Update multitask classifier
Browse files- all_results.json +18 -18
- config.json +1 -1
- eval_results.json +18 -18
- indra_label2id.json +4 -3
- model.safetensors +2 -2
- test_results.json +18 -18
- tokenizer.json +6 -1
- trainer_state.json +290 -230
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,22 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_gate1_accuracy": 0.
|
| 4 |
-
"eval_gate1_f1": 0.
|
| 5 |
-
"eval_gate1_precision": 0.
|
| 6 |
-
"eval_gate1_recall": 0.
|
| 7 |
"eval_gate1_support": 5481,
|
| 8 |
-
"eval_gate2_accuracy": 0.
|
| 9 |
-
"eval_gate2_f1": 0.
|
| 10 |
-
"eval_gate2_precision": 0.
|
| 11 |
-
"eval_gate2_recall": 0.
|
| 12 |
"eval_gate2_support": 5481,
|
| 13 |
-
"eval_gate3_accuracy": 0.
|
| 14 |
-
"eval_gate3_f1": 0.
|
| 15 |
-
"eval_gate3_precision": 0.
|
| 16 |
-
"eval_gate3_recall": 0.
|
| 17 |
-
"eval_gate3_support":
|
| 18 |
-
"eval_loss":
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gate1_accuracy": 0.9248312351760628,
|
| 4 |
+
"eval_gate1_f1": 0.9223014364537471,
|
| 5 |
+
"eval_gate1_precision": 0.9233799376462881,
|
| 6 |
+
"eval_gate1_recall": 0.9213102653636653,
|
| 7 |
"eval_gate1_support": 5481,
|
| 8 |
+
"eval_gate2_accuracy": 0.8673599708082467,
|
| 9 |
+
"eval_gate2_f1": 0.8048074187473976,
|
| 10 |
+
"eval_gate2_precision": 0.7981399002237517,
|
| 11 |
+
"eval_gate2_recall": 0.818477325235324,
|
| 12 |
"eval_gate2_support": 5481,
|
| 13 |
+
"eval_gate3_accuracy": 0.8764174514703056,
|
| 14 |
+
"eval_gate3_f1": 0.8057131317523325,
|
| 15 |
+
"eval_gate3_precision": 0.8091461396544178,
|
| 16 |
+
"eval_gate3_recall": 0.8052237388041866,
|
| 17 |
+
"eval_gate3_support": 5203,
|
| 18 |
+
"eval_loss": 0.9472318887710571,
|
| 19 |
+
"eval_runtime": 8.2407,
|
| 20 |
+
"eval_samples_per_second": 1296.485,
|
| 21 |
+
"eval_steps_per_second": 40.53
|
| 22 |
}
|
config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"gate2_loss_weight": 0.5,
|
| 10 |
"gate2_num_labels": 20,
|
| 11 |
"gate3_loss_weight": 0.25,
|
| 12 |
-
"gate3_num_labels":
|
| 13 |
"hidden_act": "gelu",
|
| 14 |
"hidden_dropout_prob": 0.1,
|
| 15 |
"hidden_size": 768,
|
|
|
|
| 9 |
"gate2_loss_weight": 0.5,
|
| 10 |
"gate2_num_labels": 20,
|
| 11 |
"gate3_loss_weight": 0.25,
|
| 12 |
+
"gate3_num_labels": 11,
|
| 13 |
"hidden_act": "gelu",
|
| 14 |
"hidden_dropout_prob": 0.1,
|
| 15 |
"hidden_size": 768,
|
eval_results.json
CHANGED
|
@@ -1,22 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_gate1_accuracy": 0.
|
| 4 |
-
"eval_gate1_f1": 0.
|
| 5 |
-
"eval_gate1_precision": 0.
|
| 6 |
-
"eval_gate1_recall": 0.
|
| 7 |
"eval_gate1_support": 5480,
|
| 8 |
-
"eval_gate2_accuracy": 0.
|
| 9 |
-
"eval_gate2_f1": 0.
|
| 10 |
-
"eval_gate2_precision": 0.
|
| 11 |
-
"eval_gate2_recall": 0.
|
| 12 |
"eval_gate2_support": 5480,
|
| 13 |
-
"eval_gate3_accuracy": 0.
|
| 14 |
-
"eval_gate3_f1": 0.
|
| 15 |
-
"eval_gate3_precision": 0.
|
| 16 |
-
"eval_gate3_recall": 0.
|
| 17 |
-
"eval_gate3_support":
|
| 18 |
-
"eval_loss":
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gate1_accuracy": 0.9240875912408759,
|
| 4 |
+
"eval_gate1_f1": 0.9198787159000936,
|
| 5 |
+
"eval_gate1_precision": 0.9214987753300372,
|
| 6 |
+
"eval_gate1_recall": 0.9183842728638181,
|
| 7 |
"eval_gate1_support": 5480,
|
| 8 |
+
"eval_gate2_accuracy": 0.8687956204379562,
|
| 9 |
+
"eval_gate2_f1": 0.7862569245385519,
|
| 10 |
+
"eval_gate2_precision": 0.7958171660250828,
|
| 11 |
+
"eval_gate2_recall": 0.7833180915653772,
|
| 12 |
"eval_gate2_support": 5480,
|
| 13 |
+
"eval_gate3_accuracy": 0.8846597462514417,
|
| 14 |
+
"eval_gate3_f1": 0.8122850869616633,
|
| 15 |
+
"eval_gate3_precision": 0.8109060527302346,
|
| 16 |
+
"eval_gate3_recall": 0.8171325515426088,
|
| 17 |
+
"eval_gate3_support": 5202,
|
| 18 |
+
"eval_loss": 0.9491556882858276,
|
| 19 |
+
"eval_runtime": 8.3758,
|
| 20 |
+
"eval_samples_per_second": 1275.348,
|
| 21 |
+
"eval_steps_per_second": 39.877
|
| 22 |
}
|
indra_label2id.json
CHANGED
|
@@ -6,7 +6,8 @@
|
|
| 6 |
"Dephosphorylation": 4,
|
| 7 |
"IncreaseAmount": 5,
|
| 8 |
"Inhibition": 6,
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
|
|
|
| 12 |
}
|
|
|
|
| 6 |
"Dephosphorylation": 4,
|
| 7 |
"IncreaseAmount": 5,
|
| 8 |
"Inhibition": 6,
|
| 9 |
+
"No_Relation": 7,
|
| 10 |
+
"Phosphorylation": 8,
|
| 11 |
+
"Translocation": 9,
|
| 12 |
+
"Ubiquitination": 10
|
| 13 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a021a34f88584036cbf7749736dcb36ea13b6be1c495e55cd5bc1fb991affbf
|
| 3 |
+
size 433062372
|
test_results.json
CHANGED
|
@@ -1,22 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_gate1_accuracy": 0.
