Hugging Face's logo

phandat128
/
bgem3_finetune

Safetensors
xlm-roberta
Model card Files Community
phandat128 commited on
Commit
6d1cb0a
·
verified ·
1 Parent(s): b06c6a1

Upload 10 files

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. colbert_linear.pt +3 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. sparse_linear.pt +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +55 -0
  10. trainer_state.json +446 -0
  11. training_args.bin +3 -0
.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
colbert_linear.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc3b1fdc59aa334992eecc00deac3f4e18a0ac59b8397d0aad07f7409e4ec2e
3
+ size 4199874
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/bgem3-neg-train-checkpoint",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 8194,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.44.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e15424ff0a1d1f7c80ffc5b7c6e3dcd364b8b52346a965f5c2d1e9c6998976e
3
+ size 2271064456
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
sparse_linear.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b83b837ac2b6ed08d137d3ffc1daf9a247d489b906dbee1227eaa2b06028b73
3
+ size 5564
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
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": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05d40e5344b7ebcd126146d4a0e66b5ea9a639ab84a2eafc109aabab25dc9ef
3
+ size 17098349
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 8192,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,446 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 29864,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01674256630056255,
13
+ "grad_norm": 0.26318585872650146,
14
+ "learning_rate": 1.6538332775359894e-06,
15
+ "loss": 0.1468,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.0334851326011251,
20
+ "grad_norm": 40.848941802978516,
21
+ "learning_rate": 3.3244057582859056e-06,
22
+ "loss": 0.1348,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.05022769890168765,
27
+ "grad_norm": 0.3210512399673462,
28
+ "learning_rate": 4.9983260796786076e-06,
29
+ "loss": 0.1292,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.0669702652022502,
34
+ "grad_norm": 51.398277282714844,
35
+ "learning_rate": 6.6722464010713095e-06,
36
+ "loss": 0.1246,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.08371283150281275,
41
+ "grad_norm": 1.8654736280441284,
42
+ "learning_rate": 8.346166722464011e-06,
43
+ "loss": 0.073,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.1004553978033753,
48
+ "grad_norm": 2.204322338104248,
49
+ "learning_rate": 9.997767607991965e-06,
50
+ "loss": 0.0861,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.11719796410393785,
55
+ "grad_norm": 0.029873741790652275,
56
+ "learning_rate": 9.81173494065558e-06,
57
+ "loss": 0.0626,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.1339405304045004,
62
+ "grad_norm": 2.218162775039673,
63
+ "learning_rate": 9.626074338653869e-06,
64
+ "loss": 0.0731,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.15068309670506294,
69
+ "grad_norm": 6.862820625305176,
70
+ "learning_rate": 9.440041671317484e-06,
71
+ "loss": 0.0756,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.1674256630056255,
76
+ "grad_norm": 1.0643534660339355,
77
+ "learning_rate": 9.2540090039811e-06,
78
+ "loss": 0.0702,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.18416822930618806,
83
+ "grad_norm": 0.14988207817077637,
84
+ "learning_rate": 9.067976336644717e-06,
85
+ "loss": 0.0675,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.2009107956067506,
90
+ "grad_norm": 0.25116392970085144,
91
+ "learning_rate": 8.882315734643004e-06,
92
+ "loss": 0.0604,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.21765336190731316,
97
+ "grad_norm": 0.3021365702152252,
98
+ "learning_rate": 8.69628306730662e-06,
99
+ "loss": 0.0515,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.2343959282078757,
104
+ "grad_norm": 22.51474952697754,
105
+ "learning_rate": 8.510250399970235e-06,
106
+ "loss": 0.0643,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.2511384945084382,
111
+ "grad_norm": 2.37544584274292,
112
+ "learning_rate": 8.324217732633852e-06,
113
