Hugging Face's logo

llama-lang-adapt
/
me5-instruct-yor-HQ-hn-m3-corrected-kd-xlingual-9000

Safetensors
xlm-roberta
Model card Files Community
KoseiUemura commited on
Commit
47a7520
·
verified ·
1 Parent(s): c9cd8ca

Add checkpoint checkpoint-9000

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. colbert_linear.pt +3 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. sentencepiece.bpe.model +3 -0
  9. sparse_linear.pt +3 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +55 -0
  13. trainer_state.json +663 -0
  14. 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:e375359f652c39ae2baebc094eb6da945b20f2c9e12bb652821775e513fa8445
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:b213a52b1b6b443a2e00424895be0e3ff8e03d7de1379f1eb9497d823bd03b4a
3
+ size 2239607176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afca24a1f3c27f92d5a134a0b83a6888539620c82060c3f649f5427b6d6173af
3
+ size 4479470178
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c1f3b7346b6efed55651e2424174bceef2634cb411d1349a17e7cf1351b91e
3
+ size 14581
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f112082a4dabebe6739adf7805a6e6e8f9ed45c377b31477dcc83bd99fc15369
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 sha256:8e9867d3b89089f22d67aa156f32c31855f66835c0f6a12eb9cf2547926dbc1e
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 +1,663 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.2352456766401319,
5
+ "eval_steps": 500,
6
+ "global_step": 9000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01372495196266813,
13
+ "grad_norm": 23.625333786010742,
14
+ "learning_rate": 6.378600823045268e-07,
15
+ "loss": 3.631,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.02744990392533626,
20
+ "grad_norm": 26.834190368652344,
21
+ "learning_rate": 1.3237311385459534e-06,
22
+ "loss": 0.887,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.04117485588800439,
27
+ "grad_norm": 20.897249221801758,
28
+ "learning_rate": 2.00960219478738e-06,
29
+ "loss": 0.5548,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.05489980785067252,
34
+ "grad_norm": 14.432657241821289,
35
+ "learning_rate": 2.6954732510288067e-06,
36
+ "loss": 0.353,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.06862475981334065,
41
+ "grad_norm": 45.2662239074707,
42
+ "learning_rate": 3.3813443072702336e-06,
43
+ "loss": 0.3153,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.08234971177600878,
48
+ "grad_norm": 10.040751457214355,
49
+ "learning_rate": 4.06721536351166e-06,
50
+ "loss": 0.2679,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.09607466373867692,
55
+ "grad_norm": 26.088348388671875,
56
+ "learning_rate": 4.753086419753087e-06,
57
+ "loss": 0.308,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.10979961570134504,
62
+ "grad_norm": 5.486932754516602,
63
+ "learning_rate": 5.438957475994513e-06,
64
+ "loss": 0.2776,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.12352456766401318,
69
+ "grad_norm": 25.890995025634766,
70
+ "learning_rate": 6.12482853223594e-06,
71
+ "loss": 0.2864,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.1372495196266813,
76
+ "grad_norm": 6.877874851226807,
77
+ "learning_rate": 6.810699588477366e-06,
78
+ "loss": 0.2502,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.15097447158934943,
83
+ "grad_norm": 8.569019317626953,
84
+ "learning_rate": 7.496570644718793e-06,
85
+ "loss": 0.2392,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.16469942355201755,
90
+ "grad_norm": 26.53949546813965,
91
+ "learning_rate": 8.18244170096022e-06,
92
+ "loss": 0.2599,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.1784243755146857,
97
+ "grad_norm": 31.634700775146484,
98
+ "learning_rate": 8.868312757201646e-06,
99
+ "loss": 0.2638,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.19214932747735383,
104
+ "grad_norm": 35.01237869262695,
105
+ "learning_rate": 9.554183813443072e-06,
106
+ "loss": 0.2672,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.20587427944002196,
111
+ "grad_norm": 15.365808486938477,
112
+ "learning_rate": 9.97331096538051e-06,
113
+ "loss": 0.2573,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.21959923140269008,
118
+ "grad_norm": 2.571429491043091,
119
+ "learning_rate": 9.897056580753394e-06,
120
+ "loss": 0.2461,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.23332418336535823,
125
+ "grad_norm": 2.3058722019195557,
126
+ "learning_rate": 9.820802196126277e-06,
127
+ "loss": 0.2688,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.24704913532802636,
