ahmedheakl commited on
Commit
d1b47d5
·
verified ·
1 Parent(s): f21f539

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +372 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
 
16
 
17
  # ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the cuda_61k_source dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 506334263902208.0,
4
+ "train_loss": 0.002037838656673496,
5
+ "train_runtime": 19073.3023,
6
+ "train_samples_per_second": 6.413,
7
+ "train_steps_per_second": 0.025
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 506334263902208.0,
4
+ "train_loss": 0.002037838656673496,
5
+ "train_runtime": 19073.3023,
6
+ "train_samples_per_second": 6.413,
7
+ "train_steps_per_second": 0.025
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 478,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04184100418410042,
14
+ "grad_norm": 0.2925145155398498,
15
+ "learning_rate": 3.7500000000000005e-06,
16
+ "loss": 0.0243,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.08368200836820083,
21
+ "grad_norm": 0.09332366083077137,
22
+ "learning_rate": 7.916666666666667e-06,
23
+ "loss": 0.0066,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.12552301255230125,
28
+ "grad_norm": 0.037000329123698675,
29
+ "learning_rate": 1.2083333333333333e-05,
30
+ "loss": 0.0044,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.16736401673640167,
35
+ "grad_norm": 0.024975645672741548,
36
+ "learning_rate": 1.6250000000000002e-05,
37
+ "loss": 0.0028,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.20920502092050208,
42
+ "grad_norm": 0.033927305503936314,
43
+ "learning_rate": 1.9999733110857237e-05,
44
+ "loss": 0.0025,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.2510460251046025,
49
+ "grad_norm": 0.014612909987451435,
50
+ "learning_rate": 1.9967723647752463e-05,
51
+ "loss": 0.0018,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.2928870292887029,
56
+ "grad_norm": 0.017483510752084472,
57
+ "learning_rate": 1.988253206622306e-05,
58
+ "loss": 0.0019,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.33472803347280333,
63
+ "grad_norm": 0.014386718401807688,
64
+ "learning_rate": 1.9744612900216588e-05,
65
+ "loss": 0.0026,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.37656903765690375,
70
+ "grad_norm": 0.039483682416672744,
71
+ "learning_rate": 1.9554702008157567e-05,
72
+ "loss": 0.0017,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.41841004184100417,
77
+ "grad_norm": 0.017654984549017917,
78
+ "learning_rate": 1.9313812646824432e-05,
79
+ "loss": 0.0013,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.4602510460251046,
84
+ "grad_norm": 0.00968661778293667,
85
+ "learning_rate": 1.9023230065186192e-05,
86
+ "loss": 0.0031,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.502092050209205,
91
+ "grad_norm": 0.023973932216176105,
92
+ "learning_rate": 1.8684504647043093e-05,
93
+ "loss": 0.0022,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.5439330543933054,
98
+ "grad_norm": 0.021080771265352845,
99
+ "learning_rate": 1.8299443639058238e-05,
100
+ "loss": 0.0024,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.5857740585774058,
105
+ "grad_norm": 0.02233998245288774,
106
+ "learning_rate": 1.7870101508314686e-05,
107
+ "loss": 0.0008,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.6276150627615062,
112
+ "grad_norm": 0.015428869613923153,
113
+ "learning_rate": 1.7398768980844664e-05,
114
+ "loss": 0.002,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.6694560669456067,
119
+ "grad_norm": 0.011099263805834297,
120
+ "learning_rate": 1.6887960819615025e-05,
121
+ "loss": 0.0011,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.7112970711297071,
126
+ "grad_norm": 0.015474457950600984,
127
+ "learning_rate": 1.634040240717878e-05,
128
+ "loss": 0.0008,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.7531380753138075,
133
+ "grad_norm": 0.016896916614250686,
134
+ "learning_rate": 1.5759015204579958e-05,
135
+ "loss": 0.0012,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.7949790794979079,
140
+ "grad_norm": 0.010764154560653242,
141
+ "learning_rate": 1.5146901164094914e-05,
142
+ "loss": 0.0013,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.8368200836820083,
147
+ "grad_norm": 0.02624812740713589,
148
+ "learning_rate": 1.4507326178974789e-05,
149
+ "loss": 0.0021,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.8786610878661087,
154
+ "grad_norm": 0.02213838592470387,
155
+ "learning_rate": 1.3843702658491961e-05,
156
+ "loss": 0.0014,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.9205020920502092,
161
+ "grad_norm": 0.03256425649897184,
162
+ "learning_rate": 1.3159571321260114e-05,
163
+ "loss": 0.0007,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.9623430962343096,
168
+ "grad_norm": 0.008534054334232773,
169
+ "learning_rate": 1.2458582303968466e-05,
170
+ "loss": 0.0011,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 1.00418410041841,
175
+ "grad_norm": 0.015659822283413834,
176
+ "learning_rate": 1.1744475686323225e-05,
