Hugging Face's logo

llama-lang-adapt
/
me5-instruct-afri-more-langs-checkpoint-6000

Safetensors
xlm-roberta
Model card Files
xet
Community
KoseiUemura commited on
Commit
b2543a7
·
verified ·
1 Parent(s): 068ce31

Add checkpoint checkpoint-6000 - ME5 instruct model for African languages

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +28 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. sentencepiece.bpe.model +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +55 -0
  11. trainer_state.json +453 -0
  12. 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
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/multilingual-e5-large-instruct",
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": 514,
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": "4.46.2",
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 sha256:6d36fef9dd38cff355fb8201449c3b179648d1755f451fb20d8f972f4e54d3d8
3
+ size 2239607176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1bc4366925d78bebde6f79722f86108af5161a9c7c890c309562750bd02ea0
3
+ size 4471061702
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55a22a2a57a61c0cb152f88060ea4135486c663576aa29f04727cbd6c6b742c3
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6080484d97fffc0f69f861daf5442c741150049de572fdf2bad5169bac15441
3
+ size 1465
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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 sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
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
+ "additional_special_tokens": [],
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.11833619312466719,
5
+ "eval_steps": 500,
6
+ "global_step": 6000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0019722698854111194,
13
+ "grad_norm": 67.04732513427734,
14
+ "learning_rate": 1.8931177282587262e-07,
15
+ "loss": 3.4926,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.003944539770822239,
20
+ "grad_norm": 39.206844329833984,
21
+ "learning_rate": 3.845395385525538e-07,
22
+ "loss": 2.7703,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.005916809656233359,
27
+ "grad_norm": 27.58599281311035,
28
+ "learning_rate": 5.817393019128378e-07,
29
+ "loss": 2.4388,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.007889079541644478,
34
+ "grad_norm": 34.81669616699219,
35
+ "learning_rate": 7.789390652731218e-07,
36
+ "loss": 2.2036,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.009861349427055598,
41
+ "grad_norm": 32.964962005615234,
42
+ "learning_rate": 9.761388286334058e-07,
43
+ "loss": 2.0266,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.011833619312466718,
48
+ "grad_norm": 42.337581634521484,
49
+ "learning_rate": 1.1733385919936897e-06,
50
+ "loss": 2.1158,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.013805889197877837,
55
+ "grad_norm": 21.399593353271484,
56
+ "learning_rate": 1.3705383553539735e-06,
57
+ "loss": 2.2383,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.015778159083288956,
62
+ "grad_norm": 21.51966667175293,
63
+ "learning_rate": 1.5677381187142576e-06,
64
+ "loss": 2.0389,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.017750428968700077,
69
+ "grad_norm": 34.57212448120117,
70
+ "learning_rate": 1.7649378820745417e-06,
71
+ "loss": 2.0948,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.019722698854111195,
76
+ "grad_norm": 25.938730239868164,
77
+ "learning_rate": 1.9621376454348255e-06,
78
+ "loss": 2.0942,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.021694968739522317,
83
+ "grad_norm": 32.7101936340332,
84
+ "learning_rate": 2.15933740879511e-06,
85
+ "loss": 2.1916,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.023667238624933435,
90
+ "grad_norm": 25.46886444091797,
91
+ "learning_rate": 2.3565371721553937e-06,
92
+ "loss": 2.0302,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.025639508510344557,
97
+ "grad_norm": 32.50448226928711,
98
+ "learning_rate": 2.5537369355156775e-06,
99
+ "loss": 2.0705,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.027611778395755675,
104
+ "grad_norm": 22.87787628173828,
105
+ "learning_rate": 2.750936698875962e-06,
106
+ "loss": 2.2077,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.029584048281166796,
111
+ "grad_norm": 26.768518447875977,
112
+ "learning_rate": 2.9481364622362457e-06,
113
