Hugging Face's logo

tyzhu
/
lmind_hotpot_train8000_eval7405_v1_doc_qa_3e-5_lora2

Safetensors
Model card Files Community
tyzhu commited on
Commit
d4b155e
•
1 Parent(s): 394de52

Training in progress, epoch 4, checkpoint

Browse files
Files changed (14) hide show
  1. checkpoint-5446/adapter_config.json +1 -1
  2. checkpoint-5446/adapter_model.bin +3 -0
  3. checkpoint-5446/added_tokens.json +3 -3
  4. checkpoint-5446/optimizer.pt +2 -2
  5. checkpoint-5446/rng_state_0.pth +1 -1
  6. checkpoint-5446/rng_state_1.pth +1 -1
  7. checkpoint-5446/rng_state_2.pth +1 -1
  8. checkpoint-5446/rng_state_3.pth +1 -1
  9. checkpoint-5446/special_tokens_map.json +4 -12
  10. checkpoint-5446/tokenizer.json +0 -0
  11. checkpoint-5446/tokenizer.model +3 -0
  12. checkpoint-5446/tokenizer_config.json +17 -20
  13. checkpoint-5446/trainer_state.json +152 -220
  14. checkpoint-5446/training_args.bin +2 -2
checkpoint-5446/adapter_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "Qwen/Qwen1.5-4B",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
checkpoint-5446/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3d030ce47e17875dc706de428bee0806bdf4966e482a0732f21dfd01f5699e
3
+ size 143269386
checkpoint-5446/added_tokens.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "<|endoftext|>": 151643,
3
- "<|im_end|>": 151645,
4
- "<|im_start|>": 151644
5
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
  }
checkpoint-5446/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be3f5033fa1da53d4b9ef5ea221860351b94d8e360b0ba10b11974a052bc2c1e
3
- size 224537202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9085c71f552d865436d2bf31618943a61a1ca86cbcbed0f59ad56d061c543829
3
+ size 286585234
checkpoint-5446/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab22161f95c3a5746a9ad6bf25a0c07619b1ca6e7abc865ef1d75b1440bf7904
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c3b847ecda6c8e8bd19c44e449620e183202932633a4dcd2f9fe96380ada58
3
  size 15024
checkpoint-5446/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32a637518d7847974d4a257b18c3e3d36e2f8bf7ddfc6828e042694229edc3a9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e42005ac6e4f696396487b09bc6d69d35ee713c9731444585fa7e0a37253745
3
  size 15024
checkpoint-5446/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faf0c46bd46d039fffa00811d2128aa448540b5a82288da8565fd2ada59f2ee6
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e29ba7488dcbceaf6b89b98400b9772e1a46e3e08e30861b145fe4f60b06d7
3
  size 15024
checkpoint-5446/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceb3714c1111bc236c3656fb5368ae3e3adbb7c35d908723446eda5635f29996
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ee3ae09ec2c7c674c48ce37c40dbcb1caeb63cb9809f22a0b2e2bb72b5fe6f
3
  size 15024
checkpoint-5446/special_tokens_map.json CHANGED
@@ -1,14 +1,6 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>"
5
- ],
6
- "eos_token": {
7
- "content": "<|endoftext|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "pad_token": "<|endoftext|>"
14
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
6
  }
checkpoint-5446/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-5446/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-5446/tokenizer_config.json CHANGED
@@ -1,24 +1,23 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "151643": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "151644": {
13
- "content": "<|im_start|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "151645": {
21
- "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -26,18 +25,16 @@
26
  "special": true
27
  }
28
  },
29
- "additional_special_tokens": [
30
- "<|im_start|>",
31
- "<|im_end|>"
32
- ],
33
- "bos_token": null,
34
- "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
  "clean_up_tokenization_spaces": false,
36
- "eos_token": "<|endoftext|>",
37
- "errors": "replace",
38
- "model_max_length": 32768,
39
- "pad_token": "<|endoftext|>",
40
- "split_special_tokens": false,
41
- "tokenizer_class": "Qwen2Tokenizer",
42
- "unk_token": null
 