|
| 4 |
-
"eval_gate1_f1": 0.
|
| 5 |
-
"eval_gate1_precision": 0.
|
| 6 |
-
"eval_gate1_recall": 0.
|
| 7 |
"eval_gate1_support": 5481,
|
| 8 |
-
"eval_gate2_accuracy": 0.
|
| 9 |
-
"eval_gate2_f1": 0.
|
| 10 |
-
"eval_gate2_precision": 0.
|
| 11 |
-
"eval_gate2_recall": 0.
|
| 12 |
"eval_gate2_support": 5481,
|
| 13 |
-
"eval_gate3_accuracy": 0.
|
| 14 |
-
"eval_gate3_f1": 0.
|
| 15 |
-
"eval_gate3_precision": 0.
|
| 16 |
-
"eval_gate3_recall": 0.
|
| 17 |
-
"eval_gate3_support":
|
| 18 |
-
"eval_loss":
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gate1_accuracy": 0.9248312351760628,
|
| 4 |
+
"eval_gate1_f1": 0.9223014364537471,
|
| 5 |
+
"eval_gate1_precision": 0.9233799376462881,
|
| 6 |
+
"eval_gate1_recall": 0.9213102653636653,
|
| 7 |
"eval_gate1_support": 5481,
|
| 8 |
+
"eval_gate2_accuracy": 0.8673599708082467,
|
| 9 |
+
"eval_gate2_f1": 0.8048074187473976,
|
| 10 |
+
"eval_gate2_precision": 0.7981399002237517,
|
| 11 |
+
"eval_gate2_recall": 0.818477325235324,
|
| 12 |
"eval_gate2_support": 5481,
|
| 13 |
+
"eval_gate3_accuracy": 0.8764174514703056,
|
| 14 |
+
"eval_gate3_f1": 0.8057131317523325,
|
| 15 |
+
"eval_gate3_precision": 0.8091461396544178,
|
| 16 |
+
"eval_gate3_recall": 0.8052237388041866,
|
| 17 |
+
"eval_gate3_support": 5203,
|
| 18 |
+
"eval_loss": 0.9472318887710571,
|
| 19 |
+
"eval_runtime": 8.2407,
|
| 20 |
+
"eval_samples_per_second": 1296.485,
|
| 21 |
+
"eval_steps_per_second": 40.53
|
| 22 |
}
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 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 |
{
|
trainer_state.json
CHANGED
|
@@ -1,314 +1,374 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "output/indra_stmt_classifier/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate": 2.
|
| 16 |
-
"loss": 1.
|
| 17 |
-
"step":
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 1.0,
|
| 21 |
-
"eval_gate1_accuracy": 0.
|
| 22 |
-
"eval_gate1_f1": 0.
|
| 23 |
-
"eval_gate1_precision": 0.
|
| 24 |
-
"eval_gate1_recall": 0.
|
| 25 |
"eval_gate1_support": 5480,
|
| 26 |
-
"eval_gate2_accuracy": 0.
|
| 27 |
-
"eval_gate2_f1": 0.
|
| 28 |
-
"eval_gate2_precision": 0.
|
| 29 |
-
"eval_gate2_recall": 0.
|
| 30 |
"eval_gate2_support": 5480,
|
| 31 |
-
"eval_gate3_accuracy": 0.
|
| 32 |
-
"eval_gate3_f1": 0.
|
| 33 |
-
"eval_gate3_precision": 0.
|
| 34 |
-
"eval_gate3_recall": 0.
|
| 35 |
-
"eval_gate3_support":
|
| 36 |
-
"eval_loss": 0.
|
| 37 |
-
"eval_runtime":
|
| 38 |
-
"eval_samples_per_second":
|
| 39 |
-
"eval_steps_per_second":
|
| 40 |
-
"step":
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 2.0,
|
| 44 |
-
"grad_norm":
|
| 45 |
-
"learning_rate": 2.
|
| 46 |
-
"loss": 0.
|
| 47 |
-
"step":
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 2.0,
|
| 51 |
-
"eval_gate1_accuracy": 0.
|
| 52 |
-
"eval_gate1_f1": 0.
|
| 53 |
-
"eval_gate1_precision": 0.
|
| 54 |
-
"eval_gate1_recall": 0.
|
| 55 |
"eval_gate1_support": 5480,
|
| 56 |
-
"eval_gate2_accuracy": 0.
|
| 57 |
-
"eval_gate2_f1": 0.
