saqidr commited on
Commit
047f165
·
verified ·
1 Parent(s): 52cc1fa

Training in progress, step 1000

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-16/checkpoint-1000/model.safetensors +1 -1
  3. run-16/checkpoint-1000/optimizer.pt +1 -1
  4. run-16/checkpoint-1000/rng_state.pth +1 -1
  5. run-16/checkpoint-1000/scheduler.pt +1 -1
  6. run-16/checkpoint-1000/training_args.bin +2 -2
  7. run-16/checkpoint-1500/config.json +331 -0
  8. run-16/checkpoint-1500/model.safetensors +3 -0
  9. run-16/checkpoint-1500/optimizer.pt +3 -0
  10. run-16/checkpoint-1500/rng_state.pth +3 -0
  11. run-16/checkpoint-1500/scheduler.pt +3 -0
  12. run-16/checkpoint-1500/special_tokens_map.json +7 -0
  13. run-16/checkpoint-1500/tokenizer.json +0 -0
  14. run-16/checkpoint-1500/tokenizer_config.json +55 -0
  15. run-16/checkpoint-1500/trainer_state.json +94 -0
  16. run-16/checkpoint-1500/training_args.bin +3 -0
  17. run-16/checkpoint-1500/vocab.txt +0 -0
  18. run-16/checkpoint-2000/config.json +331 -0
  19. run-16/checkpoint-2000/model.safetensors +3 -0
  20. run-16/checkpoint-2000/optimizer.pt +3 -0
  21. run-16/checkpoint-2000/rng_state.pth +3 -0
  22. run-16/checkpoint-2000/scheduler.pt +3 -0
  23. run-16/checkpoint-2000/special_tokens_map.json +7 -0
  24. run-16/checkpoint-2000/tokenizer.json +0 -0
  25. run-16/checkpoint-2000/tokenizer_config.json +55 -0
  26. run-16/checkpoint-2000/trainer_state.json +119 -0
  27. run-16/checkpoint-2000/training_args.bin +3 -0
  28. run-16/checkpoint-2000/vocab.txt +0 -0
  29. run-17/checkpoint-1000/config.json +1 -1
  30. run-17/checkpoint-1000/model.safetensors +1 -1
  31. run-17/checkpoint-1000/optimizer.pt +1 -1
  32. run-17/checkpoint-1000/rng_state.pth +1 -1
  33. run-17/checkpoint-1000/scheduler.pt +1 -1
  34. run-17/checkpoint-1000/tokenizer.json +1 -6
  35. run-17/checkpoint-1000/trainer_state.json +41 -27
  36. run-17/checkpoint-1000/training_args.bin +2 -2
  37. run-17/checkpoint-1500/config.json +1 -1
  38. run-17/checkpoint-1500/model.safetensors +1 -1
  39. run-17/checkpoint-1500/optimizer.pt +1 -1
  40. run-17/checkpoint-1500/rng_state.pth +1 -1
  41. run-17/checkpoint-1500/scheduler.pt +1 -1
  42. run-17/checkpoint-1500/tokenizer.json +1 -6
  43. run-17/checkpoint-1500/trainer_state.json +50 -35
  44. run-17/checkpoint-1500/training_args.bin +2 -2
  45. run-17/checkpoint-2000/config.json +1 -1
  46. run-17/checkpoint-2000/tokenizer.json +1 -6
  47. run-17/checkpoint-2000/trainer_state.json +64 -48
  48. run-17/checkpoint-500/model.safetensors +1 -1
  49. run-17/checkpoint-500/optimizer.pt +1 -1
  50. run-17/checkpoint-500/rng_state.pth +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b8ad3c9e3788334f5c2adb4229ae87dd8d5043fdb7947dc8f97f35fed88c2e7
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6bef4983937b9e30464a7b09e3c4246f5506160b1e8d8de933163b5fa5950c
3
  size 268290900
run-16/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1721fc39dea5c479ece9a9b990a5ff566bf714c7eecf0183f171481708abe75
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2df58a24de7f1a3cc40d04a583b676bf16a3321d35bf68a710880ee9cd76bf
3
  size 268290900
run-16/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b4cdfafbc29bf8e784daa50f567c814079376ef64b87c8d68f3799fd390842c
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f7fa0ca9142521f40e138907865dc3b8ef46443d7cb4ad13d85411bdb187a8
3
  size 536643898
run-16/checkpoint-1000/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae8803a4cfd93a17b836d411a0cdc283947bea33521d8af530f6f31af83987d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35ee7e612988cfbcef57649260f5e638d50749c336bb364c0aaa11036e867c9
3
  size 14244
run-16/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a4307cca951ef6d42c7f184774e8b1259c78b2bf130b8443ec0b62f6dbf689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c794bc4c67ef18245dd516031ce405ab557e4d551d225d8dd1e1abc0f2be8e33
3
  size 1064
run-16/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84e53c4833b1b6976718da62c42ddd308e97f2805d420cfde5501ed7c2459e5
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf27e76d8884c946fcfa9b2e89273479b0e58bfc88fe2cda59dc077e543cf3a
3
+ size 5176
run-16/checkpoint-1500/config.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "restaurant_reviews",
13
+ "1": "nutrition_info",
14
+ "2": "account_blocked",
15
+ "3": "oil_change_how",
16
+ "4": "time",
17
+ "5": "weather",
18
+ "6": "redeem_rewards",
19
+ "7": "interest_rate",
20
+ "8": "gas_type",
21
+ "9": "accept_reservations",
22
+ "10": "smart_home",
23
+ "11": "user_name",
24
+ "12": "report_lost_card",
25
+ "13": "repeat",
26
+ "14": "whisper_mode",
27
+ "15": "what_are_your_hobbies",
28
+ "16": "order",
29
+ "17": "jump_start",
30
+ "18": "schedule_meeting",
31
+ "19": "meeting_schedule",
32
+ "20": "freeze_account",
33
+ "21": "what_song",
34
+ "22": "meaning_of_life",
35
+ "23": "restaurant_reservation",
36
+ "24": "traffic",
37
+ "25": "make_call",
38
+ "26": "text",
39
+ "27": "bill_balance",
40
+ "28": "improve_credit_score",
41
+ "29": "change_language",
42
+ "30": "no",
43
+ "31": "measurement_conversion",
44
+ "32": "timer",
45
+ "33": "flip_coin",
46
+ "34": "do_you_have_pets",
47
+ "35": "balance",
48
+ "36": "tell_joke",
49
+ "37": "last_maintenance",
50
+ "38": "exchange_rate",
51
+ "39": "uber",
52
+ "40": "car_rental",
53
+ "41": "credit_limit",
54
+ "42": "oos",
55
+ "43": "shopping_list",
56
+ "44": "expiration_date",
57
+ "45": "routing",
58
+ "46": "meal_suggestion",
59
+ "47": "tire_change",
60
+ "48": "todo_list",
61
+ "49": "card_declined",
62
+ "50": "rewards_balance",
63
+ "51": "change_accent",
64
+ "52": "vaccines",
65
+ "53": "reminder_update",
66
+ "54": "food_last",
67
+ "55": "change_ai_name",
68
+ "56": "bill_due",
69
+ "57": "who_do_you_work_for",
70
+ "58": "share_location",
71
+ "59": "international_visa",
72
+ "60": "calendar",
73
+ "61": "translate",
74
+ "62": "carry_on",
75
+ "63": "book_flight",
76
+ "64": "insurance_change",
77
+ "65": "todo_list_update",
78
+ "66": "timezone",
79
+ "67": "cancel_reservation",
80
+ "68": "transactions",
81
+ "69": "credit_score",
82
+ "70": "report_fraud",
83
+ "71": "spending_history",
84
+ "72": "directions",
85
+ "73": "spelling",
86
+ "74": "insurance",
87
+ "75": "what_is_your_name",
88
+ "76": "reminder",
89
+ "77": "where_are_you_from",
90
+ "78": "distance",
91
+ "79": "payday",
92
+ "80": "flight_status",
93
+ "81": "find_phone",
94
+ "82": "greeting",
95
+ "83": "alarm",
96
+ "84": "order_status",
97
+ "85": "confirm_reservation",
98
+ "86": "cook_time",
99
+ "87": "damaged_card",
100
+ "88": "reset_settings",
101
+ "89": "pin_change",
102
+ "90": "replacement_card_duration",
103
+ "91": "new_card",
104
+ "92": "roll_dice",
105
+ "93": "income",
106
+ "94": "taxes",
107
+ "95": "date",
108
+ "96": "who_made_you",
109
+ "97": "pto_request",
110
+ "98": "tire_pressure",
111
+ "99": "how_old_are_you",
112
+ "100": "rollover_401k",
113
+ "101": "pto_request_status",
114
+ "102": "how_busy",
115
+ "103": "application_status",
