trongg commited on
Commit
63910a1
1 Parent(s): e601ba8

Upload folder using huggingface_hub

Browse files
.gitattributes ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ checkpoint-4250/colbert_linear.pt filter=lfs diff=lfs merge=lfs -text
2
+ checkpoint-4250/global_step4250/mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
3
+ checkpoint-4250/model.safetensors filter=lfs diff=lfs merge=lfs -text
4
+ checkpoint-4250/rng_state.pth filter=lfs diff=lfs merge=lfs -text
5
+ checkpoint-4250/sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
6
+ checkpoint-4250/sparse_linear.pt filter=lfs diff=lfs merge=lfs -text
7
+ checkpoint-4250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
8
+ checkpoint-4250/training_args.bin filter=lfs diff=lfs merge=lfs -text
checkpoint-4250/colbert_linear.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c368770d57aa50b2c35229df87803703f2d3609c2e345562d3f94c7cdb5b0cea
3
+ size 2100674
checkpoint-4250/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--BAAI--bge-m3/snapshots/5617a9f61b028005a4858fdac845db406aefb181",
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": "float16",
24
+ "transformers_version": "4.44.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
checkpoint-4250/global_step4250/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7302c7647ba2f57932795fe1bbbf49de3994906354f86c3fc0fb8e9238439596
3
+ size 7963362556
checkpoint-4250/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step4250
checkpoint-4250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6514560919c46bdc248ff0aee70402296b85f4aaca21718b6916a82fd19370e6
3
+ size 1135554344
checkpoint-4250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855b5923653129b2076a5ec5a130deff15642fe6ad7c9eece9046810aed6f7a6
3
+ size 14244
checkpoint-4250/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-4250/sparse_linear.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f257052a51029d1de16930261f5209391d9103539ac5597cd8ce1aabdcd97eb
3
+ size 3516
checkpoint-4250/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
+ }
checkpoint-4250/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cd99e33ce09bdd8a6136fddfe90a1c47f85bafedf7309d0eecc19012d43586
3
+ size 17082897
checkpoint-4250/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
+ }
checkpoint-4250/trainer_state.json ADDED
@@ -0,0 +1,628 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.37677304964539005,
5
+ "eval_steps": 500,
6
+ "global_step": 4250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004432624113475178,
13
+ "grad_norm": 0.009513450788341307,
14
+ "learning_rate": 5.066502241635949e-06,
15
+ "loss": 0.0353,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.008865248226950355,
20
+ "grad_norm": 0.12959164414811705,
21
+ "learning_rate": 5.964204463534375e-06,
22
+ "loss": 0.0209,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.013297872340425532,
27
+ "grad_norm": 0.03079899259156006,
28
+ "learning_rate": 6.489326600159014e-06,
29
+ "loss": 0.0114,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.01773049645390071,
34
+ "grad_norm": 1.904334998115993,
35
+ "learning_rate": 6.855414889666249e-06,
36
+ "loss": 0.0426,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.022163120567375887,
41
+ "grad_norm": 0.00029657300723797526,
42
+ "learning_rate": 7.14571142073327e-06,
43
+ "loss": 0.0092,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.026595744680851064,
48
+ "grad_norm": 0.5635451567630495,
49
+ "learning_rate": 7.382704575824005e-06,
50
+ "loss": 0.0207,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.03102836879432624,
55
+ "grad_norm": 17.174480153841266,
56
+ "learning_rate": 7.582965380729319e-06,
57
+ "loss": 0.0128,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.03546099290780142,
62
+ "grad_norm": 0.0029856714585610065,
63
+ "learning_rate": 7.756367076993413e-06,
64
+ "loss": 0.0087,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.0398936170212766,
69
+ "grad_norm": 46.59324697917607,
70
+ "learning_rate": 7.909269732702365e-06,
71
+ "loss": 0.0358,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.044326241134751775,
76
+ "grad_norm": 0.011038539916815544,
77
+ "learning_rate": 8.046011658635775e-06,
78
+ "loss": 0.0099,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.04875886524822695,
83
+ "grad_norm": 0.06122707900561642,
84
+ "learning_rate": 8.169684802472282e-06,
85
+ "loss": 0.0257,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.05319148936170213,
90
+ "grad_norm": 11.17528630173658,
91
+ "learning_rate": 8.28257072561721e-06,
92