|
| 58 |
-
"eval_gate2_precision": 0.
|
| 59 |
-
"eval_gate2_recall": 0.
|
| 60 |
"eval_gate2_support": 5480,
|
| 61 |
-
"eval_gate3_accuracy": 0.
|
| 62 |
-
"eval_gate3_f1": 0.
|
| 63 |
-
"eval_gate3_precision": 0.
|
| 64 |
-
"eval_gate3_recall": 0.
|
| 65 |
-
"eval_gate3_support":
|
| 66 |
-
"eval_loss": 0.
|
| 67 |
-
"eval_runtime":
|
| 68 |
-
"eval_samples_per_second":
|
| 69 |
-
"eval_steps_per_second":
|
| 70 |
-
"step":
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 3.0,
|
| 74 |
-
"grad_norm":
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss": 0.
|
| 77 |
-
"step":
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 3.0,
|
| 81 |
-
"eval_gate1_accuracy": 0.
|
| 82 |
-
"eval_gate1_f1": 0.
|
| 83 |
-
"eval_gate1_precision": 0.
|
| 84 |
-
"eval_gate1_recall": 0.
|
| 85 |
"eval_gate1_support": 5480,
|
| 86 |
-
"eval_gate2_accuracy": 0.
|
| 87 |
-
"eval_gate2_f1": 0.
|
| 88 |
-
"eval_gate2_precision": 0.
|
| 89 |
-
"eval_gate2_recall": 0.
|
| 90 |
"eval_gate2_support": 5480,
|
| 91 |
-
"eval_gate3_accuracy": 0.
|
| 92 |
-
"eval_gate3_f1": 0.
|
| 93 |
-
"eval_gate3_precision": 0.
|
| 94 |
-
"eval_gate3_recall": 0.
|
| 95 |
-
"eval_gate3_support":
|
| 96 |
-
"eval_loss": 0.
|
| 97 |
-
"eval_runtime":
|
| 98 |
-
"eval_samples_per_second":
|
| 99 |
-
"eval_steps_per_second":
|
| 100 |
-
"step":
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 4.0,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate": 1.
|
| 106 |
-
"loss": 0.
|
| 107 |
-
"step":
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 4.0,
|
| 111 |
-
"eval_gate1_accuracy": 0.
|
| 112 |
-
"eval_gate1_f1": 0.
|
| 113 |
-
"eval_gate1_precision": 0.
|
| 114 |
-
"eval_gate1_recall": 0.
|
| 115 |
"eval_gate1_support": 5480,
|
| 116 |
-
"eval_gate2_accuracy": 0.
|
| 117 |
-
"eval_gate2_f1": 0.
|
| 118 |
-
"eval_gate2_precision": 0.
|
| 119 |
-
"eval_gate2_recall": 0.
|
| 120 |
"eval_gate2_support": 5480,
|
| 121 |
-
"eval_gate3_accuracy": 0.
|
| 122 |
-
"eval_gate3_f1": 0.
|
| 123 |
-
"eval_gate3_precision": 0.
|
| 124 |
-
"eval_gate3_recall": 0.
|
| 125 |
-
"eval_gate3_support":
|
| 126 |
-
"eval_loss": 0.
|
| 127 |
-
"eval_runtime":
|
| 128 |
-
"eval_samples_per_second":
|
| 129 |
-
"eval_steps_per_second":
|
| 130 |
-
"step":
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 5.0,
|
| 134 |
-
"grad_norm":
|
| 135 |
-
"learning_rate": 1.
|
| 136 |
-
"loss": 0.
|
| 137 |
-
"step":
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 5.0,
|
| 141 |
-
"eval_gate1_accuracy": 0.
|
| 142 |
-
"eval_gate1_f1": 0.
|
| 143 |
-
"eval_gate1_precision": 0.
|
| 144 |
-
"eval_gate1_recall": 0.
|
| 145 |
"eval_gate1_support": 5480,
|
| 146 |
-
"eval_gate2_accuracy": 0.
|
| 147 |
-
"eval_gate2_f1": 0.
|
| 148 |
-
"eval_gate2_precision": 0.
|
| 149 |
-
"eval_gate2_recall": 0.
|
| 150 |
"eval_gate2_support": 5480,
|
| 151 |
-
"eval_gate3_accuracy": 0.
|
| 152 |
-
"eval_gate3_f1": 0.
|
| 153 |
-
"eval_gate3_precision": 0.
|
| 154 |
-
"eval_gate3_recall": 0.
|
| 155 |
-
"eval_gate3_support":
|
| 156 |
-
"eval_loss": 0.
|
| 157 |
-
"eval_runtime":
|
| 158 |
-
"eval_samples_per_second":
|
| 159 |
-
"eval_steps_per_second":
|
| 160 |
-
"step":
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 6.0,
|
| 164 |
-
"grad_norm":
|
| 165 |
-
"learning_rate":
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 6.0,
|
| 171 |
-
"eval_gate1_accuracy": 0.
|
| 172 |
-
"eval_gate1_f1": 0.
|
| 173 |
-
"eval_gate1_precision": 0.
|
| 174 |
-
"eval_gate1_recall": 0.
|
| 175 |
"eval_gate1_support": 5480,
|
| 176 |
-
"eval_gate2_accuracy": 0.
|
| 177 |
-
"eval_gate2_f1": 0.
|
| 178 |
-
"eval_gate2_precision": 0.
|
| 179 |
-
"eval_gate2_recall": 0.
|
| 180 |
"eval_gate2_support": 5480,
|
| 181 |
-
"eval_gate3_accuracy": 0.
|
| 182 |
-
"eval_gate3_f1": 0.