116
+ "104": "recipe",
117
+ "105": "calendar_update",
118
+ "106": "play_music",
119
+ "107": "yes",
120
+ "108": "direct_deposit",
121
+ "109": "credit_limit_change",
122
+ "110": "gas",
123
+ "111": "pay_bill",
124
+ "112": "ingredients_list",
125
+ "113": "lost_luggage",
126
+ "114": "goodbye",
127
+ "115": "what_can_i_ask_you",
128
+ "116": "book_hotel",
129
+ "117": "are_you_a_bot",
130
+ "118": "next_song",
131
+ "119": "change_speed",
132
+ "120": "plug_type",
133
+ "121": "maybe",
134
+ "122": "w2",
135
+ "123": "oil_change_when",
136
+ "124": "thank_you",
137
+ "125": "shopping_list_update",
138
+ "126": "pto_balance",
139
+ "127": "order_checks",
140
+ "128": "travel_alert",
141
+ "129": "fun_fact",
142
+ "130": "sync_device",
143
+ "131": "schedule_maintenance",
144
+ "132": "apr",
145
+ "133": "transfer",
146
+ "134": "ingredient_substitution",
147
+ "135": "calories",
148
+ "136": "current_location",
149
+ "137": "international_fees",
150
+ "138": "calculator",
151
+ "139": "definition",
152
+ "140": "next_holiday",
153
+ "141": "update_playlist",
154
+ "142": "mpg",
155
+ "143": "min_payment",
156
+ "144": "change_user_name",
157
+ "145": "restaurant_suggestion",
158
+ "146": "travel_notification",
159
+ "147": "cancel",
160
+ "148": "pto_used",
161
+ "149": "travel_suggestion",
162
+ "150": "change_volume"
163
+ },
164
+ "initializer_range": 0.02,
165
+ "label2id": {
166
+ "accept_reservations": 9,
167
+ "account_blocked": 2,
168
+ "alarm": 83,
169
+ "application_status": 103,
170
+ "apr": 132,
171
+ "are_you_a_bot": 117,
172
+ "balance": 35,
173
+ "bill_balance": 27,
174
+ "bill_due": 56,
175
+ "book_flight": 63,
176
+ "book_hotel": 116,
177
+ "calculator": 138,
178
+ "calendar": 60,
179
+ "calendar_update": 105,
180
+ "calories": 135,
181
+ "cancel": 147,
182
+ "cancel_reservation": 67,
183
+ "car_rental": 40,
184
+ "card_declined": 49,
185
+ "carry_on": 62,
186
+ "change_accent": 51,
187
+ "change_ai_name": 55,
188
+ "change_language": 29,
189
+ "change_speed": 119,
190
+ "change_user_name": 144,
191
+ "change_volume": 150,
192
+ "confirm_reservation": 85,
193
+ "cook_time": 86,
194
+ "credit_limit": 41,
195
+ "credit_limit_change": 109,
196
+ "credit_score": 69,
197
+ "current_location": 136,
198
+ "damaged_card": 87,
199
+ "date": 95,
200
+ "definition": 139,
201
+ "direct_deposit": 108,
202
+ "directions": 72,
203
+ "distance": 78,
204
+ "do_you_have_pets": 34,
205
+ "exchange_rate": 38,
206
+ "expiration_date": 44,
207
+ "find_phone": 81,
208
+ "flight_status": 80,
209
+ "flip_coin": 33,
210
+ "food_last": 54,
211
+ "freeze_account": 20,
212
+ "fun_fact": 129,
213
+ "gas": 110,
214
+ "gas_type": 8,
215
+ "goodbye": 114,
216
+ "greeting": 82,
217
+ "how_busy": 102,
218
+ "how_old_are_you": 99,
219
+ "improve_credit_score": 28,
220
+ "income": 93,
221
+ "ingredient_substitution": 134,
222
+ "ingredients_list": 112,
223
+ "insurance": 74,
224
+ "insurance_change": 64,
225
+ "interest_rate": 7,
226
+ "international_fees": 137,
227
+ "international_visa": 59,
228
+ "jump_start": 17,
229
+ "last_maintenance": 37,
230
+ "lost_luggage": 113,
231
+ "make_call": 25,
232
+ "maybe": 121,
233
+ "meal_suggestion": 46,
234
+ "meaning_of_life": 22,
235
+ "measurement_conversion": 31,
236
+ "meeting_schedule": 19,
237
+ "min_payment": 143,
238
+ "mpg": 142,
239
+ "new_card": 91,
240
+ "next_holiday": 140,
241
+ "next_song": 118,
242
+ "no": 30,
243
+ "nutrition_info": 1,
244
+ "oil_change_how": 3,
245
+ "oil_change_when": 123,
246
+ "oos": 42,
247
+ "order": 16,
248
+ "order_checks": 127,
249
+ "order_status": 84,
250
+ "pay_bill": 111,
251
+ "payday": 79,
252
+ "pin_change": 89,
253
+ "play_music": 106,
254
+ "plug_type": 120,
255
+ "pto_balance": 126,
256
+ "pto_request": 97,
257
+ "pto_request_status": 101,
258
+ "pto_used": 148,
259
+ "recipe": 104,
260
+ "redeem_rewards": 6,
261
+ "reminder": 76,
262
+ "reminder_update": 53,
263
+ "repeat": 13,
264
+ "replacement_card_duration": 90,
265
+ "report_fraud": 70,
266
+ "report_lost_card": 12,
267
+ "reset_settings": 88,
268
+ "restaurant_reservation": 23,
269
+ "restaurant_reviews": 0,
270
+ "restaurant_suggestion": 145,
271
+ "rewards_balance": 50,
272
+ "roll_dice": 92,
273
+ "rollover_401k": 100,
274
+ "routing": 45,
275
+ "schedule_maintenance": 131,
276
+ "schedule_meeting": 18,
277
+ "share_location": 58,
278
+ "shopping_list": 43,
279
+ "shopping_list_update": 125,
280
+ "smart_home": 10,
281
+ "spelling": 73,
282
+ "spending_history": 71,
283
+ "sync_device": 130,
284
+ "taxes": 94,
285
+ "tell_joke": 36,
286
+ "text": 26,
287
+ "thank_you": 124,
288
+ "time": 4,
289
+ "timer": 32,
290
+ "timezone": 66,
291
+ "tire_change": 47,
292
+ "tire_pressure": 98,
293
+ "todo_list": 48,
294
+ "todo_list_update": 65,
295
+ "traffic": 24,
296
+ "transactions": 68,
297
+ "transfer": 133,
298
+ "translate": 61,
299
+ "travel_alert": 128,
300
+ "travel_notification": 146,
301
+ "travel_suggestion": 149,
302
+ "uber": 39,
303
+ "update_playlist": 141,
304
+ "user_name": 11,
305
+ "vaccines": 52,
306
+ "w2": 122,
307
+ "weather": 5,
308
+ "what_are_your_hobbies": 15,
309
+ "what_can_i_ask_you": 115,
310
+ "what_is_your_name": 75,
311
+ "what_song": 21,
312
+ "where_are_you_from": 77,
313
+ "whisper_mode": 14,
314
+ "who_do_you_work_for": 57,
315
+ "who_made_you": 96,
316
+ "yes": 107
317
+ },
318
+ "max_position_embeddings": 512,
319
+ "model_type": "distilbert",
320
+ "n_heads": 12,
321
+ "n_layers": 6,
322
+ "pad_token_id": 0,
323
+ "problem_type": "single_label_classification",
324
+ "qa_dropout": 0.1,
325
+ "seq_classif_dropout": 0.2,
326
+ "sinusoidal_pos_embds": false,
327
+ "tie_weights_": true,
328
+ "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
+ "vocab_size": 30522
331
+ }
run-16/checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c6e3d549ed202b5a6c6b2a4da9d162828a41a10893a327e214a94309e11fa9
3
+ size 268290900
run-16/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9451ef0bf31a664680e715e2697dd706cebd1eb36a2b34c6b2e26d399670a5a
3
+ size 536643898
run-16/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c10319269a5ccb2640eed78049edda0fca1ea40d757f64b6ab5474fe9e926f9
3
+ size 14244
run-16/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71453465aad25f4c5a0a948496c64b1f74df850abda497954afe3695c00756ee
3
+ size 1064
run-16/checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-16/checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-16/checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.716981132075472,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.594516129032258,
14
+ "eval_loss": 0.20309074223041534,
15
+ "eval_runtime": 1.4199,
16
+ "eval_samples_per_second": 2183.305,
17
+ "eval_steps_per_second": 45.779,
18
+ "step": 318
19
+ },
20
+ {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5301857590675354,
23
+ "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3277,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.8351612903225807,
30
+ "eval_loss": 0.09738388657569885,
31