+ "loss": 0.0399,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.057624113475177305,
97
+ "grad_norm": 0.004434274436946811,
98
+ "learning_rate": 8.386401186603816e-06,
99
+ "loss": 0.0106,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.06205673758865248,
104
+ "grad_norm": 0.00022486652288303773,
105
+ "learning_rate": 8.482521734002021e-06,
106
+ "loss": 0.0175,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.06648936170212766,
111
+ "grad_norm": 0.08252216933057055,
112
+ "learning_rate": 8.571998643735778e-06,
113
+ "loss": 0.0122,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.07092198581560284,
118
+ "grad_norm": 38.71346721678791,
119
+ "learning_rate": 8.655691228400912e-06,
120
+ "loss": 0.0107,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.07535460992907801,
125
+ "grad_norm": 0.016399532174579123,
126
+ "learning_rate": 8.734302159716567e-06,
127
+ "loss": 0.0272,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.0797872340425532,
132
+ "grad_norm": 13.96210364288869,
133
+ "learning_rate": 8.808413368821617e-06,
134
+ "loss": 0.0162,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.08421985815602837,
139
+ "grad_norm": 20.616657581291367,
140
+ "learning_rate": 8.878512216644468e-06,
141
+ "loss": 0.018,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.08865248226950355,
146
+ "grad_norm": 8.554096191036654,
147
+ "learning_rate": 8.945010936770532e-06,
148
+ "loss": 0.0122,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.09308510638297872,
153
+ "grad_norm": 9.002995310481221,
154
+ "learning_rate": 9.008261325009621e-06,
155
+ "loss": 0.004,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.0975177304964539,
160
+ "grad_norm": 0.04332552525052799,
161
+ "learning_rate": 9.068566005374956e-06,
162
+ "loss": 0.0049,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.10195035460992907,
167
+ "grad_norm": 0.566818534495066,
168
+ "learning_rate": 9.126187187473155e-06,
169
+ "loss": 0.0348,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.10638297872340426,
174
+ "grad_norm": 2.2102759352121244,
175
+ "learning_rate": 9.181353557126703e-06,
176
+ "loss": 0.0157,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.11081560283687943,
181
+ "grad_norm": 0.0007883033335850071,
182
+ "learning_rate": 9.233228424991629e-06,
183
+ "loss": 0.0153,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.11524822695035461,
188
+ "grad_norm": 8.962657174789879,
189
+ "learning_rate": 9.28410340850224e-06,
190
+ "loss": 0.011,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.1196808510638298,
195
+ "grad_norm": 0.08478258585114734,
196
+ "learning_rate": 9.333055212266742e-06,
197
+ "loss": 0.0193,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.12411347517730496,
202
+ "grad_norm": 5.126269299634291,
203
+ "learning_rate": 9.380223955900445e-06,
204
+ "loss": 0.0224,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.12854609929078015,
209
+ "grad_norm": 0.001630326745394445,
210
+ "learning_rate": 9.425734982425631e-06,
211
+ "loss": 0.0198,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.13297872340425532,
216
+ "grad_norm": 31.3251284414765,
217
+ "learning_rate": 9.469700865634203e-06,
218
+ "loss": 0.0201,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.1374113475177305,
223
+ "grad_norm": 0.003720201610220148,
224
+ "learning_rate": 9.512223087748166e-06,
225
+ "loss": 0.0386,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.14184397163120568,
230
+ "grad_norm": 1.4908536371789232,
231
+ "learning_rate": 9.553393450299339e-06,
232
+ "loss": 0.0155,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.14627659574468085,
237
+ "grad_norm": 0.18557111682138577,
238
+ "learning_rate": 9.593295267571064e-06,
239
+ "loss": 0.0132,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.15070921985815602,
244
+ "grad_norm": 0.0012351164899243579,
245
+ "learning_rate": 9.632004381614992e-06,
246
+ "loss": 0.0169,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.1551418439716312,
251
+ "grad_norm": 4.390950581164127,
252
+ "learning_rate": 9.669590029926173e-06,
253
+ "loss": 0.0188,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.1595744680851064,
258
+ "grad_norm": 1.5823201233659507,
259
+ "learning_rate": 9.706115590720043e-06,
260
+ "loss": 0.0176,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.16400709219858156,
265
+ "grad_norm": 0.6041784257950227,
266
+ "learning_rate": 9.741639225963296e-06,
267
+ "loss": 0.0076,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.16843971631205673,
272
+ "grad_norm": 8.096633927567137,
273
+ "learning_rate": 9.776214438542894e-06,
