Spaces:
Runtime error
Runtime error
Pavankalyan
commited on
Commit
·
2d6dc51
1
Parent(s):
56115d8
Upload 8 files
Browse files- config.json +186 -0
- intents.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +214 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21",
|
36 |
+
"22": "LABEL_22",
|
37 |
+
"23": "LABEL_23",
|
38 |
+
"24": "LABEL_24",
|
39 |
+
"25": "LABEL_25",
|
40 |
+
"26": "LABEL_26",
|
41 |
+
"27": "LABEL_27",
|
42 |
+
"28": "LABEL_28",
|
43 |
+
"29": "LABEL_29",
|
44 |
+
"30": "LABEL_30",
|
45 |
+
"31": "LABEL_31",
|
46 |
+
"32": "LABEL_32",
|
47 |
+
"33": "LABEL_33",
|
48 |
+
"34": "LABEL_34",
|
49 |
+
"35": "LABEL_35",
|
50 |
+
"36": "LABEL_36",
|
51 |
+
"37": "LABEL_37",
|
52 |
+
"38": "LABEL_38",
|
53 |
+
"39": "LABEL_39",
|
54 |
+
"40": "LABEL_40",
|
55 |
+
"41": "LABEL_41",
|
56 |
+
"42": "LABEL_42",
|
57 |
+
"43": "LABEL_43",
|
58 |
+
"44": "LABEL_44",
|
59 |
+
"45": "LABEL_45",
|
60 |
+
"46": "LABEL_46",
|
61 |
+
"47": "LABEL_47",
|
62 |
+
"48": "LABEL_48",
|
63 |
+
"49": "LABEL_49",
|
64 |
+
"50": "LABEL_50",
|
65 |
+
"51": "LABEL_51",
|
66 |
+
"52": "LABEL_52",
|
67 |
+
"53": "LABEL_53",
|
68 |
+
"54": "LABEL_54",
|
69 |
+
"55": "LABEL_55",
|
70 |
+
"56": "LABEL_56",
|
71 |
+
"57": "LABEL_57",
|
72 |
+
"58": "LABEL_58",
|
73 |
+
"59": "LABEL_59",
|
74 |
+
"60": "LABEL_60",
|
75 |
+
"61": "LABEL_61",
|
76 |
+
"62": "LABEL_62",
|
77 |
+
"63": "LABEL_63",
|
78 |
+
"64": "LABEL_64",
|
79 |
+
"65": "LABEL_65",
|
80 |
+
"66": "LABEL_66",
|
81 |
+
"67": "LABEL_67",
|
82 |
+
"68": "LABEL_68",
|
83 |
+
"69": "LABEL_69",
|
84 |
+
"70": "LABEL_70",
|
85 |
+
"71": "LABEL_71",
|
86 |
+
"72": "LABEL_72",
|
87 |
+
"73": "LABEL_73",
|
88 |
+
"74": "LABEL_74",
|
89 |
+
"75": "LABEL_75",
|
90 |
+
"76": "LABEL_76"
|
91 |
+
},
|
92 |
+
"initializer_range": 0.02,
|
93 |
+
"intermediate_size": 3072,
|
94 |
+
"label2id": {
|
95 |
+
"LABEL_0": 0,
|
96 |
+
"LABEL_1": 1,
|
97 |
+
"LABEL_10": 10,
|
98 |
+
"LABEL_11": 11,
|
99 |
+
"LABEL_12": 12,
|
100 |
+
"LABEL_13": 13,
|
101 |
+
"LABEL_14": 14,
|
102 |
+
"LABEL_15": 15,
|
103 |
+
"LABEL_16": 16,
|
104 |
+
"LABEL_17": 17,
|
105 |
+
"LABEL_18": 18,
|
106 |
+
"LABEL_19": 19,
|
107 |
+
"LABEL_2": 2,
|
108 |
+
"LABEL_20": 20,
|
109 |
+
"LABEL_21": 21,
|
110 |
+
"LABEL_22": 22,
|
111 |
+
"LABEL_23": 23,
|
112 |
+
"LABEL_24": 24,
|
113 |
+
"LABEL_25": 25,
|
114 |
+
"LABEL_26": 26,
|
115 |
+
"LABEL_27": 27,
|
116 |
+
"LABEL_28": 28,
|
117 |
+
"LABEL_29": 29,
|
118 |
+
"LABEL_3": 3,
|
119 |
+
"LABEL_30": 30,
|
120 |
+
"LABEL_31": 31,
|
121 |
+
"LABEL_32": 32,
|
122 |
+
"LABEL_33": 33,
|
123 |
+
"LABEL_34": 34,
|
124 |
+
"LABEL_35": 35,
|
125 |
+
"LABEL_36": 36,
|
126 |
+
"LABEL_37": 37,
|
127 |
+
"LABEL_38": 38,
|
128 |
+
"LABEL_39": 39,
|
129 |
+
"LABEL_4": 4,
|
130 |
+
"LABEL_40": 40,
|
131 |
+
"LABEL_41": 41,
|
132 |
+
"LABEL_42": 42,
|
133 |
+
"LABEL_43": 43,
|
134 |
+
"LABEL_44": 44,
|
135 |
+
