Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +132 -162
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 344790040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8962e483a174ca887089bca215fcc134b3d7cd29049dc3fa9e81f411b10ad198
|
3 |
size 344790040
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 689692538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a26081b96d44f7aa4a12360a1ef108c0d93dfb7afab42e1e27b764c11652af27
|
3 |
size 689692538
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbbd8b4a2dbc8fd3db2017ceb5ff77a698159c33408d0a4db73e8ca4ac709c19
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,201 +1,171 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./results/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"eval_steps":
|
6 |
-
"global_step":
|
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,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_precision": 0.
|
17 |
-
"eval_recall":
|
18 |
-
"eval_roc_auc": 0.
|
19 |
-
"eval_runtime":
|
20 |
-
"eval_samples_per_second": 22.
|
21 |
-
"eval_steps_per_second": 0.
|
22 |
"step": 0
|
23 |
},
|
24 |
{
|
25 |
-
"epoch": 0.
|
26 |
-
"grad_norm":
|
27 |
-
"learning_rate": 5e-05,
|
28 |
-
"loss": 0.
|
29 |
-
"step":
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"epoch": 0.3225806451612903,
|
33 |
-
"grad_norm": 282179.78125,
|
34 |
-
"learning_rate": 4.918032786885246e-05,
|
35 |
-
"loss": 0.3455,
|
36 |
-
"step": 20
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"epoch": 0.4838709677419355,
|
40 |
-
"grad_norm": 89623.296875,
|
41 |
-
"learning_rate": 4.836065573770492e-05,
|
42 |
-
"loss": 0.1399,
|
43 |
-
"step": 30
|
44 |
},
|
45 |
{
|
46 |
-
"epoch": 0.
|
47 |
-
"eval_accuracy": 0.
|
48 |
-
"eval_f1": 0.
|
49 |
-
"eval_loss": 0.
|
50 |
"eval_precision": 1.0,
|
51 |
-
"eval_recall": 0.
|
52 |
-
"eval_roc_auc": 0.
|
53 |
-
"eval_runtime":
|
54 |
-
"eval_samples_per_second":
|
55 |
-
"eval_steps_per_second": 0.
|
56 |
-
"step":
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.6451612903225806,
|
60 |
-
"grad_norm": 94711.421875,
|
61 |
-
"learning_rate": 4.754098360655738e-05,
|
62 |
-
"loss": 0.1264,
|
63 |
-
"step": 40
|
64 |
-
},
|
65 |
-
{
|
66 |
-
"epoch": 0.8064516129032258,
|
67 |
-
"grad_norm": 5300.99853515625,
|
68 |
-
"learning_rate": 4.672131147540984e-05,
|
69 |
-
"loss": 0.0676,
|
70 |
-
"step": 50
|
71 |
-
},
|
72 |
-
{
|
73 |
-
"epoch": 0.967741935483871,
|
74 |
-
"grad_norm": 832800.4375,
|
75 |
-
"learning_rate": 4.59016393442623e-05,
|
76 |
-
"loss": 0.1843,
|
77 |
-
"step": 60
|
78 |
-
},
|
79 |
-
{
|
80 |
-
"epoch": 0.967741935483871,
|
81 |
-
"eval_accuracy": 0.9938650306748467,
|
82 |
-
"eval_f1": 0.9945553539019963,
|
83 |
-
"eval_loss": 0.016523737460374832,
|
84 |
-
"eval_precision": 0.9963636363636363,
|
85 |
-
"eval_recall": 0.9927536231884058,
|
86 |
-
"eval_roc_auc": 0.9940293937538274,
|
87 |
-
"eval_runtime": 23.1377,
|
88 |
-
"eval_samples_per_second": 21.134,
|
89 |
-
"eval_steps_per_second": 0.346,
|
90 |
-
"step": 60
|
91 |
},
|
92 |
{
|
93 |
-
"epoch":
|
94 |
-
"grad_norm":
|
95 |
-
"learning_rate":
|
96 |
-
"loss": 0.
|
97 |
-
"step":
|
98 |
-
},
|
99 |
-
{
|
100 |
-
"epoch": 1.2903225806451613,
|
101 |
-
"grad_norm": 6823.15771484375,
|
102 |
-
"learning_rate": 4.426229508196721e-05,
|
103 |
-
"loss": 0.0504,
|
104 |
-
"step": 80
|
105 |
},
|
106 |
{
|
107 |
-
"epoch":
|
108 |
-
"
|
109 |
-
"
|
110 |
-
"
|
111 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
},
|
113 |
{
|
114 |
-
"epoch":
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"eval_recall": 0.9963768115942029,
|
120 |
-
"eval_roc_auc": 0.9934935701163503,
|
121 |
-
"eval_runtime": 23.6734,
|
122 |
-
"eval_samples_per_second": 20.656,
|
123 |
-
"eval_steps_per_second": 0.338,
|
124 |
-
"step": 90
|
125 |
},
|
126 |
{
|
127 |
-
"epoch":
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
},
|
133 |
{
|
134 |
-
"epoch":
|
135 |
-
"grad_norm":
|
136 |
-
"learning_rate":
|
137 |
-
"loss": 0.