274
+ "loss": 0.0254,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.17287234042553193,
279
+ "grad_norm": 0.001381384244099819,
280
+ "learning_rate": 9.80989055697396e-06,
281
+ "loss": 0.021,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.1773049645390071,
286
+ "grad_norm": 0.6173202999510908,
287
+ "learning_rate": 9.842713158668956e-06,
288
+ "loss": 0.0153,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.18173758865248227,
293
+ "grad_norm": 0.4702304667158159,
294
+ "learning_rate": 9.874724440882673e-06,
295
+ "loss": 0.0322,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.18617021276595744,
300
+ "grad_norm": 0.007418267836546937,
301
+ "learning_rate": 9.905963546908046e-06,
302
+ "loss": 0.0189,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.19060283687943264,
307
+ "grad_norm": 0.040611583128721894,
308
+ "learning_rate": 9.936466853848526e-06,
309
+ "loss": 0.004,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.1950354609929078,
314
+ "grad_norm": 35.80087991837194,
315
+ "learning_rate": 9.96626822727338e-06,
316
+ "loss": 0.022,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.19946808510638298,
321
+ "grad_norm": 0.44489231698014525,
322
+ "learning_rate": 9.995399247226628e-06,
323
+ "loss": 0.0165,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.20390070921985815,
328
+ "grad_norm": 0.0002357955980587179,
329
+ "learning_rate": 9.980299448384557e-06,
330
+ "loss": 0.0091,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.20833333333333334,
335
+ "grad_norm": 0.011156109382490509,
336
+ "learning_rate": 9.955673758865249e-06,
337
+ "loss": 0.0293,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.2127659574468085,
342
+ "grad_norm": 0.010237311021590336,
343
+ "learning_rate": 9.931048069345942e-06,
344
+ "loss": 0.0267,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.21719858156028368,
349
+ "grad_norm": 0.1907181340319684,
350
+ "learning_rate": 9.906422379826635e-06,
351
+ "loss": 0.0035,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.22163120567375885,
356
+ "grad_norm": 7.244482111036572,
357
+ "learning_rate": 9.881796690307329e-06,
358
+ "loss": 0.0129,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.22606382978723405,
363
+ "grad_norm": 2.614333142067009,
364
+ "learning_rate": 9.857171000788024e-06,
365
+ "loss": 0.0176,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.23049645390070922,
370
+ "grad_norm": 0.19026758190049964,
371
+ "learning_rate": 9.832545311268717e-06,
372
+ "loss": 0.0118,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.2349290780141844,
377
+ "grad_norm": 1.926354870277716,
378
+ "learning_rate": 9.80791962174941e-06,
379
+ "loss": 0.0113,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.2393617021276596,
384
+ "grad_norm": 1.3390029353713434e-05,
385
+ "learning_rate": 9.783293932230104e-06,
386
+ "loss": 0.0095,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.24379432624113476,
391
+ "grad_norm": 0.25506782394102356,
392
+ "learning_rate": 9.758668242710797e-06,
393
+ "loss": 0.0235,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.24822695035460993,
398
+ "grad_norm": 0.0011667263533171556,
399
+ "learning_rate": 9.73404255319149e-06,
400
+ "loss": 0.01,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.2526595744680851,
405
+ "grad_norm": 2.676783820787547,
406
+ "learning_rate": 9.709416863672184e-06,
407
+ "loss": 0.0305,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.2570921985815603,
412
+ "grad_norm": 0.0019099837220493063,
413
+ "learning_rate": 9.684791174152877e-06,
414
+ "loss": 0.0246,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.26152482269503546,
419
+ "grad_norm": 0.6898702380926142,
420
+ "learning_rate": 9.66016548463357e-06,
421
+ "loss": 0.0211,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.26595744680851063,
426
+ "grad_norm": 0.0006438124789484562,
427
+ "learning_rate": 9.635539795114264e-06,
428
+ "loss": 0.008,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.2703900709219858,
433
+ "grad_norm": 3.819700570925564e-05,
434
+ "learning_rate": 9.610914105594957e-06,
435
+ "loss": 0.0199,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 0.274822695035461,
440
+ "grad_norm": 0.019487722143147885,
441
+ "learning_rate": 9.58628841607565e-06,
442
+ "loss": 0.0126,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 0.27925531914893614,
447
+ "grad_norm": 0.49075883570668455,
448
+ "learning_rate": 9.561662726556344e-06,
449
+ "loss": 0.0114,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 0.28368794326241137,
454
