stewy33 commited on
Commit
9b890c2
·
verified ·
1 Parent(s): 529eef7

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: togethercomputer/gemma-3-12b-it
3
+ library_name: peft
4
+ ---
5
+ ### Framework versions
6
+
7
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "togethercomputer/gemma-3-12b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc92972f467b5ae9a97c66037375592027c4dc5570c4cc23b5e5c86b14ded78
3
+ size 1047617032
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e316dda1f34f410e1a27d086d70cbb20164153422fcae753e180a47b083c99b3
3
+ size 18452294
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,756 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 102,
7
+ "global_step": 102,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00980392156862745,
14
+ "grad_norm": 2.500279188156128,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.3876,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0196078431372549,
21
+ "grad_norm": 2.360731840133667,
22
+ "learning_rate": 9.901960784313727e-06,
23
+ "loss": 2.3224,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.029411764705882353,
28
+ "grad_norm": 2.111973285675049,
29
+ "learning_rate": 9.803921568627451e-06,
30
+ "loss": 2.3377,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0392156862745098,
35
+ "grad_norm": 1.7793817520141602,
36
+ "learning_rate": 9.705882352941177e-06,
37
+ "loss": 2.2592,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.049019607843137254,
42
+ "grad_norm": 1.3986390829086304,
43
+ "learning_rate": 9.607843137254903e-06,
44
+ "loss": 2.2263,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.058823529411764705,
49
+ "grad_norm": 1.1015570163726807,
50
+ "learning_rate": 9.509803921568628e-06,
51
+ "loss": 2.2227,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.06862745098039216,
56
+ "grad_norm": 0.9321516752243042,
57
+ "learning_rate": 9.411764705882354e-06,
58
+ "loss": 2.1582,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0784313725490196,
63
+ "grad_norm": 0.8922587633132935,
64
+ "learning_rate": 9.31372549019608e-06,
65
+ "loss": 2.1078,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.08823529411764706,
70
+ "grad_norm": 0.9146968126296997,
71
+ "learning_rate": 9.215686274509804e-06,
72
+ "loss": 2.0554,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.09803921568627451,
77
+ "grad_norm": 0.9473930597305298,
78
+ "learning_rate": 9.11764705882353e-06,
79
+ "loss": 2.0022,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.10784313725490197,
84
+ "grad_norm": 0.9462062120437622,
85
+ "learning_rate": 9.019607843137256e-06,
86
+ "loss": 2.0462,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.11764705882352941,
91
+ "grad_norm": 0.959138810634613,
92
+ "learning_rate": 8.921568627450982e-06,
93
+ "loss": 2.0612,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.12745098039215685,
98
+ "grad_norm": 0.9512083530426025,
99
+ "learning_rate": 8.823529411764707e-06,
100
+ "loss": 1.9063,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.13725490196078433,
105
+ "grad_norm": 0.9136151671409607,
106
+ "learning_rate": 8.725490196078433e-06,
107
+ "loss": 2.0061,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.14705882352941177,
112
+ "grad_norm": 0.8621863722801208,
113
+ "learning_rate": 8.627450980392157e-06,
114
+ "loss": 1.9088,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.1568627450980392,
119
+ "grad_norm": 0.8003532290458679,
120
+ "learning_rate": 8.529411764705883e-06,
121
+ "loss": 1.8919,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.16666666666666666,
126
+ "grad_norm": 0.7299250364303589,
127
+ "learning_rate": 8.43137254901961e-06,
128
+ "loss": 1.8571,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.17647058823529413,
133
+ "grad_norm": 0.6769949197769165,
134
+ "learning_rate": 8.333333333333334e-06,
135
+ "loss": 1.8633,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.18627450980392157,