+ "eval_runtime": 1.3686,
32
+ "eval_samples_per_second": 2265.13,
33
+ "eval_steps_per_second": 47.495,
34
+ "step": 636
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.8835483870967742,
39
+ "eval_loss": 0.06395673006772995,
40
+ "eval_runtime": 1.3721,
41
+ "eval_samples_per_second": 2259.293,
42
+ "eval_steps_per_second": 47.372,
43
+ "step": 954
44
+ },
45
+ {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.4834806025028229,
48
+ "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.1129,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.8983870967741936,
55
+ "eval_loss": 0.048434291034936905,
56
+ "eval_runtime": 1.3648,
57
+ "eval_samples_per_second": 2271.334,
58
+ "eval_steps_per_second": 47.625,
59
+ "step": 1272
60
+ },
61
+ {
62
+ "epoch": 4.716981132075472,
63
+ "grad_norm": 0.3106568455696106,
64
+ "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0703,
66
+ "step": 1500
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 3180,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 10,
73
+ "save_steps": 500,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": false
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 402837063777120.0,
87
+ "train_batch_size": 48,
88
+ "trial_name": null,
89
+ "trial_params": {
90
+ "alpha": 0.35485465599924254,
91
+ "num_train_epochs": 10,
92
+ "temperature": 9
93
+ }
94
+ }
run-16/checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf27e76d8884c946fcfa9b2e89273479b0e58bfc88fe2cda59dc077e543cf3a
3
+ size 5176
run-16/checkpoint-1500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-2000/config.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "restaurant_reviews",
13
+ "1": "nutrition_info",
14
+ "2": "account_blocked",
15
+ "3": "oil_change_how",
16
+ "4": "time",
17
+ "5": "weather",
18
+ "6": "redeem_rewards",
19
+ "7": "interest_rate",
20
+ "8": "gas_type",
21
+ "9": "accept_reservations",
22
+ "10": "smart_home",
23
+ "11": "user_name",
24
+ "12": "report_lost_card",
25
+ "13": "repeat",
26
+ "14": "whisper_mode",
27
+ "15": "what_are_your_hobbies",
28
+ "16": "order",
29
+ "17": "jump_start",
30
+ "18": "schedule_meeting",
31
+ "19": "meeting_schedule",
32
+ "20": "freeze_account",
33
+ "21": "what_song",
34
+ "22": "meaning_of_life",
35
+ "23": "restaurant_reservation",
36
+ "24": "traffic",
37
+ "25": "make_call",
38
+ "26": "text",
39
+ "27": "bill_balance",
40
+ "28": "improve_credit_score",
41
+ "29": "change_language",
42
+ "30": "no",
43
+ "31": "measurement_conversion",
44
+ "32": "timer",
45
+ "33": "flip_coin",
46
+ "34": "do_you_have_pets",
47
+ "35": "balance",
48
+ "36": "tell_joke",
49
+ "37": "last_maintenance",
50
+ "38": "exchange_rate",
51
+ "39": "uber",
52
+ "40": "car_rental",
53
+ "41": "credit_limit",
54
+ "42": "oos",
55
+ "43": "shopping_list",
56
+ "44": "expiration_date",
57
+ "45": "routing",
58
+ "46": "meal_suggestion",
59
+ "47": "tire_change",
60
+ "48": "todo_list",
61
+ "49": "card_declined",
62
+ "50": "rewards_balance",
63
+ "51": "change_accent",
64
+ "52": "vaccines",
65
+ "53": "reminder_update",
66
+ "54": "food_last",
67
+ "55": "change_ai_name",
68
+ "56": "bill_due",
69
+ "57": "who_do_you_work_for",
70
+ "58": "share_location",
71
+ "59": "international_visa",
72
+ "60": "calendar",
73
+ "61": "translate",
74
+ "62": "carry_on",
75
+ "63": "book_flight",
76
+ "64": "insurance_change",
77
+ "65": "todo_list_update",
78
+ "66": "timezone",
79
+ "67": "cancel_reservation",
80
+ "68": "transactions",
81
+ "69": "credit_score",
82
+ "70": "report_fraud",
83
+ "71": "spending_history",
84
+ "72": "directions",
85
+ "73": "spelling",
86
+ "74": "insurance",
87
+ "75": "what_is_your_name",
88
+ "76": "reminder",
89
+ "77": "where_are_you_from",
90
+ "78": "distance",
91
+ "79": "payday",
92
+ "80": "flight_status",
93
+ "81": "find_phone",
94
+ "82": "greeting",
95
+ "83": "alarm",
96
+ "84": "order_status",
97
+ "85": "confirm_reservation",
98
+ "86": "cook_time",
99
+ "87": "damaged_card",
100
+ "88": "reset_settings",
101
+ "89": "pin_change",
102
+ "90": "replacement_card_duration",
103
+ "91": "new_card",
104
+ "92": "roll_dice",
105
+ "93": "income",
106
+ "94": "taxes",
107
+ "95": "date",
108
+ "96": "who_made_you",
109
+ "97": "pto_request",
110
+ "98": "tire_pressure",
111
+ "99": "how_old_are_you",
112
+ "100": "rollover_401k",
113
+ "101": "pto_request_status",
114
+ "102": "how_busy",
115
+ "103": "application_status",
116
+ "104": "recipe",
117
+ "105": "calendar_update",
118
+ "106": "play_music",
119
+ "107": "yes",
120
+ "108": "direct_deposit",
121
+ "109": "credit_limit_change",
122
+ "110": "gas",
123
+ "111": "pay_bill",
124
+ "112": "ingredients_list",
125
+ "113": "lost_luggage",
126
+ "114": "goodbye",
127
+ "115": "what_can_i_ask_you",
128
+ "116": "book_hotel",
129
+ "117": "are_you_a_bot",
130
+ "118": "next_song",
131
+ "119": "change_speed",
132
+ "120": "plug_type",
133
+ "121": "maybe",
134
+ "122": "w2",
135
+ "123": "oil_change_when",
136
+ "124": "thank_you",
137
+ "125": "shopping_list_update",
138
+ "126": "pto_balance",
139
+ "127": "order_checks",
140
+ "128": "travel_alert",
141
+ "129": "fun_fact",
142
+ "130": "sync_device",
143
+ "131": "schedule_maintenance",
144
+ "132": "apr",
145
+ "133": "transfer",
146
+ "134": "ingredient_substitution",
147
+ "135": "calories",
148
+ "136": "current_location",
149
+ "137": "international_fees",
150
+ "138": "calculator",
151
+ "139": "definition",
152
+ "140": "next_holiday",
153
+ "141": "update_playlist",
154
+ "142": "mpg",
155
+ "143": "min_payment",
156
+ "144": "change_user_name",
157
+ "145": "restaurant_suggestion",
158
+ "146": "travel_notification",
159
+ "147": "cancel",
160
+ "148": "pto_used",
161
+ "149": "travel_suggestion",
162
+ "150": "change_volume"
163
+ },
164
+ "initializer_range": 0.02,
165
+ "label2id": {
166
+ "accept_reservations": 9,
167
+ "account_blocked": 2,
168
+ "alarm": 83,
169
+ "application_status": 103,
170
+ "apr": 132,
171
+ "are_you_a_bot": 117,
172
+ "balance": 35,
173
+ "bill_balance": 27,
174
+ "bill_due": 56,
175
+ "book_flight": 63,
176
+ "book_hotel": 116,
177
+ "calculator": 138,
178
+ "calendar": 60,
179
+ "calendar_update": 105,
180
+ "calories": 135,
181
+ "cancel": 147,
182
+ "cancel_reservation": 67,
183
+ "car_rental": 40,
184
+ "card_declined": 49,
185
+ "carry_on": 62,
186
+ "change_accent": 51,
187
+ "change_ai_name": 55,
188
+ "change_language": 29,
189
+ "change_speed": 119,
190
+ "change_user_name": 144,
191
+ "change_volume": 150,
192
+ "confirm_reservation": 85,
193
+ "cook_time": 86,
194
+ "credit_limit": 41,
195
+ "credit_limit_change": 109,
196
+ "credit_score": 69,
197
+ "current_location": 136,
198
+ "damaged_card": 87,
199
+ "date": 95,
200
+ "definition": 139,
201
+ "direct_deposit": 108,
202
+ "directions": 72,
203
+ "distance": 78,
204
+ "do_you_have_pets": 34,
205
+ "exchange_rate": 38,
206
+ "expiration_date": 44,
207
+ "find_phone": 81,
208
+ "flight_status": 80,
209
+ "flip_coin": 33,
210
+ "food_last": 54,
211
+ "freeze_account": 20,