 
43
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
 
 
 
 
30
  "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "left",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
  }
checkpoint-5446/trainer_state.json CHANGED
@@ -9,478 +9,410 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.09180628873077806,
13
- "grad_norm": 0.5307241678237915,
14
  "learning_rate": 3e-05,
15
- "loss": 2.0176,
16
  "step": 100
17
  },
18
  {
19
- "epoch": 0.18361257746155613,
20
- "grad_norm": 0.6362708210945129,
21
  "learning_rate": 3e-05,
22
- "loss": 1.7953,
23
  "step": 200
24
  },
25
  {
26
- "epoch": 0.2754188661923342,
27
- "grad_norm": 0.3823029696941376,
28
  "learning_rate": 3e-05,
29
- "loss": 1.7849,
30
  "step": 300
31
  },
32
  {
33
- "epoch": 0.36722515492311225,
34
- "grad_norm": 0.43036168813705444,
35
  "learning_rate": 3e-05,
36
- "loss": 1.7818,
37
  "step": 400
38
  },
39
  {
40
- "epoch": 0.4590314436538903,
41
- "grad_norm": 0.5922847390174866,
42
  "learning_rate": 3e-05,
43
- "loss": 1.7649,
44
  "step": 500
45
  },
46
  {
47
- "epoch": 0.5508377323846684,
48
- "grad_norm": 0.40470582246780396,
49
  "learning_rate": 3e-05,
50
- "loss": 1.7902,
51
  "step": 600
52
  },
53
  {
54
- "epoch": 0.6426440211154464,
55
- "grad_norm": 0.49739205837249756,
56
  "learning_rate": 3e-05,
57
- "loss": 1.7606,
58
  "step": 700
59
  },
60
  {
61
- "epoch": 0.7344503098462245,
62
- "grad_norm": 0.43984296917915344,
63
  "learning_rate": 3e-05,
64
- "loss": 1.7746,
65
  "step": 800
66
  },
67
  {
68
- "epoch": 0.8262565985770025,
69
- "grad_norm": 0.4566909968852997,
70
  "learning_rate": 3e-05,
71
- "loss": 1.7586,
72
  "step": 900
73
  },
74
  {
75
- "epoch": 0.9180628873077806,
76
- "grad_norm": 0.4243898093700409,
77
  "learning_rate": 3e-05,
78
- "loss": 1.7775,
79
  "step": 1000
80
  },
81
  {
82
- "epoch": 0.999770484278173,
83
- "eval_accuracy": 0.5157460317460317,
84
- "eval_loss": 2.3358356952667236,
85
- "eval_runtime": 5.2798,
86
- "eval_samples_per_second": 94.7,
87
- "eval_steps_per_second": 11.932,
88
  "step": 1089
89
  },
90
  {
91
- "epoch": 0.999770484278173,
92
- "eval_exact_match": 19.0,
93
- "eval_f1": 26.812075147075163,
94
  "step": 1089
95
  },
96
  {
97
- "epoch": 1.0098691760385587,
98
- "grad_norm": 0.47265738248825073,
99
  "learning_rate": 3e-05,
100
- "loss": 1.7676,
101
  "step": 1100
102
  },
103
  {
104
- "epoch": 1.1016754647693368,
105
- "grad_norm": 0.6015958189964294,
106
  "learning_rate": 3e-05,
107
- "loss": 1.7397,
108
  "step": 1200
109
  },
110
  {
111
- "epoch": 1.1934817535001148,
112
- "grad_norm": 0.5499740242958069,
113
  "learning_rate": 3e-05,
114
- "loss": 1.7254,
115
  "step": 1300
116
  },
117
  {
118
- "epoch": 1.2852880422308928,
119
- "grad_norm": 0.5272372961044312,
120
  "learning_rate": 3e-05,
121
- "loss": 1.73,
122
  "step": 1400
