
933
+ "grad_norm": 0.325250506401062,
934
+ "learning_rate": 0.00011374452721039477,
935
+ "loss": 1.7192,
936
+ "mean_token_accuracy": 0.5636343933641911,
937
+ "step": 1160
938
+ },
939
+ {
940
+ "epoch": 0.47652988494043375,
941
+ "grad_norm": 0.32918378710746765,
942
+ "learning_rate": 0.00011243644856139403,
943
+ "loss": 1.6048,
944
+ "mean_token_accuracy": 0.6072004094719887,
945
+ "step": 1170
946
+ },
947
+ {
948
+ "epoch": 0.48060278993992467,
949
+ "grad_norm": 0.2892746031284332,
950
+ "learning_rate": 0.00011112620484693223,
951
+ "loss": 1.6785,
952
+ "mean_token_accuracy": 0.5872686378657818,
953
+ "step": 1180
954
+ },
955
+ {
956
+ "epoch": 0.48467569493941554,
957
+ "grad_norm": 0.2459000200033188,
958
+ "learning_rate": 0.0001098140241677728,
959
+ "loss": 1.5799,
960
+ "mean_token_accuracy": 0.6077749952673912,
961
+ "step": 1190
962
+ },
963
+ {
964
+ "epoch": 0.4887485999389064,
965
+ "grad_norm": 0.3696756660938263,
966
+ "learning_rate": 0.00010850013496188606,
967
+ "loss": 1.5966,
968
+ "mean_token_accuracy": 0.5970290452241898,
969
+ "step": 1200
970
+ },
971
+ {
972
+ "epoch": 0.4928215049383973,
973
+ "grad_norm": 0.27681517601013184,
974
+ "learning_rate": 0.00010718476596468028,
975
+ "loss": 1.7161,
976
+ "mean_token_accuracy": 0.5730410292744637,
977
+ "step": 1210
978
+ },
979
+ {
980
+ "epoch": 0.4968944099378882,
981
+ "grad_norm": 0.2720302641391754,
982
+ "learning_rate": 0.00010586814616918113,
983
+ "loss": 1.6991,
984
+ "mean_token_accuracy": 0.5764113113284111,
985
+ "step": 1220
986
+ },
987
+ {
988
+ "epoch": 0.5009673149373791,
989
+ "grad_norm": 0.34990179538726807,
990
+ "learning_rate": 0.00010455050478616617,
991
+ "loss": 1.7114,
992
+ "mean_token_accuracy": 0.5776129819452762,
993
+ "step": 1230
994
+ },
995
+ {
996
+ "epoch": 0.50504021993687,
997
+ "grad_norm": 0.33753877878189087,
998
+ "learning_rate": 0.00010323207120426142,
999
+ "loss": 1.8174,
1000
+ "mean_token_accuracy": 0.5551487416028976,
1001
+ "step": 1240
1002
+ },
1003
+ {
1004
+ "epoch": 0.5091131249363609,
1005
+ "grad_norm": 0.41568267345428467,
1006
+ "learning_rate": 0.00010191307495000712,
1007
+ "loss": 1.799,
1008
+ "mean_token_accuracy": 0.5767477229237556,
1009
+ "step": 1250
1010
+ },
1011
+ {
1012
+ "epoch": 0.5131860299358517,
1013
+ "grad_norm": 0.2747114300727844,
1014
+ "learning_rate": 0.00010059374564789932,
1015
+ "loss": 1.4763,
1016
+ "mean_token_accuracy": 0.6238099962472916,
1017
+ "step": 1260
1018
+ },
1019
+ {
1020
+ "epoch": 0.5172589349353426,
1021
+ "grad_norm": 0.2458280771970749,
1022
+ "learning_rate": 9.927431298041441e-05,
1023
+ "loss": 1.5262,
1024
+ "mean_token_accuracy": 0.6056429393589496,
1025
+ "step": 1270
1026
+ },
1027
+ {
1028
+ "epoch": 0.5213318399348336,
1029
+ "grad_norm": 0.2757134437561035,
1030
+ "learning_rate": 9.795500664802385e-05,
1031
+ "loss": 1.621,
1032
+ "mean_token_accuracy": 0.5842474676668644,
1033
+ "step": 1280
1034
+ },
1035
+ {
1036
+ "epoch": 0.5254047449343244,
1037
+ "grad_norm": 0.21551673114299774,
1038
+ "learning_rate": 9.663605632920518e-05,
1039
+ "loss": 1.659,
1040
+ "mean_token_accuracy": 0.5935076788067818,
1041
+ "step": 1290
1042
+ },
1043
+ {
1044
+ "epoch": 0.5294776499338153,
1045
+ "grad_norm": 0.5034237504005432,
1046
+ "learning_rate": 9.53176916404576e-05,
1047
+ "loss": 1.7666,
1048
+ "mean_token_accuracy": 0.5699214018881321,
1049
+ "step": 1300
1050
+ },
1051
+ {
1052
+ "epoch": 0.5335505549333062,
1053
+ "grad_norm": 0.26525890827178955,
1054
+ "learning_rate": 9.400014209632763e-05,
1055
+ "loss": 1.6026,
1056
+ "mean_token_accuracy": 0.5935329027473927,
1057
+ "step": 1310
1058
+ },
1059
+ {
1060
+ "epoch": 0.537623459932797,
1061
+ "grad_norm": 0.28077974915504456,
1062
+ "learning_rate": 9.268363706945312e-05,
1063
+ "loss": 1.7769,
1064
+ "mean_token_accuracy": 0.5664741955697536,
1065
+ "step": 1320
1066
+ },
1067
+ {