212
+ "fun_fact": 129,
213
+ "gas": 110,
214
+ "gas_type": 8,
215
+ "goodbye": 114,
216
+ "greeting": 82,
217
+ "how_busy": 102,
218
+ "how_old_are_you": 99,
219
+ "improve_credit_score": 28,
220
+ "income": 93,
221
+ "ingredient_substitution": 134,
222
+ "ingredients_list": 112,
223
+ "insurance": 74,
224
+ "insurance_change": 64,
225
+ "interest_rate": 7,
226
+ "international_fees": 137,
227
+ "international_visa": 59,
228
+ "jump_start": 17,
229
+ "last_maintenance": 37,
230
+ "lost_luggage": 113,
231
+ "make_call": 25,
232
+ "maybe": 121,
233
+ "meal_suggestion": 46,
234
+ "meaning_of_life": 22,
235
+ "measurement_conversion": 31,
236
+ "meeting_schedule": 19,
237
+ "min_payment": 143,
238
+ "mpg": 142,
239
+ "new_card": 91,
240
+ "next_holiday": 140,
241
+ "next_song": 118,
242
+ "no": 30,
243
+ "nutrition_info": 1,
244
+ "oil_change_how": 3,
245
+ "oil_change_when": 123,
246
+ "oos": 42,
247
+ "order": 16,
248
+ "order_checks": 127,
249
+ "order_status": 84,
250
+ "pay_bill": 111,
251
+ "payday": 79,
252
+ "pin_change": 89,
253
+ "play_music": 106,
254
+ "plug_type": 120,
255
+ "pto_balance": 126,
256
+ "pto_request": 97,
257
+ "pto_request_status": 101,
258
+ "pto_used": 148,
259
+ "recipe": 104,
260
+ "redeem_rewards": 6,
261
+ "reminder": 76,
262
+ "reminder_update": 53,
263
+ "repeat": 13,
264
+ "replacement_card_duration": 90,
265
+ "report_fraud": 70,
266
+ "report_lost_card": 12,
267
+ "reset_settings": 88,
268
+ "restaurant_reservation": 23,
269
+ "restaurant_reviews": 0,
270
+ "restaurant_suggestion": 145,
271
+ "rewards_balance": 50,
272
+ "roll_dice": 92,
273
+ "rollover_401k": 100,
274
+ "routing": 45,
275
+ "schedule_maintenance": 131,
276
+ "schedule_meeting": 18,
277
+ "share_location": 58,
278
+ "shopping_list": 43,
279
+ "shopping_list_update": 125,
280
+ "smart_home": 10,
281
+ "spelling": 73,
282
+ "spending_history": 71,
283
+ "sync_device": 130,
284
+ "taxes": 94,
285
+ "tell_joke": 36,
286
+ "text": 26,
287
+ "thank_you": 124,
288
+ "time": 4,
289
+ "timer": 32,
290
+ "timezone": 66,
291
+ "tire_change": 47,
292
+ "tire_pressure": 98,
293
+ "todo_list": 48,
294
+ "todo_list_update": 65,
295
+ "traffic": 24,
296
+ "transactions": 68,
297
+ "transfer": 133,
298
+ "translate": 61,
299
+ "travel_alert": 128,
300
+ "travel_notification": 146,
301
+ "travel_suggestion": 149,
302
+ "uber": 39,
303
+ "update_playlist": 141,
304
+ "user_name": 11,
305
+ "vaccines": 52,
306
+ "w2": 122,
307
+ "weather": 5,
308
+ "what_are_your_hobbies": 15,
309
+ "what_can_i_ask_you": 115,
310
+ "what_is_your_name": 75,
311
+ "what_song": 21,
312
+ "where_are_you_from": 77,
313
+ "whisper_mode": 14,
314
+ "who_do_you_work_for": 57,
315
+ "who_made_you": 96,
316
+ "yes": 107
317
+ },
318
+ "max_position_embeddings": 512,
319
+ "model_type": "distilbert",
320
+ "n_heads": 12,
321
+ "n_layers": 6,
322
+ "pad_token_id": 0,
323
+ "problem_type": "single_label_classification",
324
+ "qa_dropout": 0.1,
325
+ "seq_classif_dropout": 0.2,
326
+ "sinusoidal_pos_embds": false,
327
+ "tie_weights_": true,
328
+ "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
+ "vocab_size": 30522
331
+ }
run-16/checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08ab1c235552ffa6fa59c221acf782f742d78c2dc50cc6baf6832fb03f987ea
3
+ size 268290900
run-16/checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b7814a15b8b7429c20731854d4cbff37b4c3749451f59d1ddfad961fc1ad34
3
+ size 536643898
run-16/checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ccc14cc902672c3d8e770c2a2ce3a532b454981f3118cb18a09274102a99fc
3
+ size 14244
run-16/checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d45918bfeb622ba899798234ec7646c7a90dd3f5771db086f5b7dee1d5a530
3
+ size 1064
run-16/checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-16/checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-16/checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.289308176100629,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.594516129032258,
14
+ "eval_loss": 0.20309074223041534,
15
+ "eval_runtime": 1.4199,
16
+ "eval_samples_per_second": 2183.305,
17
+ "eval_steps_per_second": 45.779,
18
+ "step": 318
19
+ },
20
+ {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5301857590675354,
23
+ "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3277,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.8351612903225807,
30
+ "eval_loss": 0.09738388657569885,
31
+ "eval_runtime": 1.3686,
32
+ "eval_samples_per_second": 2265.13,
33
+ "eval_steps_per_second": 47.495,
34
+ "step": 636
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.8835483870967742,
39
+ "eval_loss": 0.06395673006772995,
40
+ "eval_runtime": 1.3721,
41
+ "eval_samples_per_second": 2259.293,
42
+ "eval_steps_per_second": 47.372,
43
+ "step": 954
44
+ },
45
+ {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.4834806025028229,
48
+ "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.1129,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.8983870967741936,
55
+ "eval_loss": 0.048434291034936905,
56
+ "eval_runtime": 1.3648,
57
+ "eval_samples_per_second": 2271.334,
58
+ "eval_steps_per_second": 47.625,
59
+ "step": 1272
60
+ },
61
+ {
62
+ "epoch": 4.716981132075472,
63
+ "grad_norm": 0.3106568455696106,
64
+ "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0703,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_accuracy": 0.9112903225806451,
71
+ "eval_loss": 0.03913173824548721,
72
+ "eval_runtime": 1.3844,
73
+ "eval_samples_per_second": 2239.167,
74
+ "eval_steps_per_second": 46.95,
75
+ "step": 1590
76
+ },
77
+ {
78
+ "epoch": 6.0,
79
+ "eval_accuracy": 0.9212903225806451,
80
+ "eval_loss": 0.034084782004356384,
81
+ "eval_runtime": 1.3664,
82
+ "eval_samples_per_second": 2268.753,
83
+ "eval_steps_per_second": 47.571,
84
+ "step": 1908
85
+ },
86
+ {
87
+ "epoch": 6.289308176100629,
88
+ "grad_norm": 0.2402593046426773,
89
+ "learning_rate": 7.421383647798742e-06,
90
+ "loss": 0.0546,
91
+ "step": 2000
92
+ }
93
+ ],
94
+ "logging_steps": 500,
95
+ "max_steps": 3180,
96
+ "num_input_tokens_seen": 0,
97
+ "num_train_epochs": 10,
98
+ "save_steps": 500,
99
+ "stateful_callbacks": {
100
+ "TrainerControl": {
101
+ "args": {
102
+ "should_epoch_stop": false,
103
+ "should_evaluate": false,
104
+ "should_log": false,
105
+ "should_save": true,
106
+ "should_training_stop": false
107
+ },
108
+ "attributes": {}
109
+ }
110
+ },
111
+ "total_flos": 532459451005944.0,
112
+ "train_batch_size": 48,
113
+ "trial_name": null,
114
+ "trial_params": {
115
+ "alpha": 0.35485465599924254,
116
+ "num_train_epochs": 10,
117
+ "temperature": 9
118
+ }
119
+ }
run-16/checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf27e76d8884c946fcfa9b2e89273479b0e58bfc88fe2cda59dc077e543cf3a
3
+ size 5176
run-16/checkpoint-2000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-17/checkpoint-1000/config.json CHANGED
@@ -326,6 +326,6 @@
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
- "transformers_version": "4.37.2",
330
  "vocab_size": 30522
331
  }
 