"LABEL_45": 45,
|
136 |
+
"LABEL_46": 46,
|
137 |
+
"LABEL_47": 47,
|
138 |
+
"LABEL_48": 48,
|
139 |
+
"LABEL_49": 49,
|
140 |
+
"LABEL_5": 5,
|
141 |
+
"LABEL_50": 50,
|
142 |
+
"LABEL_51": 51,
|
143 |
+
"LABEL_52": 52,
|
144 |
+
"LABEL_53": 53,
|
145 |
+
"LABEL_54": 54,
|
146 |
+
"LABEL_55": 55,
|
147 |
+
"LABEL_56": 56,
|
148 |
+
"LABEL_57": 57,
|
149 |
+
"LABEL_58": 58,
|
150 |
+
"LABEL_59": 59,
|
151 |
+
"LABEL_6": 6,
|
152 |
+
"LABEL_60": 60,
|
153 |
+
"LABEL_61": 61,
|
154 |
+
"LABEL_62": 62,
|
155 |
+
"LABEL_63": 63,
|
156 |
+
"LABEL_64": 64,
|
157 |
+
"LABEL_65": 65,
|
158 |
+
"LABEL_66": 66,
|
159 |
+
"LABEL_67": 67,
|
160 |
+
"LABEL_68": 68,
|
161 |
+
"LABEL_69": 69,
|
162 |
+
"LABEL_7": 7,
|
163 |
+
"LABEL_70": 70,
|
164 |
+
"LABEL_71": 71,
|
165 |
+
"LABEL_72": 72,
|
166 |
+
"LABEL_73": 73,
|
167 |
+
"LABEL_74": 74,
|
168 |
+
"LABEL_75": 75,
|
169 |
+
"LABEL_76": 76,
|
170 |
+
"LABEL_8": 8,
|
171 |
+
"LABEL_9": 9
|
172 |
+
},
|
173 |
+
"layer_norm_eps": 1e-05,
|
174 |
+
"max_position_embeddings": 514,
|
175 |
+
"model_type": "roberta",
|
176 |
+
"num_attention_heads": 12,
|
177 |
+
"num_hidden_layers": 12,
|
178 |
+
"pad_token_id": 1,
|
179 |
+
"position_embedding_type": "absolute",
|
180 |
+
"problem_type": "single_label_classification",
|
181 |
+
"torch_dtype": "float32",
|
182 |
+
"transformers_version": "4.31.0",
|
183 |
+
"type_vocab_size": 1,
|
184 |
+
"use_cache": true,
|
185 |
+
"vocab_size": 50265
|
186 |
+
}
|
intents.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"0": "lost_or_stolen_phone", "1": "declined_transfer", "2": "cash_withdrawal_charge", "3": "topping_up_by_card", "4": "country_support", "5": "balance_not_updated_after_bank_transfer", "6": "pending_transfer", "7": "beneficiary_not_allowed", "8": "virtual_card_not_working", "9": "declined_cash_withdrawal", "10": "supported_cards_and_currencies", "11": "Refund_not_showing_up", "12": "pending_card_payment", "13": "get_physical_card", "14": "activate_my_card", "15": "terminate_account", "16": "top_up_limits", "17": "pending_top_up", "18": "top_up_by_cash_or_cheque", "19": "reverted_card_payment?", "20": "card_acceptance", "21": "age_limit", "22": "card_payment_not_recognised", "23": "automatic_top_up", "24": "cash_withdrawal_not_recognised", "25": "verify_top_up", "26": "wrong_amount_of_cash_received", "27": "fiat_currency_support", "28": "top_up_reverted", "29": "verify_my_identity", "30": "exchange_via_app", "31": "lost_or_stolen_card", "32": "transfer_not_received_by_recipient", "33": "visa_or_mastercard", "34": "transfer_fee_charged", "35": "card_linking", "36": "card_arrival", "37": "wrong_exchange_rate_for_cash_withdrawal", "38": "unable_to_verify_identity", "39": "card_payment_fee_charged", "40": "top_up_failed", "41": "card_not_working", "42": "atm_support", "43": "cancel_transfer", "44": "order_physical_card", "45": "card_about_to_expire", "46": "pin_blocked", "47