+ "loss": 2.0721,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.03155631816657791,
118
+ "grad_norm": 29.448543548583984,
119
+ "learning_rate": 3.14533622559653e-06,
120
+ "loss": 1.9885,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.033528588051989036,
125
+ "grad_norm": 28.677627563476562,
126
+ "learning_rate": 3.3425359889568138e-06,
127
+ "loss": 2.1427,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.035500857937400154,
132
+ "grad_norm": 21.812522888183594,
133
+ "learning_rate": 3.5397357523170976e-06,
134
+ "loss": 2.1057,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.03747312782281127,
139
+ "grad_norm": 44.289085388183594,
140
+ "learning_rate": 3.736935515677381e-06,
141
+ "loss": 2.018,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.03944539770822239,
146
+ "grad_norm": 15.590181350708008,
147
+ "learning_rate": 3.934135279037665e-06,
148
+ "loss": 2.1122,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.041417667593633516,
153
+ "grad_norm": 35.98659133911133,
154
+ "learning_rate": 4.131335042397949e-06,
155
+ "loss": 2.1107,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.043389937479044634,
160
+ "grad_norm": 44.836509704589844,
161
+ "learning_rate": 4.3285348057582335e-06,
162
+ "loss": 2.0407,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.04536220736445575,
167
+ "grad_norm": 21.399402618408203,
168
+ "learning_rate": 4.525734569118517e-06,
169
+ "loss": 2.03,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.04733447724986687,
174
+ "grad_norm": 31.757156372070312,
175
+ "learning_rate": 4.722934332478801e-06,
176
+ "loss": 2.0217,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.04930674713527799,
181
+ "grad_norm": 50.079410552978516,
182
+ "learning_rate": 4.9201340958390855e-06,
183
+ "loss": 1.9586,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.05127901702068911,
188
+ "grad_norm": 37.94638442993164,
189
+ "learning_rate": 5.117333859199369e-06,
190
+ "loss": 2.0377,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.05325128690610023,
195
+ "grad_norm": 35.663753509521484,
196
+ "learning_rate": 5.314533622559653e-06,
197
+ "loss": 1.941,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.05522355679151135,
202
+ "grad_norm": 36.772029876708984,
203
+ "learning_rate": 5.5117333859199375e-06,
204
+ "loss": 2.0187,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.05719582667692247,
209
+ "grad_norm": 22.433650970458984,
210
+ "learning_rate": 5.708933149280222e-06,
211
+ "loss": 1.9755,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.05916809656233359,
216
+ "grad_norm": 57.76415252685547,
217
+ "learning_rate": 5.906132912640505e-06,
218
+ "loss": 1.9486,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.06114036644774471,
223
+ "grad_norm": 31.0864200592041,
224
+ "learning_rate": 6.1033326760007895e-06,
225
+ "loss": 2.0447,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.06311263633315582,
230
+ "grad_norm": 32.29108810424805,
231
+ "learning_rate": 6.300532439361074e-06,
232
+ "loss": 2.0367,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.06508490621856695,
237
+ "grad_norm": 20.73668670654297,
238
+ "learning_rate": 6.495760205087754e-06,
239
+ "loss": 2.0181,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.06705717610397807,
244
+ "grad_norm": 32.148006439208984,
245
+ "learning_rate": 6.692959968448039e-06,
246
+ "loss": 2.013,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.06902944598938919,
251
+ "grad_norm": 23.00872802734375,
252
+ "learning_rate": 6.890159731808322e-06,
253
+ "loss": 2.1131,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.07100171587480031,
258
+ "grad_norm": 23.956350326538086,
259
+ "learning_rate": 7.087359495168606e-06,
260
+ "loss": 2.0121,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.07297398576021143,
265
+ "grad_norm": 37.15364456176758,
266
+ "learning_rate": 7.284559258528891e-06,
267
+ "loss": 2.0139,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.07494625564562254,
272
+ "grad_norm": 30.48556137084961,
273
+ "learning_rate": 7.481759021889174e-06,
274
+ "loss": 2.0144,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.07691852553103366,
279
+ "grad_norm": 61.636573791503906,
280
+ "learning_rate": 7.678958785249458e-06,
281
+ "loss": 2.0422,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.07889079541644478,
286