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
  "vocab_size": 30522
331
  }
run-17/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:876efb8717af81a656b7ac19c6b30c5e46231a26626bb6bd55af97ec7fd3099d
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6bef4983937b9e30464a7b09e3c4246f5506160b1e8d8de933163b5fa5950c
3
  size 268290900
run-17/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c31e8830b035d69f929263a42d2764c572dd48d8fe87cddd5b0c79e7e00607e9
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51d083e84643d2f1634b790089e7d0ab47c37699b837e4bb7653916448e0e0c
3
  size 536643898
run-17/checkpoint-1000/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae8803a4cfd93a17b836d411a0cdc283947bea33521d8af530f6f31af83987d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35ee7e612988cfbcef57649260f5e638d50749c336bb364c0aaa11036e867c9
3
  size 14244
run-17/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a4307cca951ef6d42c7f184774e8b1259c78b2bf130b8443ec0b62f6dbf689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045cf4abe065257226fe11ac1a91dfd4c5b953cb2366365ef8bb18b4cf33e734
3
  size 1064
run-17/checkpoint-1000/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
run-17/checkpoint-1000/trainer_state.json CHANGED
@@ -10,55 +10,69 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6732258064516129,
14
- "eval_loss": 0.4103888273239136,
15
- "eval_runtime": 1.2819,
16
- "eval_samples_per_second": 2418.21,
17
- "eval_steps_per_second": 50.704,
18
  "step": 318
19
  },
20
  {
21
- "epoch": 1.57,
22
- "learning_rate": 1.650593990216632e-05,
23
- "loss": 0.6437,
 