140
+ "grad_norm": 0.6527869701385498,
141
+ "learning_rate": 8.23529411764706e-06,
142
+ "loss": 1.7669,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.19607843137254902,
147
+ "grad_norm": 0.6449242234230042,
148
+ "learning_rate": 8.137254901960784e-06,
149
+ "loss": 1.7996,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.20588235294117646,
154
+ "grad_norm": 0.6480177044868469,
155
+ "learning_rate": 8.03921568627451e-06,
156
+ "loss": 1.7738,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.21568627450980393,
161
+ "grad_norm": 0.6246963739395142,
162
+ "learning_rate": 7.941176470588236e-06,
163
+ "loss": 1.7386,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.22549019607843138,
168
+ "grad_norm": 0.6275233626365662,
169
+ "learning_rate": 7.84313725490196e-06,
170
+ "loss": 1.8029,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.23529411764705882,
175
+ "grad_norm": 0.5825409889221191,
176
+ "learning_rate": 7.745098039215687e-06,
177
+ "loss": 1.6673,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.24509803921568626,
182
+ "grad_norm": 0.5436587929725647,
183
+ "learning_rate": 7.647058823529411e-06,
184
+ "loss": 1.6992,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.2549019607843137,
189
+ "grad_norm": 0.5287730097770691,
190
+ "learning_rate": 7.549019607843138e-06,
191
+ "loss": 1.6691,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.2647058823529412,
196
+ "grad_norm": 0.5117806792259216,
197
+ "learning_rate": 7.450980392156863e-06,
198
+ "loss": 1.6736,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.27450980392156865,
203
+ "grad_norm": 0.5041622519493103,
204
+ "learning_rate": 7.352941176470589e-06,
205
+ "loss": 1.6874,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.28431372549019607,
210
+ "grad_norm": 0.47983038425445557,
211
+ "learning_rate": 7.2549019607843145e-06,
212
+ "loss": 1.6406,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.29411764705882354,
217
+ "grad_norm": 0.4921911358833313,
218
+ "learning_rate": 7.15686274509804e-06,
219
+ "loss": 1.6127,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.30392156862745096,
224
+ "grad_norm": 0.48269519209861755,
225
+ "learning_rate": 7.058823529411766e-06,
226
+ "loss": 1.6611,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.3137254901960784,
231
+ "grad_norm": 0.5123285055160522,
232
+ "learning_rate": 6.96078431372549e-06,
233
+ "loss": 1.6019,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.3235294117647059,
238
+ "grad_norm": 0.4910086691379547,
239
+ "learning_rate": 6.862745098039216e-06,
240
+ "loss": 1.5817,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.3333333333333333,
245
+ "grad_norm": 0.49109798669815063,
246
+ "learning_rate": 6.764705882352942e-06,
247
+ "loss": 1.5944,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.3431372549019608,
252
+ "grad_norm": 0.4968704581260681,
253
+ "learning_rate": 6.666666666666667e-06,
254
+ "loss": 1.5942,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.35294117647058826,
259
+ "grad_norm": 0.47293922305107117,
260
+ "learning_rate": 6.568627450980393e-06,
261
+ "loss": 1.564,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.3627450980392157,
266
+ "grad_norm": 0.44330501556396484,
267
+ "learning_rate": 6.470588235294119e-06,
268
+ "loss": 1.5762,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.37254901960784315,
273
+ "grad_norm": 0.4455674886703491,
274
+ "learning_rate": 6.372549019607843e-06,
275
+ "loss": 1.5843,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.38235294117647056,
280
+ "grad_norm": 0.41862353682518005,
281
+ "learning_rate": 6.274509803921569e-06,
282
+ "loss": 1.5127,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.39215686274509803,
287
+ "grad_norm": 0.4261449873447418,
288
+ "learning_rate": 6.176470588235295e-06,
289
+ "loss": 1.5167,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.4019607843137255,
