yunlong10 commited on
Commit
cba5264
·
1 Parent(s): d9a468d

Add model checkpoint folders

Browse files
clip/ViT-L-14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cca3fd41ae0c99ba7e8951adf17d267cdb84cd88be6f7c2e0eca1737a03836
3
+ size 932768134
llava-vicuna-v1-5-7b-stage1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./data/vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "mm_use_im_patch_token": false,
15
+ "mm_use_im_start_end": false,
16
+ "model_type": "V2XumLLM",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.31.0",
27
+ "tune_mm_mlp_adapter": true,
28
+ "use_cache": true,
29
+ "use_mm_proj": true,
30
+ "vocab_size": 32000
31
+ }
llava-vicuna-v1-5-7b-stage1/mm_projector.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043423537642223cc822233553f5227b03df5b111fd5f8bf19b68c3f8a54873b
3
+ size 6300731
llava-vicuna-v1-5-7b-stage1/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
v2xumllm-vicuna-v1-5-7b-stage2-e2/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
v2xumllm-vicuna-v1-5-7b-stage2-e2/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 128,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "up_proj",
18
+ "k_proj",
19
+ "v_proj",
20
+ "gate_proj",
21
+ "o_proj",
22
+ "down_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
v2xumllm-vicuna-v1-5-7b-stage2-e2/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34657f67c9e078949cd381d90b19750c974ac41afe95130dc1152565f5ea4557
3
+ size 319971402
v2xumllm-vicuna-v1-5-7b-stage2-e2/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmsys/vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": true,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "V2XumLLM",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.31.0",
25
+ "tune_mm_mlp_adapter": false,
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
v2xumllm-vicuna-v1-5-7b-stage2-e2/non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
3
+ size 912
v2xumllm-vicuna-v1-5-7b-stage2-e2/trainer_state.json ADDED
@@ -0,0 +1,961 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9952038369304557,
5
+ "global_step": 156,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 2e-05,
13
+ "loss": 3.5587,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4e-05,
19
+ "loss": 3.4889,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 6e-05,
25
+ "loss": 3.4863,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 8e-05,
31
+ "loss": 2.8639,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 0.0001,
37
+ "loss": 2.2722,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "learning_rate": 9.998917893031616e-05,
43
+ "loss": 1.6969,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.09,
48
+ "learning_rate": 9.995672040508655e-05,
49
+ "loss": 1.2651,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.1,
54
+ "learning_rate": 9.990263847374976e-05,
55
+ "loss": 1.1056,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.12,
60
+ "learning_rate": 9.982695654527965e-05,
61
+ "loss": 0.9884,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.13,
66
+ "learning_rate": 9.972970737805311e-05,
67
+ "loss": 0.9128,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.14,
72
+ "learning_rate": 9.961093306567075e-05,
73
+ "loss": 0.8706,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.15,
78
+ "learning_rate": 9.947068501873701e-05,
79
+ "loss": 0.8783,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.17,
84
+ "learning_rate": 9.930902394260747e-05,
85
+ "loss": 0.7829,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.18,
90
+ "learning_rate": 9.912601981111286e-05,
91
+ "loss": 0.7684,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.19,
96
+ "learning_rate": 9.892175183627161e-05,
97
+ "loss": 0.758,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.2,
102
+ "learning_rate": 9.86963084340033e-05,
103
+ "loss": 0.7694,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.22,
108
+ "learning_rate": 9.844978718585855e-05,
109
+ "loss": 0.7196,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.23,
114
+ "learning_rate": 9.818229479678158e-05,
115
+ "loss": 0.7079,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.24,
120
+ "learning_rate": 9.789394704892364e-05,
121
+ "loss": 0.6731,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.26,
126
+ "learning_rate": 9.758486875152766e-05,
127
+ "loss": 0.6634,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.27,