24
  "step": 500
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.8432258064516129,
29
- "eval_loss": 0.13950829207897186,
30
- "eval_runtime": 1.2856,
31
- "eval_samples_per_second": 2411.271,
32
- "eval_steps_per_second": 50.559,
33
  "step": 636
34
  },
35
  {
36
  "epoch": 3.0,
37
- "eval_accuracy": 0.9003225806451612,
38
- "eval_loss": 0.07073405385017395,
39
- "eval_runtime": 1.2761,
40
- "eval_samples_per_second": 2429.337,
41
- "eval_steps_per_second": 50.938,
42
  "step": 954
43
  },
44
  {
45
- "epoch": 3.14,
46
- "learning_rate": 1.3011879804332637e-05,
47
- "loss": 0.1631,
 
48
  "step": 1000
49
  }
50
  ],
51
  "logging_steps": 500,
52
- "max_steps": 2862,
53
  "num_input_tokens_seen": 0,
54
- "num_train_epochs": 9,
55
  "save_steps": 500,
56
- "total_flos": 424768346970828.0,
 
 
 
 
 
 
 
 
 
 
 
 
57
  "train_batch_size": 48,
58
  "trial_name": null,
59
  "trial_params": {
60
- "alpha": 0.34724487520007086,
61
- "num_train_epochs": 9,
62
- "temperature": 2
63
  }
64
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6390322580645161,
14
+ "eval_loss": 0.2914898693561554,
15
+ "eval_runtime": 1.3599,
16
+ "eval_samples_per_second": 2279.516,
17
+ "eval_steps_per_second": 47.796,
18
  "step": 318
19
  },
20
  {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.7131265997886658,
23
+ "learning_rate": 1.606918238993711e-05,
24
+ "loss": 0.4624,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8441935483870968,
30
+ "eval_loss": 0.12102781236171722,
31
+ "eval_runtime": 1.3504,
32
+ "eval_samples_per_second": 2295.675,
33
+ "eval_steps_per_second": 48.135,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8887096774193548,
39
+ "eval_loss": 0.0709487721323967,
40
+ "eval_runtime": 1.3676,
41
+ "eval_samples_per_second": 2266.756,
42
+ "eval_steps_per_second": 47.529,
43
  "step": 954
44
  },
45
  {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.6162304878234863,
48
+ "learning_rate": 1.2138364779874214e-05,
49
+ "loss": 0.1415,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 2544,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 8,
57
  "save_steps": 500,
58
+ "stateful_callbacks": {
59
+ "TrainerControl": {
60
+ "args": {
61
+ "should_epoch_stop": false,
62
+ "should_evaluate": false,
63
+ "should_log": false,
64
+ "should_save": true,
65
+ "should_training_stop": false
66
+ },
67
+ "attributes": {}
68
+ }
69
+ },
70
+ "total_flos": 319943755193412.0,
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
+ "alpha": 0.7281665463662037,
75
+ "num_train_epochs": 8,
76
+ "temperature": 3
77
  }
78
  }
run-17/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ecffc9352fe3049303c30dad0aa46b5b31065b1c973c1f20e15bae4914342d6
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f77ccbc6073cca1defa141fd1e3f67eb83e9f377f70358773cc59eff779ed27
3
+ size 5176
run-17/checkpoint-1500/config.json CHANGED
@@ -326,6 +326,6 @@
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
- "transformers_version": "4.37.2",
330
  "vocab_size": 30522
331
  }
 
