Sushmita85 commited on
Commit
6daf574
·
verified ·
1 Parent(s): 58ff2ac

Model save

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/phi-1_5
3
+ datasets:
4
+ - samsum
5
+ library_name: peft
6
+ license: mit
7
+ tags:
8
+ - trl
9
+ - sft
10
+ - generated_from_trainer
11
+ model-index:
12
+ - name: test_model
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # test_model
20
+
21
+ This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the samsum dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 3.0429
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-07
43
+ - train_batch_size: 2
44
+ - eval_batch_size: 2
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 2.8377 | 1.0 | 250 | 3.0473 |
55
+ | 2.9821 | 2.0 | 500 | 3.0425 |
56
+ | 2.9724 | 3.0 | 750 | 3.0429 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - PEFT 0.11.1
62
+ - Transformers 4.41.2
63
+ - Pytorch 2.3.0+cu121
64
+ - Datasets 2.20.0
65
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-1_5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d92e3783982e3886c76e360c7a4363660259262a76f4eab77e5e9446170d2a
3
+ size 9456424
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
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 3.042874813079834,
4
+ "eval_runtime": 37.1738,
5
+ "eval_samples": 100,
6
+ "eval_samples_per_second": 2.69,
7
+ "eval_steps_per_second": 1.345,
8
+ "total_flos": 3617591393476608.0,
9
+ "train_loss": 3.0439649012883505,
10
+ "train_runtime": 1336.343,
11
+ "train_samples": 500,
12
+ "train_samples_per_second": 1.122,
13
+ "train_steps_per_second": 0.561
14
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 3.042874813079834,
4
+ "eval_runtime": 37.1738,
5
+ "eval_samples": 100,
6
+ "eval_samples_per_second": 2.69,
7
+ "eval_steps_per_second": 1.345
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul12_13-34-37_7d0228143436/events.out.tfevents.1720791287.7d0228143436.1500.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59aa4605d387403b4021e2f4d597aab425e61d1b2793de5c1864e07aa0c590a8
3
+ size 5554
runs/Jul12_13-49-41_7d0228143436/events.out.tfevents.1720792190.7d0228143436.1500.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e16754df33165734d85632ae82cc83ca005cf86435aeaabe758ca1e3058e66
3
+ size 38204
runs/Jul12_13-49-41_7d0228143436/events.out.tfevents.1720793564.7d0228143436.1500.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6650f48b7255fd3215ffe6cd28ec8d752151a0198efbae9c46945407d9d64ccb
3
+ size 359
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
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Input: \n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '### Instruction: \n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Response: \n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Response:' }}\n{% endif %}\n{% endfor %}",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "model_max_length": 2048,
322
+ "pad_token": "<|endoftext|>",
323
+ "return_token_type_ids": false,
324
+ "tokenizer_class": "CodeGenTokenizer",
325
+ "unk_token": "<|endoftext|>"
326
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3617591393476608.0,
4
+ "train_loss": 3.0439649012883505,
5
+ "train_runtime": 1336.343,
6
+ "train_samples": 500,
7
+ "train_samples_per_second": 1.122,
8
+ "train_steps_per_second": 0.561
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004,
13
+ "grad_norm": 0.515625,
14
+ "learning_rate": 4.993333333333333e-07,
15
+ "loss": 3.0113,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 0.443359375,