132
+ "learning_rate": 9.725519368690538e-05,
133
+ "loss": 0.6646,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.28,
138
+ "learning_rate": 9.690506455253073e-05,
139
+ "loss": 0.6451,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.29,
144
+ "learning_rate": 9.653463289927411e-05,
145
+ "loss": 0.6435,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.31,
150
+ "learning_rate": 9.614405906580485e-05,
151
+ "loss": 0.6535,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.32,
156
+ "learning_rate": 9.573351210918974e-05,
157
+ "loss": 0.651,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.33,
162
+ "learning_rate": 9.53031697317178e-05,
163
+ "loss": 0.633,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.35,
168
+ "learning_rate": 9.485321820398321e-05,
169
+ "loss": 0.6183,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.36,
174
+ "learning_rate": 9.438385228425938e-05,
175
+ "loss": 0.638,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.37,
180
+ "learning_rate": 9.389527513419934e-05,
181
+ "loss": 0.641,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.38,
186
+ "learning_rate": 9.338769823089853e-05,
187
+ "loss": 0.627,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.4,
192
+ "learning_rate": 9.286134127535859e-05,
193
+ "loss": 0.5917,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.41,
198
+ "learning_rate": 9.231643209739128e-05,
199
+ "loss": 0.6462,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.42,
204
+ "learning_rate": 9.175320655700406e-05,
205
+ "loss": 0.6199,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.43,
210
+ "learning_rate": 9.117190844230971e-05,
211
+ "loss": 0.614,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.45,
216
+ "learning_rate": 9.057278936400453e-05,
217
+ "loss": 0.5996,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.46,
222
+ "learning_rate": 8.99561086464603e-05,
223
+ "loss": 0.5827,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.47,
228
+ "learning_rate": 8.93221332154777e-05,
229
+ "loss": 0.6186,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.49,
234
+ "learning_rate": 8.86711374827494e-05,
235
+ "loss": 0.5951,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.5,
240
+ "learning_rate": 8.800340322708291e-05,
241
+ "loss": 0.6095,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.51,
246
+ "learning_rate": 8.731921947243469e-05,
247
+ "loss": 0.6066,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.52,
252
+ "learning_rate": 8.661888236280813e-05,
253
+ "loss": 0.627,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.54,
258
+ "learning_rate": 8.590269503406985e-05,
259
+ "loss": 0.5973,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.55,
264
+ "learning_rate": 8.517096748273951e-05,
265
+ "loss": 0.5421,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.56,
270
+ "learning_rate": 8.442401643181e-05,
271
+ "loss": 0.5914,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.58,
276
+ "learning_rate": 8.366216519365621e-05,
277
+ "loss": 0.5926,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.59,
282
+ "learning_rate": 8.288574353009164e-05,
283
+ "loss": 0.6159,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.6,
288
+ "learning_rate": 8.209508750963328e-05,
289
+ "loss": 0.5809,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.61,
294
+ "learning_rate": 8.129053936203687e-05,
295
+ "loss": 0.5659,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.63,
300
+ "learning_rate": 8.047244733016522e-05,
301
+ "loss": 0.6108,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.64,
306
+ "learning_rate": 7.964116551925365e-05,
307
+ "loss": 0.5699,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.65,
312
+ "learning_rate": 7.879705374363831e-05,
313
+ "loss": 0.5865,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.67,
318
+ "learning_rate": 7.794047737101297e-05,
319
+ "loss": 0.5801,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.68,
324
+ "learning_rate": 7.707180716428237e-05,
325
+ "loss": 0.5611,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.69,
330
+ "learning_rate": 7.619141912108008e-05,
331
+ "loss": 0.5814,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.7,
336
+ "learning_rate": 7.529969431102064e-05,
337
+ "loss": 0.5713,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.72,