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
  "vocab_size": 30522
331
  }
run-17/checkpoint-1500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:106d03fb619431388a2c6c0fb5cde37e682e671427afbe1afcbf94001d8b7d97
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f3c6c489ef679d2654152010f773836a23fb499791929c0661de70a5daa912
3
  size 268290900
run-17/checkpoint-1500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c49b8976e5565b04a3c3eeaf8b10a084d4b630d25d75444f5de103bbc5331fd1
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76742aa32d82f2d02329174e45bdf8a574abf11393c47be188586fb74abff8e
3
  size 536643898
run-17/checkpoint-1500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4150b40cdd095f99e6d506db714a6c0a9a316d6b4d021acbfec8d198c96919
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c10319269a5ccb2640eed78049edda0fca1ea40d757f64b6ab5474fe9e926f9
3
  size 14244
run-17/checkpoint-1500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693ec081eb0fa0af7d13e289edb194450dd19fdada23346e2af4292ea228535f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7b4645e59a5c5cb66f63e8bcb5f006c535fd0ea63db9ae152dd586fd465b28
3
  size 1064
run-17/checkpoint-1500/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
run-17/checkpoint-1500/trainer_state.json CHANGED
@@ -10,70 +10,85 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6732258064516129,
14
- "eval_loss": 0.4103888273239136,
15
- "eval_runtime": 1.2819,
16
- "eval_samples_per_second": 2418.21,
17
- "eval_steps_per_second": 50.704,
18
  "step": 318
19
  },
20
  {
21
- "epoch": 1.57,
22
- "learning_rate": 1.650593990216632e-05,
23
- "loss": 0.6437,
 
24
  "step": 500
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.8432258064516129,
29
- "eval_loss": 0.13950829207897186,
30
- "eval_runtime": 1.2856,
31
- "eval_samples_per_second": 2411.271,
32
- "eval_steps_per_second": 50.559,
33
  "step": 636
34
  },
35
  {
36
  "epoch": 3.0,
37
- "eval_accuracy": 0.9003225806451612,
38
- "eval_loss": 0.07073405385017395,
39
- "eval_runtime": 1.2761,
40
- "eval_samples_per_second": 2429.337,
41
- "eval_steps_per_second": 50.938,
42
  "step": 954
43
  },
44
  {
45
- "epoch": 3.14,
46
- "learning_rate": 1.3011879804332637e-05,
47
- "loss": 0.1631,
 
48
  "step": 1000
49
  },
50
  {
51
  "epoch": 4.0,
52
- "eval_accuracy": 0.9193548387096774,
53
- "eval_loss": 0.050263434648513794,
54
- "eval_runtime": 1.2809,
55
- "eval_samples_per_second": 2420.202,
56
- "eval_steps_per_second": 50.746,
57
  "step": 1272
58
  },
59
  {
60
- "epoch": 4.72,
61
- "learning_rate": 9.517819706498952e-06,
62
- "loss": 0.0819,
 
63
  "step": 1500
64
  }
65
  ],
66
  "logging_steps": 500,
67
- "max_steps": 2862,
68
  "num_input_tokens_seen": 0,
69
- "num_train_epochs": 9,
70
  "save_steps": 500,
71
- "total_flos": 555087517179216.0,
 
 
 
 
 
 
 
 
 
 
 
 
72
  "train_batch_size": 48,
73
  "trial_name": null,
74
  "trial_params": {
75
- "alpha": 0.34724487520007086,
76
- "num_train_epochs": 9,
77
- "temperature": 2
78
  }
79
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6390322580645161,
14
+ "eval_loss": 0.2914898693561554,
15
+ "eval_runtime": 1.3599,
16
+ "eval_samples_per_second": 2279.516,
17
+ "eval_steps_per_second": 47.796,
18
  "step": 318
19
  },
20
  {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.7131265997886658,
23
+ "learning_rate": 1.606918238993711e-05,
24
+ "loss": 0.4624,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8441935483870968,
30
+ "eval_loss": 0.12102781236171722,
31
+ "eval_runtime": 1.3504,
32
+ "eval_samples_per_second": 2295.675,
33
+ "eval_steps_per_second": 48.135,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8887096774193548,
39
+ "eval_loss": 0.0709487721323967,
40
+ "eval_runtime": 1.3676,
41
+ "eval_samples_per_second": 2266.756,
42
+ "eval_steps_per_second": 47.529,
43
  "step": 954
44
  },
45
  {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.6162304878234863,
48
+ "learning_rate": 1.2138364779874214e-05,
49
+ "loss": 0.1415,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9035483870967742,
55
+ "eval_loss": 0.051646389067173004,
56
+ "eval_runtime": 1.3981,
57
+ "eval_samples_per_second": 2217.284,
58
+ "eval_steps_per_second": 46.491,
59
  "step": 1272
60
  },
61
  {
62
+ "epoch": 4.716981132075472,
63
+ "grad_norm": 0.39001786708831787,
64
+ "learning_rate": 8.207547169811321e-06,
65
+ "loss": 0.0805,
66
  "step": 1500
67
  }
68
  ],
69
  "logging_steps": 500,
70
+ "max_steps": 2544,
71
  "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 8,
73
  "save_steps": 500,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": false
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 450371359983132.0,
87
  "train_batch_size": 48,
88
  "trial_name": null,
89
  "trial_params": {
90
+ "alpha": 0.7281665463662037,
91
+ "num_train_epochs": 8,
92
+ "temperature": 3
93
  }
94
  }
run-17/checkpoint-1500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ecffc9352fe3049303c30dad0aa46b5b31065b1c973c1f20e15bae4914342d6
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f77ccbc6073cca1defa141fd1e3f67eb83e9f377f70358773cc59eff779ed27
3
+ size 5176
run-17/checkpoint-2000/config.json CHANGED
@@ -326,6 +326,6 @@
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
- "transformers_version": "4.37.2",
330
  "vocab_size": 30522
331
  }
 
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
  "vocab_size": 30522
331
  }
run-17/checkpoint-2000/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
run-17/checkpoint-2000/trainer_state.json CHANGED
@@ -10,94 +10,110 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6732258064516129,
14
- "eval_loss": 0.4103888273239136,
15
- "eval_runtime": 1.2819,
16
- "eval_samples_per_second": 2418.21,
17
- "eval_steps_per_second": 50.704,
18
  "step": 318
19
  },
20
  {
21
- "epoch": 1.57,
22
- "learning_rate": 1.650593990216632e-05,
23
- "loss": 0.6437,
 