|
138 |
-
"step":
|
139 |
},
|
140 |
{
|
141 |
-
"epoch":
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
146 |
},
|
147 |
{
|
148 |
-
"epoch":
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"eval_recall": 0.9601449275362319,
|
154 |
-
"eval_roc_auc": 0.980072463768116,
|
155 |
-
"eval_runtime": 23.0631,
|
156 |
-
"eval_samples_per_second": 21.203,
|
157 |
-
"eval_steps_per_second": 0.347,
|
158 |
-
"step": 120
|
159 |
},
|
160 |
{
|
161 |
-
"epoch":
|
162 |
-
"
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
},
|
167 |
{
|
168 |
-
"epoch":
|
169 |
-
"grad_norm":
|
170 |
-
"learning_rate":
|
171 |
-
"loss": 0.
|
172 |
-
"step":
|
173 |
},
|
174 |
{
|
175 |
-
"epoch":
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"
|
179 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
},
|
181 |
{
|
182 |
-
"epoch":
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"
|
187 |
-
|
188 |
-
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
}
|
194 |
],
|
195 |
-
"logging_steps":
|
196 |
-
"max_steps":
|
197 |
"num_input_tokens_seen": 0,
|
198 |
-
"num_train_epochs":
|
199 |
"save_steps": 150,
|
200 |
"stateful_callbacks": {
|
201 |
"TrainerControl": {
|
@@ -204,12 +174,12 @@
|
|
204 |
"should_evaluate": false,
|
205 |
"should_log": false,
|
206 |
"should_save": true,
|
207 |
-
"should_training_stop":
|
208 |
},
|
209 |
"attributes": {}
|
210 |
}
|
211 |
},
|
212 |
-
"total_flos":
|
213 |
"train_batch_size": 32,
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9884615384615384,
|
3 |
+
"best_model_checkpoint": "./results/checkpoint-30",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 5,
|
6 |
+
"global_step": 38,
|
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,
|
13 |
+
"eval_accuracy": 0.43902439024390244,
|
14 |
+
"eval_f1": 0.7958371594735232,
|
15 |
+
"eval_loss": 0.8333200216293335,
|
16 |
+
"eval_precision": 0.43807919123841615,
|
17 |
+
"eval_recall": 1.0,
|
18 |
+
"eval_roc_auc": 0.5014947683109118,
|
19 |
+
"eval_runtime": 52.2016,
|
20 |
+
"eval_samples_per_second": 22.777,
|
21 |
+
"eval_steps_per_second": 0.364,
|
22 |
"step": 0
|
23 |
},
|
24 |
{
|
25 |
+
"epoch": 0.13157894736842105,
|
26 |
+
"grad_norm": 499350.4375,
|
27 |
+
"learning_rate": 2.5e-05,
|
28 |
+
"loss": 0.7332,
|
29 |
+
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
},
|
31 |
{
|
32 |
+
"epoch": 0.13157894736842105,
|
33 |
+
"eval_accuracy": 0.6181665264928511,
|
34 |
+
"eval_f1": 0.1537744641192917,
|
35 |
+
"eval_loss": 0.6050995588302612,
|
36 |
"eval_precision": 1.0,
|
37 |
+
"eval_recall": 0.12692307692307692,
|
38 |
+
"eval_roc_auc": 0.5634615384615385,
|
39 |
+
"eval_runtime": 52.7835,
|
40 |
+
"eval_samples_per_second": 22.526,
|
41 |
+
"eval_steps_per_second": 0.36,
|
42 |
+
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
},
|
44 |
{
|
45 |
+
"epoch": 0.2631578947368421,
|
46 |
+
"grad_norm": 544000.625,
|
47 |
+
"learning_rate": 5e-05,
|
48 |
+
"loss": 0.5445,
|
49 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
},
|
51 |
{
|
52 |
+
"epoch": 0.2631578947368421,
|
53 |
+
"eval_accuracy": 0.8275862068965517,
|
54 |
+
"eval_f1": 0.9246697607997144,
|
55 |
+
"eval_loss": 0.3963133990764618,
|
56 |
+
"eval_precision": 0.7184466019417476,
|
57 |
+
"eval_recall": 0.9961538461538462,
|
58 |
+
"eval_roc_auc": 0.8463579395193745,
|
59 |
+
"eval_runtime": 51.9808,
|
60 |
+
"eval_samples_per_second": 22.874,
|
61 |
+
"eval_steps_per_second": 0.366,
|
62 |
+
"step": 10
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 0.39473684210526316,
|
66 |
+
"grad_norm": 215321.078125,
|
67 |
+
"learning_rate": 4.107142857142857e-05,
|
68 |
+
"loss": 0.328,
|
69 |
+
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 0.39473684210526316,
|
73 |
+
"eval_accuracy": 0.928511354079058,
