appvoid commited on
Commit
2152534
1 Parent(s): 1da9397

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[BOS]": 32001,
3
+ "[EOS]": 32002,
4
+ "[PAD]": 32000
5
+ }
checkpoint-1687/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "appvoid/arco-mini-run-2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1536,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.45.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32003
32
+ }
checkpoint-1687/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.45.1"
7
+ }
checkpoint-1687/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9d27ac4b295e4746555823edebfe9e7fba8277f49704ed1b90b09f0bca4b24
3
+ size 997345472
checkpoint-1687/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20dbe3427785d24816e157e6103f4212a3b982bff3365373a75f7e0cf334b1c
3
+ size 1994737722
checkpoint-1687/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
checkpoint-1687/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607c2a40623d630951be1e137e8a77a03c45e2b37089ed9decc753aa53bdeaa1
3
+ size 1064
checkpoint-1687/trainer_state.json ADDED
@@ -0,0 +1,1209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997037037037036,
5
+ "eval_steps": 5000,
6
+ "global_step": 1687,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005925925925925926,
13
+ "grad_norm": 0.5658125281333923,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.9859,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.011851851851851851,
20
+ "grad_norm": 0.4840392470359802,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.9552,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.017777777777777778,
27
+ "grad_norm": 0.5106642246246338,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.8641,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.023703703703703703,
34
+ "grad_norm": 0.3882107436656952,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.8952,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.02962962962962963,
41
+ "grad_norm": 0.5257787704467773,
42
+ "learning_rate": 1e-05,
43
+ "loss": 2.0206,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.035555555555555556,
48
+ "grad_norm": 0.466878741979599,
49
+ "learning_rate": 1.2e-05,
50
+ "loss": 1.8342,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.04148148148148148,
55
+ "grad_norm": 0.5169644355773926,
56
+ "learning_rate": 1.4000000000000001e-05,
57
+ "loss": 1.9108,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.047407407407407405,
62
+ "grad_norm": 0.5135151743888855,
63
+ "learning_rate": 1.6000000000000003e-05,
64
+ "loss": 2.0776,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.05333333333333334,
69
+ "grad_norm": 0.6329066157341003,
70
+ "learning_rate": 1.8e-05,
71
+ "loss": 2.0294,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.05925925925925926,
76
+ "grad_norm": 0.5724173188209534,
77
+ "learning_rate": 2e-05,
78
+ "loss": 2.0369,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.06518518518518518,
83
+ "grad_norm": 0.6717743277549744,
84
+ "learning_rate": 2.2000000000000003e-05,
85
+ "loss": 2.0009,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.07111111111111111,
90
+ "grad_norm": 0.7047879099845886,
91
+ "learning_rate": 2.4e-05,
92
+ "loss": 2.1022,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.07703703703703704,
97
+ "grad_norm": 0.5536562204360962,
98
+ "learning_rate": 2.6000000000000002e-05,
99
+ "loss": 1.9473,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.08296296296296296,
104
+ "grad_norm": 0.7499417066574097,
105
+ "learning_rate": 2.8000000000000003e-05,
106
+ "loss": 1.8281,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.08888888888888889,
111
+ "grad_norm": 0.767043948173523,
112
+ "learning_rate": 3e-05,
113
+ "loss": 2.0454,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.09481481481481481,
118
+ "grad_norm": 0.717535138130188,
119
+ "learning_rate": 3.2000000000000005e-05,
120
+ "loss": 1.9561,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.10074074074074074,
125
+ "grad_norm": 0.6414211392402649,
126
+ "learning_rate": 3.4000000000000007e-05,