132
+ "grad_norm": 24.54079246520996,
133
+ "learning_rate": 9.744547811499163e-06,
134
+ "loss": 0.2524,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.26077408729069446,
139
+ "grad_norm": 4.643412113189697,
140
+ "learning_rate": 9.668293426872047e-06,
141
+ "loss": 0.2797,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.2744990392533626,
146
+ "grad_norm": 11.36482048034668,
147
+ "learning_rate": 9.592039042244929e-06,
148
+ "loss": 0.2426,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.28822399121603076,
153
+ "grad_norm": 30.41916275024414,
154
+ "learning_rate": 9.515784657617814e-06,
155
+ "loss": 0.245,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.30194894317869886,
160
+ "grad_norm": 31.319168090820312,
161
+ "learning_rate": 9.439530272990698e-06,
162
+ "loss": 0.2365,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.315673895141367,
167
+ "grad_norm": 2.134601593017578,
168
+ "learning_rate": 9.363275888363582e-06,
169
+ "loss": 0.214,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.3293988471040351,
174
+ "grad_norm": 18.417972564697266,
175
+ "learning_rate": 9.287021503736465e-06,
176
+ "loss": 0.2669,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.34312379906670326,
181
+ "grad_norm": 3.676449775695801,
182
+ "learning_rate": 9.21076711910935e-06,
183
+ "loss": 0.2301,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.3568487510293714,
188
+ "grad_norm": 21.718795776367188,
189
+ "learning_rate": 9.134512734482233e-06,
190
+ "loss": 0.2332,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.3705737029920395,
195
+ "grad_norm": 15.048168182373047,
196
+ "learning_rate": 9.058258349855117e-06,
197
+ "loss": 0.1976,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.38429865495470766,
202
+ "grad_norm": 17.38605308532715,
203
+ "learning_rate": 8.982003965228e-06,
204
+ "loss": 0.2236,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.3980236069173758,
209
+ "grad_norm": 30.235185623168945,
210
+ "learning_rate": 8.905749580600886e-06,
211
+ "loss": 0.1932,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.4117485588800439,
216
+ "grad_norm": 21.414888381958008,
217
+ "learning_rate": 8.82949519597377e-06,
218
+ "loss": 0.2256,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.42547351084271207,
223
+ "grad_norm": 2.553528070449829,
224
+ "learning_rate": 8.753240811346654e-06,
225
+ "loss": 0.2145,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.43919846280538016,
230
+ "grad_norm": 5.725930213928223,
231
+ "learning_rate": 8.676986426719537e-06,
232
+ "loss": 0.2089,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.4529234147680483,
237
+ "grad_norm": 4.194558620452881,
238
+ "learning_rate": 8.600732042092421e-06,
239
+ "loss": 0.2349,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.46664836673071647,
244
+ "grad_norm": 4.438018321990967,
245
+ "learning_rate": 8.524477657465305e-06,
246
+ "loss": 0.2161,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.48037331869338457,
251
+ "grad_norm": 4.64914608001709,
252
+ "learning_rate": 8.448223272838189e-06,
253
+ "loss": 0.1956,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.4940982706560527,
258
+ "grad_norm": 11.573904991149902,
259
+ "learning_rate": 8.371968888211072e-06,
260
+ "loss": 0.1946,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.5078232226187208,
265
+ "grad_norm": 10.568695068359375,
266
+ "learning_rate": 8.295714503583956e-06,
267
+ "loss": 0.2072,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.5215481745813889,
272
+ "grad_norm": 1.9153978824615479,
273
+ "learning_rate": 8.21946011895684e-06,
274
+ "loss": 0.1983,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.5352731265440571,
279
+ "grad_norm": 19.77039337158203,
280
+ "learning_rate": 8.143205734329724e-06,
281
+ "loss": 0.2112,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.5489980785067252,
286
+ "grad_norm": 2.6344797611236572,
287
+ "learning_rate": 8.06695134970261e-06,
288
+ "loss": 0.1957,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.5627230304693933,
293
+ "grad_norm": 41.998775482177734,
294
+ "learning_rate": 7.990696965075493e-06,
295
+ "loss": 0.1756,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.5764479824320615,
300
+ "grad_norm": 9.939011573791504,
301
+ "learning_rate": 7.914442580448377e-06,
302
+ "loss": 0.1856,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.5901729343947296,
307
+ "grad_norm": 32.17470932006836,
308
+ "learning_rate": 7.83818819582126e-06,
309
