KoseiUemura commited on
Commit
3c349b2
·
verified ·
1 Parent(s): a7491ae

Add checkpoint checkpoint-7000

Browse files
.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 sha256:64f7f793ee439530f3370b4ec9504072ade58ee8b5bb0295594487e51a220e0c
3
+ size 4200349
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mila/u/uemurak/scratch/hf_cache/hub/models--intfloat--multilingual-e5-large-instruct/snapshots/274baa43b0e13e37fafa6428dbc7938e62e5c439",
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 sha256:3c927ea9a8bea58f4aec74e898c119ad3a1e2291e371dc5f77597d72032569d4
3
+ size 2239607176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2de989e578db2a37ba36e5d19ca11ac760e6e9f6a276c09e4b3cb10fd2d2635
3
+ size 4479470178
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba8d1689bb839a2a661ae9d2cf9da130c843fb8c6c794431d26a891b7153c11
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcaca90104bf3c01a37144375c8875c362b4c0b1f8a2b568b6387db14e0c669
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
sparse_linear.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56b3e38694d2f38bd66d2a3bdabed594e34bbf901cd6d0802f24f77ac824903
3
+ size 5973
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 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5028013216491883,
5
+ "eval_steps": 500,
6
+ "global_step": 7000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007182876023559833,
13
+ "grad_norm": 102.55565643310547,
14
+ "learning_rate": 3.339317773788151e-07,
15
+ "loss": 4.51,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.014365752047119667,
20
+ "grad_norm": 20.8671875,
21
+ "learning_rate": 6.929982046678636e-07,
22
+ "loss": 1.3058,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.0215486280706795,
27
+ "grad_norm": 16.238826751708984,
28
+ "learning_rate": 1.0520646319569122e-06,
29
+ "loss": 0.7671,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.028731504094239333,
34
+ "grad_norm": 12.669879913330078,
35
+ "learning_rate": 1.4111310592459606e-06,
36
+ "loss": 0.639,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.03591438011779917,
41
+ "grad_norm": 13.375199317932129,
42
+ "learning_rate": 1.770197486535009e-06,
43
+ "loss": 0.5396,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.043097256141359,
48
+ "grad_norm": 36.680416107177734,
49
+ "learning_rate": 2.1292639138240576e-06,
50
+ "loss": 0.4649,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.050280132164918834,
55
+ "grad_norm": 15.553112983703613,
56
+ "learning_rate": 2.488330341113106e-06,
57
+ "loss": 0.4561,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.057463008188478666,
62
+ "grad_norm": 28.032434463500977,
63
+ "learning_rate": 2.847396768402155e-06,
64
+ "loss": 0.4152,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.0646458842120385,
69
+ "grad_norm": 40.55122756958008,
70
+ "learning_rate": 3.2064631956912027e-06,
71
+ "loss": 0.412,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.07182876023559834,
76
+ "grad_norm": 48.380340576171875,
77
+ "learning_rate": 3.5655296229802514e-06,
78
+ "loss": 0.4159,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.07901163625915816,
83
+ "grad_norm": 18.708255767822266,
84
+ "learning_rate": 3.9245960502693e-06,
85
+ "loss": 0.3397,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.086194512282718,
90
+ "grad_norm": 10.165841102600098,
91
+ "learning_rate": 4.283662477558348e-06,
92
+ "loss": 0.355,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.09337738830627783,
97
+ "grad_norm": 17.107013702392578,
98
+ "learning_rate": 4.6427289048473974e-06,
99
+ "loss": 0.3312,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.10056026432983767,
104
+ "grad_norm": 38.87083053588867,
105
+ "learning_rate": 5.001795332136446e-06,
106
+ "loss": 0.2452,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.1077431403533975,
111
+ "grad_norm": 17.743247985839844,
112
+ "learning_rate": 5.360861759425494e-06,
113
+ "loss": 0.2204,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.11492601637695733,
118
+ "grad_norm": 35.18050765991211,
119
+ "learning_rate": 5.719928186714543e-06,
120
+ "loss": 0.2338,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.12210889240051717,
125
+ "grad_norm": 8.888273239135742,
126
+ "learning_rate": 6.078994614003591e-06,
127
+ "loss": 0.2269,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.129291768424077,
132
+ "grad_norm": 6.807362079620361,
133
+ "learning_rate": 6.4380610412926396e-06,
134
+ "loss": 0.233,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.13647464444763682,
139
+ "grad_norm": 3.313542366027832,
140
+ "learning_rate": 6.797127468581688e-06,
141
+ "loss": 0.2033,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.14365752047119668,
146
+ "grad_norm": 4.184378623962402,
147