127
+ "loss": 1.9112,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.10666666666666667,
132
+ "grad_norm": 0.6495911478996277,
133
+ "learning_rate": 3.6e-05,
134
+ "loss": 1.96,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.11259259259259259,
139
+ "grad_norm": 0.6383408308029175,
140
+ "learning_rate": 3.8e-05,
141
+ "loss": 1.9678,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.11851851851851852,
146
+ "grad_norm": 0.5086091756820679,
147
+ "learning_rate": 4e-05,
148
+ "loss": 1.863,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.12444444444444444,
153
+ "grad_norm": 0.6146989464759827,
154
+ "learning_rate": 4.2e-05,
155
+ "loss": 1.8957,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.13037037037037036,
160
+ "grad_norm": 0.8208276629447937,
161
+ "learning_rate": 4.4000000000000006e-05,
162
+ "loss": 1.8206,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.1362962962962963,
167
+ "grad_norm": 0.7568028569221497,
168
+ "learning_rate": 4.600000000000001e-05,
169
+ "loss": 1.952,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.14222222222222222,
174
+ "grad_norm": 0.7779513597488403,
175
+ "learning_rate": 4.8e-05,
176
+ "loss": 2.037,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.14814814814814814,
181
+ "grad_norm": 0.6543411016464233,
182
+ "learning_rate": 5e-05,
183
+ "loss": 1.9939,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.15407407407407409,
188
+ "grad_norm": 0.6476520895957947,
189
+ "learning_rate": 5.2000000000000004e-05,
190
+ "loss": 1.8528,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.16,
195
+ "grad_norm": 0.5776610374450684,
196
+ "learning_rate": 5.4000000000000005e-05,
197
+ "loss": 2.0216,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.16592592592592592,
202
+ "grad_norm": 0.6913073658943176,
203
+ "learning_rate": 5.6000000000000006e-05,
204
+ "loss": 2.0332,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.17185185185185184,
209
+ "grad_norm": 0.7126554250717163,
210
+ "learning_rate": 5.8e-05,
211
+ "loss": 2.071,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.17777777777777778,
216
+ "grad_norm": 0.7475311756134033,
217
+ "learning_rate": 6e-05,
218
+ "loss": 2.0481,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.1837037037037037,
223
+ "grad_norm": 0.6156488656997681,
224
+ "learning_rate": 6.2e-05,
225
+ "loss": 2.0077,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.18962962962962962,
230
+ "grad_norm": 0.6974404454231262,
231
+ "learning_rate": 6.400000000000001e-05,
232
+ "loss": 2.0649,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.19555555555555557,
237
+ "grad_norm": 0.6685057282447815,
238
+ "learning_rate": 6.6e-05,
239
+ "loss": 2.0685,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.20148148148148148,
244
+ "grad_norm": 0.5366894006729126,
245
+ "learning_rate": 6.800000000000001e-05,
246
+ "loss": 1.8826,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.2074074074074074,
251
+ "grad_norm": 0.6276523470878601,
252
+ "learning_rate": 7e-05,
253
+ "loss": 1.9935,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.21333333333333335,
258
+ "grad_norm": 0.5763794779777527,
259
+ "learning_rate": 7.2e-05,
260
+ "loss": 1.7043,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.21925925925925926,
265
+ "grad_norm": 0.7299754023551941,
266
+ "learning_rate": 7.4e-05,
267
+ "loss": 1.9996,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.22518518518518518,
272
+ "grad_norm": 0.7397586107254028,
273
+ "learning_rate": 7.6e-05,
274
+ "loss": 2.0128,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.2311111111111111,
279
+ "grad_norm": 0.5862900614738464,
280
+ "learning_rate": 7.800000000000001e-05,
281
+ "loss": 1.8096,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.23703703703703705,
286
+ "grad_norm": 0.5037183165550232,
287
+ "learning_rate": 8e-05,
288
+ "loss": 2.0381,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.24296296296296296,
293
+ "grad_norm": 0.5471982359886169,
294
+ "learning_rate": 8.2e-05,
295