1068
+ "epoch": 0.5416963649322879,
1069
+ "grad_norm": 0.514976978302002,
1070
+ "learning_rate": 9.136840575063147e-05,
1071
+ "loss": 1.5157,
1072
+ "mean_token_accuracy": 0.6034789860248566,
1073
+ "step": 1330
1074
+ },
1075
+ {
1076
+ "epoch": 0.5457692699317789,
1077
+ "grad_norm": 0.318249374628067,
1078
+ "learning_rate": 9.005467710891987e-05,
1079
+ "loss": 1.8756,
1080
+ "mean_token_accuracy": 0.5630597174167633,
1081
+ "step": 1340
1082
+ },
1083
+ {
1084
+ "epoch": 0.5498421749312697,
1085
+ "grad_norm": 0.24940232932567596,
1086
+ "learning_rate": 8.874267985177394e-05,
1087
+ "loss": 1.5708,
1088
+ "mean_token_accuracy": 0.5888857699930667,
1089
+ "step": 1350
1090
+ },
1091
+ {
1092
+ "epoch": 0.5539150799307606,
1093
+ "grad_norm": 0.26299914717674255,
1094
+ "learning_rate": 8.743264238523199e-05,
1095
+ "loss": 1.6876,
1096
+ "mean_token_accuracy": 0.5782084472477436,
1097
+ "step": 1360
1098
+ },
1099
+ {
1100
+ "epoch": 0.5579879849302515,
1101
+ "grad_norm": 0.2588869333267212,
1102
+ "learning_rate": 8.612479277415174e-05,
1103
+ "loss": 1.6694,
1104
+ "mean_token_accuracy": 0.585976778715849,
1105
+ "step": 1370
1106
+ },
1107
+ {
1108
+ "epoch": 0.5620608899297423,
1109
+ "grad_norm": 0.2464841604232788,
1110
+ "learning_rate": 8.481935870250637e-05,
1111
+ "loss": 1.5838,
1112
+ "mean_token_accuracy": 0.605075704306364,
1113
+ "step": 1380
1114
+ },
1115
+ {
1116
+ "epoch": 0.5661337949292333,
1117
+ "grad_norm": 0.3231446146965027,
1118
+ "learning_rate": 8.351656743374709e-05,
1119
+ "loss": 1.6321,
1120
+ "mean_token_accuracy": 0.5716924026608468,
1121
+ "step": 1390
1122
+ },
1123
+ {
1124
+ "epoch": 0.5702066999287242,
1125
+ "grad_norm": 0.23010632395744324,
1126
+ "learning_rate": 8.22166457712386e-05,
1127
+ "loss": 1.5016,
1128
+ "mean_token_accuracy": 0.6048496462404728,
1129
+ "step": 1400
1130
+ },
1131
+ {
1132
+ "epoch": 0.5742796049282151,
1133
+ "grad_norm": 0.3723667860031128,
1134
+ "learning_rate": 8.091982001877493e-05,
1135
+ "loss": 1.5412,
1136
+ "mean_token_accuracy": 0.6111127749085427,
1137
+ "step": 1410
1138
+ },
1139
+ {
1140
+ "epoch": 0.5783525099277059,
1141
+ "grad_norm": 0.24990710616111755,
1142
+ "learning_rate": 7.962631594118208e-05,
1143
+ "loss": 1.7629,
1144
+ "mean_token_accuracy": 0.5585654892027379,
1145
+ "step": 1420
1146
+ },
1147
+ {
1148
+ "epoch": 0.5824254149271968,
1149
+ "grad_norm": 0.3681967556476593,
1150
+ "learning_rate": 7.833635872501462e-05,
1151
+ "loss": 1.6342,
1152
+ "mean_token_accuracy": 0.5907308183610439,
1153
+ "step": 1430
1154
+ },
1155
+ {
1156
+ "epoch": 0.5864983199266877,
1157
+ "grad_norm": 0.3382493555545807,
1158
+ "learning_rate": 7.705017293935281e-05,
1159
+ "loss": 1.5803,
1160
+ "mean_token_accuracy": 0.6061145611107349,
1161
+ "step": 1440
1162
+ },
1163
+ {
1164
+ "epoch": 0.5905712249261786,
1165
+ "grad_norm": 0.28145501017570496,
1166
+ "learning_rate": 7.576798249670725e-05,
1167
+ "loss": 1.8459,
1168
+ "mean_token_accuracy": 0.5457224696874619,
1169
+ "step": 1450
1170
+ },
1171
+ {
1172
+ "epoch": 0.5946441299256695,
1173
+ "grad_norm": 0.3189752697944641,
1174
+ "learning_rate": 7.449001061403809e-05,
1175
+ "loss": 1.5263,
1176
+ "mean_token_accuracy": 0.5937092356383801,
1177
+ "step": 1460
1178
+ },
1179
+ {
1180
+ "epoch": 0.5987170349251604,
1181
+ "grad_norm": 0.2588890492916107,
1182
+ "learning_rate": 7.321647977389479e-05,
1183
+ "loss": 1.5965,
1184
+ "mean_token_accuracy": 0.5941358201205731,
1185
+ "step": 1470
1186
+ },
1187
+ {
1188
+ "epoch": 0.6027899399246512,
1189
+ "grad_norm": 0.2777283191680908,
1190
+ "learning_rate": 7.194761168568445e-05,
1191
+ "loss": 1.5667,
1192
+ "mean_token_accuracy": 0.6003799811005592,
1193
+ "step": 1480
1194
+ },
1195
+ {
1196
+ "epoch": 0.6068628449241421,
1197
+ "grad_norm": 0.23376941680908203,
1198
+ "learning_rate": 7.068362724707392e-05,
1199
+ "loss": 1.4813,
1200