|
74 |
+
"eval_f1": 0.9660574412532638,
|
75 |
+
"eval_loss": 0.2025815099477768,
|
76 |
+
"eval_precision": 0.8618968386023295,
|
77 |
+
"eval_recall": 0.9961538461538462,
|
78 |
+
"eval_roc_auc": 0.9360440381740831,
|
79 |
+
"eval_runtime": 52.187,
|
80 |
+
"eval_samples_per_second": 22.783,
|
81 |
+
"eval_steps_per_second": 0.364,
|
82 |
+
"step": 15
|
83 |
},
|
84 |
{
|
85 |
+
"epoch": 0.5263157894736842,
|
86 |
+
"grad_norm": 447920.53125,
|
87 |
+
"learning_rate": 3.2142857142857144e-05,
|
88 |
+
"loss": 0.2165,
|
89 |
+
"step": 20
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 0.5263157894736842,
|
93 |
+
"eval_accuracy": 0.9865433137089992,
|
94 |
+
"eval_f1": 0.9799382716049382,
|
95 |
+
"eval_loss": 0.061642639338970184,
|
96 |
+
"eval_precision": 0.9921875,
|
97 |
+
"eval_recall": 0.9769230769230769,
|
98 |
+
"eval_roc_auc": 0.9854720018397148,
|
99 |
+
"eval_runtime": 51.8127,
|
100 |
+
"eval_samples_per_second": 22.948,
|
101 |
+
"eval_steps_per_second": 0.367,
|
102 |
+
"step": 20
|
103 |
},
|
104 |
{
|
105 |
+
"epoch": 0.6578947368421053,
|
106 |
+
"grad_norm": 41190.76953125,
|
107 |
+
"learning_rate": 2.3214285714285715e-05,
|
108 |
+
"loss": 0.0754,
|
109 |
+
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
110 |
},
|
111 |
{
|
112 |
+
"epoch": 0.6578947368421053,
|
113 |
+
"eval_accuracy": 0.9806560134566863,
|
114 |
+
"eval_f1": 0.9854573287409109,
|
115 |
+
"eval_loss": 0.050207946449518204,
|
116 |
+
"eval_precision": 0.9662288930581614,
|
117 |
+
"eval_recall": 0.9903846153846154,
|
118 |
+
"eval_roc_auc": 0.9817393928941014,
|
119 |
+
"eval_runtime": 51.4902,
|
120 |
+
"eval_samples_per_second": 23.092,
|
121 |
+
"eval_steps_per_second": 0.369,
|
122 |
+
"step": 25
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 0.7894736842105263,
|
126 |
+
"grad_norm": 14033.9931640625,
|
127 |
+
"learning_rate": 1.4285714285714285e-05,
|
128 |
+
"loss": 0.022,
|
129 |
+
"step": 30
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 0.7894736842105263,
|
133 |
+
"eval_accuracy": 0.9899074852817493,
|
134 |
+
"eval_f1": 0.9884615384615384,
|
135 |
+
"eval_loss": 0.03608058765530586,
|
136 |
+
"eval_precision": 0.9884615384615385,
|
137 |
+
"eval_recall": 0.9884615384615385,
|
138 |
+
"eval_roc_auc": 0.9897464642980338,
|
139 |
+
"eval_runtime": 51.3673,
|
140 |
+
"eval_samples_per_second": 23.147,
|
141 |
+
"eval_steps_per_second": 0.37,
|
142 |
+
"step": 30
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 0.9210526315789473,
|
146 |
+
"grad_norm": 249264.84375,
|
147 |
+
"learning_rate": 5.357142857142857e-06,
|
148 |
+
"loss": 0.1406,
|
149 |
+
"step": 35
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9210526315789473,
|
153 |
+
"eval_accuracy": 0.9915895710681245,
|
154 |
+
"eval_f1": 0.9880585516178735,
|
155 |
+
"eval_loss": 0.031022196635603905,
|
156 |
+
"eval_precision": 0.9941860465116279,
|
157 |
+
"eval_recall": 0.9865384615384616,
|
158 |
+
"eval_roc_auc": 0.9910270783028631,
|
159 |
+
"eval_runtime": 50.7403,
|
160 |
+
"eval_samples_per_second": 23.433,
|
161 |
+
"eval_steps_per_second": 0.374,
|
162 |
+
"step": 35
|
163 |
}
|
164 |
],
|
165 |
+
"logging_steps": 5,
|
166 |
+
"max_steps": 38,
|
167 |
"num_input_tokens_seen": 0,
|
168 |
+
"num_train_epochs": 1,
|
169 |
"save_steps": 150,
|
170 |
"stateful_callbacks": {
|
171 |
"TrainerControl": {
|
|
|
174 |
"should_evaluate": false,
|
175 |
"should_log": false,
|
176 |
"should_save": true,
|
177 |
+
"should_training_stop": true
|
178 |
},
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 8.0526013794091e+16,
|
183 |
"train_batch_size": 32,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90e971f68a25b36c7a8c2486713a843d411a1a82953b9bc60c3ca9075d2d3d72
|
3 |
size 5304
|