+ "loss": 1.9769,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.24888888888888888,
300
+ "grad_norm": 0.6831430792808533,
301
+ "learning_rate": 8.4e-05,
302
+ "loss": 2.0524,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.2548148148148148,
307
+ "grad_norm": 0.7648348808288574,
308
+ "learning_rate": 8.6e-05,
309
+ "loss": 2.0836,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.2607407407407407,
314
+ "grad_norm": 0.7717330455780029,
315
+ "learning_rate": 8.800000000000001e-05,
316
+ "loss": 2.0693,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.26666666666666666,
321
+ "grad_norm": 0.6415191292762756,
322
+ "learning_rate": 9e-05,
323
+ "loss": 2.0827,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.2725925925925926,
328
+ "grad_norm": 0.6595004796981812,
329
+ "learning_rate": 9.200000000000001e-05,
330
+ "loss": 1.7722,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.2785185185185185,
335
+ "grad_norm": 0.6670510768890381,
336
+ "learning_rate": 9.4e-05,
337
+ "loss": 2.0679,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.28444444444444444,
342
+ "grad_norm": 0.6167762875556946,
343
+ "learning_rate": 9.6e-05,
344
+ "loss": 2.1062,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.2903703703703704,
349
+ "grad_norm": 0.657123863697052,
350
+ "learning_rate": 9.8e-05,
351
+ "loss": 1.9496,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.2962962962962963,
356
+ "grad_norm": 0.7975080013275146,
357
+ "learning_rate": 0.0001,
358
+ "loss": 2.0326,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.3022222222222222,
363
+ "grad_norm": 0.5824917554855347,
364
+ "learning_rate": 9.91575400168492e-05,
365
+ "loss": 1.9284,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.30814814814814817,
370
+ "grad_norm": 0.608211874961853,
371
+ "learning_rate": 9.83150800336984e-05,
372
+ "loss": 1.955,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.31407407407407406,
377
+ "grad_norm": 0.6209816336631775,
378
+ "learning_rate": 9.74726200505476e-05,
379
+ "loss": 2.0276,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.32,
384
+ "grad_norm": 0.5495818853378296,
385
+ "learning_rate": 9.66301600673968e-05,
386
+ "loss": 1.9229,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.32592592592592595,
391
+ "grad_norm": 0.5053668022155762,
392
+ "learning_rate": 9.5787700084246e-05,
393
+ "loss": 1.8056,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.33185185185185184,
398
+ "grad_norm": 0.518039882183075,
399
+ "learning_rate": 9.49452401010952e-05,
400
+ "loss": 1.9308,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.3377777777777778,
405
+ "grad_norm": 0.6717711687088013,
406
+ "learning_rate": 9.41027801179444e-05,
407
+ "loss": 1.9352,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.3437037037037037,
412
+ "grad_norm": 0.7411617636680603,
413
+ "learning_rate": 9.32603201347936e-05,
414
+ "loss": 2.0059,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.3496296296296296,
419
+ "grad_norm": 0.48582813143730164,
420
+ "learning_rate": 9.24178601516428e-05,
421
+ "loss": 1.8693,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.35555555555555557,
426
+ "grad_norm": 0.5219349265098572,
427
+ "learning_rate": 9.1575400168492e-05,
428
+ "loss": 1.9478,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.36148148148148146,
433
+ "grad_norm": 0.6107354760169983,
434
+ "learning_rate": 9.07329401853412e-05,
435
+ "loss": 1.9171,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.3674074074074074,
440
+ "grad_norm": 0.6376306414604187,
441
+ "learning_rate": 8.98904802021904e-05,
442
+ "loss": 2.0132,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.37333333333333335,
447
+ "grad_norm": 0.5478475093841553,
448
+ "learning_rate": 8.90480202190396e-05,
449
+ "loss": 1.863,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.37925925925925924,
454
+ "grad_norm": 0.5968965291976929,
455
+ "learning_rate": 8.82055602358888e-05,
456
+ "loss": 1.9489,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.3851851851851852,
461
+ "grad_norm": 0.6038496494293213,
462