+ "loss": 0.07,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.2678810608090008,
118
+ "grad_norm": 57.23020553588867,
119
+ "learning_rate": 8.138185065297467e-06,
120
+ "loss": 0.0557,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.28462362710956335,
125
+ "grad_norm": 0.0032292637042701244,
126
+ "learning_rate": 7.952152397961083e-06,
127
+ "loss": 0.0614,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.3013661934101259,
132
+ "grad_norm": 5.582527160644531,
133
+ "learning_rate": 7.766119730624698e-06,
134
+ "loss": 0.0577,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.31810875971068847,
139
+ "grad_norm": 0.04729452729225159,
140
+ "learning_rate": 7.580087063288314e-06,
141
+ "loss": 0.0582,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.334851326011251,
146
+ "grad_norm": 2.683903217315674,
147
+ "learning_rate": 7.394426461286602e-06,
148
+ "loss": 0.0549,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.35159389231181354,
153
+ "grad_norm": 0.9779844880104065,
154
+ "learning_rate": 7.208393793950218e-06,
155
+ "loss": 0.0615,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.3683364586123761,
160
+ "grad_norm": 79.76528930664062,
161
+ "learning_rate": 7.0223611266138335e-06,
162
+ "loss": 0.0519,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.38507902491293866,
167
+ "grad_norm": 0.3208529055118561,
168
+ "learning_rate": 6.836328459277449e-06,
169
+ "loss": 0.0591,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.4018215912135012,
174
+ "grad_norm": 23.068653106689453,
175
+ "learning_rate": 6.650295791941065e-06,
176
+ "loss": 0.0539,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.41856415751406373,
181
+ "grad_norm": 0.6496044993400574,
182
+ "learning_rate": 6.464635189939353e-06,
183
+ "loss": 0.0549,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.4353067238146263,
188
+ "grad_norm": 38.81090545654297,
189
+ "learning_rate": 6.2786025226029705e-06,
190
+ "loss": 0.0543,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.45204929011518885,
195
+ "grad_norm": 2.4993317127227783,
196
+ "learning_rate": 6.092569855266585e-06,
197
+ "loss": 0.0614,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.4687918564157514,
202
+ "grad_norm": 0.5560814738273621,
203
+ "learning_rate": 5.906537187930201e-06,
204
+ "loss": 0.048,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.485534422716314,
209
+ "grad_norm": 1.5382946729660034,
210
+ "learning_rate": 5.720504520593817e-06,
211
+ "loss": 0.0558,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.5022769890168765,
216
+ "grad_norm": 0.026120496913790703,
217
+ "learning_rate": 5.534471853257432e-06,
218
+ "loss": 0.0492,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.519019555317439,
223
+ "grad_norm": 1.6323872804641724,
224
+ "learning_rate": 5.348439185921048e-06,
225
+ "loss": 0.0633,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.5357621216180016,
230
+ "grad_norm": 0.012650725431740284,
231
+ "learning_rate": 5.162406518584664e-06,
232
+ "loss": 0.0447,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.5525046879185641,
237
+ "grad_norm": 8.42776107788086,
238
+ "learning_rate": 4.976745916582952e-06,
239
+ "loss": 0.043,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.5692472542191267,
244
+ "grad_norm": 2.717674732208252,
245
+ "learning_rate": 4.790713249246568e-06,
246
+ "loss": 0.0517,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.5859898205196893,
251
+ "grad_norm": 0.01320638321340084,
252
+ "learning_rate": 4.604680581910183e-06,
253
+ "loss": 0.0768,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.6027323868202518,
258
+ "grad_norm": 68.84772491455078,
259
+ "learning_rate": 4.418647914573799e-06,
260
+ "loss": 0.0578,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.6194749531208144,
265
+ "grad_norm": 0.05758577585220337,
266
+ "learning_rate": 4.232987312572088e-06,
267
+ "loss": 0.0575,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.6362175194213769,
272
+ "grad_norm": 0.02908864989876747,
273
+ "learning_rate": 4.046954645235704e-06,
274
+ "loss": 0.0527,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.6529600857219394,
279
+ "grad_norm": 5.406867027282715,
280
+ "learning_rate": 3.86092197789932e-06,
281