|
| 183 |
-
"eval_gate3_precision": 0.
|
| 184 |
-
"eval_gate3_recall": 0.
|
| 185 |
-
"eval_gate3_support":
|
| 186 |
-
"eval_loss": 0.
|
| 187 |
-
"eval_runtime":
|
| 188 |
-
"eval_samples_per_second":
|
| 189 |
-
"eval_steps_per_second":
|
| 190 |
-
"step":
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"epoch": 7.0,
|
| 194 |
-
"grad_norm":
|
| 195 |
-
"learning_rate":
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 7.0,
|
| 201 |
-
"eval_gate1_accuracy": 0.
|
| 202 |
-
"eval_gate1_f1": 0.
|
| 203 |
-
"eval_gate1_precision": 0.
|
| 204 |
-
"eval_gate1_recall": 0.
|
| 205 |
"eval_gate1_support": 5480,
|
| 206 |
-
"eval_gate2_accuracy": 0.
|
| 207 |
-
"eval_gate2_f1": 0.
|
| 208 |
-
"eval_gate2_precision": 0.
|
| 209 |
-
"eval_gate2_recall": 0.
|
| 210 |
"eval_gate2_support": 5480,
|
| 211 |
-
"eval_gate3_accuracy": 0.
|
| 212 |
-
"eval_gate3_f1": 0.
|
| 213 |
-
"eval_gate3_precision": 0.
|
| 214 |
-
"eval_gate3_recall": 0.
|
| 215 |
-
"eval_gate3_support":
|
| 216 |
-
"eval_loss":
|
| 217 |
-
"eval_runtime":
|
| 218 |
-
"eval_samples_per_second":
|
| 219 |
-
"eval_steps_per_second":
|
| 220 |
-
"step":
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 8.0,
|
| 224 |
-
"grad_norm":
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 0.
|
| 227 |
-
"step":
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 8.0,
|
| 231 |
-
"eval_gate1_accuracy": 0.
|
| 232 |
-
"eval_gate1_f1": 0.
|
| 233 |
-
"eval_gate1_precision": 0.
|
| 234 |
-
"eval_gate1_recall": 0.
|
| 235 |
"eval_gate1_support": 5480,
|
| 236 |
-
"eval_gate2_accuracy": 0.
|
| 237 |
-
"eval_gate2_f1": 0.
|
| 238 |
-
"eval_gate2_precision": 0.
|
| 239 |
-
"eval_gate2_recall": 0.
|
| 240 |
"eval_gate2_support": 5480,
|
| 241 |
-
"eval_gate3_accuracy": 0.
|
| 242 |
-
"eval_gate3_f1": 0.
|
| 243 |
-
"eval_gate3_precision": 0.
|
| 244 |
-
"eval_gate3_recall": 0.
|
| 245 |
-
"eval_gate3_support":
|
| 246 |
-
"eval_loss":
|
| 247 |
-
"eval_runtime":
|
| 248 |
-
"eval_samples_per_second":
|
| 249 |
-
"eval_steps_per_second":
|
| 250 |
-
"step":
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"epoch":
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
| 258 |
-
"train_samples_per_second": 407.055,
|
| 259 |
-
"train_steps_per_second": 25.446
|
| 260 |
},
|
| 261 |
{
|
| 262 |
-
"epoch":
|
| 263 |
-
"eval_gate1_accuracy": 0.
|
| 264 |
-
"eval_gate1_f1": 0.
|
| 265 |
-
"eval_gate1_precision": 0.
|
| 266 |
-
"eval_gate1_recall": 0.
|
| 267 |
"eval_gate1_support": 5480,
|
| 268 |
-
"eval_gate2_accuracy": 0.
|
| 269 |
-
"eval_gate2_f1": 0.
|
| 270 |
-
"eval_gate2_precision": 0.
|
| 271 |
-
"eval_gate2_recall": 0.
|
| 272 |
"eval_gate2_support": 5480,
|
| 273 |
-
"eval_gate3_accuracy": 0.
|
| 274 |
-
"eval_gate3_f1": 0.
|
| 275 |
-
"eval_gate3_precision": 0.
|
| 276 |
-
"eval_gate3_recall": 0.
|
| 277 |
-
"eval_gate3_support":
|
| 278 |
-
"eval_loss":
|
| 279 |
-
"eval_runtime":
|
| 280 |
-
"eval_samples_per_second":
|
| 281 |
-
"eval_steps_per_second":
|
| 282 |
-
"step":
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
"eval_gate1_support": 5481,
|
| 291 |
-
"eval_gate2_accuracy": 0.
|
| 292 |
-
"eval_gate2_f1": 0.
|
| 293 |
-
"eval_gate2_precision": 0.
|
| 294 |
-
"eval_gate2_recall": 0.
|
| 295 |
"eval_gate2_support": 5481,
|
| 296 |
-
"eval_gate3_accuracy": 0.
|
| 297 |
-
"eval_gate3_f1": 0.
|
| 298 |
-
"eval_gate3_precision": 0.
|
| 299 |
-
"eval_gate3_recall": 0.