21
+ "learning_rate": 4.966666666666666e-07,
22
+ "loss": 3.1364,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.04,
27
+ "grad_norm": 0.69921875,
28
+ "learning_rate": 4.933333333333333e-07,
29
+ "loss": 3.0859,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.06,
34
+ "grad_norm": 0.419921875,
35
+ "learning_rate": 4.9e-07,
36
+ "loss": 2.7779,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.08,
41
+ "grad_norm": 0.453125,
42
+ "learning_rate": 4.866666666666666e-07,
43
+ "loss": 3.1198,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "grad_norm": 0.44140625,
49
+ "learning_rate": 4.833333333333333e-07,
50
+ "loss": 2.9446,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.12,
55
+ "grad_norm": 0.59765625,
56
+ "learning_rate": 4.8e-07,
57
+ "loss": 2.9396,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.14,
62
+ "grad_norm": 0.7890625,
63
+ "learning_rate": 4.7666666666666667e-07,
64
+ "loss": 3.032,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.16,
69
+ "grad_norm": 0.443359375,
70
+ "learning_rate": 4.733333333333333e-07,
71
+ "loss": 2.9203,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.18,
76
+ "grad_norm": 0.462890625,
77
+ "learning_rate": 4.6999999999999995e-07,
78
+ "loss": 3.2915,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.2,
83
+ "grad_norm": 0.5390625,
84
+ "learning_rate": 4.6666666666666666e-07,
85
+ "loss": 3.3207,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.22,
90
+ "grad_norm": 0.71484375,
91
+ "learning_rate": 4.633333333333333e-07,
92
+ "loss": 2.9583,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.24,
97
+ "grad_norm": 0.48046875,
98
+ "learning_rate": 4.6e-07,
99
+ "loss": 3.133,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.26,
104
+ "grad_norm": 0.71875,
105
+ "learning_rate": 4.5666666666666665e-07,
106
+ "loss": 2.9234,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.28,
111
+ "grad_norm": 0.39453125,
112
+ "learning_rate": 4.5333333333333326e-07,
113
+ "loss": 2.9115,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.3,
118
+ "grad_norm": 0.7578125,
119
+ "learning_rate": 4.5e-07,
120
+ "loss": 3.2351,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.32,
125
+ "grad_norm": 0.4765625,
126
+ "learning_rate": 4.4666666666666664e-07,
127
+ "loss": 2.9413,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.34,
132
+ "grad_norm": 0.44921875,
133
+ "learning_rate": 4.4333333333333336e-07,
134
+ "loss": 3.0558,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.36,
139
+ "grad_norm": 0.46484375,
140
+ "learning_rate": 4.3999999999999997e-07,
141
+ "loss": 2.9375,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.38,
146
+ "grad_norm": 0.5,
147
+ "learning_rate": 4.3666666666666663e-07,
148
+ "loss": 2.9765,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.4,
153
+ "grad_norm": 0.76953125,
154
+ "learning_rate": 4.3333333333333335e-07,
155
+ "loss": 2.8949,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.42,
160
+ "grad_norm": 0.455078125,
161
+ "learning_rate": 4.2999999999999996e-07,
162
+ "loss": 2.9066,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.44,
167
+ "grad_norm": 0.45703125,
168
+ "learning_rate": 4.266666666666667e-07,
169
+ "loss": 2.9894,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.46,
174
+ "grad_norm": 0.3515625,
175
+ "learning_rate": 4.2333333333333334e-07,
176
+ "loss": 3.0943,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.48,
181