123
  },
124
  {
125
- "epoch": 1.377094330961671,
126
- "grad_norm": 0.5437406897544861,
127
  "learning_rate": 3e-05,
128
- "loss": 1.7292,
129
  "step": 1500
130
  },
131
  {
132
- "epoch": 1.468900619692449,
133
- "grad_norm": 0.5464481115341187,
134
  "learning_rate": 3e-05,
135
- "loss": 1.728,
136
  "step": 1600
137
  },
138
  {
139
- "epoch": 1.560706908423227,
140
- "grad_norm": 0.6755242347717285,
141
  "learning_rate": 3e-05,
142
- "loss": 1.7407,
143
  "step": 1700
144
  },
145
  {
146
- "epoch": 1.652513197154005,
147
- "grad_norm": 0.5893722176551819,
148
  "learning_rate": 3e-05,
149
- "loss": 1.7244,
150
  "step": 1800
151
  },
152
  {
153
- "epoch": 1.744319485884783,
154
- "grad_norm": 0.5930923223495483,
155
  "learning_rate": 3e-05,
156
- "loss": 1.7225,
157
  "step": 1900
158
  },
159
  {
160
- "epoch": 1.836125774615561,
161
- "grad_norm": 0.5917518734931946,
162
  "learning_rate": 3e-05,
163
- "loss": 1.7189,
164
  "step": 2000
165
  },
166
  {
167
- "epoch": 1.9279320633463393,
168
- "grad_norm": 0.6680920124053955,
169
  "learning_rate": 3e-05,
170
- "loss": 1.7313,
171
  "step": 2100
172
  },
173
  {
174
- "epoch": 1.999540968556346,
175
- "eval_accuracy": 0.5178730158730158,
176
- "eval_loss": 2.3068432807922363,
177
- "eval_runtime": 5.4629,
178
- "eval_samples_per_second": 91.527,
179
- "eval_steps_per_second": 11.532,
180
  "step": 2178
181
  },
182
  {
183
- "epoch": 1.999540968556346,
184
- "eval_exact_match": 17.8,
185
- "eval_f1": 26.628214855320138,
186
  "step": 2178
187
  },
188
  {
189
- "epoch": 2.0197383520771175,
190
- "grad_norm": 0.6736780405044556,
191
  "learning_rate": 3e-05,
192
- "loss": 1.7046,
193
  "step": 2200
194
  },
195
  {
196
- "epoch": 2.1115446408078955,
197
- "grad_norm": 0.7276094555854797,
198
  "learning_rate": 3e-05,
199
- "loss": 1.6607,
200
  "step": 2300
201
  },
202
  {
203
- "epoch": 2.2033509295386735,
204
- "grad_norm": 0.7279476523399353,
205
  "learning_rate": 3e-05,
206
- "loss": 1.6791,
207
  "step": 2400
208
  },
209
  {
210
- "epoch": 2.2951572182694515,
211
- "grad_norm": 0.7652662992477417,
212
  "learning_rate": 3e-05,
213
- "loss": 1.6709,
214
  "step": 2500
215
  },
216
  {
217
- "epoch": 2.3869635070002295,
218
- "grad_norm": 0.6291841268539429,
219
  "learning_rate": 3e-05,
220
- "loss": 1.6659,
221
  "step": 2600
222
  },
223
  {
224
- "epoch": 2.4787697957310075,
225
- "grad_norm": 0.7375943660736084,
226
  "learning_rate": 3e-05,
227
- "loss": 1.67,
228
  "step": 2700
229
  },
230
  {
231
- "epoch": 2.5705760844617855,
232
- "grad_norm": 0.7475445866584778,
233
  "learning_rate": 3e-05,
234
- "loss": 1.6769,
235
  "step": 2800
236
  },
237
  {
238
- "epoch": 2.6623823731925635,
239
- "grad_norm": 5.488095283508301,
240
  "learning_rate": 3e-05,
241
- "loss": 1.6726,
242
  "step": 2900
243
  },
244