+ "loss": 0.205,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.6038978863573977,
314
+ "grad_norm": 19.29119110107422,
315
+ "learning_rate": 7.761933811194144e-06,
316
+ "loss": 0.1973,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.6176228383200659,
321
+ "grad_norm": 2.429710865020752,
322
+ "learning_rate": 7.685679426567028e-06,
323
+ "loss": 0.2009,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.631347790282734,
328
+ "grad_norm": 3.910445213317871,
329
+ "learning_rate": 7.609425041939912e-06,
330
+ "loss": 0.1725,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.6450727422454021,
335
+ "grad_norm": 13.112035751342773,
336
+ "learning_rate": 7.5331706573127965e-06,
337
+ "loss": 0.1939,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.6587976942080702,
342
+ "grad_norm": 18.058584213256836,
343
+ "learning_rate": 7.45691627268568e-06,
344
+ "loss": 0.1751,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.6725226461707384,
349
+ "grad_norm": 11.847052574157715,
350
+ "learning_rate": 7.380661888058563e-06,
351
+ "loss": 0.1903,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.6862475981334065,
356
+ "grad_norm": 7.183902740478516,
357
+ "learning_rate": 7.304407503431448e-06,
358
+ "loss": 0.1795,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.6999725500960746,
363
+ "grad_norm": 11.07944107055664,
364
+ "learning_rate": 7.2281531188043316e-06,
365
+ "loss": 0.1854,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.7136975020587428,
370
+ "grad_norm": 14.285106658935547,
371
+ "learning_rate": 7.151898734177216e-06,
372
+ "loss": 0.1885,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.7274224540214109,
377
+ "grad_norm": 20.710567474365234,
378
+ "learning_rate": 7.075644349550099e-06,
379
+ "loss": 0.1911,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.741147405984079,
384
+ "grad_norm": 20.737842559814453,
385
+ "learning_rate": 6.999389964922984e-06,
386
+ "loss": 0.1826,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.7548723579467472,
391
+ "grad_norm": 15.488795280456543,
392
+ "learning_rate": 6.9231355802958675e-06,
393
+ "loss": 0.1777,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.7685973099094153,
398
+ "grad_norm": 20.551816940307617,
399
+ "learning_rate": 6.846881195668752e-06,
400
+ "loss": 0.1692,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.7823222618720834,
405
+ "grad_norm": 4.317481517791748,
406
+ "learning_rate": 6.770626811041635e-06,
407
+ "loss": 0.1596,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.7960472138347516,
412
+ "grad_norm": 11.099555015563965,
413
+ "learning_rate": 6.69437242641452e-06,
414
+ "loss": 0.1891,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.8097721657974197,
419
+ "grad_norm": 0.8909740447998047,
420
+ "learning_rate": 6.6181180417874034e-06,
421
+ "loss": 0.1728,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.8234971177600878,
426
+ "grad_norm": 5.078292369842529,
427
+ "learning_rate": 6.541863657160286e-06,
428
+ "loss": 0.1856,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.8372220697227559,
433
+ "grad_norm": 7.8703532218933105,
434
+ "learning_rate": 6.465609272533171e-06,
435
+ "loss": 0.183,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.8509470216854241,
440
+ "grad_norm": 15.550518989562988,
441
+ "learning_rate": 6.389354887906056e-06,
442
+ "loss": 0.1631,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.8646719736480922,
447
+ "grad_norm": 9.581011772155762,
448
+ "learning_rate": 6.313100503278939e-06,
449
+ "loss": 0.148,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.8783969256107603,
454
+ "grad_norm": 3.0507142543792725,
455
+ "learning_rate": 6.236846118651822e-06,
456
+ "loss": 0.1925,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.8921218775734285,
461
+ "grad_norm": 10.670945167541504,
462
+ "learning_rate": 6.160591734024707e-06,
463
+ "loss": 0.1487,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.9058468295360966,
468
+ "grad_norm": 19.39102554321289,
469
+ "learning_rate": 6.084337349397591e-06,
470
+ "loss": 0.1754,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.9195717814987647,
475
+ "grad_norm": 35.748374938964844,
476
+ "learning_rate": 6.008082964770475e-06,
477
+ "loss": 0.1712,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.9332967334614329,
482
+ "grad_norm": 2.9247872829437256,
483
+ "learning_rate": 5.931828580143358e-06,
484
+ "loss": 0.1531,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.947021685424101,
489
+ "grad_norm": 2.437190294265747,