+ "learning_rate": 8.736310025273799e-05,
463
+ "loss": 1.7222,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.39111111111111113,
468
+ "grad_norm": 0.5897707343101501,
469
+ "learning_rate": 8.652064026958719e-05,
470
+ "loss": 1.951,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.397037037037037,
475
+ "grad_norm": 0.5143914222717285,
476
+ "learning_rate": 8.567818028643639e-05,
477
+ "loss": 2.0544,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.40296296296296297,
482
+ "grad_norm": 0.5237649083137512,
483
+ "learning_rate": 8.483572030328559e-05,
484
+ "loss": 2.002,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.4088888888888889,
489
+ "grad_norm": 0.6607901453971863,
490
+ "learning_rate": 8.399326032013479e-05,
491
+ "loss": 1.968,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.4148148148148148,
496
+ "grad_norm": 0.816532552242279,
497
+ "learning_rate": 8.3150800336984e-05,
498
+ "loss": 1.8108,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.42074074074074075,
503
+ "grad_norm": 0.5817467570304871,
504
+ "learning_rate": 8.23083403538332e-05,
505
+ "loss": 1.9755,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.4266666666666667,
510
+ "grad_norm": 0.5732384324073792,
511
+ "learning_rate": 8.146588037068241e-05,
512
+ "loss": 1.9885,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.4325925925925926,
517
+ "grad_norm": 0.7058317065238953,
518
+ "learning_rate": 8.06234203875316e-05,
519
+ "loss": 2.0017,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.43851851851851853,
524
+ "grad_norm": 0.589218258857727,
525
+ "learning_rate": 7.97809604043808e-05,
526
+ "loss": 2.094,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.4444444444444444,
531
+ "grad_norm": 0.4636491537094116,
532
+ "learning_rate": 7.893850042123e-05,
533
+ "loss": 1.8869,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.45037037037037037,
538
+ "grad_norm": 0.6695517301559448,
539
+ "learning_rate": 7.80960404380792e-05,
540
+ "loss": 1.8622,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.4562962962962963,
545
+ "grad_norm": 0.545862078666687,
546
+ "learning_rate": 7.72535804549284e-05,
547
+ "loss": 1.7885,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.4622222222222222,
552
+ "grad_norm": 0.7133297920227051,
553
+ "learning_rate": 7.64111204717776e-05,
554
+ "loss": 2.1167,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.46814814814814815,
559
+ "grad_norm": 0.5214343667030334,
560
+ "learning_rate": 7.55686604886268e-05,
561
+ "loss": 1.9065,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.4740740740740741,
566
+ "grad_norm": 0.46373251080513,
567
+ "learning_rate": 7.4726200505476e-05,
568
+ "loss": 1.8037,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.48,
573
+ "grad_norm": 0.646965742111206,
574
+ "learning_rate": 7.388374052232519e-05,
575
+ "loss": 1.7713,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.48592592592592593,
580
+ "grad_norm": 0.5974875092506409,
581
+ "learning_rate": 7.304128053917439e-05,
582
+ "loss": 1.7497,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.4918518518518519,
587
+ "grad_norm": 0.5363378524780273,
588
+ "learning_rate": 7.219882055602359e-05,
589
+ "loss": 1.8432,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.49777777777777776,
594
+ "grad_norm": 0.5419060587882996,
595
+ "learning_rate": 7.135636057287279e-05,
596
+ "loss": 1.8984,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.5037037037037037,
601
+ "grad_norm": 0.5365799069404602,
602
+ "learning_rate": 7.0513900589722e-05,
603
+ "loss": 1.9747,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.5096296296296297,
608
+ "grad_norm": 0.5691491365432739,
609
+ "learning_rate": 6.96714406065712e-05,
610
+ "loss": 2.0097,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.5155555555555555,
615
+ "grad_norm": 0.4764457643032074,
616
+ "learning_rate": 6.88289806234204e-05,
617
+ "loss": 2.0322,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.5214814814814814,
622
+ "grad_norm": 0.532008707523346,
623
+ "learning_rate": 6.79865206402696e-05,
624