+ "learning_rate": 7.156193895870737e-06,
148
+ "loss": 0.1904,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.1508403964947565,
153
+ "grad_norm": 29.64693832397461,
154
+ "learning_rate": 7.515260323159785e-06,
155
+ "loss": 0.2063,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.15802327251831633,
160
+ "grad_norm": 19.15960121154785,
161
+ "learning_rate": 7.874326750448834e-06,
162
+ "loss": 0.2206,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.16520614854187618,
167
+ "grad_norm": 12.115074157714844,
168
+ "learning_rate": 8.233393177737883e-06,
169
+ "loss": 0.1949,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.172389024565436,
174
+ "grad_norm": 9.53875732421875,
175
+ "learning_rate": 8.59245960502693e-06,
176
+ "loss": 0.2,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.17957190058899583,
181
+ "grad_norm": 3.5382916927337646,
182
+ "learning_rate": 8.951526032315979e-06,
183
+ "loss": 0.1875,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.18675477661255566,
188
+ "grad_norm": 1.2547463178634644,
189
+ "learning_rate": 9.310592459605027e-06,
190
+ "loss": 0.2033,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.1939376526361155,
195
+ "grad_norm": 1.9213370084762573,
196
+ "learning_rate": 9.669658886894077e-06,
197
+ "loss": 0.1946,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.20112052865967533,
202
+ "grad_norm": 35.58647155761719,
203
+ "learning_rate": 9.996807534219244e-06,
204
+ "loss": 0.2231,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.20830340468323516,
209
+ "grad_norm": 3.3178770542144775,
210
+ "learning_rate": 9.956901711959775e-06,
211
+ "loss": 0.1868,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.215486280706795,
216
+ "grad_norm": 22.328224182128906,
217
+ "learning_rate": 9.916995889700309e-06,
218
+ "loss": 0.2107,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.22266915673035484,
223
+ "grad_norm": 28.90311050415039,
224
+ "learning_rate": 9.877090067440841e-06,
225
+ "loss": 0.2068,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.22985203275391466,
230
+ "grad_norm": 4.699060916900635,
231
+ "learning_rate": 9.837184245181373e-06,
232
+ "loss": 0.1987,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.2370349087774745,
237
+ "grad_norm": 16.968143463134766,
238
+ "learning_rate": 9.797278422921906e-06,
239
+ "loss": 0.1688,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.24421778480103434,
244
+ "grad_norm": 8.749013900756836,
245
+ "learning_rate": 9.757372600662436e-06,
246
+ "loss": 0.1803,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.25140066082459417,
251
+ "grad_norm": 16.449424743652344,
252
+ "learning_rate": 9.71746677840297e-06,
253
+ "loss": 0.2231,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.258583536848154,
258
+ "grad_norm": 0.8674511313438416,
259
+ "learning_rate": 9.677560956143502e-06,
260
+ "loss": 0.1853,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.2657664128717138,
265
+ "grad_norm": 6.190998554229736,
266
+ "learning_rate": 9.637655133884035e-06,
267
+ "loss": 0.1669,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.27294928889527365,
272
+ "grad_norm": 10.102142333984375,
273
+ "learning_rate": 9.597749311624567e-06,
274
+ "loss": 0.2075,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.2801321649188335,
279
+ "grad_norm": 22.571224212646484,
280
+ "learning_rate": 9.557843489365099e-06,
281
+ "loss": 0.2019,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.28731504094239335,
286
+ "grad_norm": 29.87354278564453,
287
+ "learning_rate": 9.517937667105631e-06,
288
+ "loss": 0.2022,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.2944979169659532,
293
+ "grad_norm": 4.910442352294922,
294
+ "learning_rate": 9.478031844846164e-06,
295
+ "loss": 0.1816,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.301680792989513,
300
+ "grad_norm": 18.66014289855957,
301
+ "learning_rate": 9.438126022586697e-06,
302
+ "loss": 0.1998,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.30886366901307283,
307
+ "grad_norm": 42.844818115234375,
308
+ "learning_rate": 9.398220200327228e-06,
309
+ "loss": 0.193,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.31604654503663265,
314
+ "grad_norm": 8.83779525756836,
315
+ "learning_rate": 9.35831437806776e-06,
316
+ "loss": 0.1681,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.3232294210601925,
321
+ "grad_norm": 3.474717140197754,
322
+ "learning_rate": 9.318408555808294e-06,
323
+ "loss": 0.1608,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.33041229708375236,
328
+ "grad_norm": 4.746242046356201,
329
+ "learning_rate": 9.278502733548825e-06,
330
+ "loss": 0.1552,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.3375951731073122,
335
+ "grad_norm": 4.5783915519714355,
336
+ "learning_rate": 9.238596911289359e-06,