+ "grad_norm": 0.6171875,
182
+ "learning_rate": 4.1999999999999995e-07,
183
+ "loss": 2.938,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.5,
188
+ "grad_norm": 0.59375,
189
+ "learning_rate": 4.1666666666666667e-07,
190
+ "loss": 3.1882,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.52,
195
+ "grad_norm": 0.6015625,
196
+ "learning_rate": 4.1333333333333333e-07,
197
+ "loss": 3.0927,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.54,
202
+ "grad_norm": 0.427734375,
203
+ "learning_rate": 4.0999999999999994e-07,
204
+ "loss": 3.0316,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.56,
209
+ "grad_norm": 0.455078125,
210
+ "learning_rate": 4.0666666666666666e-07,
211
+ "loss": 3.0778,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.58,
216
+ "grad_norm": 0.86328125,
217
+ "learning_rate": 4.033333333333333e-07,
218
+ "loss": 3.1895,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.6,
223
+ "grad_norm": 0.65625,
224
+ "learning_rate": 4e-07,
225
+ "loss": 2.8721,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.62,
230
+ "grad_norm": 0.609375,
231
+ "learning_rate": 3.9666666666666665e-07,
232
+ "loss": 3.1312,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.64,
237
+ "grad_norm": 0.6640625,
238
+ "learning_rate": 3.933333333333333e-07,
239
+ "loss": 3.1511,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.66,
244
+ "grad_norm": 0.54296875,
245
+ "learning_rate": 3.8999999999999997e-07,
246
+ "loss": 3.1,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.68,
251
+ "grad_norm": 0.412109375,
252
+ "learning_rate": 3.8666666666666664e-07,
253
+ "loss": 3.042,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.7,
258
+ "grad_norm": 1.0546875,
259
+ "learning_rate": 3.8333333333333335e-07,
260
+ "loss": 2.9667,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.72,
265
+ "grad_norm": 0.37109375,
266
+ "learning_rate": 3.7999999999999996e-07,
267
+ "loss": 3.389,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.74,
272
+ "grad_norm": 0.8046875,
273
+ "learning_rate": 3.766666666666666e-07,
274
+ "loss": 3.1293,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.76,
279
+ "grad_norm": 0.56640625,
280
+ "learning_rate": 3.7333333333333334e-07,
281
+ "loss": 3.0617,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.78,
286
+ "grad_norm": 0.62890625,
287
+ "learning_rate": 3.7e-07,
288
+ "loss": 3.1602,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.8,
293
+ "grad_norm": 0.54296875,
294
+ "learning_rate": 3.666666666666666e-07,
295
+ "loss": 3.0768,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.82,
300
+ "grad_norm": 0.4921875,
301
+ "learning_rate": 3.6333333333333333e-07,
302
+ "loss": 2.9545,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.84,
307
+ "grad_norm": 0.70703125,
308
+ "learning_rate": 3.6e-07,
309
+ "loss": 3.1713,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.86,
314
+ "grad_norm": 0.447265625,
315
+ "learning_rate": 3.5666666666666666e-07,
316
+ "loss": 3.0322,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.88,
321
+ "grad_norm": 0.498046875,
322
+ "learning_rate": 3.533333333333333e-07,
323
+ "loss": 2.9385,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.9,
328
+ "grad_norm": 0.59765625,
329
+ "learning_rate": 3.5e-07,
330
+ "loss": 3.0316,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.92,
335
+ "grad_norm": 0.3046875,
336
+ "learning_rate": 3.4666666666666665e-07,
337
+ "loss": 3.4933,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.94,