|
| 300 |
-
"eval_gate3_support":
|
| 301 |
-
"eval_loss":
|
| 302 |
-
"eval_runtime":
|
| 303 |
-
"eval_samples_per_second":
|
| 304 |
-
"eval_steps_per_second":
|
| 305 |
-
"step":
|
| 306 |
}
|
| 307 |
],
|
| 308 |
"logging_steps": 500,
|
| 309 |
-
"max_steps":
|
| 310 |
"num_input_tokens_seen": 0,
|
| 311 |
-
"num_train_epochs":
|
| 312 |
"save_steps": 500,
|
| 313 |
"stateful_callbacks": {
|
| 314 |
"TrainerControl": {
|
|
@@ -322,8 +382,8 @@
|
|
| 322 |
"attributes": {}
|
| 323 |
}
|
| 324 |
},
|
| 325 |
-
"total_flos":
|
| 326 |
-
"train_batch_size":
|
| 327 |
"trial_name": null,
|
| 328 |
"trial_params": null
|
| 329 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 24039,
|
| 3 |
+
"best_metric": 0.9198787159000936,
|
| 4 |
+
"best_model_checkpoint": "output/indra_stmt_classifier/checkpoint-24039",
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 26710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 47.85763931274414,
|
| 15 |
+
"learning_rate": 2.7001123174840886e-05,
|
| 16 |
+
"loss": 1.096,
|
| 17 |
+
"step": 2671
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 1.0,
|
| 21 |
+
"eval_gate1_accuracy": 0.8760948905109489,
|
| 22 |
+
"eval_gate1_f1": 0.8689092717452258,
|
| 23 |
+
"eval_gate1_precision": 0.8713719523264891,
|
| 24 |
+
"eval_gate1_recall": 0.8667668606533185,
|
| 25 |
"eval_gate1_support": 5480,
|
| 26 |
+
"eval_gate2_accuracy": 0.7824817518248175,
|
| 27 |
+
"eval_gate2_f1": 0.5621839936527114,
|
| 28 |
+
"eval_gate2_precision": 0.5645465119560173,
|
| 29 |
+
"eval_gate2_recall": 0.5736060548580606,
|
| 30 |
"eval_gate2_support": 5480,
|
| 31 |
+
"eval_gate3_accuracy": 0.8492887351018839,
|
| 32 |
+
"eval_gate3_f1": 0.7602413926113012,
|
| 33 |
+
"eval_gate3_precision": 0.7693172953195895,
|
| 34 |
+
"eval_gate3_recall": 0.7578355849403795,
|
| 35 |
+
"eval_gate3_support": 5202,
|
| 36 |
+
"eval_loss": 0.7759597301483154,
|
| 37 |
+
"eval_runtime": 8.4166,
|
| 38 |
+
"eval_samples_per_second": 1269.164,
|
| 39 |
+
"eval_steps_per_second": 39.684,
|
| 40 |
+
"step": 2671
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 2.0,
|
| 44 |
+
"grad_norm": 23.181921005249023,
|
| 45 |
+
"learning_rate": 2.4001123174840884e-05,
|
| 46 |
+
"loss": 0.6261,
|
| 47 |
+
"step": 5342
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 2.0,
|
| 51 |
+
"eval_gate1_accuracy": 0.8967153284671533,
|
| 52 |
+
"eval_gate1_f1": 0.8892135436021471,
|
| 53 |
+
"eval_gate1_precision": 0.8992800620286656,
|
| 54 |
+
"eval_gate1_recall": 0.8823722876851883,
|
| 55 |
"eval_gate1_support": 5480,
|
| 56 |
+
"eval_gate2_accuracy": 0.8087591240875912,
|
| 57 |
+
"eval_gate2_f1": 0.6336830760464771,
|
| 58 |
+
"eval_gate2_precision": 0.648374818296507,
|
| 59 |
+
"eval_gate2_recall": 0.6429898577936985,
|
| 60 |
"eval_gate2_support": 5480,
|
| 61 |
+
"eval_gate3_accuracy": 0.856401384083045,
|
| 62 |
+
"eval_gate3_f1": 0.7796712690058606,
|
| 63 |
+
"eval_gate3_precision": 0.7733791231232439,
|
| 64 |
+
"eval_gate3_recall": 0.7949296041903785,
|
| 65 |
+
"eval_gate3_support": 5202,
|
| 66 |
+
"eval_loss": 0.7020143270492554,
|
| 67 |
+
"eval_runtime": 8.2978,
|
| 68 |
+
"eval_samples_per_second": 1287.322,
|
| 69 |
+
"eval_steps_per_second": 40.251,
|
| 70 |
+
"step": 5342
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 3.0,
|
| 74 |
+
"grad_norm": 27.699832916259766,
|
| 75 |
+
"learning_rate": 2.1001123174840883e-05,
|
| 76 |
+
"loss": 0.4319,
|
| 77 |
+
"step": 8013
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 3.0,
|
| 81 |
+
"eval_gate1_accuracy": 0.9136861313868613,
|
| 82 |
+
"eval_gate1_f1": 0.9090361599898706,
|
| 83 |
+
"eval_gate1_precision": 0.9099473620236753,
|
| 84 |
+
"eval_gate1_recall": 0.9081687024129339,
|
| 85 |
"eval_gate1_support": 5480,
|
| 86 |
+
"eval_gate2_accuracy": 0.8375912408759124,
|
| 87 |
+
"eval_gate2_f1": 0.716570976615394,
|
| 88 |
+
"eval_gate2_precision": 0.7672632620550218,
|
| 89 |
+
"eval_gate2_recall": 0.7053523131003135,
|
| 90 |
"eval_gate2_support": 5480,