+ "mean_token_accuracy": 0.6078310683369637,
1201
+ "step": 1490
1202
+ },
1203
+ {
1204
+ "epoch": 0.610935749923633,
1205
+ "grad_norm": 0.2295948565006256,
1206
+ "learning_rate": 6.942474650553408e-05,
1207
+ "loss": 1.6786,
1208
+ "mean_token_accuracy": 0.5886344678699971,
1209
+ "step": 1500
1210
+ },
1211
+ {
1212
+ "epoch": 0.615008654923124,
1213
+ "grad_norm": 0.3243666887283325,
1214
+ "learning_rate": 6.817118862003132e-05,
1215
+ "loss": 1.6343,
1216
+ "mean_token_accuracy": 0.5855603873729706,
1217
+ "step": 1510
1218
+ },
1219
+ {
1220
+ "epoch": 0.6190815599226148,
1221
+ "grad_norm": 0.7187057733535767,
1222
+ "learning_rate": 6.692317182287432e-05,
1223
+ "loss": 1.8144,
1224
+ "mean_token_accuracy": 0.5671629451215268,
1225
+ "step": 1520
1226
+ },
1227
+ {
1228
+ "epoch": 0.6231544649221057,
1229
+ "grad_norm": 0.35659492015838623,
1230
+ "learning_rate": 6.568091338172195e-05,
1231
+ "loss": 1.6117,
1232
+ "mean_token_accuracy": 0.601442601531744,
1233
+ "step": 1530
1234
+ },
1235
+ {
1236
+ "epoch": 0.6272273699215966,
1237
+ "grad_norm": 0.3395217955112457,
1238
+ "learning_rate": 6.444462956175876e-05,
1239
+ "loss": 1.6222,
1240
+ "mean_token_accuracy": 0.5970501154661179,
1241
+ "step": 1540
1242
+ },
1243
+ {
1244
+ "epoch": 0.6313002749210874,
1245
+ "grad_norm": 0.26399192214012146,
1246
+ "learning_rate": 6.321453558804571e-05,
1247
+ "loss": 1.6048,
1248
+ "mean_token_accuracy": 0.5844796732068062,
1249
+ "step": 1550
1250
+ },
1251
+ {
1252
+ "epoch": 0.6353731799205784,
1253
+ "grad_norm": 0.2993052899837494,
1254
+ "learning_rate": 6.199084560805121e-05,
1255
+ "loss": 1.7073,
1256
+ "mean_token_accuracy": 0.5789771333336831,
1257
+ "step": 1560
1258
+ },
1259
+ {
1260
+ "epoch": 0.6394460849200693,
1261
+ "grad_norm": 0.2676873505115509,
1262
+ "learning_rate": 6.077377265437043e-05,
1263
+ "loss": 1.8152,
1264
+ "mean_token_accuracy": 0.5734024614095687,
1265
+ "step": 1570
1266
+ },
1267
+ {
1268
+ "epoch": 0.6435189899195601,
1269
+ "grad_norm": 0.293557733297348,
1270
+ "learning_rate": 5.956352860763809e-05,
1271
+ "loss": 1.7108,
1272
+ "mean_token_accuracy": 0.5808110930025577,
1273
+ "step": 1580
1274
+ },
1275
+ {
1276
+ "epoch": 0.647591894919051,
1277
+ "grad_norm": 0.23729322850704193,
1278
+ "learning_rate": 5.83603241596423e-05,
1279
+ "loss": 1.4793,
1280
+ "mean_token_accuracy": 0.6202867470681668,
1281
+ "step": 1590
1282
+ },
1283
+ {
1284
+ "epoch": 0.6516647999185419,
1285
+ "grad_norm": 0.30609002709388733,
1286
+ "learning_rate": 5.716436877664517e-05,
1287
+ "loss": 1.752,
1288
+ "mean_token_accuracy": 0.5730870619416237,
1289
+ "step": 1600
1290
+ },
1291
+ {
1292
+ "epoch": 0.6557377049180327,
1293
+ "grad_norm": 0.30717799067497253,
1294
+ "learning_rate": 5.5975870662916484e-05,
1295
+ "loss": 1.7172,
1296
+ "mean_token_accuracy": 0.5701417997479439,
1297
+ "step": 1610
1298
+ },
1299
+ {
1300
+ "epoch": 0.6598106099175237,
1301
+ "grad_norm": 0.44037064909935,
1302
+ "learning_rate": 5.4795036724487735e-05,
1303
+ "loss": 1.5377,
1304
+ "mean_token_accuracy": 0.6102925211191177,
1305
+ "step": 1620
1306
+ },
1307
+ {
1308
+ "epoch": 0.6638835149170146,
1309
+ "grad_norm": 0.24488377571105957,
1310
+ "learning_rate": 5.362207253313136e-05,
1311
+ "loss": 1.4547,
1312
+ "mean_token_accuracy": 0.6181615687906742,
1313
+ "step": 1630
1314
+ },
1315
+ {
1316
+ "epoch": 0.6679564199165055,
1317
+ "grad_norm": 0.2750435769557953,
1318
+ "learning_rate": 5.245718229057326e-05,
1319
+ "loss": 1.6086,
1320
+ "mean_token_accuracy": 0.5703060247004033,
1321
+ "step": 1640
1322
+ },
1323
+ {
1324
+ "epoch": 0.6720293249159963,
1325
+ "grad_norm": 0.2821342647075653,
1326
+ "learning_rate": 5.1300568792942535e-05,
1327
+ "loss": 1.6018,
1328
+ "mean_token_accuracy": 0.5989562854170799,
1329
+ "step": 1650
1330
+ },
1331
+ {
1332
+ "epoch": 0.6761022299154872,
1333
+ "grad_norm": 0.22521165013313293,