342
+ "learning_rate": 7.439701871075641e-05,
343
+ "loss": 0.5774,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.73,
348
+ "learning_rate": 7.34837830369103e-05,
349
+ "loss": 0.5646,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.74,
354
+ "learning_rate": 7.256038257695687e-05,
355
+ "loss": 0.5508,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.75,
360
+ "learning_rate": 7.162721701812505e-05,
361
+ "loss": 0.585,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.77,
366
+ "learning_rate": 7.068469027439642e-05,
367
+ "loss": 0.5572,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.78,
372
+ "learning_rate": 6.973321031167383e-05,
373
+ "loss": 0.5994,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.79,
378
+ "learning_rate": 6.87731889711965e-05,
379
+ "loss": 0.5753,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.81,
384
+ "learning_rate": 6.780504179127734e-05,
385
+ "loss": 0.5625,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.82,
390
+ "learning_rate": 6.682918782744032e-05,
391
+ "loss": 0.5641,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.83,
396
+ "learning_rate": 6.584604947103514e-05,
397
+ "loss": 0.5671,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.84,
402
+ "learning_rate": 6.485605226640837e-05,
403
+ "loss": 0.5536,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.86,
408
+ "learning_rate": 6.385962472670953e-05,
409
+ "loss": 0.5833,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.87,
414
+ "learning_rate": 6.28571981484123e-05,
415
+ "loss": 0.5651,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.88,
420
+ "learning_rate": 6.184920642463094e-05,
421
+ "loss": 0.5636,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.9,
426
+ "learning_rate": 6.083608585731283e-05,
427
+ "loss": 0.5473,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.91,
432
+ "learning_rate": 5.981827496838822e-05,
433
+ "loss": 0.5709,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.92,
438
+ "learning_rate": 5.8796214309959276e-05,
439
+ "loss": 0.5693,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.93,
444
+ "learning_rate": 5.7770346273610254e-05,
445
+ "loss": 0.5523,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.95,
450
+ "learning_rate": 5.674111489892144e-05,
451
+ "loss": 0.5578,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.96,
456
+ "learning_rate": 5.570896568126993e-05,
457
+ "loss": 0.5794,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.97,
462
+ "learning_rate": 5.4674345379e-05,
463
+ "loss": 0.5534,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.98,
468
+ "learning_rate": 5.36377018200472e-05,
469
+ "loss": 0.5675,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 1.0,
474
+ "learning_rate": 5.2599483708099016e-05,
475
+ "loss": 0.5592,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 1.01,
480
+ "learning_rate": 5.1560140428376956e-05,
481
+ "loss": 0.5718,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 1.02,
486
+ "learning_rate": 5.052012185312322e-05,
487
+ "loss": 0.5722,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 1.04,
492
+ "learning_rate": 4.9479878146876794e-05,
493
+ "loss": 0.5326,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 1.05,
498
+ "learning_rate": 4.8439859571623035e-05,
499
+ "loss": 0.569,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 1.06,
504
+ "learning_rate": 4.740051629190099e-05,
505
+ "loss": 0.5615,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 1.07,
510
+ "learning_rate": 4.636229817995281e-05,
511
+ "loss": 0.5438,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 1.09,
516
+ "learning_rate": 4.532565462099999e-05,
517
+ "loss": 0.5264,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 1.1,
522
+ "learning_rate": 4.429103431873009e-05,
523
+ "loss": 0.5417,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 1.11,
528
+ "learning_rate": 4.325888510107856e-05,
529
+ "loss": 0.5569,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 1.13,
534
+ "learning_rate": 4.2229653726389765e-05,
535
+ "loss": 0.5866,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 1.14,
540
+ "learning_rate": 4.120378569004074e-05,
541
+ "loss": 0.5587,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 1.15,
546
+ "learning_rate": 4.0181725031611795e-05,
547
+ "loss": 0.5381,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 1.16,