+ "grad_norm": 37.870880126953125,
287
+ "learning_rate": 7.876158548609743e-06,
288
+ "loss": 2.0768,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.0808630653018559,
293
+ "grad_norm": 33.507110595703125,
294
+ "learning_rate": 8.073358311970027e-06,
295
+ "loss": 1.9964,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.08283533518726703,
300
+ "grad_norm": 25.337188720703125,
301
+ "learning_rate": 8.270558075330311e-06,
302
+ "loss": 1.9615,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.08480760507267815,
307
+ "grad_norm": 24.217805862426758,
308
+ "learning_rate": 8.467757838690594e-06,
309
+ "loss": 2.0473,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.08677987495808927,
314
+ "grad_norm": 39.8419303894043,
315
+ "learning_rate": 8.664957602050878e-06,
316
+ "loss": 2.0923,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.08875214484350039,
321
+ "grad_norm": 33.75648498535156,
322
+ "learning_rate": 8.862157365411162e-06,
323
+ "loss": 2.0848,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.0907244147289115,
328
+ "grad_norm": 28.586196899414062,
329
+ "learning_rate": 9.059357128771447e-06,
330
+ "loss": 1.8756,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.09269668461432262,
335
+ "grad_norm": 14.528404235839844,
336
+ "learning_rate": 9.256556892131731e-06,
337
+ "loss": 1.9906,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.09466895449973374,
342
+ "grad_norm": 8.93252182006836,
343
+ "learning_rate": 9.453756655492015e-06,
344
+ "loss": 2.1737,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.09664122438514486,
349
+ "grad_norm": 34.46258544921875,
350
+ "learning_rate": 9.650956418852298e-06,
351
+ "loss": 2.0293,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.09861349427055598,
356
+ "grad_norm": 34.29590606689453,
357
+ "learning_rate": 9.848156182212582e-06,
358
+ "loss": 1.9045,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.10058576415596711,
363
+ "grad_norm": 11.751779556274414,
364
+ "learning_rate": 9.994959677419356e-06,
365
+ "loss": 2.0457,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.10255803404137823,
370
+ "grad_norm": 17.423030853271484,
371
+ "learning_rate": 9.97304523141655e-06,
372
+ "loss": 2.091,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.10453030392678934,
377
+ "grad_norm": 15.934210777282715,
378
+ "learning_rate": 9.951130785413746e-06,
379
+ "loss": 2.061,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.10650257381220046,
384
+ "grad_norm": 21.839845657348633,
385
+ "learning_rate": 9.92921633941094e-06,
386
+ "loss": 2.0003,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.10847484369761158,
391
+ "grad_norm": 9.299293518066406,
392
+ "learning_rate": 9.907301893408135e-06,
393
+ "loss": 2.0278,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.1104471135830227,
398
+ "grad_norm": 34.51756286621094,
399
+ "learning_rate": 9.88538744740533e-06,
400
+ "loss": 2.1308,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.11241938346843382,
405
+ "grad_norm": 37.36806106567383,
406
+ "learning_rate": 9.863473001402525e-06,
407
+ "loss": 2.059,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.11439165335384494,
412
+ "grad_norm": 40.66093826293945,
413
+ "learning_rate": 9.841558555399721e-06,
414
+ "loss": 2.0161,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.11636392323925605,
419
+ "grad_norm": 41.07834243774414,
420
+ "learning_rate": 9.819644109396916e-06,
421
+ "loss": 2.0413,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.11833619312466719,
426
+ "grad_norm": 22.08112907409668,
427
+ "learning_rate": 9.797729663394109e-06,
428
+ "loss": 2.0019,
429
+ "step": 6000
430
+ }
431
+ ],
432
+ "logging_steps": 100,
433
+ "max_steps": 50703,
434
+ "num_input_tokens_seen": 0,
435
+ "num_train_epochs": 1,
436
+ "save_steps": 100,
437
+ "stateful_callbacks": {
438
+ "TrainerControl": {
439
+ "args": {
440
+ "should_epoch_stop": false,
441
+ "should_evaluate": false,
442
+ "should_log": false,
443
+ "should_save": true,
444
+ "should_training_stop": false
445
+ },
446
+ "attributes": {}
447
+ }
448
+ },
449
+ "total_flos": 0.0,
450
+ "train_batch_size": 1,
451
+ "trial_name": null,
452
+ "trial_params": null
453
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089e9ad122468b88d15c7ea47eace242541e0922c0f2126e0a2520c382ad8b25
3
+ size 6033