490
+ "learning_rate": 5.855574195516243e-06,
491
+ "loss": 0.1546,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.9607466373867691,
496
+ "grad_norm": 3.3819751739501953,
497
+ "learning_rate": 5.779319810889127e-06,
498
+ "loss": 0.1485,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.9744715893494372,
503
+ "grad_norm": 2.5567026138305664,
504
+ "learning_rate": 5.70306542626201e-06,
505
+ "loss": 0.1529,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.9881965413121054,
510
+ "grad_norm": 3.1037750244140625,
511
+ "learning_rate": 5.626811041634894e-06,
512
+ "loss": 0.1583,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 1.0019214932747735,
517
+ "grad_norm": 8.52094554901123,
518
+ "learning_rate": 5.550556657007779e-06,
519
+ "loss": 0.1814,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 1.0156464452374416,
524
+ "grad_norm": 2.9368324279785156,
525
+ "learning_rate": 5.4743022723806626e-06,
526
+ "loss": 0.1437,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 1.0293713972001097,
531
+ "grad_norm": 5.706370830535889,
532
+ "learning_rate": 5.3980478877535455e-06,
533
+ "loss": 0.1474,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 1.0430963491627778,
538
+ "grad_norm": 18.225793838500977,
539
+ "learning_rate": 5.32179350312643e-06,
540
+ "loss": 0.1339,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 1.0568213011254461,
545
+ "grad_norm": 7.467564105987549,
546
+ "learning_rate": 5.245539118499314e-06,
547
+ "loss": 0.1244,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 1.0705462530881142,
552
+ "grad_norm": 1.9714295864105225,
553
+ "learning_rate": 5.1692847338721985e-06,
554
+ "loss": 0.1376,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 1.0842712050507823,
559
+ "grad_norm": 4.701173782348633,
560
+ "learning_rate": 5.0930303492450814e-06,
561
+ "loss": 0.1232,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 1.0979961570134504,
566
+ "grad_norm": 9.477237701416016,
567
+ "learning_rate": 5.016775964617966e-06,
568
+ "loss": 0.1327,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 1.1117211089761185,
573
+ "grad_norm": 2.713070869445801,
574
+ "learning_rate": 4.94052157999085e-06,
575
+ "loss": 0.1184,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 1.1254460609387866,
580
+ "grad_norm": 27.41179847717285,
581
+ "learning_rate": 4.864267195363734e-06,
582
+ "loss": 0.1236,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 1.1391710129014547,
587
+ "grad_norm": 1.996870994567871,
588
+ "learning_rate": 4.788012810736617e-06,
589
+ "loss": 0.1391,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 1.152895964864123,
594
+ "grad_norm": 2.3036551475524902,
595
+ "learning_rate": 4.711758426109502e-06,
596
+ "loss": 0.1368,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 1.1666209168267911,
601
+ "grad_norm": 14.458354949951172,
602
+ "learning_rate": 4.635504041482386e-06,
603
+ "loss": 0.1433,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 1.1803458687894592,
608
+ "grad_norm": 3.8688037395477295,
609
+ "learning_rate": 4.5592496568552695e-06,
610
+ "loss": 0.1483,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 1.1940708207521273,
615
+ "grad_norm": 25.26601791381836,
616
+ "learning_rate": 4.482995272228153e-06,
617
+ "loss": 0.1444,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 1.2077957727147954,
622
+ "grad_norm": 3.356841802597046,
623
+ "learning_rate": 4.406740887601038e-06,
624
+ "loss": 0.1361,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 1.2215207246774635,
629
+ "grad_norm": 3.6947531700134277,
630
+ "learning_rate": 4.330486502973921e-06,
631
+ "loss": 0.1265,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 1.2352456766401319,
636
+ "grad_norm": 3.885274648666382,
637
+ "learning_rate": 4.2542321183468055e-06,
638
+ "loss": 0.1208,
639
+ "step": 9000
640
+ }
641
+ ],
642
+ "logging_steps": 100,
643
+ "max_steps": 14572,
644
+ "num_input_tokens_seen": 0,
645
+ "num_train_epochs": 2,
646
+ "save_steps": 100,
647
+ "stateful_callbacks": {
648
+ "TrainerControl": {
649
+ "args": {
650
+ "should_epoch_stop": false,
651
+ "should_evaluate": false,
652
+ "should_log": false,
653
+ "should_save": true,
654
+ "should_training_stop": false
655
+ },
656
+ "attributes": {}
657
+ }
658
+ },
659
+ "total_flos": 0.0,
660
+ "train_batch_size": 1,
661
+ "trial_name": null,
662
+ "trial_params": null
663
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bf8997cd3eed0adbc43c8fd13a963d02c8d09d5e99d19963b0354356506ced
3
+ size 6161