  {
245
- "epoch": 2.754188661923342,
246
- "grad_norm": 11046773.0,
247
  "learning_rate": 3e-05,
248
- "loss": 2.4041,
249
  "step": 3000
250
  },
251
  {
252
- "epoch": 2.84599495065412,
253
- "grad_norm": 9348.0419921875,
254
  "learning_rate": 3e-05,
255
- "loss": 3.254,
256
  "step": 3100
257
  },
258
  {
259
- "epoch": 2.937801239384898,
260
- "grad_norm": 42427.7578125,
261
  "learning_rate": 3e-05,
262
- "loss": 3.648,
263
  "step": 3200
264
  },
265
  {
266
- "epoch": 2.9993114528345193,
267
- "eval_accuracy": 0.4067936507936508,
268
- "eval_loss": 4.151577949523926,
269
- "eval_runtime": 5.4271,
270
- "eval_samples_per_second": 92.13,
271
- "eval_steps_per_second": 11.608,
272
  "step": 3267
273
  },
274
  {
275
- "epoch": 2.9993114528345193,
276
- "eval_exact_match": 0.0,
277
- "eval_f1": 1.3877253548324662,
278
  "step": 3267
279
  },
280
  {
281
- "epoch": 3.029607528115676,
282
- "grad_norm": 69864.046875,
283
  "learning_rate": 3e-05,
284
- "loss": 3.6794,
285
  "step": 3300
286
  },
287
  {
288
- "epoch": 3.121413816846454,
289
- "grad_norm": 763.395263671875,
290
  "learning_rate": 3e-05,
291
- "loss": 3.6341,
292
  "step": 3400
293
  },
294
  {
295
- "epoch": 3.213220105577232,
296
- "grad_norm": 297052.0625,
297
  "learning_rate": 3e-05,
298
- "loss": 6.3864,
299
  "step": 3500
300
  },
301
  {
302
- "epoch": 3.30502639430801,
303
- "grad_norm": 327590.21875,
304
  "learning_rate": 3e-05,
305
- "loss": 8.1688,
306
  "step": 3600
307
  },
308
  {
309
- "epoch": 3.396832683038788,
310
- "grad_norm": 35.1007080078125,
311
  "learning_rate": 3e-05,
312
- "loss": 7.4099,
313
  "step": 3700
314
  },
315
  {
316
- "epoch": 3.488638971769566,
317
- "grad_norm": 709.9918823242188,
318
  "learning_rate": 3e-05,
319
- "loss": 3.7034,
320
  "step": 3800
321
  },
322
  {
323
- "epoch": 3.580445260500344,
324
- "grad_norm": 5584611.5,
325
  "learning_rate": 3e-05,
326
- "loss": 3.832,
327
  "step": 3900
328
  },
329
  {
330
- "epoch": 3.672251549231122,
331
- "grad_norm": 684474.4375,
332
  "learning_rate": 3e-05,
333
- "loss": 4.8077,
334
  "step": 4000
335
  },
336
  {
337
- "epoch": 3.7640578379619005,
338
- "grad_norm": 137445040.0,
339
  "learning_rate": 3e-05,
340
- "loss": 7.6647,
341
  "step": 4100
342
  },
343
  {
344
- "epoch": 3.8558641266926785,
345
- "grad_norm": 15619359.0,
346
  "learning_rate": 3e-05,
347
- "loss": 9.0532,
348
  "step": 4200
349
  },
350
  {
351
- "epoch": 3.9476704154234565,
352
- "grad_norm": 252526384.0,
353
  "learning_rate": 3e-05,
354
- "loss": 9.0562,
355
  "step": 4300
356
  },
357
  {
358
  "epoch": 4.0,
359
- "eval_accuracy": 0.26304761904761903,
360
- "eval_loss": 9.931685447692871,
361
- "eval_runtime": 5.1725,
362
- "eval_samples_per_second": 96.665,
363
- "eval_steps_per_second": 12.18,
364
  "step": 4357
365
  },
366
  {
367
  "epoch": 4.0,