1334
+ "learning_rate": 5.015243339546731e-05,
1335
+ "loss": 1.7574,
1336
+ "mean_token_accuracy": 0.5801547184586525,
1337
+ "step": 1660
1338
+ },
1339
+ {
1340
+ "epoch": 0.6801751349149782,
1341
+ "grad_norm": 0.29259297251701355,
1342
+ "learning_rate": 4.90129759774202e-05,
1343
+ "loss": 1.7425,
1344
+ "mean_token_accuracy": 0.5723637498915195,
1345
+ "step": 1670
1346
+ },
1347
+ {
1348
+ "epoch": 0.684248039914469,
1349
+ "grad_norm": 0.2705146074295044,
1350
+ "learning_rate": 4.7882394907321674e-05,
1351
+ "loss": 1.6121,
1352
+ "mean_token_accuracy": 0.6098110035061837,
1353
+ "step": 1680
1354
+ },
1355
+ {
1356
+ "epoch": 0.6883209449139599,
1357
+ "grad_norm": 0.2677505910396576,
1358
+ "learning_rate": 4.676088700840575e-05,
1359
+ "loss": 1.6416,
1360
+ "mean_token_accuracy": 0.5757282719016075,
1361
+ "step": 1690
1362
+ },
1363
+ {
1364
+ "epoch": 0.6923938499134508,
1365
+ "grad_norm": 0.2644527554512024,
1366
+ "learning_rate": 4.564864752435509e-05,
1367
+ "loss": 1.6675,
1368
+ "mean_token_accuracy": 0.6154301188886165,
1369
+ "step": 1700
1370
+ },
1371
+ {
1372
+ "epoch": 0.6964667549129416,
1373
+ "grad_norm": 0.23048701882362366,
1374
+ "learning_rate": 4.454587008531097e-05,
1375
+ "loss": 1.6641,
1376
+ "mean_token_accuracy": 0.5855869121849537,
1377
+ "step": 1710
1378
+ },
1379
+ {
1380
+ "epoch": 0.7005396599124325,
1381
+ "grad_norm": 0.2789078652858734,
1382
+ "learning_rate": 4.345274667416399e-05,
1383
+ "loss": 1.6978,
1384
+ "mean_token_accuracy": 0.5762215368449688,
1385
+ "step": 1720
1386
+ },
1387
+ {
1388
+ "epoch": 0.7046125649119235,
1389
+ "grad_norm": 0.271881103515625,
1390
+ "learning_rate": 4.2369467593131926e-05,
1391
+ "loss": 1.681,
1392
+ "mean_token_accuracy": 0.5667479492723941,
1393
+ "step": 1730
1394
+ },
1395
+ {
1396
+ "epoch": 0.7086854699114143,
1397
+ "grad_norm": 0.24953240156173706,
1398
+ "learning_rate": 4.129622143062985e-05,
1399
+ "loss": 1.5405,
1400
+ "mean_token_accuracy": 0.6005463972687721,
1401
+ "step": 1740
1402
+ },
1403
+ {
1404
+ "epoch": 0.7127583749109052,
1405
+ "grad_norm": 0.3925758898258209,
1406
+ "learning_rate": 4.02331950284387e-05,
1407
+ "loss": 1.7217,
1408
+ "mean_token_accuracy": 0.5689709268510341,
1409
+ "step": 1750
1410
+ },
1411
+ {
1412
+ "epoch": 0.7168312799103961,
1413
+ "grad_norm": 0.2544846832752228,
1414
+ "learning_rate": 3.918057344917795e-05,
1415
+ "loss": 1.5948,
1416
+ "mean_token_accuracy": 0.5933421194553375,
1417
+ "step": 1760
1418
+ },
1419
+ {
1420
+ "epoch": 0.720904184909887,
1421
+ "grad_norm": 0.32760509848594666,
1422
+ "learning_rate": 3.813853994408793e-05,
1423
+ "loss": 1.6678,
1424
+ "mean_token_accuracy": 0.5856216661632061,
1425
+ "step": 1770
1426
+ },
1427
+ {
1428
+ "epoch": 0.7249770899093778,
1429
+ "grad_norm": 0.2847062647342682,
1430
+ "learning_rate": 3.7107275921127704e-05,
1431
+ "loss": 1.682,
1432
+ "mean_token_accuracy": 0.5889982558786869,
1433
+ "step": 1780
1434
+ },
1435
+ {
1436
+ "epoch": 0.7290499949088688,
1437
+ "grad_norm": 0.22774401307106018,
1438
+ "learning_rate": 3.60869609133936e-05,
1439
+ "loss": 1.7135,
1440
+ "mean_token_accuracy": 0.5773006275296211,
1441
+ "step": 1790
1442
+ },
1443
+ {
1444
+ "epoch": 0.7331228999083597,
1445
+ "grad_norm": 0.2606080174446106,
1446
+ "learning_rate": 3.507777254786425e-05,
1447
+ "loss": 1.4999,
1448
+ "mean_token_accuracy": 0.6269011601805687,
1449
+ "step": 1800
1450
+ },
1451
+ {
1452
+ "epoch": 0.7371958049078505,
1453
+ "grad_norm": 0.2962757647037506,
1454
+ "learning_rate": 3.407988651447738e-05,
1455
+ "loss": 1.6202,
1456
+ "mean_token_accuracy": 0.5973276488482953,
1457
+ "step": 1810
1458
+ },
1459
+ {
1460
+ "epoch": 0.7412687099073414,
1461
+ "grad_norm": 0.29107147455215454,
1462
+ "learning_rate": 3.3093476535544074e-05,
1463
+ "loss": 1.5502,
1464
+ "mean_token_accuracy": 0.6133273020386696,
1465
+ "step": 1820