342
+ "grad_norm": 0.58984375,
343
+ "learning_rate": 3.433333333333333e-07,
344
+ "loss": 3.07,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.96,
349
+ "grad_norm": 0.71484375,
350
+ "learning_rate": 3.4000000000000003e-07,
351
+ "loss": 2.9426,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.98,
356
+ "grad_norm": 0.64453125,
357
+ "learning_rate": 3.3666666666666664e-07,
358
+ "loss": 3.122,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "grad_norm": 0.53515625,
364
+ "learning_rate": 3.333333333333333e-07,
365
+ "loss": 2.8377,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 1.0,
370
+ "eval_loss": 3.0472724437713623,
371
+ "eval_runtime": 37.1649,
372
+ "eval_samples_per_second": 2.691,
373
+ "eval_steps_per_second": 1.345,
374
+ "step": 250
375
+ },
376
+ {
377
+ "epoch": 1.02,
378
+ "grad_norm": 0.4375,
379
+ "learning_rate": 3.3e-07,
380
+ "loss": 2.9272,
381
+ "step": 255
382
+ },
383
+ {
384
+ "epoch": 1.04,
385
+ "grad_norm": 0.578125,
386
+ "learning_rate": 3.2666666666666663e-07,
387
+ "loss": 2.9946,
388
+ "step": 260
389
+ },
390
+ {
391
+ "epoch": 1.06,
392
+ "grad_norm": 0.8359375,
393
+ "learning_rate": 3.233333333333333e-07,
394
+ "loss": 3.3259,
395
+ "step": 265
396
+ },
397
+ {
398
+ "epoch": 1.08,
399
+ "grad_norm": 0.609375,
400
+ "learning_rate": 3.2e-07,
401
+ "loss": 2.8449,
402
+ "step": 270
403
+ },
404
+ {
405
+ "epoch": 1.1,
406
+ "grad_norm": 0.3203125,
407
+ "learning_rate": 3.166666666666666e-07,
408
+ "loss": 3.0095,
409
+ "step": 275
410
+ },
411
+ {
412
+ "epoch": 1.12,
413
+ "grad_norm": 0.328125,
414
+ "learning_rate": 3.1333333333333333e-07,
415
+ "loss": 2.8402,
416
+ "step": 280
417
+ },
418
+ {
419
+ "epoch": 1.1400000000000001,
420
+ "grad_norm": 0.8984375,
421
+ "learning_rate": 3.1e-07,
422
+ "loss": 3.1718,
423
+ "step": 285
424
+ },
425
+ {
426
+ "epoch": 1.16,
427
+ "grad_norm": 0.60546875,
428
+ "learning_rate": 3.066666666666666e-07,
429
+ "loss": 2.9385,
430
+ "step": 290
431
+ },
432
+ {
433
+ "epoch": 1.18,
434
+ "grad_norm": 0.83203125,
435
+ "learning_rate": 3.033333333333333e-07,
436
+ "loss": 3.2249,
437
+ "step": 295
438
+ },
439
+ {
440
+ "epoch": 1.2,
441
+ "grad_norm": 0.29296875,
442
+ "learning_rate": 3e-07,
443
+ "loss": 3.1023,
444
+ "step": 300
445
+ },
446
+ {
447
+ "epoch": 1.22,
448
+ "grad_norm": 0.48828125,
449
+ "learning_rate": 2.966666666666667e-07,
450
+ "loss": 2.8704,
451
+ "step": 305
452
+ },
453
+ {
454
+ "epoch": 1.24,
455
+ "grad_norm": 0.453125,
456
+ "learning_rate": 2.933333333333333e-07,
457
+ "loss": 3.1789,
458
+ "step": 310
459
+ },
460
+ {
461
+ "epoch": 1.26,
462
+ "grad_norm": 0.455078125,
463
+ "learning_rate": 2.9e-07,
464
+ "loss": 3.135,
465
+ "step": 315
466
+ },
467
+ {
468
+ "epoch": 1.28,
469
+ "grad_norm": 0.4609375,
470
+ "learning_rate": 2.866666666666667e-07,
471
+ "loss": 2.9556,
472
+ "step": 320
473
+ },
474
+ {
475
+ "epoch": 1.3,
476
+ "grad_norm": 0.482421875,
477
+ "learning_rate": 2.833333333333333e-07,
478
+ "loss": 3.0085,
479
+ "step": 325
480
+ },
481
+ {
482
+ "epoch": 1.32,
483
+ "grad_norm": 0.609375,
484
+ "learning_rate": 2.8e-07,
485
+ "loss": 3.1164,
486
+ "step": 330
487
+ },
488
+ {
489
+ "epoch": 1.34,
490
+ "grad_norm": 0.48046875,
491
+ "learning_rate": 2.766666666666667e-07,
492
+ "loss": 3.137,
493
+ "step": 335
494
+ },
495
+ {
496
+ "epoch": 1.3599999999999999,
497
+ "grad_norm": 0.73828125,
498
+ "learning_rate": 2.733333333333333e-07,
499
+ "loss": 3.0196,
500
+ "step": 340