368
- "eval_exact_match": 0.0,
369
- "eval_f1": 0.1,
370
  "step": 4357
371
  },
372
  {
373
- "epoch": 4.039476704154235,
374
- "grad_norm": 96136593408.0,
375
  "learning_rate": 3e-05,
376
- "loss": 9.1763,
377
  "step": 4400
378
  },
379
  {
380
- "epoch": 4.131282992885013,
381
- "grad_norm": 1025443364864.0,
382
  "learning_rate": 3e-05,
383
- "loss": 9.1246,
384
  "step": 4500
385
  },
386
  {
387
- "epoch": 4.223089281615791,
388
- "grad_norm": 265109962752.0,
389
  "learning_rate": 3e-05,
390
- "loss": 9.1531,
391
  "step": 4600
392
  },
393
  {
394
- "epoch": 4.314895570346569,
395
- "grad_norm": 3019844.25,
396
  "learning_rate": 3e-05,
397
- "loss": 9.7419,
398
  "step": 4700
399
  },
400
  {
401
- "epoch": 4.406701859077347,
402
- "grad_norm": 118806648.0,
403
  "learning_rate": 3e-05,
404
- "loss": 10.3409,
405
  "step": 4800
406
  },
407
  {
408
- "epoch": 4.498508147808125,
409
- "grad_norm": 14.5001859664917,
410
  "learning_rate": 3e-05,
411
- "loss": 9.5802,
412
  "step": 4900
413
  },
414
  {
415
- "epoch": 4.590314436538903,
416
- "grad_norm": 11.577363014221191,
417
  "learning_rate": 3e-05,
418
- "loss": 6.5391,
419
  "step": 5000
420
  },
421
  {
422
- "epoch": 4.682120725269681,
423
- "grad_norm": 6.0267863273620605,
424
  "learning_rate": 3e-05,
425
- "loss": 4.3604,
426
  "step": 5100
427
  },
428
  {
429
- "epoch": 4.773927014000459,
430
- "grad_norm": 99.47637176513672,
431
  "learning_rate": 3e-05,
432
- "loss": 2.5788,
433
  "step": 5200
434
  },
435
  {
436
- "epoch": 4.865733302731237,
437
- "grad_norm": 4.200494766235352,
438
  "learning_rate": 3e-05,
439
- "loss": 2.3746,
440
  "step": 5300
441
  },
442
  {
443
- "epoch": 4.957539591462015,
444
- "grad_norm": 43.855430603027344,
445
  "learning_rate": 3e-05,
446
- "loss": 2.4535,
447
  "step": 5400
448
  },
449
  {
450
- "epoch": 4.999770484278173,
451
- "eval_accuracy": 0.363015873015873,
452
- "eval_loss": 4.993338108062744,
453
- "eval_runtime": 5.5548,
454
- "eval_samples_per_second": 90.012,
455
- "eval_steps_per_second": 11.342,
456
  "step": 5446
457
  },
458
  {
459
- "epoch": 4.999770484278173,
460
- "eval_exact_match": 0.0,
461
- "eval_f1": 0.8575555035818295,
462
  "step": 5446
463
  }
464
  ],
465
  "logging_steps": 100,
466
  "max_steps": 54450,
467
- "num_input_tokens_seen": 0,
468
  "num_train_epochs": 50,
469
  "save_steps": 500,
470
- "stateful_callbacks": {
471
- "TrainerControl": {
472
- "args": {
473
- "should_epoch_stop": false,
474
- "should_evaluate": false,
475
- "should_log": false,
476
- "should_save": true,
477
- "should_training_stop": false
478
- },
479
- "attributes": {}
480
- }
481
- },
482
- "total_flos": 3.757643678340874e+17,
483
- "train_batch_size": 1,
484
  "trial_name": null,
485
  "trial_params": null
486
  }
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.09,
 