1466
+ },
1467
+ {
1468
+ "epoch": 0.7453416149068323,
1469
+ "grad_norm": 0.20980948209762573,
1470
+ "learning_rate": 3.211871433550513e-05,
1471
+ "loss": 1.6333,
1472
+ "mean_token_accuracy": 0.6155988665297627,
1473
+ "step": 1830
1474
+ },
1475
+ {
1476
+ "epoch": 0.7494145199063232,
1477
+ "grad_norm": 0.24882718920707703,
1478
+ "learning_rate": 3.1155769611035825e-05,
1479
+ "loss": 1.4907,
1480
+ "mean_token_accuracy": 0.6201219961047173,
1481
+ "step": 1840
1482
+ },
1483
+ {
1484
+ "epoch": 0.7534874249058141,
1485
+ "grad_norm": 0.23715901374816895,
1486
+ "learning_rate": 3.0204810001503124e-05,
1487
+ "loss": 1.8018,
1488
+ "mean_token_accuracy": 0.5756942637264728,
1489
+ "step": 1850
1490
+ },
1491
+ {
1492
+ "epoch": 0.757560329905305,
1493
+ "grad_norm": 0.35216882824897766,
1494
+ "learning_rate": 2.9266001059781258e-05,
1495
+ "loss": 1.7305,
1496
+ "mean_token_accuracy": 0.5722471877932549,
1497
+ "step": 1860
1498
+ },
1499
+ {
1500
+ "epoch": 0.7616332349047958,
1501
+ "grad_norm": 0.2924104332923889,
1502
+ "learning_rate": 2.83395062234308e-05,
1503
+ "loss": 1.6642,
1504
+ "mean_token_accuracy": 0.58627370595932,
1505
+ "step": 1870
1506
+ },
1507
+ {
1508
+ "epoch": 0.7657061399042867,
1509
+ "grad_norm": 0.27772393822669983,
1510
+ "learning_rate": 2.742548678624548e-05,
1511
+ "loss": 1.8349,
1512
+ "mean_token_accuracy": 0.5614061944186688,
1513
+ "step": 1880
1514
+ },
1515
+ {
1516
+ "epoch": 0.7697790449037776,
1517
+ "grad_norm": 0.31574469804763794,
1518
+ "learning_rate": 2.6524101870172846e-05,
1519
+ "loss": 1.7883,
1520
+ "mean_token_accuracy": 0.561104378849268,
1521
+ "step": 1890
1522
+ },
1523
+ {
1524
+ "epoch": 0.7738519499032686,
1525
+ "grad_norm": 0.253779798746109,
1526
+ "learning_rate": 2.5635508397612262e-05,
1527
+ "loss": 1.6654,
1528
+ "mean_token_accuracy": 0.5888113439083099,
1529
+ "step": 1900
1530
+ },
1531
+ {
1532
+ "epoch": 0.7779248549027594,
1533
+ "grad_norm": 0.2504970133304596,
1534
+ "learning_rate": 2.4759861064096603e-05,
1535
+ "loss": 1.6478,
1536
+ "mean_token_accuracy": 0.5726306334137916,
1537
+ "step": 1910
1538
+ },
1539
+ {
1540
+ "epoch": 0.7819977599022503,
1541
+ "grad_norm": 0.23571030795574188,
1542
+ "learning_rate": 2.3897312311360955e-05,
1543
+ "loss": 1.5355,
1544
+ "mean_token_accuracy": 0.6026113323867321,
1545
+ "step": 1920
1546
+ },
1547
+ {
1548
+ "epoch": 0.7860706649017412,
1549
+ "grad_norm": 0.2395690232515335,
1550
+ "learning_rate": 2.3048012300804222e-05,
1551
+ "loss": 1.5565,
1552
+ "mean_token_accuracy": 0.5976604223251343,
1553
+ "step": 1930
1554
+ },
1555
+ {
1556
+ "epoch": 0.790143569901232,
1557
+ "grad_norm": 0.5269713997840881,
1558
+ "learning_rate": 2.221210888734736e-05,
1559
+ "loss": 1.636,
1560
+ "mean_token_accuracy": 0.5818449839949608,
1561
+ "step": 1940
1562
+ },
1563
+ {
1564
+ "epoch": 0.7942164749007229,
1565
+ "grad_norm": 0.4233987033367157,
1566
+ "learning_rate": 2.13897475936933e-05,
1567
+ "loss": 1.7844,
1568
+ "mean_token_accuracy": 0.5720866233110428,
1569
+ "step": 1950
1570
+ },
1571
+ {
1572
+ "epoch": 0.7982893799002139,
1573
+ "grad_norm": 0.2641923427581787,
1574
+ "learning_rate": 2.0581071584992818e-05,
1575
+ "loss": 1.5874,
1576
+ "mean_token_accuracy": 0.5966846913099288,
1577
+ "step": 1960
1578
+ },
1579
+ {
1580
+ "epoch": 0.8023622848997047,
1581
+ "grad_norm": 0.27280351519584656,
1582
+ "learning_rate": 1.9786221643920844e-05,
1583
+ "loss": 1.6279,
1584
+ "mean_token_accuracy": 0.5751761384308338,
1585
+ "step": 1970
1586
+ },
1587
+ {
1588
+ "epoch": 0.8064351898991956,
1589
+ "grad_norm": 0.3823714256286621,
1590
+ "learning_rate": 1.9005336146167686e-05,
1591
+ "loss": 1.6269,
1592
+ "mean_token_accuracy": 0.5963201723992825,
1593
+ "step": 1980
1594
+ },
1595
+ {
1596
+ "epoch": 0.8105080948986865,
1597
+ "grad_norm": 0.25173816084861755,
1598
+ "learning_rate": 1.8238551036349028e-05,