": "why_verify_identity", "48": "transaction_charged_twice", "49": "direct_debit_payment_not_recognised", "50": "card_delivery_estimate", "51": "contactless_not_working", "52": "exchange_charge", "53": "get_disposable_virtual_card", "54": "compromised_card", "55": "card_payment_wrong_exchange_rate", "56": "request_refund", "57": "receiving_money", "58": "transfer_timing", "59": "verify_source_of_funds", "60": "apple_pay_or_google_pay", "61": "exchange_rate", "62": "edit_personal_details", "63": "balance_not_updated_after_cheque_or_cash_deposit", "64": "transfer_into_account", "65": "getting_virtual_card", "66": "getting_spare_card", "67": "disposable_card_limits", "68": "pending_cash_withdrawal", "69": "top_up_by_bank_transfer_charge", "70": "top_up_by_card_charge", "71": "extra_charge_on_statement", "72": "passcode_forgotten", "73": "declined_card_payment", "74": "change_pin", "75": "card_swallowed", "76": "failed_transfer"}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953a0107261e59a7c0b326be2398638c2d62db1f36cb6e23f648307b75f4b71a
|
3 |
+
size 997756485
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fa8d7e8162dc7d9119172c69c4648055c7dea8aca0457e17d15106fa3703188
|
3 |
+
size 498888305
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e39fdaefe5e7bb58da16ed6f952ba8f89d04d5705450539452a679df09e5db0
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbb0979a4f31fb59fd1a059ec6dc56099d17007b6a95dc5b134d92f658d10197
|
3 |
+
size 563
|
trainer_state.json
ADDED
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.46609172224998474,
|
3 |
+
"best_model_checkpoint": "./results_classification/checkpoint-1008",
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 1890,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.47876061969015493,
|
13 |
+
"eval_f1": 0.4269991937425738,
|
14 |
+
"eval_loss": 2.655285120010376,
|
15 |
+
"eval_precision": 0.5494019355743038,
|
16 |
+
"eval_recall": 0.47876061969015493,
|
17 |
+
"eval_runtime": 7.4841,
|
18 |
+
"eval_samples_per_second": 267.365,
|
19 |
+
"eval_steps_per_second": 4.276,
|
20 |
+
"step": 126
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.7426286856571714,
|
25 |
+
"eval_f1": 0.7138537650916374,
|
26 |
+
"eval_loss": 1.5136545896530151,
|
27 |
+
"eval_precision": 0.7537780922874874,
|
28 |
+
"eval_recall": 0.7426286856571714,
|
29 |
+
"eval_runtime": 7.5247,
|
30 |
+
"eval_samples_per_second": 265.923,
|
31 |
+
"eval_steps_per_second": 4.253,
|
32 |
+
"step": 252
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.8235882058970515,
|
37 |
+
"eval_f1": 0.8100185021709088,
|
38 |
+
"eval_loss": 0.9697439074516296,
|
39 |
+
"eval_precision": 0.8502379869379162,
|
40 |
+
"eval_recall": 0.8235882058970515,
|
41 |
+
"eval_runtime": 7.5422,
|
42 |
+
"eval_samples_per_second": 265.307,
|
43 |
+
"eval_steps_per_second": 4.243,
|
44 |
+
"step": 378
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.97,
