Hugging Face's logo

llama-lang-adapt
/
me5-instruct-top14-langs-checkpoint-6000

Safetensors
xlm-roberta
Model card Files
xet
Community
KoseiUemura commited on
Commit
fc1d488
·
verified ·
1 Parent(s): 2bd6baf

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:c7cbbe742048e480803e1a0c4d7709a4807895544df59eed1ed2e3367cf75df9
3
+ size 2239607176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a554df7ef1e8933ff19d5cf3616725778e296a72990e00238b83539d50906373
3
+ size 4471061702
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527889776812ba44e485bf8229b5ddc7c0909f3451933705e5202c033fca7be1
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f586bb5cdaba4891a1ee7a55819ef72c0f828b5d0630c5b1fe592d540ed46844
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": 0.4596644449551827,
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": 0.007661074082586378,
13
+ "grad_norm": 101.71317291259766,
14
+ "learning_rate": 7.350689127105667e-08,
15
+ "loss": 3.3393,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.015322148165172756,
20
+ "grad_norm": 31.139225006103516,
21
+ "learning_rate": 1.5007656967840735e-07,
22
+ "loss": 3.0671,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.022983222247759137,
27
+ "grad_norm": 40.13219451904297,
28
+ "learning_rate": 2.26646248085758e-07,
29
+ "loss": 2.4152,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.030644296330345513,
34
+ "grad_norm": 40.68937683105469,
35
+ "learning_rate": 3.0321592649310873e-07,
36
+ "loss": 2.1563,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.038305370412931895,
41
+ "grad_norm": 14.248607635498047,
42
+ "learning_rate": 3.797856049004594e-07,
43
+ "loss": 2.0665,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.045966444495518274,
48
+ "grad_norm": 59.703857421875,
49
+ "learning_rate": 4.563552833078101e-07,
50
+ "loss": 2.1346,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.05362751857810465,
55
+ "grad_norm": 24.38258934020996,
56
+ "learning_rate": 5.329249617151608e-07,
57
+ "loss": 1.9339,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.061288592660691026,
62
+ "grad_norm": 51.95455551147461,
63
+ "learning_rate": 6.094946401225115e-07,
64
+ "loss": 1.9002,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.0689496667432774,
69
+ "grad_norm": 30.304096221923828,
70
+ "learning_rate": 6.860643185298621e-07,
71
+ "loss": 1.9943,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.07661074082586379,
76
+ "grad_norm": 60.5661506652832,
77
+ "learning_rate": 7.626339969372128e-07,
78
+ "loss": 1.9459,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.08427181490845016,
83
+ "grad_norm": 14.830733299255371,
84
+ "learning_rate": 8.392036753445635e-07,
85
+ "loss": 1.8775,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.09193288899103655,
90
+ "grad_norm": 33.56428146362305,
91
+ "learning_rate": 9.157733537519142e-07,
92
+ "loss": 1.8554,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.09959396307362292,
97
+ "grad_norm": 31.33570671081543,
98
+ "learning_rate": 9.92343032159265e-07,
99
+ "loss": 1.9377,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.1072550371562093,
104
+ "grad_norm": 34.497676849365234,
105
+ "learning_rate": 9.923384693964416e-07,
106
+ "loss": 1.8444,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.11491611123879568,
111
+ "grad_norm": 50.38022994995117,
112
+ "learning_rate": 9.838256576147102e-07,
113
+ "loss": 1.8652,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.12257718532138205,
118
+ "grad_norm": 20.895923614501953,
119
+ "learning_rate": 9.753128458329787e-07,
120
+ "loss": 1.7354,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.13023825940396844,
125
+ "grad_norm": 30.610666275024414,
126
+ "learning_rate": 9.66800034051247e-07,
127
+ "loss": 1.851,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.1378993334865548,
132
+ "grad_norm": 23.91990852355957,
133
+ "learning_rate": 9.582872222695155e-07,
134
+ "loss": 1.8025,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.14556040756914118,
139
+ "grad_norm": 25.79492950439453,
140
+ "learning_rate": 9.497744104877841e-07,
141
+ "loss": 1.8883,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.15322148165172758,
146
+ "grad_norm": 40.9505500793457,
147
+ "learning_rate": 9.413467268238699e-07,
148
+ "loss": 1.8133,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.16088255573431395,
153
+ "grad_norm": 15.241936683654785,
154
+ "learning_rate": 9.328339150421384e-07,
155
+ "loss": 1.8268,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.16854362981690033,
160
+ "grad_norm": 29.481456756591797,
161
+ "learning_rate": 9.243211032604069e-07,
162
+ "loss": 1.7925,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.1762047038994867,
167
+ "grad_norm": 22.76151466369629,
168
+ "learning_rate": 9.158082914786754e-07,
169
+ "loss": 1.7218,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.1838657779820731,
174
+ "grad_norm": 35.234901428222656,
175
+ "learning_rate": 9.072954796969439e-07,
176
+ "loss": 1.7647,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.19152685206465947,
181
+ "grad_norm": 29.202571868896484,
182
+ "learning_rate": 8.987826679152124e-07,
183
+ "loss": 1.8084,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.19918792614724584,
188
+ "grad_norm": 29.16272735595703,
189
+ "learning_rate": 8.902698561334808e-07,
190
+ "loss": 1.7772,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.20684900022983221,
195
+ "grad_norm": 20.253196716308594,
196
+ "learning_rate": 8.817570443517494e-07,
197
+ "loss": 1.754,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.2145100743124186,
202
+ "grad_norm": 15.704442977905273,
203
+ "learning_rate": 8.732442325700179e-07,
204
+ "loss": 1.8346,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.22217114839500499,
209