1599
+ "loss": 1.5308,
1600
+ "mean_token_accuracy": 0.6112879984080791,
1601
+ "step": 1990
1602
+ },
1603
+ {
1604
+ "epoch": 0.8145809998981773,
1605
+ "grad_norm": 0.21256780624389648,
1606
+ "learning_rate": 1.7485999804339348e-05,
1607
+ "loss": 1.5568,
1608
+ "mean_token_accuracy": 0.5963364981114865,
1609
+ "step": 2000
1610
+ },
1611
+ {
1612
+ "epoch": 0.8186539048976683,
1613
+ "grad_norm": 0.2510949969291687,
1614
+ "learning_rate": 1.6747813462032615e-05,
1615
+ "loss": 1.6787,
1616
+ "mean_token_accuracy": 0.58960345312953,
1617
+ "step": 2010
1618
+ },
1619
+ {
1620
+ "epoch": 0.8227268098971592,
1621
+ "grad_norm": 0.255790650844574,
1622
+ "learning_rate": 1.6024120520534326e-05,
1623
+ "loss": 1.6416,
1624
+ "mean_token_accuracy": 0.5875880800187587,
1625
+ "step": 2020
1626
+ },
1627
+ {
1628
+ "epoch": 0.82679971489665,
1629
+ "grad_norm": 0.307492196559906,
1630
+ "learning_rate": 1.5315046967789082e-05,
1631
+ "loss": 1.69,
1632
+ "mean_token_accuracy": 0.5625761769711971,
1633
+ "step": 2030
1634
+ },
1635
+ {
1636
+ "epoch": 0.8308726198961409,
1637
+ "grad_norm": 0.2648999094963074,
1638
+ "learning_rate": 1.4620716246647203e-05,
1639
+ "loss": 1.6092,
1640
+ "mean_token_accuracy": 0.6106476083397865,
1641
+ "step": 2040
1642
+ },
1643
+ {
1644
+ "epoch": 0.8349455248956318,
1645
+ "grad_norm": 0.2488166093826294,
1646
+ "learning_rate": 1.394124923337462e-05,
1647
+ "loss": 1.6848,
1648
+ "mean_token_accuracy": 0.5697021905332804,
1649
+ "step": 2050
1650
+ },
1651
+ {
1652
+ "epoch": 0.8390184298951227,
1653
+ "grad_norm": 0.2427694946527481,
1654
+ "learning_rate": 1.3276764216609294e-05,
1655
+ "loss": 1.5843,
1656
+ "mean_token_accuracy": 0.6084981314837933,
1657
+ "step": 2060
1658
+ },
1659
+ {
1660
+ "epoch": 0.8430913348946136,
1661
+ "grad_norm": 0.2833966910839081,
1662
+ "learning_rate": 1.2627376876768593e-05,
1663
+ "loss": 1.5443,
1664
+ "mean_token_accuracy": 0.6015144042670727,
1665
+ "step": 2070
1666
+ },
1667
+ {
1668
+ "epoch": 0.8471642398941045,
1669
+ "grad_norm": 0.4057978689670563,
1670
+ "learning_rate": 1.1993200265910131e-05,
1671
+ "loss": 1.6073,
1672
+ "mean_token_accuracy": 0.5917512811720371,
1673
+ "step": 2080
1674
+ },
1675
+ {
1676
+ "epoch": 0.8512371448935954,
1677
+ "grad_norm": 0.25613030791282654,
1678
+ "learning_rate": 1.1374344788050829e-05,
1679
+ "loss": 1.8038,
1680
+ "mean_token_accuracy": 0.5568435616791249,
1681
+ "step": 2090
1682
+ },
1683
+ {
1684
+ "epoch": 0.8553100498930862,
1685
+ "grad_norm": 0.30181950330734253,
1686
+ "learning_rate": 1.0770918179946388e-05,
1687
+ "loss": 1.5022,
1688
+ "mean_token_accuracy": 0.6081097513437271,
1689
+ "step": 2100
1690
+ },
1691
+ {
1692
+ "epoch": 0.8593829548925771,
1693
+ "grad_norm": 0.23373402655124664,
1694
+ "learning_rate": 1.0183025492335408e-05,
1695
+ "loss": 1.7432,
1696
+ "mean_token_accuracy": 0.5653887689113617,
1697
+ "step": 2110
1698
+ },
1699
+ {
1700
+ "epoch": 0.863455859892068,
1701
+ "grad_norm": 0.2826649248600006,
1702
+ "learning_rate": 9.610769071651193e-06,
1703
+ "loss": 1.6706,
1704
+ "mean_token_accuracy": 0.5875243842601776,
1705
+ "step": 2120
1706
+ },
1707
+ {
1708
+ "epoch": 0.867528764891559,
1709
+ "grad_norm": 0.3047688603401184,
1710
+ "learning_rate": 9.05424854220408e-06,
1711
+ "loss": 1.5901,
1712
+ "mean_token_accuracy": 0.6013362683355808,
1713
+ "step": 2130
1714
+ },
1715
+ {
1716
+ "epoch": 0.8716016698910498,
1717
+ "grad_norm": 0.3211512863636017,
1718
+ "learning_rate": 8.513560788837916e-06,
1719
+ "loss": 1.6414,
1720
+ "mean_token_accuracy": 0.5845984369516373,
1721
+ "step": 2140
1722
+ },
1723
+ {
1724
+ "epoch": 0.8756745748905407,
1725
+ "grad_norm": 0.22475050389766693,
1726
+ "learning_rate": 7.988799940063297e-06,
1727
+ "loss": 1.6038,
1728
+ "mean_token_accuracy": 0.5835995152592659,
1729
+ "step": 2150
1730
+ },
1731
+ {
1732