+ "loss": 1.8917,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.5274074074074074,
629
+ "grad_norm": 0.6209381818771362,
630
+ "learning_rate": 6.714406065711879e-05,
631
+ "loss": 1.9184,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.5333333333333333,
636
+ "grad_norm": 0.5349578857421875,
637
+ "learning_rate": 6.630160067396799e-05,
638
+ "loss": 1.8408,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.5392592592592592,
643
+ "grad_norm": 0.5553748607635498,
644
+ "learning_rate": 6.545914069081719e-05,
645
+ "loss": 2.0037,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.5451851851851852,
650
+ "grad_norm": 0.5438774228096008,
651
+ "learning_rate": 6.461668070766639e-05,
652
+ "loss": 1.9709,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.5511111111111111,
657
+ "grad_norm": 0.5479866862297058,
658
+ "learning_rate": 6.377422072451559e-05,
659
+ "loss": 2.0121,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.557037037037037,
664
+ "grad_norm": 0.479965478181839,
665
+ "learning_rate": 6.293176074136478e-05,
666
+ "loss": 1.7643,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.562962962962963,
671
+ "grad_norm": 0.41314756870269775,
672
+ "learning_rate": 6.208930075821398e-05,
673
+ "loss": 1.9746,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.5688888888888889,
678
+ "grad_norm": 0.5965597629547119,
679
+ "learning_rate": 6.124684077506318e-05,
680
+ "loss": 1.9464,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.5748148148148148,
685
+ "grad_norm": 0.5767338275909424,
686
+ "learning_rate": 6.0404380791912386e-05,
687
+ "loss": 1.9955,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.5807407407407408,
692
+ "grad_norm": 0.5822139978408813,
693
+ "learning_rate": 5.9561920808761584e-05,
694
+ "loss": 1.9824,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.5866666666666667,
699
+ "grad_norm": 0.5352127552032471,
700
+ "learning_rate": 5.871946082561078e-05,
701
+ "loss": 2.0282,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5925925925925926,
706
+ "grad_norm": 0.4747357964515686,
707
+ "learning_rate": 5.787700084245998e-05,
708
+ "loss": 1.9458,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.5985185185185186,
713
+ "grad_norm": 0.6914563775062561,
714
+ "learning_rate": 5.703454085930918e-05,
715
+ "loss": 1.8725,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.6044444444444445,
720
+ "grad_norm": 0.5494988560676575,
721
+ "learning_rate": 5.6192080876158384e-05,
722
+ "loss": 1.986,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.6103703703703703,
727
+ "grad_norm": 0.5098171830177307,
728
+ "learning_rate": 5.534962089300758e-05,
729
+ "loss": 1.8683,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.6162962962962963,
734
+ "grad_norm": 0.6599770784378052,
735
+ "learning_rate": 5.450716090985678e-05,
736
+ "loss": 1.7654,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.6222222222222222,
741
+ "grad_norm": 0.6061760783195496,
742
+ "learning_rate": 5.366470092670598e-05,
743
+ "loss": 1.9257,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.6281481481481481,
748
+ "grad_norm": 0.4598886966705322,
749
+ "learning_rate": 5.282224094355518e-05,
750
+ "loss": 1.8542,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.6340740740740741,
755
+ "grad_norm": 0.7132225632667542,
756
+ "learning_rate": 5.1979780960404376e-05,
757
+ "loss": 1.878,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.64,
762
+ "grad_norm": 0.47084617614746094,
763
+ "learning_rate": 5.113732097725358e-05,
764
+ "loss": 1.785,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.6459259259259259,
769
+ "grad_norm": 0.4628468453884125,
770
+ "learning_rate": 5.029486099410278e-05,
771
+ "loss": 1.6897,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.6518518518518519,
776
+ "grad_norm": 0.4679886996746063,
777
+ "learning_rate": 4.9452401010951984e-05,
778
+ "loss": 1.7765,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.6577777777777778,
783
+ "grad_norm": 0.6136245727539062,
784
+ "learning_rate": 4.860994102780118e-05,
785