|
| 91 |
+
"eval_gate3_accuracy": 0.8612072279892349,
|
| 92 |
+
"eval_gate3_f1": 0.7652294432661969,
|
| 93 |
+
"eval_gate3_precision": 0.81933757284518,
|
| 94 |
+
"eval_gate3_recall": 0.7376765450537605,
|
| 95 |
+
"eval_gate3_support": 5202,
|
| 96 |
+
"eval_loss": 0.6838930249214172,
|
| 97 |
+
"eval_runtime": 8.3142,
|
| 98 |
+
"eval_samples_per_second": 1284.784,
|
| 99 |
+
"eval_steps_per_second": 40.172,
|
| 100 |
+
"step": 8013
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 4.0,
|
| 104 |
+
"grad_norm": 8.99526309967041,
|
| 105 |
+
"learning_rate": 1.8001123174840884e-05,
|
| 106 |
+
"loss": 0.319,
|
| 107 |
+
"step": 10684
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 4.0,
|
| 111 |
+
"eval_gate1_accuracy": 0.9113138686131387,
|
| 112 |
+
"eval_gate1_f1": 0.9066571186319019,
|
| 113 |
+
"eval_gate1_precision": 0.9070095024338034,
|
| 114 |
+
"eval_gate1_recall": 0.9063116888828937,
|
| 115 |
"eval_gate1_support": 5480,
|
| 116 |
+
"eval_gate2_accuracy": 0.8434306569343065,
|
| 117 |
+
"eval_gate2_f1": 0.7453256510027118,
|
| 118 |
+
"eval_gate2_precision": 0.783574110030759,
|
| 119 |
+
"eval_gate2_recall": 0.7407995323997061,
|
| 120 |
"eval_gate2_support": 5480,
|
| 121 |
+
"eval_gate3_accuracy": 0.87120338331411,
|
| 122 |
+
"eval_gate3_f1": 0.7836320711248788,
|
| 123 |
+
"eval_gate3_precision": 0.823566591748077,
|
| 124 |
+
"eval_gate3_recall": 0.7547062062356837,
|
| 125 |
+
"eval_gate3_support": 5202,
|
| 126 |
+
"eval_loss": 0.7108728885650635,
|
| 127 |
+
"eval_runtime": 8.3006,
|
| 128 |
+
"eval_samples_per_second": 1286.889,
|
| 129 |
+
"eval_steps_per_second": 40.238,
|
| 130 |
+
"step": 10684
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 5.0,
|
| 134 |
+
"grad_norm": 5.843006610870361,
|
| 135 |
+
"learning_rate": 1.5001123174840884e-05,
|
| 136 |
+
"loss": 0.2375,
|
| 137 |
+
"step": 13355
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 5.0,
|
| 141 |
+
"eval_gate1_accuracy": 0.9191605839416058,
|
| 142 |
+
"eval_gate1_f1": 0.9147161084936839,
|
| 143 |
+
"eval_gate1_precision": 0.9161134345731146,
|
| 144 |
+
"eval_gate1_recall": 0.9134155447895695,
|
| 145 |
"eval_gate1_support": 5480,
|
| 146 |
+
"eval_gate2_accuracy": 0.8563868613138687,
|
| 147 |
+
"eval_gate2_f1": 0.7598792736508855,
|
| 148 |
+
"eval_gate2_precision": 0.7518271395861019,
|
| 149 |
+
"eval_gate2_recall": 0.772553107812257,
|
| 150 |
"eval_gate2_support": 5480,
|
| 151 |
+
"eval_gate3_accuracy": 0.8796616685890042,
|
| 152 |
+
"eval_gate3_f1": 0.8103507915834345,
|
| 153 |
+
"eval_gate3_precision": 0.795275163060746,
|
| 154 |
+
"eval_gate3_recall": 0.8286988441198276,
|
| 155 |
+
"eval_gate3_support": 5202,
|
| 156 |
+
"eval_loss": 0.7357046604156494,
|
| 157 |
+
"eval_runtime": 8.2987,
|
| 158 |
+
"eval_samples_per_second": 1287.188,
|
| 159 |
+
"eval_steps_per_second": 40.247,
|
| 160 |
+
"step": 13355
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 6.0,
|
| 164 |
+
"grad_norm": 0.8739603757858276,
|
| 165 |
+
"learning_rate": 1.2001123174840884e-05,
|
| 166 |
+
"loss": 0.1823,
|
| 167 |
+
"step": 16026
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 6.0,
|
| 171 |
+
"eval_gate1_accuracy": 0.9202554744525547,
|
| 172 |
+
"eval_gate1_f1": 0.9158266975335383,
|
| 173 |
+
"eval_gate1_precision": 0.9174725833086337,
|
| 174 |
+
"eval_gate1_recall": 0.9143118698567939,
|
| 175 |
"eval_gate1_support": 5480,
|
| 176 |
+
"eval_gate2_accuracy": 0.8625912408759124,
|
| 177 |
+
"eval_gate2_f1": 0.7834573094835664,
|
| 178 |
+
"eval_gate2_precision": 0.7833879179077755,
|
| 179 |
+
"eval_gate2_recall": 0.7941424379945043,
|
| 180 |
"eval_gate2_support": 5480,
|
| 181 |
+
"eval_gate3_accuracy": 0.8788927335640139,
|
| 182 |
+
"eval_gate3_f1": 0.8107447964013891,
|
| 183 |
+
"eval_gate3_precision": 0.7977529473487692,
|
| 184 |
+
"eval_gate3_recall": 0.8263627573376545,
|
| 185 |
+
"eval_gate3_support": 5202,
|
| 186 |
+
"eval_loss": 0.7493559718132019,
|
| 187 |
+
"eval_runtime": 8.2869,