501
+ },
502
+ {
503
+ "epoch": 1.38,
504
+ "grad_norm": 0.640625,
505
+ "learning_rate": 2.7e-07,
506
+ "loss": 3.1515,
507
+ "step": 345
508
+ },
509
+ {
510
+ "epoch": 1.4,
511
+ "grad_norm": 0.400390625,
512
+ "learning_rate": 2.6666666666666667e-07,
513
+ "loss": 3.181,
514
+ "step": 350
515
+ },
516
+ {
517
+ "epoch": 1.42,
518
+ "grad_norm": 0.462890625,
519
+ "learning_rate": 2.633333333333333e-07,
520
+ "loss": 3.0423,
521
+ "step": 355
522
+ },
523
+ {
524
+ "epoch": 1.44,
525
+ "grad_norm": 0.56640625,
526
+ "learning_rate": 2.6e-07,
527
+ "loss": 3.2057,
528
+ "step": 360
529
+ },
530
+ {
531
+ "epoch": 1.46,
532
+ "grad_norm": 0.416015625,
533
+ "learning_rate": 2.5666666666666666e-07,
534
+ "loss": 2.9651,
535
+ "step": 365
536
+ },
537
+ {
538
+ "epoch": 1.48,
539
+ "grad_norm": 0.77734375,
540
+ "learning_rate": 2.533333333333333e-07,
541
+ "loss": 3.0129,
542
+ "step": 370
543
+ },
544
+ {
545
+ "epoch": 1.5,
546
+ "grad_norm": 0.51953125,
547
+ "learning_rate": 2.5e-07,
548
+ "loss": 2.9392,
549
+ "step": 375
550
+ },
551
+ {
552
+ "epoch": 1.52,
553
+ "grad_norm": 0.8125,
554
+ "learning_rate": 2.4666666666666665e-07,
555
+ "loss": 3.2183,
556
+ "step": 380
557
+ },
558
+ {
559
+ "epoch": 1.54,
560
+ "grad_norm": 0.64453125,
561
+ "learning_rate": 2.433333333333333e-07,
562
+ "loss": 2.8756,
563
+ "step": 385
564
+ },
565
+ {
566
+ "epoch": 1.56,
567
+ "grad_norm": 0.54296875,
568
+ "learning_rate": 2.4e-07,
569
+ "loss": 3.0185,
570
+ "step": 390
571
+ },
572
+ {
573
+ "epoch": 1.58,
574
+ "grad_norm": 0.359375,
575
+ "learning_rate": 2.3666666666666664e-07,
576
+ "loss": 2.8795,
577
+ "step": 395
578
+ },
579
+ {
580
+ "epoch": 1.6,
581
+ "grad_norm": 0.65625,
582
+ "learning_rate": 2.3333333333333333e-07,
583
+ "loss": 3.1054,
584
+ "step": 400
585
+ },
586
+ {
587
+ "epoch": 1.62,
588
+ "grad_norm": 0.455078125,
589
+ "learning_rate": 2.3e-07,
590
+ "loss": 3.039,
591
+ "step": 405
592
+ },
593
+ {
594
+ "epoch": 1.6400000000000001,
595
+ "grad_norm": 0.76953125,
596
+ "learning_rate": 2.2666666666666663e-07,
597
+ "loss": 3.114,
598
+ "step": 410
599
+ },
600
+ {
601
+ "epoch": 1.6600000000000001,
602
+ "grad_norm": 0.7109375,
603
+ "learning_rate": 2.2333333333333332e-07,
604
+ "loss": 3.0176,
605
+ "step": 415
606
+ },
607
+ {
608
+ "epoch": 1.6800000000000002,
609
+ "grad_norm": 0.48046875,
610
+ "learning_rate": 2.1999999999999998e-07,
611
+ "loss": 3.014,
612
+ "step": 420
613
+ },
614
+ {
615
+ "epoch": 1.7,
616
+ "grad_norm": 0.54296875,
617
+ "learning_rate": 2.1666666666666667e-07,
618
+ "loss": 2.9937,
619
+ "step": 425
620
+ },
621
+ {
622
+ "epoch": 1.72,
623
+ "grad_norm": 0.474609375,
624
+ "learning_rate": 2.1333333333333334e-07,
625
+ "loss": 3.0268,
626
+ "step": 430
627
+ },
628
+ {
629
+ "epoch": 1.74,
630
+ "grad_norm": 0.72265625,
631
+ "learning_rate": 2.0999999999999997e-07,
632
+ "loss": 3.1097,
633
+ "step": 435
634
+ },
635
+ {
636
+ "epoch": 1.76,
637
+ "grad_norm": 0.5703125,
638
+ "learning_rate": 2.0666666666666666e-07,
639
+ "loss": 3.0335,
640
+ "step": 440
641
+ },
642
+ {
643
+ "epoch": 1.78,
644
+ "grad_norm": 0.79296875,
645
+ "learning_rate": 2.0333333333333333e-07,
646
+ "loss": 3.0041,
647
+ "step": 445
648
+ },
649
+ {
650
+ "epoch": 1.8,
651
+ "grad_norm": 0.59375,
652
+ "learning_rate": 2e-07,
653
+ "loss": 2.8949,
654
+ "step": 450
655
+ },
656
+ {
657
+ "epoch": 1.8199999999999998,
658
+ "grad_norm": 0.482421875,
659
+ "learning_rate": 1.9666666666666665e-07,