24
  "step": 500
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.8432258064516129,
29
- "eval_loss": 0.13950829207897186,
30
- "eval_runtime": 1.2856,
31
- "eval_samples_per_second": 2411.271,
32
- "eval_steps_per_second": 50.559,
33
  "step": 636
34
  },
35
  {
36
  "epoch": 3.0,
37
- "eval_accuracy": 0.9003225806451612,
38
- "eval_loss": 0.07073405385017395,
39
- "eval_runtime": 1.2761,
40
- "eval_samples_per_second": 2429.337,
41
- "eval_steps_per_second": 50.938,
42
  "step": 954
43
  },
44
  {
45
- "epoch": 3.14,
46
- "learning_rate": 1.3011879804332637e-05,
47
- "loss": 0.1631,
 
48
  "step": 1000
49
  },
50
  {
51
  "epoch": 4.0,
52
- "eval_accuracy": 0.9193548387096774,
53
- "eval_loss": 0.050263434648513794,
54
- "eval_runtime": 1.2809,
55
- "eval_samples_per_second": 2420.202,
56
- "eval_steps_per_second": 50.746,
57
  "step": 1272
58
  },
59
  {
60
- "epoch": 4.72,
61
- "learning_rate": 9.517819706498952e-06,
62
- "loss": 0.0819,
 
63
  "step": 1500
64
  },
65
  {
66
  "epoch": 5.0,
67
- "eval_accuracy": 0.93,
68
- "eval_loss": 0.04236248508095741,
69
- "eval_runtime": 1.2781,
70
- "eval_samples_per_second": 2425.4,
71
- "eval_steps_per_second": 50.855,
72
  "step": 1590
73
  },
74
  {
75
  "epoch": 6.0,
76
- "eval_accuracy": 0.9303225806451613,
77
- "eval_loss": 0.03793748468160629,
78
- "eval_runtime": 1.2793,
79
- "eval_samples_per_second": 2423.196,
80
- "eval_steps_per_second": 50.809,
81
  "step": 1908
82
  },
83
  {
84
- "epoch": 6.29,
85
- "learning_rate": 6.02375960866527e-06,
86
- "loss": 0.0618,
 
87
  "step": 2000
88
  }
89
  ],
90
  "logging_steps": 500,
91
- "max_steps": 2862,
92
  "num_input_tokens_seen": 0,
93
- "num_train_epochs": 9,
94
  "save_steps": 500,
95
- "total_flos": 684048401579340.0,
 
 
 
 
 
 
 
 
 
 
 
 
96
  "train_batch_size": 48,
97
  "trial_name": null,
98
  "trial_params": {
99
- "alpha": 0.34724487520007086,
100
- "num_train_epochs": 9,
101
- "temperature": 2
102
  }
103
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6390322580645161,
14
+ "eval_loss": 0.2914898693561554,
15
+ "eval_runtime": 1.3599,
16
+ "eval_samples_per_second": 2279.516,
17
+ "eval_steps_per_second": 47.796,
18
  "step": 318
19
  },
20
  {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.7131265997886658,
23
+ "learning_rate": 1.606918238993711e-05,
24
+ "loss": 0.4624,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8441935483870968,
30
+ "eval_loss": 0.12102781236171722,
31
+ "eval_runtime": 1.3504,
32
+ "eval_samples_per_second": 2295.675,
33
+ "eval_steps_per_second": 48.135,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8887096774193548,
39
+ "eval_loss": 0.0709487721323967,
40
+ "eval_runtime": 1.3676,
41
+ "eval_samples_per_second": 2266.756,
42
+ "eval_steps_per_second": 47.529,
43
  "step": 954
44
  },
45
  {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.6162304878234863,
48
+ "learning_rate": 1.2138364779874214e-05,
49
+ "loss": 0.1415,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9035483870967742,
55
+ "eval_loss": 0.051646389067173004,
56
+ "eval_runtime": 1.3981,
57
+ "eval_samples_per_second": 2217.284,
58
+ "eval_steps_per_second": 46.491,
59
  "step": 1272
60
  },
61
  {
62
+ "epoch": 4.716981132075472,
63
+ "grad_norm": 0.39001786708831787,
64
+ "learning_rate": 8.207547169811321e-06,
65
+ "loss": 0.0805,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
+ "eval_accuracy": 0.9174193548387096,
71
+ "eval_loss": 0.04204501211643219,
72
+ "eval_runtime": 1.3693,
73
+ "eval_samples_per_second": 2263.945,
74
+ "eval_steps_per_second": 47.47,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
+ "eval_accuracy": 0.9225806451612903,
80
+ "eval_loss": 0.03724784776568413,
81
+ "eval_runtime": 1.369,
82
+ "eval_samples_per_second": 2264.397,
83
+ "eval_steps_per_second": 47.479,
84
  "step": 1908
85
  },
86
  {
87
+ "epoch": 6.289308176100629,
88
+ "grad_norm": 0.31736573576927185,
89
+ "learning_rate": 4.276729559748428e-06,
90
+ "loss": 0.0624,
91
  "step": 2000
92
  }
93
  ],
94
  "logging_steps": 500,
95
+ "max_steps": 2544,
96
  "num_input_tokens_seen": 0,
97
+ "num_train_epochs": 8,
98
  "save_steps": 500,
99
+ "stateful_callbacks": {
100
+ "TrainerControl": {
101
+ "args": {
102
+ "should_epoch_stop": false,
103
+ "should_evaluate": false,
104
+ "should_log": false,
105
+ "should_save": true,
106
+ "should_training_stop": false
107
+ },
108
+ "attributes": {}
109
+ }
110
+ },
111
+ "total_flos": 579993747211956.0,
112
  "train_batch_size": 48,
113
  "trial_name": null,
114
  "trial_params": {
115
+ "alpha": 0.7281665463662037,
116
+ "num_train_epochs": 8,
117
+ "temperature": 3
118
  }
119
  }
run-17/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:377901badbdc882ddb2bb0ea45eaae5e0bb5bd275cc3989a0997f48ce153110d
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:979dfdf7f7a52776e674f9cd88575e0174a0f16a5d641d1ac04228dfef87d766
3
  size 268290900
run-17/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e36fba8bc76dfa3a75a29131eecd277ae6b094071f6873563580fe5037ebef1b
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4042e254b9bf37ce29b2d64292a80294380b5d74124d7c3f93b4d388ccd18dab
3
  size 536643898
run-17/checkpoint-500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8174c1d6ac2627de77161655e4e20ef37d9f2235e2e7c4adc0da0d4e0e14b6d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9fb2a0dfb1b0ccef3590fe01e9bd16b6db86f247cc9c7e77290c217a53bac20
3
  size 14244