|
| 188 |
+
"eval_samples_per_second": 1289.017,
|
| 189 |
+
"eval_steps_per_second": 40.304,
|
| 190 |
+
"step": 16026
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"epoch": 7.0,
|
| 194 |
+
"grad_norm": 6.645991802215576,
|
| 195 |
+
"learning_rate": 9.001123174840884e-06,
|
| 196 |
+
"loss": 0.1393,
|
| 197 |
+
"step": 18697
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 7.0,
|
| 201 |
+
"eval_gate1_accuracy": 0.9208029197080292,
|
| 202 |
+
"eval_gate1_f1": 0.916658712113726,
|
| 203 |
+
"eval_gate1_precision": 0.9169464363987025,
|
| 204 |
+
"eval_gate1_recall": 0.916375490587046,
|
| 205 |
"eval_gate1_support": 5480,
|
| 206 |
+
"eval_gate2_accuracy": 0.8624087591240875,
|
| 207 |
+
"eval_gate2_f1": 0.7853563687427353,
|
| 208 |
+
"eval_gate2_precision": 0.8070903645887496,
|
| 209 |
+
"eval_gate2_recall": 0.7701247313578428,
|
| 210 |
"eval_gate2_support": 5480,
|
| 211 |
+
"eval_gate3_accuracy": 0.8819684736639753,
|
| 212 |
+
"eval_gate3_f1": 0.8023548675258322,
|
| 213 |
+
"eval_gate3_precision": 0.8218130097693663,
|
| 214 |
+
"eval_gate3_recall": 0.7905833163517992,
|
| 215 |
+
"eval_gate3_support": 5202,
|
| 216 |
+
"eval_loss": 0.8566591739654541,
|
| 217 |
+
"eval_runtime": 8.3576,
|
| 218 |
+
"eval_samples_per_second": 1278.113,
|
| 219 |
+
"eval_steps_per_second": 39.963,
|
| 220 |
+
"step": 18697
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 8.0,
|
| 224 |
+
"grad_norm": 23.729028701782227,
|
| 225 |
+
"learning_rate": 6.001123174840884e-06,
|
| 226 |
+
"loss": 0.1053,
|
| 227 |
+
"step": 21368
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 8.0,
|
| 231 |
+
"eval_gate1_accuracy": 0.9204379562043795,
|
| 232 |
+
"eval_gate1_f1": 0.9158315272170139,
|
| 233 |
+
"eval_gate1_precision": 0.9185518950364968,
|
| 234 |
+
"eval_gate1_recall": 0.9134409679806464,
|
| 235 |
"eval_gate1_support": 5480,
|
| 236 |
+
"eval_gate2_accuracy": 0.8647810218978103,
|
| 237 |
+
"eval_gate2_f1": 0.7930689269607176,
|
| 238 |
+
"eval_gate2_precision": 0.7965862889095636,
|
| 239 |
+
"eval_gate2_recall": 0.793312720903019,
|
| 240 |
"eval_gate2_support": 5480,
|
| 241 |
+
"eval_gate3_accuracy": 0.8813917723952326,
|
| 242 |
+
"eval_gate3_f1": 0.8117269824014105,
|
| 243 |
+
"eval_gate3_precision": 0.8009879534677691,
|
| 244 |
+
"eval_gate3_recall": 0.826162604748559,
|
| 245 |
+
"eval_gate3_support": 5202,
|
| 246 |
+
"eval_loss": 0.9113713502883911,
|
| 247 |
+
"eval_runtime": 8.2775,
|
| 248 |
+
"eval_samples_per_second": 1290.488,
|
| 249 |
+
"eval_steps_per_second": 40.35,
|
| 250 |
+
"step": 21368
|
| 251 |
},
|
| 252 |
{
|
| 253 |
+
"epoch": 9.0,
|
| 254 |
+
"grad_norm": 5.157261371612549,
|
| 255 |
+
"learning_rate": 3.001123174840884e-06,
|
| 256 |
+
"loss": 0.0846,
|
| 257 |
+
"step": 24039
|
|
|
|
|
|
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 9.0,
|
| 261 |
+
"eval_gate1_accuracy": 0.9240875912408759,
|
| 262 |
+
"eval_gate1_f1": 0.9198787159000936,
|
| 263 |
+
"eval_gate1_precision": 0.9214987753300372,
|
| 264 |
+
"eval_gate1_recall": 0.9183842728638181,
|
| 265 |
"eval_gate1_support": 5480,
|
| 266 |
+
"eval_gate2_accuracy": 0.8687956204379562,
|
| 267 |
+
"eval_gate2_f1": 0.7862569245385519,
|
| 268 |
+
"eval_gate2_precision": 0.7958171660250828,
|
| 269 |
+
"eval_gate2_recall": 0.7833180915653772,
|
| 270 |
"eval_gate2_support": 5480,
|
| 271 |
+
"eval_gate3_accuracy": 0.8846597462514417,
|
| 272 |
+
"eval_gate3_f1": 0.8122850869616633,
|
| 273 |
+
"eval_gate3_precision": 0.8109060527302346,
|
| 274 |
+
"eval_gate3_recall": 0.8171325515426088,
|
| 275 |
+
"eval_gate3_support": 5202,
|
| 276 |
+
"eval_loss": 0.9491556882858276,
|
| 277 |
+
"eval_runtime": 8.2789,
|
| 278 |
+
"eval_samples_per_second": 1290.275,
|
| 279 |
+
"eval_steps_per_second": 40.344,
|
| 280 |
+
"step": 24039
|
| 281 |
},
|
| 282 |
{
|
| 283 |
+
"epoch": 10.0,
|
| 284 |
+
"grad_norm": 16.858612060546875,
|
| 285 |
+
"learning_rate": 1.1231748408835642e-09,
|
| 286 |
+
"loss": 0.0657,
|
| 287 |