660
+ "loss": 3.1279,
661
+ "step": 455
662
+ },
663
+ {
664
+ "epoch": 1.8399999999999999,
665
+ "grad_norm": 0.61328125,
666
+ "learning_rate": 1.9333333333333332e-07,
667
+ "loss": 2.9593,
668
+ "step": 460
669
+ },
670
+ {
671
+ "epoch": 1.8599999999999999,
672
+ "grad_norm": 0.4609375,
673
+ "learning_rate": 1.8999999999999998e-07,
674
+ "loss": 2.9162,
675
+ "step": 465
676
+ },
677
+ {
678
+ "epoch": 1.88,
679
+ "grad_norm": 0.5703125,
680
+ "learning_rate": 1.8666666666666667e-07,
681
+ "loss": 3.1065,
682
+ "step": 470
683
+ },
684
+ {
685
+ "epoch": 1.9,
686
+ "grad_norm": 0.46875,
687
+ "learning_rate": 1.833333333333333e-07,
688
+ "loss": 3.2712,
689
+ "step": 475
690
+ },
691
+ {
692
+ "epoch": 1.92,
693
+ "grad_norm": 0.48046875,
694
+ "learning_rate": 1.8e-07,
695
+ "loss": 2.988,
696
+ "step": 480
697
+ },
698
+ {
699
+ "epoch": 1.94,
700
+ "grad_norm": 0.51171875,
701
+ "learning_rate": 1.7666666666666666e-07,
702
+ "loss": 3.0023,
703
+ "step": 485
704
+ },
705
+ {
706
+ "epoch": 1.96,
707
+ "grad_norm": 0.6484375,
708
+ "learning_rate": 1.7333333333333332e-07,
709
+ "loss": 3.0329,
710
+ "step": 490
711
+ },
712
+ {
713
+ "epoch": 1.98,
714
+ "grad_norm": 0.4765625,
715
+ "learning_rate": 1.7000000000000001e-07,
716
+ "loss": 2.8625,
717
+ "step": 495
718
+ },
719
+ {
720
+ "epoch": 2.0,
721
+ "grad_norm": 0.63671875,
722
+ "learning_rate": 1.6666666666666665e-07,
723
+ "loss": 2.9821,
724
+ "step": 500
725
+ },
726
+ {
727
+ "epoch": 2.0,
728
+ "eval_loss": 3.0425307750701904,
729
+ "eval_runtime": 37.1787,
730
+ "eval_samples_per_second": 2.69,
731
+ "eval_steps_per_second": 1.345,
732
+ "step": 500
733
+ },
734
+ {
735
+ "epoch": 2.02,
736
+ "grad_norm": 0.50390625,
737
+ "learning_rate": 1.6333333333333331e-07,
738
+ "loss": 3.0855,
739
+ "step": 505
740
+ },
741
+ {
742
+ "epoch": 2.04,
743
+ "grad_norm": 0.51953125,
744
+ "learning_rate": 1.6e-07,
745
+ "loss": 2.9503,
746
+ "step": 510
747
+ },
748
+ {
749
+ "epoch": 2.06,
750
+ "grad_norm": 0.51171875,
751
+ "learning_rate": 1.5666666666666667e-07,
752
+ "loss": 2.9242,
753
+ "step": 515
754
+ },
755
+ {
756
+ "epoch": 2.08,
757
+ "grad_norm": 0.52734375,
758
+ "learning_rate": 1.533333333333333e-07,
759
+ "loss": 3.1268,
760
+ "step": 520
761
+ },
762
+ {
763
+ "epoch": 2.1,
764
+ "grad_norm": 0.439453125,
765
+ "learning_rate": 1.5e-07,
766
+ "loss": 3.0643,
767
+ "step": 525
768
+ },
769
+ {
770
+ "epoch": 2.12,
771
+ "grad_norm": 0.53125,
772
+ "learning_rate": 1.4666666666666666e-07,
773
+ "loss": 3.0038,
774
+ "step": 530
775
+ },
776
+ {
777
+ "epoch": 2.14,
778
+ "grad_norm": 0.46484375,
779
+ "learning_rate": 1.4333333333333335e-07,
780
+ "loss": 3.2325,
781
+ "step": 535
782
+ },
783
+ {
784
+ "epoch": 2.16,
785
+ "grad_norm": 0.427734375,
786
+ "learning_rate": 1.4e-07,
787
+ "loss": 2.7652,
788
+ "step": 540
789
+ },
790
+ {
791
+ "epoch": 2.18,
792
+ "grad_norm": 0.5625,
793
+ "learning_rate": 1.3666666666666665e-07,
794
+ "loss": 3.2086,
795
+ "step": 545
796
+ },
797
+ {
798
+ "epoch": 2.2,
799
+ "grad_norm": 0.58203125,
800
+ "learning_rate": 1.3333333333333334e-07,
801
+ "loss": 3.0982,
802
+ "step": 550
803
+ },
804
+ {
805
+ "epoch": 2.22,
806
+ "grad_norm": 0.474609375,
807
+ "learning_rate": 1.3e-07,
808
+ "loss": 3.1022,
809
+ "step": 555
810
+ },
811
+ {
812
+ "epoch": 2.24,
813
+ "grad_norm": 0.41015625,
814
+ "learning_rate": 1.2666666666666666e-07,
815
+ "loss": 2.9948,
816
+ "step": 560
817
+ },
818
+ {
819
+ "epoch": 2.26,
820