552
+ "learning_rate": 3.9163914142687184e-05,
553
+ "loss": 0.539,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 1.18,
558
+ "learning_rate": 3.8150793575369066e-05,
559
+ "loss": 0.5523,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 1.19,
564
+ "learning_rate": 3.714280185158771e-05,
565
+ "loss": 0.5478,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 1.2,
570
+ "learning_rate": 3.614037527329048e-05,
571
+ "loss": 0.5777,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 1.22,
576
+ "learning_rate": 3.514394773359163e-05,
577
+ "loss": 0.5388,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 1.23,
582
+ "learning_rate": 3.415395052896487e-05,
583
+ "loss": 0.5245,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 1.24,
588
+ "learning_rate": 3.31708121725597e-05,
589
+ "loss": 0.5435,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 1.25,
594
+ "learning_rate": 3.219495820872265e-05,
595
+ "loss": 0.5552,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 1.27,
600
+ "learning_rate": 3.122681102880352e-05,
601
+ "loss": 0.5295,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 1.28,
606
+ "learning_rate": 3.0266789688326186e-05,
607
+ "loss": 0.5414,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 1.29,
612
+ "learning_rate": 2.9315309725603596e-05,
613
+ "loss": 0.5412,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 1.3,
618
+ "learning_rate": 2.8372782981874963e-05,
619
+ "loss": 0.5543,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 1.32,
624
+ "learning_rate": 2.7439617423043145e-05,
625
+ "loss": 0.5564,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 1.33,
630
+ "learning_rate": 2.6516216963089698e-05,
631
+ "loss": 0.5432,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 1.34,
636
+ "learning_rate": 2.5602981289243578e-05,
637
+ "loss": 0.516,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 1.36,
642
+ "learning_rate": 2.470030568897938e-05,
643
+ "loss": 0.5461,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 1.37,
648
+ "learning_rate": 2.3808580878919946e-05,
649
+ "loss": 0.5818,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 1.38,
654
+ "learning_rate": 2.2928192835717644e-05,
655
+ "loss": 0.5374,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 1.39,
660
+ "learning_rate": 2.205952262898704e-05,
661
+ "loss": 0.5549,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 1.41,
666
+ "learning_rate": 2.120294625636171e-05,
667
+ "loss": 0.5395,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 1.42,
672
+ "learning_rate": 2.0358834480746365e-05,
673
+ "loss": 0.5529,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 1.43,
678
+ "learning_rate": 1.9527552669834798e-05,
679
+ "loss": 0.5338,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 1.45,
684
+ "learning_rate": 1.8709460637963123e-05,
685
+ "loss": 0.5588,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 1.46,
690
+ "learning_rate": 1.790491249036672e-05,
691
+ "loss": 0.5565,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 1.47,
696
+ "learning_rate": 1.711425646990838e-05,
697
+ "loss": 0.5306,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 1.48,
702
+ "learning_rate": 1.6337834806343783e-05,
703
+ "loss": 0.5434,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 1.5,
708
+ "learning_rate": 1.557598356819e-05,
709
+ "loss": 0.5559,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 1.51,
714
+ "learning_rate": 1.4829032517260489e-05,
715
+ "loss": 0.5478,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 1.52,
720
+ "learning_rate": 1.4097304965930158e-05,
721
+ "loss": 0.5386,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 1.53,
726
+ "learning_rate": 1.3381117637191886e-05,
727
+ "loss": 0.5672,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 1.55,
732
+ "learning_rate": 1.268078052756531e-05,
733
+ "loss": 0.5401,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 1.56,
738
+ "learning_rate": 1.199659677291709e-05,
739
+ "loss": 0.5222,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 1.57,
744
+ "learning_rate": 1.132886251725061e-05,
745
+ "loss": 0.5357,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 1.59,
750
+ "learning_rate": 1.0677866784522317e-05,
751
+ "loss": 0.5516,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 1.6,
756
+ "learning_rate": 1.004389135353972e-05,