+ "grad_norm": 0.661703227107662,
455
+ "learning_rate": 9.537037037037037e-06,
456
+ "loss": 0.0081,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 0.28812056737588654,
461
+ "grad_norm": 0.00012406562558187035,
462
+ "learning_rate": 9.512411347517732e-06,
463
+ "loss": 0.0154,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 0.2925531914893617,
468
+ "grad_norm": 10.456271349514031,
469
+ "learning_rate": 9.487785657998426e-06,
470
+ "loss": 0.0056,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 0.2969858156028369,
475
+ "grad_norm": 34.88954914653437,
476
+ "learning_rate": 9.463159968479119e-06,
477
+ "loss": 0.0215,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 0.30141843971631205,
482
+ "grad_norm": 0.0037401951660654617,
483
+ "learning_rate": 9.43853427895981e-06,
484
+ "loss": 0.0073,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 0.3058510638297872,
489
+ "grad_norm": 1.9770145427070573,
490
+ "learning_rate": 9.413908589440504e-06,
491
+ "loss": 0.026,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 0.3102836879432624,
496
+ "grad_norm": 0.0005171843885202088,
497
+ "learning_rate": 9.389282899921197e-06,
498
+ "loss": 0.0054,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 0.3147163120567376,
503
+ "grad_norm": 6.671945039975605,
504
+ "learning_rate": 9.364657210401892e-06,
505
+ "loss": 0.0193,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 0.3191489361702128,
510
+ "grad_norm": 24.199369765973504,
511
+ "learning_rate": 9.340031520882586e-06,
512
+ "loss": 0.0253,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 0.32358156028368795,
517
+ "grad_norm": 0.03237450123162466,
518
+ "learning_rate": 9.31540583136328e-06,
519
+ "loss": 0.0108,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 0.3280141843971631,
524
+ "grad_norm": 0.06582091922650166,
525
+ "learning_rate": 9.290780141843973e-06,
526
+ "loss": 0.0052,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 0.3324468085106383,
531
+ "grad_norm": 1.1046639468259907,
532
+ "learning_rate": 9.266154452324666e-06,
533
+ "loss": 0.0077,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 0.33687943262411346,
538
+ "grad_norm": 0.12685978465854558,
539
+ "learning_rate": 9.24152876280536e-06,
540
+ "loss": 0.0055,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 0.34131205673758863,
545
+ "grad_norm": 0.001176875548815465,
546
+ "learning_rate": 9.216903073286053e-06,
547
+ "loss": 0.0116,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 0.34574468085106386,
552
+ "grad_norm": 19.93923722594081,
553
+ "learning_rate": 9.192277383766746e-06,
554
+ "loss": 0.0339,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 0.350177304964539,
559
+ "grad_norm": 0.5136555426144171,
560
+ "learning_rate": 9.16765169424744e-06,
561
+ "loss": 0.0109,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 0.3546099290780142,
566
+ "grad_norm": 29.577148937276096,
567
+ "learning_rate": 9.143026004728133e-06,
568
+ "loss": 0.0195,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 0.35904255319148937,
573
+ "grad_norm": 5.471652062023114,
574
+ "learning_rate": 9.118400315208826e-06,
575
+ "loss": 0.0075,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 0.36347517730496454,
580
+ "grad_norm": 0.0039179745195827426,
581
+ "learning_rate": 9.09377462568952e-06,
582
+ "loss": 0.0203,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 0.3679078014184397,
587
+ "grad_norm": 30.214203138409303,
588
+ "learning_rate": 9.069148936170213e-06,
589
+ "loss": 0.0323,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 0.3723404255319149,
594
+ "grad_norm": 1.0344365911211837,
595
+ "learning_rate": 9.044523246650908e-06,
596
+ "loss": 0.0252,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 0.37677304964539005,
601
+ "grad_norm": 0.6080095692433664,
602
+ "learning_rate": 9.019897557131601e-06,
603
+ "loss": 0.0065,
604
+ "step": 4250
605
+ }
606
+ ],
607
+ "logging_steps": 50,
608
+ "max_steps": 22560,
609
+ "num_input_tokens_seen": 0,
610
+ "num_train_epochs": 2,
611
+ "save_steps": 4250,
612
+ "stateful_callbacks": {
613
+ "TrainerControl": {
614
+ "args": {
615
+ "should_epoch_stop": false,
616
+ "should_evaluate": false,
617
+ "should_log": false,
618
+ "should_save": true,
619
+ "should_training_stop": false
620
+ },
621
+ "attributes": {}
622
+ }
623
+ },
624
+ "total_flos": 0.0,
625
+ "train_batch_size": 1,
626
+ "trial_name": null,
627
+ "trial_params": null
628
+ }
checkpoint-4250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7329fafa0075eedf11ff5cbda13c031c19b86ade8ca006a5a13695dcf1cf91
3
+ size 7416