+ "grad_norm": 0.94921875,
821
+ "learning_rate": 1.2333333333333333e-07,
822
+ "loss": 3.0617,
823
+ "step": 565
824
+ },
825
+ {
826
+ "epoch": 2.2800000000000002,
827
+ "grad_norm": 0.416015625,
828
+ "learning_rate": 1.2e-07,
829
+ "loss": 2.9632,
830
+ "step": 570
831
+ },
832
+ {
833
+ "epoch": 2.3,
834
+ "grad_norm": 0.55078125,
835
+ "learning_rate": 1.1666666666666667e-07,
836
+ "loss": 3.0321,
837
+ "step": 575
838
+ },
839
+ {
840
+ "epoch": 2.32,
841
+ "grad_norm": 0.44140625,
842
+ "learning_rate": 1.1333333333333332e-07,
843
+ "loss": 2.9494,
844
+ "step": 580
845
+ },
846
+ {
847
+ "epoch": 2.34,
848
+ "grad_norm": 0.56640625,
849
+ "learning_rate": 1.0999999999999999e-07,
850
+ "loss": 2.9734,
851
+ "step": 585
852
+ },
853
+ {
854
+ "epoch": 2.36,
855
+ "grad_norm": 0.423828125,
856
+ "learning_rate": 1.0666666666666667e-07,
857
+ "loss": 2.9476,
858
+ "step": 590
859
+ },
860
+ {
861
+ "epoch": 2.38,
862
+ "grad_norm": 0.408203125,
863
+ "learning_rate": 1.0333333333333333e-07,
864
+ "loss": 2.9636,
865
+ "step": 595
866
+ },
867
+ {
868
+ "epoch": 2.4,
869
+ "grad_norm": 0.353515625,
870
+ "learning_rate": 1e-07,
871
+ "loss": 2.9811,
872
+ "step": 600
873
+ },
874
+ {
875
+ "epoch": 2.42,
876
+ "grad_norm": 0.58203125,
877
+ "learning_rate": 9.666666666666666e-08,
878
+ "loss": 3.1042,
879
+ "step": 605
880
+ },
881
+ {
882
+ "epoch": 2.44,
883
+ "grad_norm": 0.984375,
884
+ "learning_rate": 9.333333333333334e-08,
885
+ "loss": 3.2165,
886
+ "step": 610
887
+ },
888
+ {
889
+ "epoch": 2.46,
890
+ "grad_norm": 0.51171875,
891
+ "learning_rate": 9e-08,
892
+ "loss": 3.0101,
893
+ "step": 615
894
+ },
895
+ {
896
+ "epoch": 2.48,
897
+ "grad_norm": 0.95703125,
898
+ "learning_rate": 8.666666666666666e-08,
899
+ "loss": 3.2647,
900
+ "step": 620
901
+ },
902
+ {
903
+ "epoch": 2.5,
904
+ "grad_norm": 0.64453125,
905
+ "learning_rate": 8.333333333333333e-08,
906
+ "loss": 3.0509,
907
+ "step": 625
908
+ },
909
+ {
910
+ "epoch": 2.52,
911
+ "grad_norm": 0.55859375,
912
+ "learning_rate": 8e-08,
913
+ "loss": 3.1422,
914
+ "step": 630
915
+ },
916
+ {
917
+ "epoch": 2.54,
918
+ "grad_norm": 0.84765625,
919
+ "learning_rate": 7.666666666666665e-08,
920
+ "loss": 3.0169,
921
+ "step": 635
922
+ },
923
+ {
924
+ "epoch": 2.56,
925
+ "grad_norm": 0.57421875,
926
+ "learning_rate": 7.333333333333333e-08,
927
+ "loss": 3.0908,
928
+ "step": 640
929
+ },
930
+ {
931
+ "epoch": 2.58,
932
+ "grad_norm": 0.80078125,
933
+ "learning_rate": 7e-08,
934
+ "loss": 3.0154,
935
+ "step": 645
936
+ },
937
+ {
938
+ "epoch": 2.6,
939
+ "grad_norm": 0.625,
940
+ "learning_rate": 6.666666666666667e-08,
941
+ "loss": 2.9793,
942
+ "step": 650
943
+ },
944
+ {
945
+ "epoch": 2.62,
946
+ "grad_norm": 0.55078125,
947
+ "learning_rate": 6.333333333333333e-08,
948
+ "loss": 3.2019,
949
+ "step": 655
950
+ },
951
+ {
952
+ "epoch": 2.64,
953
+ "grad_norm": 0.63671875,
954
+ "learning_rate": 6e-08,
955
+ "loss": 3.2179,
956
+ "step": 660
957
+ },
958
+ {
959
+ "epoch": 2.66,
960
+ "grad_norm": 0.5546875,
961
+ "learning_rate": 5.666666666666666e-08,
962
+ "loss": 2.9562,
963
+ "step": 665
964
+ },
965
+ {
966
+ "epoch": 2.68,
967
+ "grad_norm": 0.7890625,
968
+ "learning_rate": 5.3333333333333334e-08,
969
+ "loss": 3.1532,
970
+ "step": 670
971
+ },
972
+ {
973
+ "epoch": 2.7,
974
+ "grad_norm": 0.546875,
975
+ "learning_rate": 5e-08,
976
+ "loss": 2.8235,
977
+ "step": 675
978
+ },
979
+ {
980
+ "epoch": 2.7199999999999998,
981
+ "grad_norm": 0.703125,