337
+ "loss": 0.1646,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.344778049130872,
342
+ "grad_norm": 9.975970268249512,
343
+ "learning_rate": 9.198691089029889e-06,
344
+ "loss": 0.1791,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.35196092515443184,
349
+ "grad_norm": 1.2798261642456055,
350
+ "learning_rate": 9.158785266770423e-06,
351
+ "loss": 0.1842,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.35914380117799166,
356
+ "grad_norm": 6.015448570251465,
357
+ "learning_rate": 9.118879444510955e-06,
358
+ "loss": 0.1751,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.3663266772015515,
363
+ "grad_norm": 7.062718391418457,
364
+ "learning_rate": 9.078973622251488e-06,
365
+ "loss": 0.1751,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.3735095532251113,
370
+ "grad_norm": 0.9326837062835693,
371
+ "learning_rate": 9.03906779999202e-06,
372
+ "loss": 0.1646,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.3806924292486712,
377
+ "grad_norm": 1.695087194442749,
378
+ "learning_rate": 8.999161977732552e-06,
379
+ "loss": 0.1577,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.387875305272231,
384
+ "grad_norm": 19.320249557495117,
385
+ "learning_rate": 8.959256155473084e-06,
386
+ "loss": 0.1729,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.39505818129579084,
391
+ "grad_norm": 3.8522274494171143,
392
+ "learning_rate": 8.919350333213616e-06,
393
+ "loss": 0.1781,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.40224105731935067,
398
+ "grad_norm": 2.3610100746154785,
399
+ "learning_rate": 8.879444510954149e-06,
400
+ "loss": 0.1975,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.4094239333429105,
405
+ "grad_norm": 6.998334884643555,
406
+ "learning_rate": 8.839538688694681e-06,
407
+ "loss": 0.1629,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.4166068093664703,
412
+ "grad_norm": 15.58069896697998,
413
+ "learning_rate": 8.799632866435213e-06,
414
+ "loss": 0.1764,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.42378968539003015,
419
+ "grad_norm": 40.70027160644531,
420
+ "learning_rate": 8.759727044175747e-06,
421
+ "loss": 0.1923,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.43097256141359,
426
+ "grad_norm": 8.034761428833008,
427
+ "learning_rate": 8.719821221916278e-06,
428
+ "loss": 0.1795,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.43815543743714985,
433
+ "grad_norm": 1.1275875568389893,
434
+ "learning_rate": 8.679915399656812e-06,
435
+ "loss": 0.1477,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.4453383134607097,
440
+ "grad_norm": 8.35661792755127,
441
+ "learning_rate": 8.640009577397342e-06,
442
+ "loss": 0.1687,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.4525211894842695,
447
+ "grad_norm": 19.17778968811035,
448
+ "learning_rate": 8.600103755137876e-06,
449
+ "loss": 0.1409,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.45970406550782933,
454
+ "grad_norm": 22.45587730407715,
455
+ "learning_rate": 8.560197932878408e-06,
456
+ "loss": 0.1676,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.46688694153138915,
461
+ "grad_norm": 27.29585075378418,
462
+ "learning_rate": 8.520292110618939e-06,
463
+ "loss": 0.1656,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.474069817554949,
468
+ "grad_norm": 2.3996095657348633,
469
+ "learning_rate": 8.480386288359473e-06,
470
+ "loss": 0.1622,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.48125269357850886,
475
+ "grad_norm": 15.577359199523926,
476
+ "learning_rate": 8.440480466100005e-06,
477
+ "loss": 0.1748,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.4884355696020687,
482
+ "grad_norm": 16.934419631958008,
483
+ "learning_rate": 8.400574643840537e-06,
484
+ "loss": 0.1689,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.4956184456256285,
489
+ "grad_norm": 2.9546115398406982,
490
+ "learning_rate": 8.36066882158107e-06,
491
+ "loss": 0.1695,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.5028013216491883,
496
+ "grad_norm": 2.370490550994873,
497
+ "learning_rate": 8.320762999321602e-06,
498
+ "loss": 0.1396,
499
+ "step": 7000
500
+ }
501
+ ],
502
+ "logging_steps": 100,
503
+ "max_steps": 27844,
504
+ "num_input_tokens_seen": 0,
505
+ "num_train_epochs": 2,
506
+ "save_steps": 100,
507
+ "stateful_callbacks": {
508
+ "TrainerControl": {
509
+ "args": {
510
+ "should_epoch_stop": false,
511
+ "should_evaluate": false,
512
+ "should_log": false,
513
+ "should_save": true,
514
+ "should_training_stop": false
515
+ },
516
+ "attributes": {}
517
+ }
518
+ },
519
+ "total_flos": 0.0,
520
+ "train_batch_size": 1,
521
+ "trial_name": null,
522
+ "trial_params": null
523
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0835fa9e65929ce5c4ce980add81f40b68b6210ffe106bcce6d2b6de868d3a2
3
+ size 6225