13
  "learning_rate": 3e-05,
14
+ "loss": 1.5477,
15
  "step": 100
16
  },
17
  {
18
+ "epoch": 0.18,
 
19
  "learning_rate": 3e-05,
20
+ "loss": 1.3248,
21
  "step": 200
22
  },
23
  {
24
+ "epoch": 0.28,
 
25
  "learning_rate": 3e-05,
26
+ "loss": 1.2394,
27
  "step": 300
28
  },
29
  {
30
+ "epoch": 0.37,
 
31
  "learning_rate": 3e-05,
32
+ "loss": 1.2549,
33
  "step": 400
34
  },
35
  {
36
+ "epoch": 0.46,
 
37
  "learning_rate": 3e-05,
38
+ "loss": 1.2163,
39
  "step": 500
40
  },
41
  {
42
+ "epoch": 0.55,
 
43
  "learning_rate": 3e-05,
44
+ "loss": 1.2202,
45
  "step": 600
46
  },
47
  {
48
+ "epoch": 0.64,
 
49
  "learning_rate": 3e-05,
50
+ "loss": 1.2099,
51
  "step": 700
52
  },
53
  {
54
+ "epoch": 0.73,
 
55
  "learning_rate": 3e-05,
56
+ "loss": 1.2213,
57
  "step": 800
58
  },
59
  {
60
+ "epoch": 0.83,
 
61
  "learning_rate": 3e-05,
62
+ "loss": 1.2203,
63
  "step": 900
64
  },
65
  {
66
+ "epoch": 0.92,
 
67
  "learning_rate": 3e-05,
68
+ "loss": 1.2166,
69
  "step": 1000
70
  },
71
  {
72
+ "epoch": 1.0,
73
+ "eval_accuracy": 0.5925822784810126,
74
+ "eval_loss": 1.858124017715454,
75
+ "eval_runtime": 4.7843,
76
+ "eval_samples_per_second": 104.509,
77
+ "eval_steps_per_second": 13.168,
78
  "step": 1089
79
  },
80
  {
81
+ "epoch": 1.0,
82
+ "eval_exact_match": 25.0,
83
+ "eval_f1": 33.90013632566266,
84
  "step": 1089
85
  },
86
  {
87
+ "epoch": 1.01,
 
88
  "learning_rate": 3e-05,
89
+ "loss": 1.2141,
90
  "step": 1100
91
  },
92
  {
93
+ "epoch": 1.1,
 
94
  "learning_rate": 3e-05,
95
+ "loss": 1.2178,
96
  "step": 1200
97
  },
98
  {
99
+ "epoch": 1.19,
 
100
  "learning_rate": 3e-05,
101
+ "loss": 1.1986,
102
  "step": 1300
103
  },
104
  {
105
+ "epoch": 1.29,
 
106
  "learning_rate": 3e-05,
107
+ "loss": 1.1903,
108
  "step": 1400
109
  },
110
  {
111
+ "epoch": 1.38,
 
112
  "learning_rate": 3e-05,
113
+ "loss": 1.1925,
114
  "step": 1500
115
  },
116
  {
117
+ "epoch": 1.47,
 
118
  "learning_rate": 3e-05,
119
+ "loss": 1.1954,
120
  "step": 1600
121
  },
122
  {
123
+ "epoch": 1.56,
 
124
  "learning_rate": 3e-05,
125
+ "loss": 1.1859,
126
  "step": 1700
127
  },
128
  {
129
+ "epoch": 1.65,
 
130
  "learning_rate": 3e-05,
131
+ "loss": 1.1979,
132
  "step": 1800
133
  },
134
  {
135
+ "epoch": 1.74,
 
136
  "learning_rate": 3e-05,
137
+ "loss": 1.201,
138
  "step": 1900
139
  },
140
  {
141
+ "epoch": 1.84,
 
142
  "learning_rate": 3e-05,
143
+ "loss": 1.1871,
144
  "step": 2000
145
  },
146
  {
147
+ "epoch": 1.93,
 
148
  "learning_rate": 3e-05,
149
+ "loss": 1.1949,
150
  "step": 2100
151
  },
152
  {
153
+ "epoch": 2.0,
154
+ "eval_accuracy": 0.5960506329113924,
155
+ "eval_loss": 1.834545373916626,
156
+ "eval_runtime": 4.5511,
157
+ "eval_samples_per_second": 109.863,
158
+ "eval_steps_per_second": 13.843,
159
  "step": 2178
160
  },
161
  {
162
+ "epoch": 2.0,
163
+ "eval_exact_match": 25.2,
164
+ "eval_f1": 34.41373827926461,
165
  "step": 2178
166
  },
167
  {
168
+ "epoch": 2.02,
 
169
  "learning_rate": 3e-05,
170
+ "loss": 1.1775,
171
  "step": 2200
172
  },
173
  {
174
+ "epoch": 2.11,
 
175
  "learning_rate": 3e-05,
176
+ "loss": 1.1579,
177
  "step": 2300
178
  },
179
  {
180
+ "epoch": 2.2,
 
181
  "learning_rate": 3e-05,
182
+ "loss": 1.1678,
183
  "step": 2400
184
  },
185
  {
186
+ "epoch": 2.3,
 
187
  "learning_rate": 3e-05,
188
+ "loss": 1.1758,
189
  "step": 2500
190
  },
191
  {
192
+ "epoch": 2.39,
 
193
  "learning_rate": 3e-05,
194
+ "loss": 1.1374,
195
  "step": 2600
196
  },
197
  {
198
+ "epoch": 2.48,
 
199
  "learning_rate": 3e-05,
200
+ "loss": 1.16,
201
  "step": 2700
202
  },
203
  {
204
+ "epoch": 2.57,
 
205
  "learning_rate": 3e-05,
206
+ "loss": 1.1647,
207
  "step": 2800
208
  },
209
  {
210
+ "epoch": 2.66,
 
211
  "learning_rate": 3e-05,
212
+ "loss": 1.1579,
213
  "step": 2900
214
  },
215
  {
216
+ "epoch": 2.75,
 
217
  "learning_rate": 3e-05,
218
+ "loss": 1.1647,
219
  "step": 3000
220
  },
221
  {
222
+ "epoch": 2.85,
 
223
  "learning_rate": 3e-05,
224
+ "loss": 1.1581,
225
  "step": 3100
226
  },
227
  {
228
+ "epoch": 2.94,
 
229
  "learning_rate": 3e-05,
230
+ "loss": 1.1542,
231
  "step": 3200
232
  },
233
  {
234
+ "epoch": 3.0,
235
+ "eval_accuracy": 0.596379746835443,
236
+ "eval_loss": 1.8205524682998657,
237
+ "eval_runtime": 4.5724,
238
+ "eval_samples_per_second": 109.352,
239
+ "eval_steps_per_second": 13.778,
240
  "step": 3267
241
  },
242
  {
243
+ "epoch": 3.0,
244
+ "eval_exact_match": 24.6,
245
+ "eval_f1": 34.42903485403487,
246
  "step": 3267
247
  },
248
  {
249
+ "epoch": 3.03,
 
250
  "learning_rate": 3e-05,
251
+ "loss": 1.1336,
252
  "step": 3300
253
  },
254
  {
255
+ "epoch": 3.12,
 
256
  "learning_rate": 3e-05,
257
+ "loss": 1.1112,
258
  "step": 3400
259
  },
260
  {
261
+ "epoch": 3.21,
 
262
  "learning_rate": 3e-05,
263
+ "loss": 1.123,
264
  "step": 3500
265
  },
266
  {
267
+ "epoch": 3.31,
 
268
  "learning_rate": 3e-05,
269
+ "loss": 1.1278,
270
  "step": 3600
271
  },
272
  {
273
+ "epoch": 3.4,
 
274
  "learning_rate": 3e-05,
275
+ "loss": 1.1226,
276
  "step": 3700
277
  },
278
  {
279
+ "epoch": 3.49,
 
280
  "learning_rate": 3e-05,
281
+ "loss": 1.1132,
282
  "step": 3800
283
  },
284
  {
285
+ "epoch": 3.58,
 
286
  "learning_rate": 3e-05,
287
+ "loss": 1.1075,
288
  "step": 3900
289
  },
290
  {
291
+ "epoch": 3.67,
 
292
  "learning_rate": 3e-05,
293
+ "loss": 1.128,
294
  "step": 4000
295
  },
296
  {
297
+ "epoch": 3.76,
 
298
  "learning_rate": 3e-05,
299
+ "loss": 1.1182,
300
  "step": 4100
301
  },
302
  {
303
+ "epoch": 3.86,
 
304
  "learning_rate": 3e-05,
305
+ "loss": 1.1288,
306
  "step": 4200
307
  },
308
  {
309
+ "epoch": 3.95,
 
310
  "learning_rate": 3e-05,
311
+ "loss": 1.1236,
312
  "step": 4300
313
  },
314
  {
315
  "epoch": 4.0,
316
+ "eval_accuracy": 0.600379746835443,
317
+ "eval_loss": 1.822967290878296,
318
+ "eval_runtime": 4.5641,
319
+ "eval_samples_per_second": 109.55,
320
+ "eval_steps_per_second": 13.803,
321
  "step": 4357
322
  },
323
  {
324
  "epoch": 4.0,
325
+ "eval_exact_match": 23.0,
326
+ "eval_f1": 32.55568709068711,
327
  "step": 4357
328
  },
329
  {
330
+ "epoch": 4.04,
 
331
  "learning_rate": 3e-05,
332
+ "loss": 1.1034,
333
  "step": 4400
334
  },
335
  {
336
+ "epoch": 4.13,
 
337
  "learning_rate": 3e-05,
338
+ "loss": 1.0822,
339
  "step": 4500
340
  },
341
  {
342
+ "epoch": 4.22,
 
343
  "learning_rate": 3e-05,
344
+ "loss": 1.0869,
345
  "step": 4600
346
  },
347
  {
348
+ "epoch": 4.31,
 
349
  "learning_rate": 3e-05,
350
+ "loss": 1.0813,
351
  "step": 4700
352
  },
353
  {
354
+ "epoch": 4.41,
 
355
  "learning_rate": 3e-05,
356
+ "loss": 1.081,
357
  "step": 4800
358
  },
359
  {
360
+ "epoch": 4.5,
 
361
  "learning_rate": 3e-05,
362
+ "loss": 1.1065,
363
  "step": 4900
364
  },
365
  {
366
+ "epoch": 4.59,
 
367
  "learning_rate": 3e-05,
368
+ "loss": 1.1018,
369
  "step": 5000
370
  },
371
  {
372
+ "epoch": 4.68,
 
373
  "learning_rate": 3e-05,
374
+ "loss": 1.0737,
375
  "step": 5100
376
  },
377
  {
378
+ "epoch": 4.77,
 
379
  "learning_rate": 3e-05,
380
+ "loss": 1.0823,
381
  "step": 5200
382
  },
383
  {
384
+ "epoch": 4.87,
 
385
  "learning_rate": 3e-05,
386
+ "loss": 1.0916,
387
  "step": 5300
388
  },
389
  {
390
+ "epoch": 4.96,
 
391
  "learning_rate": 3e-05,
392
+ "loss": 1.0989,
393
  "step": 5400
394
  },
395
  {
396
+ "epoch": 5.0,
397
+ "eval_accuracy": 0.6035696202531645,
398
+ "eval_loss": 1.8370839357376099,
399
+ "eval_runtime": 4.3939,
400
+ "eval_samples_per_second": 113.795,
401
+ "eval_steps_per_second": 14.338,
402
  "step": 5446
403
  },
404
  {
405
+ "epoch": 5.0,
406
+ "eval_exact_match": 23.8,
407
+ "eval_f1": 33.387894882894905,
408
  "step": 5446
409
  }
410
  ],
411
  "logging_steps": 100,
412
  "max_steps": 54450,
 
413
  "num_train_epochs": 50,
414
  "save_steps": 500,
415
+ "total_flos": 1.0253725986340209e+18,
 
 
 
 
 
 
 
 
 
 
 
 
 
416
  "trial_name": null,
417
  "trial_params": null
418
  }
checkpoint-5446/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5377ce2541570511bdbb29b699438bab217d7b0b49a543f6293cd608457a8a9d
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990ba0ec6800794569e1f142d0a98c1c27c344ee04644eb9619680965b92e617
3
+ size 4728