294
+ "grad_norm": 0.4266234040260315,
295
+ "learning_rate": 6.07843137254902e-06,
296
+ "loss": 1.5048,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.4117647058823529,
301
+ "grad_norm": 0.432207852602005,
302
+ "learning_rate": 5.980392156862746e-06,
303
+ "loss": 1.4852,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.4215686274509804,
308
+ "grad_norm": 0.40910154581069946,
309
+ "learning_rate": 5.882352941176471e-06,
310
+ "loss": 1.4988,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.43137254901960786,
315
+ "grad_norm": 0.4706984758377075,
316
+ "learning_rate": 5.784313725490197e-06,
317
+ "loss": 1.5645,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.4411764705882353,
322
+ "grad_norm": 0.40101850032806396,
323
+ "learning_rate": 5.686274509803922e-06,
324
+ "loss": 1.4994,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.45098039215686275,
329
+ "grad_norm": 0.40438491106033325,
330
+ "learning_rate": 5.588235294117647e-06,
331
+ "loss": 1.5272,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.46078431372549017,
336
+ "grad_norm": 0.39020276069641113,
337
+ "learning_rate": 5.4901960784313735e-06,
338
+ "loss": 1.4562,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.47058823529411764,
343
+ "grad_norm": 0.37909573316574097,
344
+ "learning_rate": 5.392156862745098e-06,
345
+ "loss": 1.4873,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.4803921568627451,
350
+ "grad_norm": 0.3828938603401184,
351
+ "learning_rate": 5.294117647058824e-06,
352
+ "loss": 1.4798,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.49019607843137253,
357
+ "grad_norm": 0.367044597864151,
358
+ "learning_rate": 5.19607843137255e-06,
359
+ "loss": 1.4328,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.5,
364
+ "grad_norm": 0.36673134565353394,
365
+ "learning_rate": 5.098039215686274e-06,
366
+ "loss": 1.4307,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.5098039215686274,
371
+ "grad_norm": 0.3599296808242798,
372
+ "learning_rate": 5e-06,
373
+ "loss": 1.4069,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.5196078431372549,
378
+ "grad_norm": 0.3603789806365967,
379
+ "learning_rate": 4.901960784313726e-06,
380
+ "loss": 1.4296,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.5294117647058824,
385
+ "grad_norm": 0.3620091676712036,
386
+ "learning_rate": 4.803921568627452e-06,
387
+ "loss": 1.4063,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.5392156862745098,
392
+ "grad_norm": 0.33629655838012695,
393
+ "learning_rate": 4.705882352941177e-06,
394
+ "loss": 1.421,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.5490196078431373,
399
+ "grad_norm": 0.3413692116737366,
400
+ "learning_rate": 4.607843137254902e-06,
401
+ "loss": 1.4518,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.5588235294117647,
406
+ "grad_norm": 0.3161819279193878,
407
+ "learning_rate": 4.509803921568628e-06,
408
+ "loss": 1.3914,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.5686274509803921,
413
+ "grad_norm": 0.3277413547039032,
414
+ "learning_rate": 4.411764705882353e-06,
415
+ "loss": 1.389,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.5784313725490197,
420
+ "grad_norm": 0.3128764033317566,
421
+ "learning_rate": 4.313725490196079e-06,
422
+ "loss": 1.395,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.5882352941176471,
427
+ "grad_norm": 0.31412273645401,
428
+ "learning_rate": 4.215686274509805e-06,
429
+ "loss": 1.3735,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.5980392156862745,
434
+ "grad_norm": 0.3194039762020111,
435
+ "learning_rate": 4.11764705882353e-06,
436
+ "loss": 1.4189,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.6078431372549019,
441
+ "grad_norm": 0.3120681941509247,
442
+ "learning_rate": 4.019607843137255e-06,
443
+ "loss": 1.3911,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.6176470588235294,
448