+ "loss": 1.7136,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.6637037037037037,
790
+ "grad_norm": 0.5701176524162292,
791
+ "learning_rate": 4.776748104465038e-05,
792
+ "loss": 1.9895,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.6696296296296296,
797
+ "grad_norm": 0.5996720194816589,
798
+ "learning_rate": 4.692502106149958e-05,
799
+ "loss": 1.9563,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.6755555555555556,
804
+ "grad_norm": 0.5536661744117737,
805
+ "learning_rate": 4.608256107834878e-05,
806
+ "loss": 1.8388,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.6814814814814815,
811
+ "grad_norm": 0.47468143701553345,
812
+ "learning_rate": 4.5240101095197975e-05,
813
+ "loss": 1.8644,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.6874074074074074,
818
+ "grad_norm": 0.5488613843917847,
819
+ "learning_rate": 4.439764111204718e-05,
820
+ "loss": 1.8448,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.6933333333333334,
825
+ "grad_norm": 0.5627337098121643,
826
+ "learning_rate": 4.355518112889638e-05,
827
+ "loss": 1.8129,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.6992592592592592,
832
+ "grad_norm": 0.5869198441505432,
833
+ "learning_rate": 4.271272114574558e-05,
834
+ "loss": 1.8029,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.7051851851851851,
839
+ "grad_norm": 0.5446140170097351,
840
+ "learning_rate": 4.1870261162594775e-05,
841
+ "loss": 1.7783,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.7111111111111111,
846
+ "grad_norm": 0.6113932728767395,
847
+ "learning_rate": 4.102780117944398e-05,
848
+ "loss": 1.7782,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.717037037037037,
853
+ "grad_norm": 0.49301135540008545,
854
+ "learning_rate": 4.018534119629318e-05,
855
+ "loss": 1.7719,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.7229629629629629,
860
+ "grad_norm": 0.6062334179878235,
861
+ "learning_rate": 3.934288121314238e-05,
862
+ "loss": 1.8681,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.7288888888888889,
867
+ "grad_norm": 0.4924413561820984,
868
+ "learning_rate": 3.850042122999158e-05,
869
+ "loss": 1.7276,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.7348148148148148,
874
+ "grad_norm": 0.5645489692687988,
875
+ "learning_rate": 3.765796124684078e-05,
876
+ "loss": 1.8095,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.7407407407407407,
881
+ "grad_norm": 0.5494862198829651,
882
+ "learning_rate": 3.681550126368998e-05,
883
+ "loss": 1.9272,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.7466666666666667,
888
+ "grad_norm": 0.45363616943359375,
889
+ "learning_rate": 3.597304128053918e-05,
890
+ "loss": 1.6991,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.7525925925925926,
895
+ "grad_norm": 0.5172736644744873,
896
+ "learning_rate": 3.5130581297388375e-05,
897
+ "loss": 1.6942,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.7585185185185185,
902
+ "grad_norm": 0.5237290859222412,
903
+ "learning_rate": 3.4288121314237574e-05,
904
+ "loss": 1.834,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.7644444444444445,
909
+ "grad_norm": 0.685662031173706,
910
+ "learning_rate": 3.344566133108677e-05,
911
+ "loss": 1.6324,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.7703703703703704,
916
+ "grad_norm": 0.5649334192276001,
917
+ "learning_rate": 3.260320134793598e-05,
918
+ "loss": 1.9939,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.7762962962962963,
923
+ "grad_norm": 0.5103081464767456,
924
+ "learning_rate": 3.1760741364785175e-05,
925
+ "loss": 1.7158,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.7822222222222223,
930
+ "grad_norm": 0.5990691781044006,
931
+ "learning_rate": 3.0918281381634374e-05,
932
+ "loss": 1.8249,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.7881481481481482,
937
+ "grad_norm": 0.4889729917049408,
938
+ "learning_rate": 3.0075821398483572e-05,
939
+ "loss": 2.0304,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.794074074074074,
944
+ "grad_norm": 0.5077411532402039,
945
+ "learning_rate": 2.923336141533277e-05,