+ "epoch": 0.8797474798900315,
1733
+ "grad_norm": 0.2239948809146881,
1734
+ "learning_rate": 7.480057351670688e-06,
1735
+ "loss": 1.6661,
1736
+ "mean_token_accuracy": 0.5898953646421432,
1737
+ "step": 2160
1738
+ },
1739
+ {
1740
+ "epoch": 0.8838203848895224,
1741
+ "grad_norm": 0.3669275641441345,
1742
+ "learning_rate": 6.987421590826282e-06,
1743
+ "loss": 1.6066,
1744
+ "mean_token_accuracy": 0.5877827815711498,
1745
+ "step": 2170
1746
+ },
1747
+ {
1748
+ "epoch": 0.8878932898890134,
1749
+ "grad_norm": 0.30003634095191956,
1750
+ "learning_rate": 6.510978420653335e-06,
1751
+ "loss": 1.6816,
1752
+ "mean_token_accuracy": 0.5926426865160466,
1753
+ "step": 2180
1754
+ },
1755
+ {
1756
+ "epoch": 0.8919661948885043,
1757
+ "grad_norm": 0.2707299590110779,
1758
+ "learning_rate": 6.050810785301597e-06,
1759
+ "loss": 1.7702,
1760
+ "mean_token_accuracy": 0.561020129173994,
1761
+ "step": 2190
1762
+ },
1763
+ {
1764
+ "epoch": 0.8960390998879951,
1765
+ "grad_norm": 0.3029952347278595,
1766
+ "learning_rate": 5.606998795507578e-06,
1767
+ "loss": 1.5417,
1768
+ "mean_token_accuracy": 0.598423033952713,
1769
+ "step": 2200
1770
+ },
1771
+ {
1772
+ "epoch": 0.900112004887486,
1773
+ "grad_norm": 0.27840766310691833,
1774
+ "learning_rate": 5.1796197146479985e-06,
1775
+ "loss": 1.5119,
1776
+ "mean_token_accuracy": 0.6152562454342843,
1777
+ "step": 2210
1778
+ },
1779
+ {
1780
+ "epoch": 0.9041849098869769,
1781
+ "grad_norm": 0.28235796093940735,
1782
+ "learning_rate": 4.768747945288987e-06,
1783
+ "loss": 1.5287,
1784
+ "mean_token_accuracy": 0.61318289488554,
1785
+ "step": 2220
1786
+ },
1787
+ {
1788
+ "epoch": 0.9082578148864677,
1789
+ "grad_norm": 0.21450947225093842,
1790
+ "learning_rate": 4.37445501623337e-06,
1791
+ "loss": 1.5842,
1792
+ "mean_token_accuracy": 0.6025399126112461,
1793
+ "step": 2230
1794
+ },
1795
+ {
1796
+ "epoch": 0.9123307198859587,
1797
+ "grad_norm": 0.29954469203948975,
1798
+ "learning_rate": 3.996809570068127e-06,
1799
+ "loss": 1.5514,
1800
+ "mean_token_accuracy": 0.6040661752223968,
1801
+ "step": 2240
1802
+ },
1803
+ {
1804
+ "epoch": 0.9164036248854496,
1805
+ "grad_norm": 0.34261876344680786,
1806
+ "learning_rate": 3.635877351214445e-06,
1807
+ "loss": 1.5493,
1808
+ "mean_token_accuracy": 0.5996488876640796,
1809
+ "step": 2250
1810
+ },
1811
+ {
1812
+ "epoch": 0.9204765298849404,
1813
+ "grad_norm": 0.24511079490184784,
1814
+ "learning_rate": 3.291721194482189e-06,
1815
+ "loss": 1.5494,
1816
+ "mean_token_accuracy": 0.6054005287587643,
1817
+ "step": 2260
1818
+ },
1819
+ {
1820
+ "epoch": 0.9245494348844313,
1821
+ "grad_norm": 0.21510252356529236,
1822
+ "learning_rate": 2.9644010141310017e-06,
1823
+ "loss": 1.6294,
1824
+ "mean_token_accuracy": 0.5961603626608849,
1825
+ "step": 2270
1826
+ },
1827
+ {
1828
+ "epoch": 0.9286223398839222,
1829
+ "grad_norm": 0.23636655509471893,
1830
+ "learning_rate": 2.65397379343979e-06,
1831
+ "loss": 1.7332,
1832
+ "mean_token_accuracy": 0.5859133303165436,
1833
+ "step": 2280
1834
+ },
1835
+ {
1836
+ "epoch": 0.932695244883413,
1837
+ "grad_norm": 0.25582408905029297,
1838
+ "learning_rate": 2.3604935747865377e-06,
1839
+ "loss": 1.6691,
1840
+ "mean_token_accuracy": 0.5889919593930244,
1841
+ "step": 2290
1842
+ },
1843
+ {
1844
+ "epoch": 0.936768149882904,
1845
+ "grad_norm": 0.3853449523448944,
1846
+ "learning_rate": 2.0840114502400086e-06,
1847
+ "loss": 1.5358,
1848
+ "mean_token_accuracy": 0.5844359740614891,
1849
+ "step": 2300
1850
+ },
1851
+ {
1852
+ "epoch": 0.9408410548823949,
1853
+ "grad_norm": 0.2177136093378067,
1854
+ "learning_rate": 1.8245755526650753e-06,
1855
+ "loss": 1.6318,
1856
+ "mean_token_accuracy": 0.5915890723466873,
1857
+ "step": 2310
1858
+ },
1859
+ {
1860
+ "epoch": 0.9449139598818858,
1861
+ "grad_norm": 0.23138591647148132,
1862
+ "learning_rate": 1.5822310473433411e-06,
1863
+ "loss": 1.5595,
1864