+ "grad_norm": 20.612945556640625,
210
+ "learning_rate": 8.647314207882863e-07,
211
+ "loss": 1.8684,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.22983222247759136,
216
+ "grad_norm": 24.869367599487305,
217
+ "learning_rate": 8.562186090065549e-07,
218
+ "loss": 1.7856,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.23749329656017773,
223
+ "grad_norm": 21.364919662475586,
224
+ "learning_rate": 8.477057972248233e-07,
225
+ "loss": 1.9965,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.2451543706427641,
230
+ "grad_norm": 28.2412052154541,
231
+ "learning_rate": 8.391929854430918e-07,
232
+ "loss": 1.8412,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.2528154447253505,
237
+ "grad_norm": 22.827234268188477,
238
+ "learning_rate": 8.306801736613604e-07,
239
+ "loss": 1.7012,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.2604765188079369,
244
+ "grad_norm": 24.38725471496582,
245
+ "learning_rate": 8.221673618796288e-07,
246
+ "loss": 1.7401,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.26813759289052325,
251
+ "grad_norm": 19.78017807006836,
252
+ "learning_rate": 8.136545500978973e-07,
253
+ "loss": 1.7862,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.2757986669731096,
258
+ "grad_norm": 21.21510887145996,
259
+ "learning_rate": 8.051417383161659e-07,
260
+ "loss": 1.8333,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.283459741055696,
265
+ "grad_norm": 34.275203704833984,
266
+ "learning_rate": 7.966289265344343e-07,
267
+ "loss": 1.8345,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.29112081513828236,
272
+ "grad_norm": 21.573719024658203,
273
+ "learning_rate": 7.881161147527028e-07,
274
+ "loss": 1.7381,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.2987818892208688,
279
+ "grad_norm": 25.18048095703125,
280
+ "learning_rate": 7.796033029709714e-07,
281
+ "loss": 1.8019,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.30644296330345516,
286
+ "grad_norm": 16.440776824951172,
287
+ "learning_rate": 7.710904911892397e-07,
288
+ "loss": 1.6649,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.31410403738604153,
293
+ "grad_norm": 34.30360412597656,
294
+ "learning_rate": 7.625776794075082e-07,
295
+ "loss": 1.7646,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.3217651114686279,
300
+ "grad_norm": 21.367576599121094,
301
+ "learning_rate": 7.540648676257768e-07,
302
+ "loss": 1.7958,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.3294261855512143,
307
+ "grad_norm": 31.468273162841797,
308
+ "learning_rate": 7.455520558440452e-07,
309
+ "loss": 1.7507,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.33708725963380065,
314
+ "grad_norm": 26.512048721313477,
315
+ "learning_rate": 7.370392440623137e-07,
316
+ "loss": 1.8063,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.344748333716387,
321
+ "grad_norm": 38.13068389892578,
322
+ "learning_rate": 7.285264322805822e-07,
323
+ "loss": 1.8687,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.3524094077989734,
328
+ "grad_norm": 18.889034271240234,
329
+ "learning_rate": 7.200136204988507e-07,
330
+ "loss": 1.7927,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.36007048188155977,
335
+ "grad_norm": 34.959999084472656,
336
+ "learning_rate": 7.115008087171192e-07,
337
+ "loss": 1.8351,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.3677315559641462,
342
+ "grad_norm": 26.197481155395508,
343
+ "learning_rate": 7.029879969353876e-07,
344
+ "loss": 1.7006,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.37539263004673257,
349
+ "grad_norm": 41.952117919921875,
350
+ "learning_rate": 6.944751851536562e-07,
351
+ "loss": 1.8509,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.38305370412931894,
356
+ "grad_norm": 35.9224853515625,
357
+ "learning_rate": 6.859623733719247e-07,
358
+ "loss": 1.7899,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.3907147782119053,
363
+ "grad_norm": 28.870563507080078,
364
+ "learning_rate": 6.774495615901931e-07,
365
+ "loss": 1.7521,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.3983758522944917,
370
+ "grad_norm": 29.25061798095703,
371
+ "learning_rate": 6.689367498084617e-07,
372
+ "loss": 1.8195,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.40603692637707806,
377
+ "grad_norm": 27.750329971313477,
378
+ "learning_rate": 6.604239380267302e-07,
379
+ "loss": 1.7895,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.41369800045966443,
384
+ "grad_norm": 27.71558952331543,
385
+ "learning_rate": 6.519111262449986e-07,
386
+ "loss": 1.7367,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.4213590745422508,
391
+ "grad_norm": 31.144386291503906,
392
+ "learning_rate": 6.433983144632672e-07,
393
+ "loss": 1.7298,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.4290201486248372,
398
+ "grad_norm": 36.28512954711914,
399
+ "learning_rate": 6.348855026815357e-07,
400
+ "loss": 1.7203,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.4366812227074236,
405
+ "grad_norm": 19.006488800048828,
406
+ "learning_rate": 6.263726908998041e-07,
407
+ "loss": 1.7735,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.44434229679000997,
412
+ "grad_norm": 13.495680809020996,
413
+ "learning_rate": 6.178598791180727e-07,
414
+ "loss": 1.7444,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.45200337087259634,
419
+ "grad_norm": 23.272104263305664,
420
+ "learning_rate": 6.093470673363411e-07,
421
+ "loss": 1.7389,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.4596644449551827,
426
+ "grad_norm": 48.6375846862793,
427
+ "learning_rate": 6.00919383672427e-07,
428
+ "loss": 1.8083,
429
+ "step": 6000
430
+ }
431
+ ],
432
+ "logging_steps": 100,
433
+ "max_steps": 13053,
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 sha256:85f8a470a64c9815bee62bd7de09edf84e08884f4f680c77aea3569b5b587ae0
3
+ size 6033