946
+ "loss": 1.8993,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.8,
951
+ "grad_norm": 0.4161909818649292,
952
+ "learning_rate": 2.8390901432181972e-05,
953
+ "loss": 1.8544,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.8059259259259259,
958
+ "grad_norm": 0.3950774669647217,
959
+ "learning_rate": 2.754844144903117e-05,
960
+ "loss": 1.9056,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.8118518518518518,
965
+ "grad_norm": 0.4794867932796478,
966
+ "learning_rate": 2.670598146588037e-05,
967
+ "loss": 1.9091,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.8177777777777778,
972
+ "grad_norm": 0.5798467397689819,
973
+ "learning_rate": 2.586352148272957e-05,
974
+ "loss": 1.7677,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.8237037037037037,
979
+ "grad_norm": 0.42939475178718567,
980
+ "learning_rate": 2.502106149957877e-05,
981
+ "loss": 1.4855,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.8296296296296296,
986
+ "grad_norm": 0.5029926300048828,
987
+ "learning_rate": 2.417860151642797e-05,
988
+ "loss": 1.7523,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.8355555555555556,
993
+ "grad_norm": 0.5045111775398254,
994
+ "learning_rate": 2.333614153327717e-05,
995
+ "loss": 1.7036,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.8414814814814815,
1000
+ "grad_norm": 0.45949357748031616,
1001
+ "learning_rate": 2.249368155012637e-05,
1002
+ "loss": 1.7477,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.8474074074074074,
1007
+ "grad_norm": 0.6068927645683289,
1008
+ "learning_rate": 2.165122156697557e-05,
1009
+ "loss": 1.7256,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.8533333333333334,
1014
+ "grad_norm": 0.47375020384788513,
1015
+ "learning_rate": 2.080876158382477e-05,
1016
+ "loss": 1.6821,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.8592592592592593,
1021
+ "grad_norm": 0.6090928316116333,
1022
+ "learning_rate": 1.996630160067397e-05,
1023
+ "loss": 1.7821,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.8651851851851852,
1028
+ "grad_norm": 0.4479965567588806,
1029
+ "learning_rate": 1.912384161752317e-05,
1030
+ "loss": 1.7752,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.8711111111111111,
1035
+ "grad_norm": 0.502055287361145,
1036
+ "learning_rate": 1.828138163437237e-05,
1037
+ "loss": 1.7502,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.8770370370370371,
1042
+ "grad_norm": 0.5576585531234741,
1043
+ "learning_rate": 1.7438921651221567e-05,
1044
+ "loss": 1.7943,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.882962962962963,
1049
+ "grad_norm": 0.443153977394104,
1050
+ "learning_rate": 1.659646166807077e-05,
1051
+ "loss": 1.7002,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.8888888888888888,
1056
+ "grad_norm": 0.5595043301582336,
1057
+ "learning_rate": 1.5754001684919967e-05,
1058
+ "loss": 1.8032,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.8948148148148148,
1063
+ "grad_norm": 0.5037031769752502,
1064
+ "learning_rate": 1.4911541701769167e-05,
1065
+ "loss": 1.9339,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.9007407407407407,
1070
+ "grad_norm": 0.592262327671051,
1071
+ "learning_rate": 1.4069081718618365e-05,
1072
+ "loss": 1.7636,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.9066666666666666,
1077
+ "grad_norm": 0.48528340458869934,
1078
+ "learning_rate": 1.3226621735467565e-05,
1079
+ "loss": 1.5757,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.9125925925925926,
1084
+ "grad_norm": 0.5274297595024109,
1085
+ "learning_rate": 1.2384161752316765e-05,
1086
+ "loss": 1.7721,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.9185185185185185,
1091
+ "grad_norm": 0.5855200886726379,
1092
+ "learning_rate": 1.1541701769165965e-05,
1093
+ "loss": 1.8039,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.9244444444444444,
1098
+ "grad_norm": 0.46873489022254944,
1099
+ "learning_rate": 1.0699241786015165e-05,
1100
+ "loss": 1.7628,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.9303703703703704,
1105
+ "grad_norm": 0.4692378044128418,