177
+ "loss": 0.0018,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 1.0460251046025104,
182
+ "grad_norm": 0.009318785906390915,
183
+ "learning_rate": 1.1021061536104093e-05,
184
+ "loss": 0.0007,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 1.0878661087866108,
189
+ "grad_norm": 0.02012715152590903,
190
+ "learning_rate": 1.02921995808042e-05,
191
+ "loss": 0.0008,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 1.1297071129707112,
196
+ "grad_norm": 0.01535009737960017,
197
+ "learning_rate": 9.561778614313876e-06,
198
+ "loss": 0.0005,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.1715481171548117,
203
+ "grad_norm": 0.011963284930504645,
204
+ "learning_rate": 8.833695748522702e-06,
205
+ "loss": 0.0011,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.213389121338912,
210
+ "grad_norm": 0.01174691491766897,
211
+ "learning_rate": 8.111835620541397e-06,
212
+ "loss": 0.0008,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.2552301255230125,
217
+ "grad_norm": 0.015140100128090778,
218
+ "learning_rate": 7.400049666482061e-06,
219
+ "loss": 0.0005,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 1.297071129707113,
224
+ "grad_norm": 0.0082059300361877,
225
+ "learning_rate": 6.702135572380078e-06,
226
+ "loss": 0.001,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.3389121338912133,
231
+ "grad_norm": 0.004079307018079572,
232
+ "learning_rate": 6.021817011896004e-06,
233
+ "loss": 0.0014,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.3807531380753137,
238
+ "grad_norm": 0.01109473064765619,
239
+ "learning_rate": 5.362723778905427e-06,
240
+ "loss": 0.001,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.4225941422594142,
245
+ "grad_norm": 0.0015855550385638771,
246
+ "learning_rate": 4.728372420978119e-06,
247
+ "loss": 0.0012,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.4644351464435146,
252
+ "grad_norm": 0.006116117187679222,
253
+ "learning_rate": 4.12214747707527e-06,
254
+ "loss": 0.0014,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.506276150627615,
259
+ "grad_norm": 0.020785630071871383,
260
+ "learning_rate": 3.5472834195697017e-06,
261
+ "loss": 0.0005,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.5481171548117154,
266
+ "grad_norm": 0.01356591109411228,
267
+ "learning_rate": 3.0068473969362998e-06,
268
+ "loss": 0.0016,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.5899581589958158,
273
+ "grad_norm": 0.0455348358926559,
274
+ "learning_rate": 2.5037228691878424e-06,
275
+ "loss": 0.0011,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.6317991631799162,
280
+ "grad_norm": 0.010270285275849788,
281
+ "learning_rate": 2.0405942233682017e-06,
282
+ "loss": 0.0011,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.6736401673640167,
287
+ "grad_norm": 0.009898474319911012,
288
+ "learning_rate": 1.619932451186048e-06,
289
+ "loss": 0.0019,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.715481171548117,
294
+ "grad_norm": 0.025182308499786255,
295
+ "learning_rate": 1.2439819652049178e-06,
296
+ "loss": 0.0008,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.7573221757322175,
301
+ "grad_norm": 0.01013827313449354,
302
+ "learning_rate": 9.147486239311032e-07,
303
+ "loss": 0.001,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.799163179916318,
308
+ "grad_norm": 0.03137196761877556,
309
+ "learning_rate": 6.339890296906493e-07,
310
+ "loss": 0.0013,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.8410041841004183,
315
+ "grad_norm": 0.016893363525461946,
316
+ "learning_rate": 4.032011563958893e-07,
317
+ "loss": 0.0014,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.8828451882845187,
322
+ "grad_norm": 0.015987721995170366,
323
+ "learning_rate": 2.2361635720651199e-07,
324
+ "loss": 0.0012,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.9246861924686192,
329
+ "grad_norm": 0.01083855584874376,
330
+ "learning_rate": 9.619279472766863e-08,
331
+ "loss": 0.0008,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.9665271966527196,
336
+ "grad_norm": 0.009804991431603429,
337
+ "learning_rate": 2.1610328797904145e-08,
338
+ "loss": 0.002,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 2.0,
343
+ "step": 478,
344
+ "total_flos": 506334263902208.0,
345
+ "train_loss": 0.002037838656673496,
346
+ "train_runtime": 19073.3023,
347
+ "train_samples_per_second": 6.413,
348
+ "train_steps_per_second": 0.025
349
+ }
350
+ ],
351
+ "logging_steps": 10,
352
+ "max_steps": 478,
353
+ "num_input_tokens_seen": 0,
354
+ "num_train_epochs": 2,
355
+ "save_steps": 500,
356
+ "stateful_callbacks": {
357
+ "TrainerControl": {
358
+ "args": {
359
+ "should_epoch_stop": false,
360
+ "should_evaluate": false,
361
+ "should_log": false,
362
+ "should_save": true,
363
+ "should_training_stop": true
364
+ },
365
+ "attributes": {}
366
+ }
367
+ },
368
+ "total_flos": 506334263902208.0,
369
+ "train_batch_size": 8,
370
+ "trial_name": null,
371
+ "trial_params": null
372
+ }
training_loss.png ADDED