757
+ "loss": 0.5588,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 1.61,
762
+ "learning_rate": 9.427210635995482e-06,
763
+ "loss": 0.5515,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 1.62,
768
+ "learning_rate": 8.828091557690289e-06,
769
+ "loss": 0.5303,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 1.64,
774
+ "learning_rate": 8.246793442995954e-06,
775
+ "loss": 0.5718,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 1.65,
780
+ "learning_rate": 7.683567902608729e-06,
781
+ "loss": 0.5201,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 1.66,
786
+ "learning_rate": 7.138658724641417e-06,
787
+ "loss": 0.5573,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 1.68,
792
+ "learning_rate": 6.6123017691014645e-06,
793
+ "loss": 0.5346,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 1.69,
798
+ "learning_rate": 6.104724865800665e-06,
799
+ "loss": 0.4899,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 1.7,
804
+ "learning_rate": 5.616147715740611e-06,
805
+ "loss": 0.5185,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 1.71,
810
+ "learning_rate": 5.1467817960167975e-06,
811
+ "loss": 0.5676,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 1.73,
816
+ "learning_rate": 4.696830268282204e-06,
817
+ "loss": 0.5177,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 1.74,
822
+ "learning_rate": 4.266487890810256e-06,
823
+ "loss": 0.5481,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 1.75,
828
+ "learning_rate": 3.855940934195146e-06,
829
+ "loss": 0.5436,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 1.76,
834
+ "learning_rate": 3.465367100725908e-06,
835
+ "loss": 0.541,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 1.78,
840
+ "learning_rate": 3.0949354474692937e-06,
841
+ "loss": 0.535,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 1.79,
846
+ "learning_rate": 2.7448063130946224e-06,
847
+ "loss": 0.5152,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 1.8,
852
+ "learning_rate": 2.4151312484723465e-06,
853
+ "loss": 0.5486,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 1.82,
858
+ "learning_rate": 2.106052951076365e-06,
859
+ "loss": 0.5484,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 1.83,
864
+ "learning_rate": 1.8177052032184283e-06,
865
+ "loss": 0.5178,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 1.84,
870
+ "learning_rate": 1.5502128141414495e-06,
871
+ "loss": 0.5408,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 1.85,
876
+ "learning_rate": 1.303691565996712e-06,
877
+ "loss": 0.5358,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 1.87,
882
+ "learning_rate": 1.0782481637284013e-06,
883
+ "loss": 0.5228,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 1.88,
888
+ "learning_rate": 8.739801888871469e-07,
889
+ "loss": 0.5429,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 1.89,
894
+ "learning_rate": 6.909760573925561e-07,
895
+ "loss": 0.5571,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 1.91,
900
+ "learning_rate": 5.29314981262985e-07,
901
+ "loss": 0.5543,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 1.92,
906
+ "learning_rate": 3.8906693432924634e-07,
907
+ "loss": 0.5471,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 1.93,
912
+ "learning_rate": 2.702926219468882e-07,
913
+ "loss": 0.5601,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 1.94,
918
+ "learning_rate": 1.7304345472035631e-07,
919
+ "loss": 0.5493,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 1.96,
924
+ "learning_rate": 9.73615262502503e-08,
925
+ "loss": 0.5458,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 1.97,
930
+ "learning_rate": 4.3279594913447905e-08,
931
+ "loss": 0.548,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 1.98,
936
+ "learning_rate": 1.082106968385288e-08,
937
+ "loss": 0.5239,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 2.0,
942
+ "learning_rate": 0.0,
943
+ "loss": 0.5618,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 2.0,
948
+ "step": 156,
949
+ "total_flos": 18465039040512.0,
950
+ "train_loss": 0.6798098935530736,
951
+ "train_runtime": 12941.1596,
952
+ "train_samples_per_second": 1.546,
953
+ "train_steps_per_second": 0.012
954
+ }
955
+ ],
956
+ "max_steps": 156,
957
+ "num_train_epochs": 2,
958
+ "total_flos": 18465039040512.0,
959
+ "trial_name": null,
960
+ "trial_params": null
961
+ }