+ "grad_norm": 0.3160897493362427,
449
+ "learning_rate": 3.92156862745098e-06,
450
+ "loss": 1.3543,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.6274509803921569,
455
+ "grad_norm": 0.31680962443351746,
456
+ "learning_rate": 3.8235294117647055e-06,
457
+ "loss": 1.3603,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.6372549019607843,
462
+ "grad_norm": 0.31749823689460754,
463
+ "learning_rate": 3.7254901960784316e-06,
464
+ "loss": 1.4025,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.6470588235294118,
469
+ "grad_norm": 0.3060447573661804,
470
+ "learning_rate": 3.6274509803921573e-06,
471
+ "loss": 1.3412,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.6568627450980392,
476
+ "grad_norm": 0.3055213391780853,
477
+ "learning_rate": 3.529411764705883e-06,
478
+ "loss": 1.3913,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.6666666666666666,
483
+ "grad_norm": 0.3184523582458496,
484
+ "learning_rate": 3.431372549019608e-06,
485
+ "loss": 1.3994,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.6764705882352942,
490
+ "grad_norm": 0.30899760127067566,
491
+ "learning_rate": 3.3333333333333333e-06,
492
+ "loss": 1.3694,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.6862745098039216,
497
+ "grad_norm": 0.29854196310043335,
498
+ "learning_rate": 3.2352941176470594e-06,
499
+ "loss": 1.3715,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.696078431372549,
504
+ "grad_norm": 0.298645555973053,
505
+ "learning_rate": 3.1372549019607846e-06,
506
+ "loss": 1.3476,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.7058823529411765,
511
+ "grad_norm": 0.2904506027698517,
512
+ "learning_rate": 3.03921568627451e-06,
513
+ "loss": 1.3476,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.7156862745098039,
518
+ "grad_norm": 0.2939620912075043,
519
+ "learning_rate": 2.9411764705882355e-06,
520
+ "loss": 1.3666,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.7254901960784313,
525
+ "grad_norm": 0.29882726073265076,
526
+ "learning_rate": 2.843137254901961e-06,
527
+ "loss": 1.347,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.7352941176470589,
532
+ "grad_norm": 0.31818199157714844,
533
+ "learning_rate": 2.7450980392156867e-06,
534
+ "loss": 1.3821,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.7450980392156863,
539
+ "grad_norm": 0.29951557517051697,
540
+ "learning_rate": 2.647058823529412e-06,
541
+ "loss": 1.3443,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.7549019607843137,
546
+ "grad_norm": 0.2927483320236206,
547
+ "learning_rate": 2.549019607843137e-06,
548
+ "loss": 1.3258,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.7647058823529411,
553
+ "grad_norm": 0.2869877219200134,
554
+ "learning_rate": 2.450980392156863e-06,
555
+ "loss": 1.3304,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.7745098039215687,
560
+ "grad_norm": 0.29732242226600647,
561
+ "learning_rate": 2.3529411764705885e-06,
562
+ "loss": 1.3465,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.7843137254901961,
567
+ "grad_norm": 0.30281081795692444,
568
+ "learning_rate": 2.254901960784314e-06,
569
+ "loss": 1.319,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.7941176470588235,
574
+ "grad_norm": 0.2886880040168762,
575
+ "learning_rate": 2.1568627450980393e-06,
576
+ "loss": 1.3312,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.803921568627451,
581
+ "grad_norm": 0.29117289185523987,
582
+ "learning_rate": 2.058823529411765e-06,
583
+ "loss": 1.3463,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.8137254901960784,
588
+ "grad_norm": 0.28929680585861206,
589
+ "learning_rate": 1.96078431372549e-06,
590
+ "loss": 1.3469,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.8235294117647058,
595
+ "grad_norm": 0.28210750222206116,
596
+ "learning_rate": 1.8627450980392158e-06,
597
+ "loss": 1.3329,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.8333333333333334,