|
48 |
+
"learning_rate": 1.0002499375156212e-05,
|
49 |
+
"loss": 2.0929,
|
50 |
+
"step": 500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.8680659670164917,
|
55 |
+
"eval_f1": 0.8634639903385385,
|
56 |
+
"eval_loss": 0.713852047920227,
|
57 |
+
"eval_precision": 0.882324990578513,
|
58 |
+
"eval_recall": 0.8680659670164917,
|
59 |
+
"eval_runtime": 7.4941,
|
60 |
+
"eval_samples_per_second": 267.008,
|
61 |
+
"eval_steps_per_second": 4.27,
|
62 |
+
"step": 504
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 5.0,
|
66 |
+
"eval_accuracy": 0.895552223888056,
|
67 |
+
"eval_f1": 0.8937627825776138,
|
68 |
+
"eval_loss": 0.5724937319755554,
|
69 |
+
"eval_precision": 0.9001995344818834,
|
70 |
+
"eval_recall": 0.895552223888056,
|
71 |
+
"eval_runtime": 7.508,
|
72 |
+
"eval_samples_per_second": 266.516,
|
73 |
+
"eval_steps_per_second": 4.262,
|
74 |
+
"step": 630
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 6.0,
|
78 |
+
"eval_accuracy": 0.9025487256371814,
|
79 |
+
"eval_f1": 0.9015269347270028,
|
80 |
+
"eval_loss": 0.5064622759819031,
|
81 |
+
"eval_precision": 0.9098775744608221,
|
82 |
+
"eval_recall": 0.9025487256371814,
|
83 |
+
"eval_runtime": 7.5479,
|
84 |
+
"eval_samples_per_second": 265.106,
|
85 |
+
"eval_steps_per_second": 4.24,
|
86 |
+
"step": 756
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 7.0,
|
90 |
+
"eval_accuracy": 0.9045477261369316,
|
91 |
+
"eval_f1": 0.9043691796671066,
|
92 |
+
"eval_loss": 0.47243431210517883,
|
93 |
+
"eval_precision": 0.9103961233141646,
|
94 |
+
"eval_recall": 0.9045477261369316,
|
95 |
+
"eval_runtime": 7.5019,
|
96 |
+
"eval_samples_per_second": 266.734,
|
97 |
+
"eval_steps_per_second": 4.266,
|
98 |
+
"step": 882
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.94,
|
102 |
+
"learning_rate": 4.998750312421895e-09,
|
103 |
+
"loss": 0.5401,
|
104 |
+
"step": 1000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 8.0,
|
108 |
+
"eval_accuracy": 0.9035482258870565,
|
109 |
+
"eval_f1": 0.9032948555406941,
|
110 |
+
"eval_loss": 0.46609172224998474,
|
111 |
+
"eval_precision": 0.9089395111974776,
|
112 |
+
"eval_recall": 0.9035482258870565,
|
113 |
+
"eval_runtime": 7.5877,
|
114 |
+
"eval_samples_per_second": 263.717,
|
115 |
+
"eval_steps_per_second": 4.217,
|
116 |
+
"step": 1008
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 9.0,
|
120 |
+
"eval_accuracy": 0.9035482258870565,
|
121 |
+
"eval_f1": 0.9032948555406941,
|
122 |
+
"eval_loss": 0.46609172224998474,
|
123 |
+
"eval_precision": 0.9089395111974776,
|
124 |
+
"eval_recall": 0.9035482258870565,
|
125 |
+
"eval_runtime": 7.5072,
|
126 |
+
"eval_samples_per_second": 266.546,
|
127 |
+
"eval_steps_per_second": 4.263,
|
128 |
+
"step": 1134
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 10.0,
|
132 |
+
"eval_accuracy": 0.9035482258870565,
|
133 |
+
"eval_f1": 0.9032948555406941,