+
"step": 26710
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 10.0,
|
| 291 |
+
"eval_gate1_accuracy": 0.9235401459854015,
|
| 292 |
+
"eval_gate1_f1": 0.9193364547603917,
|
| 293 |
+
"eval_gate1_precision": 0.920749079638352,
|
| 294 |
+
"eval_gate1_recall": 0.9180211344458186,
|
| 295 |
+
"eval_gate1_support": 5480,
|
| 296 |
+
"eval_gate2_accuracy": 0.8656934306569343,
|
| 297 |
+
"eval_gate2_f1": 0.7883336539086067,
|
| 298 |
+
"eval_gate2_precision": 0.7971566464425738,
|
| 299 |
+
"eval_gate2_recall": 0.7826535186693984,
|
| 300 |
+
"eval_gate2_support": 5480,
|
| 301 |
+
"eval_gate3_accuracy": 0.8869665513264129,
|
| 302 |
+
"eval_gate3_f1": 0.8169346166824163,
|
| 303 |
+
"eval_gate3_precision": 0.8125578804865948,
|
| 304 |
+
"eval_gate3_recall": 0.8232165240906076,
|
| 305 |
+
"eval_gate3_support": 5202,
|
| 306 |
+
"eval_loss": 1.0004887580871582,
|
| 307 |
+
"eval_runtime": 8.2766,
|
| 308 |
+
"eval_samples_per_second": 1290.62,
|
| 309 |
+
"eval_steps_per_second": 40.355,
|
| 310 |
+
"step": 26710
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 10.0,
|
| 314 |
+
"step": 26710,
|
| 315 |
+
"total_flos": 5.5743437807290584e+16,
|
| 316 |
+
"train_loss": 0.32878632540115477,
|
| 317 |
+
"train_runtime": 1939.8816,
|
| 318 |
+
"train_samples_per_second": 440.547,
|
| 319 |
+
"train_steps_per_second": 13.769
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 10.0,
|
| 323 |
+
"eval_gate1_accuracy": 0.9240875912408759,
|
| 324 |
+
"eval_gate1_f1": 0.9198787159000936,
|
| 325 |
+
"eval_gate1_precision": 0.9214987753300372,
|
| 326 |
+
"eval_gate1_recall": 0.9183842728638181,
|
| 327 |
+
"eval_gate1_support": 5480,
|
| 328 |
+
"eval_gate2_accuracy": 0.8687956204379562,
|
| 329 |
+
"eval_gate2_f1": 0.7862569245385519,
|
| 330 |
+
"eval_gate2_precision": 0.7958171660250828,
|
| 331 |
+
"eval_gate2_recall": 0.7833180915653772,
|
| 332 |
+
"eval_gate2_support": 5480,
|
| 333 |
+
"eval_gate3_accuracy": 0.8846597462514417,
|
| 334 |
+
"eval_gate3_f1": 0.8122850869616633,
|
| 335 |
+
"eval_gate3_precision": 0.8109060527302346,
|
| 336 |
+
"eval_gate3_recall": 0.8171325515426088,
|
| 337 |
+
"eval_gate3_support": 5202,
|
| 338 |
+
"eval_loss": 0.9491556882858276,
|
| 339 |
+
"eval_runtime": 8.3758,
|
| 340 |
+
"eval_samples_per_second": 1275.348,
|
| 341 |
+
"eval_steps_per_second": 39.877,
|
| 342 |
+
"step": 26710
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 10.0,
|
| 346 |
+
"eval_gate1_accuracy": 0.9248312351760628,
|
| 347 |
+
"eval_gate1_f1": 0.9223014364537471,
|
| 348 |
+
"eval_gate1_precision": 0.9233799376462881,
|
| 349 |
+
"eval_gate1_recall": 0.9213102653636653,
|
| 350 |
"eval_gate1_support": 5481,
|
| 351 |
+
"eval_gate2_accuracy": 0.8673599708082467,
|
| 352 |
+
"eval_gate2_f1": 0.8048074187473976,
|
| 353 |
+
"eval_gate2_precision": 0.7981399002237517,
|
| 354 |
+
"eval_gate2_recall": 0.818477325235324,
|
| 355 |
"eval_gate2_support": 5481,
|
| 356 |
+
"eval_gate3_accuracy": 0.8764174514703056,
|
| 357 |
+
"eval_gate3_f1": 0.8057131317523325,
|
| 358 |
+
"eval_gate3_precision": 0.8091461396544178,
|
| 359 |
+
"eval_gate3_recall": 0.8052237388041866,
|
| 360 |
+
"eval_gate3_support": 5203,
|
| 361 |
+
"eval_loss": 0.9472318887710571,
|
| 362 |
+
"eval_runtime": 8.2407,
|
| 363 |
+
"eval_samples_per_second": 1296.485,
|
| 364 |
+
"eval_steps_per_second": 40.53,
|
| 365 |
+
"step": 26710
|
| 366 |
}
|
| 367 |
],
|
| 368 |
"logging_steps": 500,
|
| 369 |
+
"max_steps": 26710,
|
| 370 |
"num_input_tokens_seen": 0,
|
| 371 |
+
"num_train_epochs": 10,
|
| 372 |
"save_steps": 500,
|
| 373 |
"stateful_callbacks": {
|
| 374 |
"TrainerControl": {
|
|
|
|
| 382 |
"attributes": {}
|
| 383 |
}
|
| 384 |
},
|
| 385 |
+
"total_flos": 5.5743437807290584e+16,
|
| 386 |
+
"train_batch_size": 32,
|
| 387 |
"trial_name": null,
|
| 388 |
"trial_params": null
|
| 389 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f9a33b1fbad43324e38078c41a59a870c901b0e80b2e1191720bcab0f09c79
|
| 3 |
size 5841
|