+ "mean_token_accuracy": 0.5974130786955356,
1865
+ "step": 2320
1866
+ },
1867
+ {
1868
+ "epoch": 0.9489868648813766,
1869
+ "grad_norm": 0.2235519289970398,
1870
+ "learning_rate": 1.357020124110231e-06,
1871
+ "loss": 1.7522,
1872
+ "mean_token_accuracy": 0.5713608346879482,
1873
+ "step": 2330
1874
+ },
1875
+ {
1876
+ "epoch": 0.9530597698808675,
1877
+ "grad_norm": 0.37900933623313904,
1878
+ "learning_rate": 1.1489819900101784e-06,
1879
+ "loss": 1.5307,
1880
+ "mean_token_accuracy": 0.6045880667865277,
1881
+ "step": 2340
1882
+ },
1883
+ {
1884
+ "epoch": 0.9571326748803585,
1885
+ "grad_norm": 0.2911360561847687,
1886
+ "learning_rate": 9.581528624710734e-07,
1887
+ "loss": 1.5633,
1888
+ "mean_token_accuracy": 0.5826431967318058,
1889
+ "step": 2350
1890
+ },
1891
+ {
1892
+ "epoch": 0.9612055798798493,
1893
+ "grad_norm": 0.25369352102279663,
1894
+ "learning_rate": 7.845659629990842e-07,
1895
+ "loss": 1.6927,
1896
+ "mean_token_accuracy": 0.5901580177247524,
1897
+ "step": 2360
1898
+ },
1899
+ {
1900
+ "epoch": 0.9652784848793402,
1901
+ "grad_norm": 0.32107028365135193,
1902
+ "learning_rate": 6.282515113952281e-07,
1903
+ "loss": 1.815,
1904
+ "mean_token_accuracy": 0.56534923017025,
1905
+ "step": 2370
1906
+ },
1907
+ {
1908
+ "epoch": 0.9693513898788311,
1909
+ "grad_norm": 0.3105465769767761,
1910
+ "learning_rate": 4.892367204943016e-07,
1911
+ "loss": 1.5694,
1912
+ "mean_token_accuracy": 0.5809950686991214,
1913
+ "step": 2380
1914
+ },
1915
+ {
1916
+ "epoch": 0.9734242948783219,
1917
+ "grad_norm": 0.2689298689365387,
1918
+ "learning_rate": 3.6754579142741495e-07,
1919
+ "loss": 1.6555,
1920
+ "mean_token_accuracy": 0.591179046779871,
1921
+ "step": 2390
1922
+ },
1923
+ {
1924
+ "epoch": 0.9774971998778128,
1925
+ "grad_norm": 0.44850870966911316,
1926
+ "learning_rate": 2.6319990940885107e-07,
1927
+ "loss": 1.7315,
1928
+ "mean_token_accuracy": 0.5772897489368916,
1929
+ "step": 2400
1930
+ },
1931
+ {
1932
+ "epoch": 0.9815701048773038,
1933
+ "grad_norm": 0.25496381521224976,
1934
+ "learning_rate": 1.762172400478601e-07,
1935
+ "loss": 1.5847,
1936
+ "mean_token_accuracy": 0.5798953503370285,
1937
+ "step": 2410
1938
+ },
1939
+ {
1940
+ "epoch": 0.9856430098767947,
1941
+ "grad_norm": 0.2383822500705719,
1942
+ "learning_rate": 1.0661292618624474e-07,
1943
+ "loss": 1.54,
1944
+ "mean_token_accuracy": 0.6138455606997013,
1945
+ "step": 2420
1946
+ },
1947
+ {
1948
+ "epoch": 0.9897159148762855,
1949
+ "grad_norm": 0.2854715585708618,
1950
+ "learning_rate": 5.439908526212456e-08,
1951
+ "loss": 1.4109,
1952
+ "mean_token_accuracy": 0.6151122771203518,
1953
+ "step": 2430
1954
+ },
1955
+ {
1956
+ "epoch": 0.9937888198757764,
1957
+ "grad_norm": 0.297370046377182,
1958
+ "learning_rate": 1.9584807200423438e-08,
1959
+ "loss": 1.5128,
1960
+ "mean_token_accuracy": 0.6013165354728699,
1961
+ "step": 2440
1962
+ },
1963
+ {
1964
+ "epoch": 0.9978617248752673,
1965
+ "grad_norm": 0.2563394010066986,
1966
+ "learning_rate": 2.176152830357658e-09,
1967
+ "loss": 1.6287,
1968
+ "mean_token_accuracy": 0.5945099242031574,
1969
+ "step": 2450
1970
+ }
1971
+ ],
1972
+ "logging_steps": 10,
1973
+ "max_steps": 2455,
1974
+ "num_input_tokens_seen": 0,
1975
+ "num_train_epochs": 1,
1976
+ "save_steps": 100,
1977
+ "stateful_callbacks": {
1978
+ "TrainerControl": {
1979
+ "args": {
1980
+ "should_epoch_stop": false,
1981
+ "should_evaluate": false,
1982
+ "should_log": false,
1983
+ "should_save": true,
1984
+ "should_training_stop": true
1985
+ },
1986
+ "attributes": {}
1987
+ }
1988
+ },
1989
+ "total_flos": 1.283473658609664e+18,
1990
+ "train_batch_size": 4,
1991
+ "trial_name": null,
1992
+ "trial_params": null
1993
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233dc34c1c2e16959d732eacbcbe4b0891d07771508d857bd458fe07662db28c
3
+ size 5624
vocab.json ADDED
The diff for this file is too large to render. See raw diff