982
+ "learning_rate": 4.666666666666667e-08,
983
+ "loss": 2.999,
984
+ "step": 680
985
+ },
986
+ {
987
+ "epoch": 2.74,
988
+ "grad_norm": 0.396484375,
989
+ "learning_rate": 4.333333333333333e-08,
990
+ "loss": 3.1061,
991
+ "step": 685
992
+ },
993
+ {
994
+ "epoch": 2.76,
995
+ "grad_norm": 0.427734375,
996
+ "learning_rate": 4e-08,
997
+ "loss": 3.0664,
998
+ "step": 690
999
+ },
1000
+ {
1001
+ "epoch": 2.7800000000000002,
1002
+ "grad_norm": 0.85546875,
1003
+ "learning_rate": 3.6666666666666664e-08,
1004
+ "loss": 3.0183,
1005
+ "step": 695
1006
+ },
1007
+ {
1008
+ "epoch": 2.8,
1009
+ "grad_norm": 0.58984375,
1010
+ "learning_rate": 3.3333333333333334e-08,
1011
+ "loss": 2.9407,
1012
+ "step": 700
1013
+ },
1014
+ {
1015
+ "epoch": 2.82,
1016
+ "grad_norm": 0.6875,
1017
+ "learning_rate": 3e-08,
1018
+ "loss": 2.9318,
1019
+ "step": 705
1020
+ },
1021
+ {
1022
+ "epoch": 2.84,
1023
+ "grad_norm": 0.68359375,
1024
+ "learning_rate": 2.6666666666666667e-08,
1025
+ "loss": 3.0431,
1026
+ "step": 710
1027
+ },
1028
+ {
1029
+ "epoch": 2.86,
1030
+ "grad_norm": 0.74609375,
1031
+ "learning_rate": 2.3333333333333334e-08,
1032
+ "loss": 2.9694,
1033
+ "step": 715
1034
+ },
1035
+ {
1036
+ "epoch": 2.88,
1037
+ "grad_norm": 0.4453125,
1038
+ "learning_rate": 2e-08,
1039
+ "loss": 2.9251,
1040
+ "step": 720
1041
+ },
1042
+ {
1043
+ "epoch": 2.9,
1044
+ "grad_norm": 0.439453125,
1045
+ "learning_rate": 1.6666666666666667e-08,
1046
+ "loss": 3.0582,
1047
+ "step": 725
1048
+ },
1049
+ {
1050
+ "epoch": 2.92,
1051
+ "grad_norm": 0.4140625,
1052
+ "learning_rate": 1.3333333333333334e-08,
1053
+ "loss": 2.835,
1054
+ "step": 730
1055
+ },
1056
+ {
1057
+ "epoch": 2.94,
1058
+ "grad_norm": 0.44140625,
1059
+ "learning_rate": 1e-08,
1060
+ "loss": 2.9812,
1061
+ "step": 735
1062
+ },
1063
+ {
1064
+ "epoch": 2.96,
1065
+ "grad_norm": 0.55859375,
1066
+ "learning_rate": 6.666666666666667e-09,
1067
+ "loss": 3.3347,
1068
+ "step": 740
1069
+ },
1070
+ {
1071
+ "epoch": 2.98,
1072
+ "grad_norm": 0.421875,
1073
+ "learning_rate": 3.3333333333333334e-09,
1074
+ "loss": 3.1562,
1075
+ "step": 745
1076
+ },
1077
+ {
1078
+ "epoch": 3.0,
1079
+ "grad_norm": 0.37890625,
1080
+ "learning_rate": 0.0,
1081
+ "loss": 2.9724,
1082
+ "step": 750
1083
+ },
1084
+ {
1085
+ "epoch": 3.0,
1086
+ "eval_loss": 3.042874813079834,
1087
+ "eval_runtime": 37.1498,
1088
+ "eval_samples_per_second": 2.692,
1089
+ "eval_steps_per_second": 1.346,
1090
+ "step": 750
1091
+ },
1092
+ {
1093
+ "epoch": 3.0,
1094
+ "step": 750,
1095
+ "total_flos": 3617591393476608.0,
1096
+ "train_loss": 3.0439649012883505,
1097
+ "train_runtime": 1336.343,
1098
+ "train_samples_per_second": 1.122,
1099
+ "train_steps_per_second": 0.561
1100
+ }
1101
+ ],
1102
+ "logging_steps": 5,
1103
+ "max_steps": 750,
1104
+ "num_input_tokens_seen": 0,
1105
+ "num_train_epochs": 3,
1106
+ "save_steps": 500,
1107
+ "stateful_callbacks": {
1108
+ "TrainerControl": {
1109
+ "args": {
1110
+ "should_epoch_stop": false,
1111
+ "should_evaluate": false,
1112
+ "should_log": false,
1113
+ "should_save": false,
1114
+ "should_training_stop": false
1115
+ },
1116
+ "attributes": {}
1117
+ }
1118
+ },
1119
+ "total_flos": 3617591393476608.0,
1120
+ "train_batch_size": 2,
1121
+ "trial_name": null,
1122
+ "trial_params": null
1123
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2825a13056975925f8567d40e4278de2dba1d9e79fa168675208cf57dc9cdeaf
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff