furmaniak commited on
Commit
53c40ae
·
verified ·
1 Parent(s): ad262c7

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +6 -11
  3. train_results.json +6 -6
  4. trainer_state.json +504 -71
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-32B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: pretrain
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # pretrain
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-32B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: pretrain
 
16
 
17
  # pretrain
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the openalex_references dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,13 +1,8 @@
1
  {
2
- "epoch": 0.9454545454545454,
3
- "eval_loss": 1.1903643608093262,
4
- "eval_runtime": 40.1525,
5
- "eval_samples_per_second": 2.441,
6
- "eval_steps_per_second": 0.324,
7
- "perplexity": 3.2882791091731414,
8
- "total_flos": 45330292801536.0,
9
- "train_loss": 1.3396454407618597,
10
- "train_runtime": 2207.3438,
11
- "train_samples_per_second": 0.398,
12
- "train_steps_per_second": 0.006
13
  }
 
1
  {
2
+ "epoch": 0.9967213114754099,
3
+ "total_flos": 534721415086080.0,
4
+ "train_loss": 1.1572106621767346,
5
+ "train_runtime": 17915.2053,
6
+ "train_samples_per_second": 0.545,
7
+ "train_steps_per_second": 0.004
 
 
 
 
 
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.9454545454545454,
3
- "total_flos": 45330292801536.0,
4
- "train_loss": 1.3396454407618597,
5
- "train_runtime": 2207.3438,
6
- "train_samples_per_second": 0.398,
7
- "train_steps_per_second": 0.006
8
  }
 
1
  {
2
+ "epoch": 0.9967213114754099,
3
+ "total_flos": 534721415086080.0,
4
+ "train_loss": 1.1572106621767346,
5
+ "train_runtime": 17915.2053,
6
+ "train_samples_per_second": 0.545,
7
+ "train_steps_per_second": 0.004
8
  }
trainer_state.json CHANGED
@@ -1,124 +1,557 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.9454545454545454,
5
- "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.07272727272727272,
13
- "grad_norm": 0.09205172210931778,
14
- "learning_rate": 5e-05,
15
- "loss": 1.2196,
16
  "step": 1
17
  },
18
  {
19
- "epoch": 0.14545454545454545,
20
- "grad_norm": 0.08487003296613693,
21
- "learning_rate": 0.0001,
22
- "loss": 1.1877,
23
  "step": 2
24
  },
25
  {
26
- "epoch": 0.21818181818181817,
27
- "grad_norm": 0.6594376564025879,
28
- "learning_rate": 9.797464868072488e-05,
29
- "loss": 1.3252,
30
  "step": 3
31
  },
32
  {
33
- "epoch": 0.2909090909090909,
34
- "grad_norm": 1.960582971572876,
35
- "learning_rate": 9.206267664155907e-05,
36
- "loss": 2.0162,
37
  "step": 4
38
  },
39
  {
40
- "epoch": 0.36363636363636365,
41
- "grad_norm": 1.3530547618865967,
42
- "learning_rate": 8.274303669726426e-05,
43
- "loss": 1.5829,
44
  "step": 5
45
  },
46
  {
47
- "epoch": 0.43636363636363634,
48
- "grad_norm": 1.9950076341629028,
49
- "learning_rate": 7.077075065009433e-05,
50
- "loss": 1.4982,
51
  "step": 6
52
  },
53
  {
54
- "epoch": 0.509090909090909,
55
- "grad_norm": 0.38373228907585144,
56
- "learning_rate": 5.7115741913664264e-05,
57
- "loss": 1.4252,
58
  "step": 7
59
  },
60
  {
61
- "epoch": 0.5818181818181818,
62
- "grad_norm": 0.14959090948104858,
63
- "learning_rate": 4.288425808633575e-05,
64
- "loss": 1.1972,
65
  "step": 8
66
  },
67
  {
68
- "epoch": 0.6545454545454545,
69
- "grad_norm": 0.10391217470169067,
70
- "learning_rate": 2.9229249349905684e-05,
71
- "loss": 1.2054,
72
  "step": 9
73
  },
74
  {
75
- "epoch": 0.7272727272727273,
76
- "grad_norm": 0.0690321996808052,
77
- "learning_rate": 1.725696330273575e-05,
78
- "loss": 1.168,
79
  "step": 10
80
  },
81
  {
82
- "epoch": 0.7272727272727273,
83
- "eval_loss": 1.1994872093200684,
84
- "eval_runtime": 40.5127,
85
- "eval_samples_per_second": 2.419,
86
- "eval_steps_per_second": 0.321,
87
- "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  },
89
  {
90
  "epoch": 0.8,
91
- "grad_norm": 0.0676456168293953,
92
- "learning_rate": 7.937323358440935e-06,
93
- "loss": 1.1932,
94
- "step": 11
95
  },
96
  {
97
- "epoch": 0.8727272727272727,
98
- "grad_norm": 0.061955519020557404,
99
- "learning_rate": 2.0253513192751373e-06,
100
- "loss": 1.2116,
101
- "step": 12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
  },
103
  {
104
- "epoch": 0.9454545454545454,
105
- "grad_norm": 0.059567924588918686,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  "learning_rate": 0.0,
107
- "loss": 1.1849,
108
- "step": 13
109
  },
110
  {
111
- "epoch": 0.9454545454545454,
112
- "step": 13,
113
- "total_flos": 45330292801536.0,
114
- "train_loss": 1.3396454407618597,
115
- "train_runtime": 2207.3438,
116
- "train_samples_per_second": 0.398,
117
- "train_steps_per_second": 0.006
118
  }
119
  ],
120
  "logging_steps": 1,
121
- "max_steps": 13,
122
  "num_input_tokens_seen": 0,
123
  "num_train_epochs": 1,
124
  "save_steps": 100,
@@ -134,7 +567,7 @@
134
  "attributes": {}
135
  }
136
  },
137
- "total_flos": 45330292801536.0,
138
  "train_batch_size": 1,
139
  "trial_name": null,
140
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9967213114754099,
5
+ "eval_steps": 500,
6
+ "global_step": 76,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.013114754098360656,
13
+ "grad_norm": 0.043162938207387924,
14
+ "learning_rate": 1.25e-05,
15
+ "loss": 1.2441,
16
  "step": 1
17
  },
18
  {
19
+ "epoch": 0.02622950819672131,
20
+ "grad_norm": 0.043701257556676865,
21
+ "learning_rate": 2.5e-05,
22
+ "loss": 1.2477,
23
  "step": 2
24
  },
25
  {
26
+ "epoch": 0.03934426229508197,
27
+ "grad_norm": 0.027155233547091484,
28
+ "learning_rate": 3.7500000000000003e-05,
29
+ "loss": 1.2284,
30
  "step": 3
31
  },
32
  {
33
+ "epoch": 0.05245901639344262,
34
+ "grad_norm": 0.10691457986831665,
35
+ "learning_rate": 5e-05,
36
+ "loss": 1.2441,
37
  "step": 4
38
  },
39
  {
40
+ "epoch": 0.06557377049180328,
41
+ "grad_norm": 0.09258124232292175,
42
+ "learning_rate": 6.25e-05,
43
+ "loss": 1.2181,
44
  "step": 5
45
  },
46
  {
47
+ "epoch": 0.07868852459016394,
48
+ "grad_norm": 0.06767486780881882,
49
+ "learning_rate": 7.500000000000001e-05,
50
+ "loss": 1.2279,
51
  "step": 6
52
  },
53
  {
54
+ "epoch": 0.09180327868852459,
55
+ "grad_norm": 0.1602831929922104,
56
+ "learning_rate": 8.75e-05,
57
+ "loss": 1.2553,
58
  "step": 7
59
  },
60
  {
61
+ "epoch": 0.10491803278688525,
62
+ "grad_norm": 0.2144620418548584,
63
+ "learning_rate": 0.0001,
64
+ "loss": 1.2558,
65
  "step": 8
66
  },
67
  {
68
+ "epoch": 0.1180327868852459,
69
+ "grad_norm": 0.06662847101688385,
70
+ "learning_rate": 9.994664874011863e-05,
71
+ "loss": 1.2333,
72
  "step": 9
73
  },
74
  {
75
+ "epoch": 0.13114754098360656,
76
+ "grad_norm": 0.13297972083091736,
77
+ "learning_rate": 9.978670881475172e-05,
78
+ "loss": 1.2274,
79
  "step": 10
80
  },
81
  {
82
+ "epoch": 0.14426229508196722,
83
+ "grad_norm": 0.06226632371544838,
84
+ "learning_rate": 9.952052154376026e-05,
85
+ "loss": 1.2171,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.15737704918032788,
90
+ "grad_norm": 0.05960860103368759,
91
+ "learning_rate": 9.91486549841951e-05,
92
+ "loss": 1.2004,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.17049180327868851,
97
+ "grad_norm": 0.057807717472314835,
98
+ "learning_rate": 9.867190271803465e-05,
99
+ "loss": 1.1961,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.18360655737704917,
104
+ "grad_norm": 0.044687915593385696,
105
+ "learning_rate": 9.809128215864097e-05,
106
+ "loss": 1.2057,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.19672131147540983,
111
+ "grad_norm": 0.042382605373859406,
112
+ "learning_rate": 9.74080323795483e-05,
113
+ "loss": 1.2015,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.2098360655737705,
118
+ "grad_norm": 0.041327111423015594,
119
+ "learning_rate": 9.662361147021779e-05,
120
+ "loss": 1.1922,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.22295081967213115,
125
+ "grad_norm": 0.03643479198217392,
126
+ "learning_rate": 9.573969342440106e-05,
127
+ "loss": 1.1801,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.2360655737704918,
132
+ "grad_norm": 0.03201618418097496,
133
+ "learning_rate": 9.475816456775313e-05,
134
+ "loss": 1.1793,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.24918032786885247,
139
+ "grad_norm": 0.033190254122018814,
140
+ "learning_rate": 9.368111953231848e-05,
141
+ "loss": 1.1727,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.26229508196721313,
146
+ "grad_norm": 0.029199425131082535,
147
+ "learning_rate": 9.251085678648072e-05,
148
+ "loss": 1.1803,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.2754098360655738,
153
+ "grad_norm": 0.019889283925294876,
154
+ "learning_rate": 9.124987372991511e-05,
155
+ "loss": 1.1739,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.28852459016393445,
160
+ "grad_norm": 0.025394951924681664,
161
+ "learning_rate": 8.9900861364012e-05,
162
+ "loss": 1.1824,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.3016393442622951,
167
+ "grad_norm": 0.02561134099960327,
168
+ "learning_rate": 8.846669854914396e-05,
169
+ "loss": 1.1704,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.31475409836065577,
174
+ "grad_norm": 0.020040003582835197,
175
+ "learning_rate": 8.695044586103296e-05,
176
+ "loss": 1.1748,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.32786885245901637,
181
+ "grad_norm": 0.0246971994638443,
182
+ "learning_rate": 8.535533905932738e-05,
183
+ "loss": 1.1726,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.34098360655737703,
188
+ "grad_norm": 0.019360244274139404,
189
+ "learning_rate": 8.368478218232787e-05,
190
+ "loss": 1.1539,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.3540983606557377,
195
+ "grad_norm": 0.021348467096686363,
196
+ "learning_rate": 8.194234028259806e-05,
197
+ "loss": 1.1641,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.36721311475409835,
202
+ "grad_norm": 0.01926092617213726,
203
+ "learning_rate": 8.013173181896283e-05,
204
+ "loss": 1.1548,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.380327868852459,
209
+ "grad_norm": 0.018094880506396294,
210
+ "learning_rate": 7.82568207211296e-05,
211
+ "loss": 1.1595,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.39344262295081966,
216
+ "grad_norm": 0.019909674301743507,
217
+ "learning_rate": 7.63216081438678e-05,
218
+ "loss": 1.1488,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.4065573770491803,
223
+ "grad_norm": 0.015068020671606064,
224
+ "learning_rate": 7.433022392834282e-05,
225
+ "loss": 1.1518,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.419672131147541,
230
+ "grad_norm": 0.019493145868182182,
231
+ "learning_rate": 7.228691778882693e-05,
232
+ "loss": 1.1643,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.43278688524590164,
237
+ "grad_norm": 0.018127303570508957,
238
+ "learning_rate": 7.019605024359474e-05,
239
+ "loss": 1.1449,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.4459016393442623,
244
+ "grad_norm": 0.015173117630183697,
245
+ "learning_rate": 6.806208330935766e-05,
246
+ "loss": 1.1632,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.45901639344262296,
251
+ "grad_norm": 0.01737191341817379,
252
+ "learning_rate": 6.588957097909508e-05,
253
+ "loss": 1.1618,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.4721311475409836,
258
+ "grad_norm": 0.015316477976739407,
259
+ "learning_rate": 6.368314950360415e-05,
260
+ "loss": 1.1445,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.4852459016393443,
265
+ "grad_norm": 0.015012883581221104,
266
+ "learning_rate": 6.14475274975067e-05,
267
+ "loss": 1.1558,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.49836065573770494,
272
+ "grad_norm": 0.015383531339466572,
273
+ "learning_rate": 5.918747589082853e-05,
274
+ "loss": 1.1331,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.5114754098360655,
279
+ "grad_norm": 0.0135785061866045,
280
+ "learning_rate": 5.6907817747594116e-05,
281
+ "loss": 1.1423,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.5245901639344263,
286
+ "grad_norm": 0.014159608632326126,
287
+ "learning_rate": 5.4613417973165106e-05,
288
+ "loss": 1.1343,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.5377049180327869,
293
+ "grad_norm": 0.014230456203222275,
294
+ "learning_rate": 5.230917293228699e-05,
295
+ "loss": 1.1344,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.5508196721311476,
300
+ "grad_norm": 0.014486027881503105,
301
+ "learning_rate": 5e-05,
302
+ "loss": 1.1298,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.5639344262295082,
307
+ "grad_norm": 0.013846023939549923,
308
+ "learning_rate": 4.7690827067713035e-05,
309
+ "loss": 1.144,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.5770491803278689,
314
+ "grad_norm": 0.012692565098404884,
315
+ "learning_rate": 4.5386582026834906e-05,
316
+ "loss": 1.1317,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.5901639344262295,
321
+ "grad_norm": 0.012511651031672955,
322
+ "learning_rate": 4.30921822524059e-05,
323
+ "loss": 1.1495,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.6032786885245902,
328
+ "grad_norm": 0.012697260826826096,
329
+ "learning_rate": 4.0812524109171476e-05,
330
+ "loss": 1.1365,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.6163934426229508,
335
+ "grad_norm": 0.013609658926725388,
336
+ "learning_rate": 3.855247250249331e-05,
337
+ "loss": 1.1332,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.6295081967213115,
342
+ "grad_norm": 0.011829257011413574,
343
+ "learning_rate": 3.631685049639586e-05,
344
+ "loss": 1.1266,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.6426229508196721,
349
+ "grad_norm": 0.011731350794434547,
350
+ "learning_rate": 3.411042902090492e-05,
351
+ "loss": 1.1325,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.6557377049180327,
356
+ "grad_norm": 0.011319032870233059,
357
+ "learning_rate": 3.1937916690642356e-05,
358
+ "loss": 1.1227,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.6688524590163935,
363
+ "grad_norm": 0.012229708954691887,
364
+ "learning_rate": 2.980394975640526e-05,
365
+ "loss": 1.1338,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.6819672131147541,
370
+ "grad_norm": 0.010175776667892933,
371
+ "learning_rate": 2.771308221117309e-05,
372
+ "loss": 1.1144,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.6950819672131148,
377
+ "grad_norm": 0.01121637411415577,
378
+ "learning_rate": 2.5669776071657192e-05,
379
+ "loss": 1.1253,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.7081967213114754,
384
+ "grad_norm": 0.010852695442736149,
385
+ "learning_rate": 2.3678391856132204e-05,
386
+ "loss": 1.1344,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.7213114754098361,
391
+ "grad_norm": 0.010888871736824512,
392
+ "learning_rate": 2.1743179278870407e-05,
393
+ "loss": 1.1342,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.7344262295081967,
398
+ "grad_norm": 0.009675499983131886,
399
+ "learning_rate": 1.9868268181037185e-05,
400
+ "loss": 1.1233,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.7475409836065574,
405
+ "grad_norm": 0.0103612020611763,
406
+ "learning_rate": 1.8057659717401947e-05,
407
+ "loss": 1.128,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.760655737704918,
412
+ "grad_norm": 0.011313353665173054,
413
+ "learning_rate": 1.631521781767214e-05,
414
+ "loss": 1.1127,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.7737704918032787,
419
+ "grad_norm": 0.009756634011864662,
420
+ "learning_rate": 1.4644660940672627e-05,
421
+ "loss": 1.1207,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.7868852459016393,
426
+ "grad_norm": 0.009867743588984013,
427
+ "learning_rate": 1.3049554138967051e-05,
428
+ "loss": 1.1154,
429
+ "step": 60
430
  },
431
  {
432
  "epoch": 0.8,
433
+ "grad_norm": 0.00982784666121006,
434
+ "learning_rate": 1.1533301450856054e-05,
435
+ "loss": 1.1272,
436
+ "step": 61
437
  },
438
  {
439
+ "epoch": 0.8131147540983606,
440
+ "grad_norm": 0.00951016042381525,
441
+ "learning_rate": 1.0099138635988026e-05,
442
+ "loss": 1.1139,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.8262295081967214,
447
+ "grad_norm": 0.010089361108839512,
448
+ "learning_rate": 8.75012627008489e-06,
449
+ "loss": 1.1304,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.839344262295082,
454
+ "grad_norm": 0.010168294422328472,
455
+ "learning_rate": 7.489143213519301e-06,
456
+ "loss": 1.109,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.8524590163934426,
461
+ "grad_norm": 0.010138073936104774,
462
+ "learning_rate": 6.318880467681526e-06,
463
+ "loss": 1.1259,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.8655737704918033,
468
+ "grad_norm": 0.009661810472607613,
469
+ "learning_rate": 5.241835432246889e-06,
470
+ "loss": 1.1184,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.8786885245901639,
475
+ "grad_norm": 0.009376097470521927,
476
+ "learning_rate": 4.260306575598949e-06,
477
+ "loss": 1.1214,
478
+ "step": 67
479
  },
480
  {
481
+ "epoch": 0.8918032786885246,
482
+ "grad_norm": 0.009214168414473534,
483
+ "learning_rate": 3.376388529782215e-06,
484
+ "loss": 1.109,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.9049180327868852,
489
+ "grad_norm": 0.009044879116117954,
490
+ "learning_rate": 2.591967620451707e-06,
491
+ "loss": 1.1116,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.9180327868852459,
496
+ "grad_norm": 0.009314059279859066,
497
+ "learning_rate": 1.908717841359048e-06,
498
+ "loss": 1.1278,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.9311475409836065,
503
+ "grad_norm": 0.009015677496790886,
504
+ "learning_rate": 1.328097281965357e-06,
505
+ "loss": 1.1211,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.9442622950819672,
510
+ "grad_norm": 0.009113411419093609,
511
+ "learning_rate": 8.513450158049108e-07,
512
+ "loss": 1.1148,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.9573770491803278,
517
+ "grad_norm": 0.008978264406323433,
518
+ "learning_rate": 4.794784562397458e-07,
519
+ "loss": 1.1207,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.9704918032786886,
524
+ "grad_norm": 0.008966252207756042,
525
+ "learning_rate": 2.1329118524827662e-07,
526
+ "loss": 1.1231,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.9836065573770492,
531
+ "grad_norm": 0.00909092091023922,
532
+ "learning_rate": 5.3351259881379014e-08,
533
+ "loss": 1.1078,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.9967213114754099,
538
+ "grad_norm": 0.00918254442512989,
539
  "learning_rate": 0.0,
540
+ "loss": 1.1241,
541
+ "step": 76
542
  },
543
  {
544
+ "epoch": 0.9967213114754099,
545
+ "step": 76,
546
+ "total_flos": 534721415086080.0,
547
+ "train_loss": 1.1572106621767346,
548
+ "train_runtime": 17915.2053,
549
+ "train_samples_per_second": 0.545,
550
+ "train_steps_per_second": 0.004
551
  }
552
  ],
553
  "logging_steps": 1,
554
+ "max_steps": 76,
555
  "num_input_tokens_seen": 0,
556
  "num_train_epochs": 1,
557
  "save_steps": 100,
 
567
  "attributes": {}
568
  }
569
  },
570
+ "total_flos": 534721415086080.0,
571
  "train_batch_size": 1,
572
  "trial_name": null,
573
  "trial_params": null
training_loss.png CHANGED