|
134 |
+
"eval_loss": 0.46609172224998474,
|
135 |
+
"eval_precision": 0.9089395111974776,
|
136 |
+
"eval_recall": 0.9035482258870565,
|
137 |
+
"eval_runtime": 7.553,
|
138 |
+
"eval_samples_per_second": 264.929,
|
139 |
+
"eval_steps_per_second": 4.237,
|
140 |
+
"step": 1260
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 11.0,
|
144 |
+
"eval_accuracy": 0.9035482258870565,
|
145 |
+
"eval_f1": 0.9032948555406941,
|
146 |
+
"eval_loss": 0.46609172224998474,
|
147 |
+
"eval_precision": 0.9089395111974776,
|
148 |
+
"eval_recall": 0.9035482258870565,
|
149 |
+
"eval_runtime": 7.5371,
|
150 |
+
"eval_samples_per_second": 265.487,
|
151 |
+
"eval_steps_per_second": 4.246,
|
152 |
+
"step": 1386
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 11.9,
|
156 |
+
"learning_rate": 0.0,
|
157 |
+
"loss": 0.4189,
|
158 |
+
"step": 1500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 12.0,
|
162 |
+
"eval_accuracy": 0.9035482258870565,
|
163 |
+
"eval_f1": 0.9032948555406941,
|
164 |
+
"eval_loss": 0.46609172224998474,
|
165 |
+
"eval_precision": 0.9089395111974776,
|
166 |
+
"eval_recall": 0.9035482258870565,
|
167 |
+
"eval_runtime": 7.515,
|
168 |
+
"eval_samples_per_second": 266.269,
|
169 |
+
"eval_steps_per_second": 4.258,
|
170 |
+
"step": 1512
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 13.0,
|
174 |
+
"eval_accuracy": 0.9035482258870565,
|
175 |
+
"eval_f1": 0.9032948555406941,
|
176 |
+
"eval_loss": 0.46609172224998474,
|
177 |
+
"eval_precision": 0.9089395111974776,
|
178 |
+
"eval_recall": 0.9035482258870565,
|
179 |
+
"eval_runtime": 7.5178,
|
180 |
+
"eval_samples_per_second": 266.167,
|
181 |
+
"eval_steps_per_second": 4.257,
|
182 |
+
"step": 1638
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 14.0,
|
186 |
+
"eval_accuracy": 0.9035482258870565,
|
187 |
+
"eval_f1": 0.9032948555406941,
|
188 |
+
"eval_loss": 0.46609172224998474,
|
189 |
+
"eval_precision": 0.9089395111974776,
|
190 |
+
"eval_recall": 0.9035482258870565,
|
191 |
+
"eval_runtime": 7.4943,
|
192 |
+
"eval_samples_per_second": 267.004,
|
193 |
+
"eval_steps_per_second": 4.27,
|
194 |
+
"step": 1764
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 15.0,
|
198 |
+
"eval_accuracy": 0.9035482258870565,
|
199 |
+
"eval_f1": 0.9032948555406941,
|
200 |
+
"eval_loss": 0.46609172224998474,
|
201 |
+
"eval_precision": 0.9089395111974776,
|
202 |
+
"eval_recall": 0.9035482258870565,
|
203 |
+
"eval_runtime": 7.5368,
|
204 |
+
"eval_samples_per_second": 265.499,
|
205 |
+
"eval_steps_per_second": 4.246,
|
206 |
+
"step": 1890
|
207 |
+
}
|
208 |
+
],
|
209 |
+
"max_steps": 1890,
|
210 |
+
"num_train_epochs": 15,
|
211 |
+
"total_flos": 5925466237910400.0,
|
212 |
+
"trial_name": null,
|
213 |
+
"trial_params": null
|
214 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6096087fe1c43816fd75bae87a05a81c78698407bbbd1d058474190bde702e
|
3 |
+
size 3963
|