+ "loss": 0.0556,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.669702652022502,
286
+ "grad_norm": 0.1083500012755394,
287
+ "learning_rate": 3.6748893105629353e-06,
288
+ "loss": 0.0607,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.6864452183230646,
293
+ "grad_norm": 13.136815071105957,
294
+ "learning_rate": 3.488856643226551e-06,
295
+ "loss": 0.0608,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.7031877846236271,
300
+ "grad_norm": 0.7505860328674316,
301
+ "learning_rate": 3.3028239758901666e-06,
302
+ "loss": 0.0691,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.7199303509241897,
307
+ "grad_norm": 56.34339141845703,
308
+ "learning_rate": 3.1167913085537823e-06,
309
+ "loss": 0.0563,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.7366729172247523,
314
+ "grad_norm": 0.267652302980423,
315
+ "learning_rate": 2.9307586412173984e-06,
316
+ "loss": 0.0688,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 0.7534154835253147,
321
+ "grad_norm": 4.030105113983154,
322
+ "learning_rate": 2.7450980392156867e-06,
323
+ "loss": 0.0637,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 0.7701580498258773,
328
+ "grad_norm": 1.6611367464065552,
329
+ "learning_rate": 2.5590653718793024e-06,
330
+ "loss": 0.0724,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 0.7869006161264399,
335
+ "grad_norm": 65.19082641601562,
336
+ "learning_rate": 2.3734047698775908e-06,
337
+ "loss": 0.0759,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 0.8036431824270024,
342
+ "grad_norm": 2.824739694595337,
343
+ "learning_rate": 2.1873721025412064e-06,
344
+ "loss": 0.0675,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 0.820385748727565,
349
+ "grad_norm": 1.6871856451034546,
350
+ "learning_rate": 2.001339435204822e-06,
351
+ "loss": 0.1016,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 0.8371283150281275,
356
+ "grad_norm": 73.87975311279297,
357
+ "learning_rate": 1.8156788332031105e-06,
358
+ "loss": 0.0995,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 0.85387088132869,
363
+ "grad_norm": 1.2010084390640259,
364
+ "learning_rate": 1.6296461658667261e-06,
365
+ "loss": 0.0871,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 0.8706134476292526,
370
+ "grad_norm": 8.91370964050293,
371
+ "learning_rate": 1.443613498530342e-06,
372
+ "loss": 0.0936,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 0.8873560139298151,
377
+ "grad_norm": 8.569842338562012,
378
+ "learning_rate": 1.2575808311939577e-06,
379
+ "loss": 0.0927,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 0.9040985802303777,
384
+ "grad_norm": 0.14943744242191315,
385
+ "learning_rate": 1.0715481638575736e-06,
386
+ "loss": 0.1108,
387
+ "step": 27000
388
+ },
389
+ {
390
+ "epoch": 0.9208411465309403,
391
+ "grad_norm": 48.06157684326172,
392
+ "learning_rate": 8.855154965211891e-07,
393
+ "loss": 0.1141,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 0.9375837128315028,
398
+ "grad_norm": 46.07848358154297,
399
+ "learning_rate": 6.994828291848049e-07,
400
+ "loss": 0.118,
401
+ "step": 28000
402
+ },
403
+ {
404
+ "epoch": 0.9543262791320654,
405
+ "grad_norm": 1.0916130542755127,
406
+ "learning_rate": 5.134501618484206e-07,
407
+ "loss": 0.138,
408
+ "step": 28500
409
+ },
410
+ {
411
+ "epoch": 0.971068845432628,
412
+ "grad_norm": 0.2534860074520111,
413
+ "learning_rate": 3.277895598467091e-07,
414
+ "loss": 0.1425,
415
+ "step": 29000
416
+ },
417
+ {
418
+ "epoch": 0.9878114117331904,
419
+ "grad_norm": 0.08512990921735764,
420
+ "learning_rate": 1.421289578449976e-07,
421
+ "loss": 0.1432,
422
+ "step": 29500
423
+ }
424
+ ],
425
+ "logging_steps": 500,
426
+ "max_steps": 29864,
427
+ "num_input_tokens_seen": 0,
428
+ "num_train_epochs": 1,
429
+ "save_steps": 500,
430
+ "stateful_callbacks": {
431
+ "TrainerControl": {
432
+ "args": {
433
+ "should_epoch_stop": false,
434
+ "should_evaluate": false,
435
+ "should_log": false,
436
+ "should_save": true,
437
+ "should_training_stop": true
438
+ },
439
+ "attributes": {}
440
+ }
441
+ },
442
+ "total_flos": 0.0,
443
+ "train_batch_size": 1,
444
+ "trial_name": null,
445
+ "trial_params": null
446
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb549a87fc9daf70bdde6ad9e6a0f57dff541051c84bff0ebb2fed598ec672e
3
+ size 5624