602
+ "grad_norm": 0.282003790140152,
603
+ "learning_rate": 1.7647058823529414e-06,
604
+ "loss": 1.2958,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.8431372549019608,
609
+ "grad_norm": 0.3041072487831116,
610
+ "learning_rate": 1.6666666666666667e-06,
611
+ "loss": 1.3422,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.8529411764705882,
616
+ "grad_norm": 0.28907510638237,
617
+ "learning_rate": 1.5686274509803923e-06,
618
+ "loss": 1.355,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.8627450980392157,
623
+ "grad_norm": 0.28159913420677185,
624
+ "learning_rate": 1.4705882352941177e-06,
625
+ "loss": 1.3366,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.8725490196078431,
630
+ "grad_norm": 0.28043174743652344,
631
+ "learning_rate": 1.3725490196078434e-06,
632
+ "loss": 1.3384,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.8823529411764706,
637
+ "grad_norm": 0.29932349920272827,
638
+ "learning_rate": 1.2745098039215686e-06,
639
+ "loss": 1.2866,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.8921568627450981,
644
+ "grad_norm": 0.2869769036769867,
645
+ "learning_rate": 1.1764705882352942e-06,
646
+ "loss": 1.3329,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.9019607843137255,
651
+ "grad_norm": 0.27412521839141846,
652
+ "learning_rate": 1.0784313725490197e-06,
653
+ "loss": 1.3273,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.9117647058823529,
658
+ "grad_norm": 0.291384220123291,
659
+ "learning_rate": 9.80392156862745e-07,
660
+ "loss": 1.3566,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.9215686274509803,
665
+ "grad_norm": 0.28981104493141174,
666
+ "learning_rate": 8.823529411764707e-07,
667
+ "loss": 1.3279,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.9313725490196079,
672
+ "grad_norm": 0.28091126680374146,
673
+ "learning_rate": 7.843137254901962e-07,
674
+ "loss": 1.2947,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.9411764705882353,
679
+ "grad_norm": 0.28839319944381714,
680
+ "learning_rate": 6.862745098039217e-07,
681
+ "loss": 1.3098,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.9509803921568627,
686
+ "grad_norm": 0.27996671199798584,
687
+ "learning_rate": 5.882352941176471e-07,
688
+ "loss": 1.3001,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.9607843137254902,
693
+ "grad_norm": 0.27735868096351624,
694
+ "learning_rate": 4.901960784313725e-07,
695
+ "loss": 1.3123,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.9705882352941176,
700
+ "grad_norm": 0.2749045193195343,
701
+ "learning_rate": 3.921568627450981e-07,
702
+ "loss": 1.3244,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.9803921568627451,
707
+ "grad_norm": 0.28808385133743286,
708
+ "learning_rate": 2.9411764705882356e-07,
709
+ "loss": 1.2847,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.9901960784313726,
714
+ "grad_norm": 0.28120607137680054,
715
+ "learning_rate": 1.9607843137254904e-07,
716
+ "loss": 1.2952,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 1.0,
721
+ "grad_norm": 0.2849506437778473,
722
+ "learning_rate": 9.803921568627452e-08,
723
+ "loss": 1.3353,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 1.0,
728
+ "eval_loss": 1.329064965248108,
729
+ "eval_runtime": 2.3109,
730
+ "eval_samples_per_second": 6.491,
731
+ "eval_steps_per_second": 0.865,
732
+ "step": 102
733
+ }
734
+ ],
735
+ "logging_steps": 1.0,
736
+ "max_steps": 102,
737
+ "num_input_tokens_seen": 0,
738
+ "num_train_epochs": 1,
739
+ "save_steps": 0,
740
+ "stateful_callbacks": {
741
+ "TrainerControl": {
742
+ "args": {
743
+ "should_epoch_stop": false,
744
+ "should_evaluate": false,
745
+ "should_log": false,
746
+ "should_save": true,
747
+ "should_training_stop": true
748
+ },
749
+ "attributes": {}
750
+ }
751
+ },
752
+ "total_flos": 1.1010882465169408e+17,
753
+ "train_batch_size": 1,
754
+ "trial_name": null,
755
+ "trial_params": null
756
+ }