1106
+ "learning_rate": 9.856781802864365e-06,
1107
+ "loss": 1.6898,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.9362962962962963,
1112
+ "grad_norm": 0.4950474500656128,
1113
+ "learning_rate": 9.014321819713565e-06,
1114
+ "loss": 1.882,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.9422222222222222,
1119
+ "grad_norm": 0.5897673964500427,
1120
+ "learning_rate": 8.171861836562763e-06,
1121
+ "loss": 1.8277,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.9481481481481482,
1126
+ "grad_norm": 0.5677273273468018,
1127
+ "learning_rate": 7.329401853411963e-06,
1128
+ "loss": 1.771,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.9540740740740741,
1133
+ "grad_norm": 1.664191484451294,
1134
+ "learning_rate": 6.4869418702611624e-06,
1135
+ "loss": 1.7564,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.96,
1140
+ "grad_norm": 0.45749393105506897,
1141
+ "learning_rate": 5.644481887110362e-06,
1142
+ "loss": 1.7552,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.965925925925926,
1147
+ "grad_norm": 0.6322038769721985,
1148
+ "learning_rate": 4.802021903959562e-06,
1149
+ "loss": 2.0075,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.9718518518518519,
1154
+ "grad_norm": 0.5579991340637207,
1155
+ "learning_rate": 3.9595619208087616e-06,
1156
+ "loss": 1.8782,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.9777777777777777,
1161
+ "grad_norm": 0.48121675848960876,
1162
+ "learning_rate": 3.1171019376579616e-06,
1163
+ "loss": 1.7393,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.9837037037037037,
1168
+ "grad_norm": 0.5826757550239563,
1169
+ "learning_rate": 2.274641954507161e-06,
1170
+ "loss": 2.0148,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.9896296296296296,
1175
+ "grad_norm": 0.513190746307373,
1176
+ "learning_rate": 1.4321819713563607e-06,
1177
+ "loss": 1.6227,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.9955555555555555,
1182
+ "grad_norm": 0.5289293527603149,
1183
+ "learning_rate": 5.897219882055603e-07,
1184
+ "loss": 1.7117,
1185
+ "step": 1680
1186
+ }
1187
+ ],
1188
+ "logging_steps": 10,
1189
+ "max_steps": 1687,
1190
+ "num_input_tokens_seen": 0,
1191
+ "num_train_epochs": 1,
1192
+ "save_steps": 5000,
1193
+ "stateful_callbacks": {
1194
+ "TrainerControl": {
1195
+ "args": {
1196
+ "should_epoch_stop": false,
1197
+ "should_evaluate": false,
1198
+ "should_log": false,
1199
+ "should_save": true,
1200
+ "should_training_stop": true
1201
+ },
1202
+ "attributes": {}
1203
+ }
1204
+ },
1205
+ "total_flos": 6.639446638618214e+16,
1206
+ "train_batch_size": 4,
1207
+ "trial_name": null,
1208
+ "trial_params": null
1209
+ }
checkpoint-1687/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f379789a412824aa75f55527d6dd364a65b19a1b15e49a719ab8565c81e3a1
3
+ size 5176
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "appvoid/arco-mini-run-2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1536,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.45.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32003
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.45.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9d27ac4b295e4746555823edebfe9e7fba8277f49704ed1b90b09f0bca4b24
3
+ size 997345472
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[EOS]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "[BOS]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "[EOS]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "additional_special_tokens": [],
56
+ "bos_token": "[BOS]",
57
+ "clean_up_tokenization_spaces": false,
58
+ "cls_token": "</s>",
59
+ "eos_token": "[EOS]",
60
+ "legacy": true,
61
+ "model_max_length": 1000000000000000019884624838656,
62
+ "pad_token": "[PAD]",
63
+ "sep_token": "</s>",
64
+ "sp_model_kwargs": {},
65
+ "spaces_between_special_tokens": false,
66
+ "tokenizer_class": "LlamaTokenizer",
67
+ "unk_token": "<unk>",
68
+ "use_default_system_prompt": false
69
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f379789a412824aa75f55527d6dd364a65b19a1b15e49a719ab8565c81e3a1
3
+ size 5176