Upload folder using huggingface_hub
Browse files- adapter_model.bin +1 -1
- all_results.json +15 -15
- eval_results.json +10 -10
- runs/Mar31_00-08-10_a67b165e443d/events.out.tfevents.1711843692.a67b165e443d.34.0 +3 -0
- runs/Mar31_00-13-11_a67b165e443d/events.out.tfevents.1711843992.a67b165e443d.34.1 +3 -0
- runs/Mar31_00-13-11_a67b165e443d/events.out.tfevents.1711863078.a67b165e443d.34.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +93 -177
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 160086542
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93aa0cf7d99ad26d47d8643e22d1ffc2cdf84ec975fa62bf6a3744af6d78bffa
|
| 3 |
size 160086542
|
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_score": 0.
|
| 5 |
-
"eval_gmean": 0.
|
| 6 |
-
"eval_loss": 0.
|
| 7 |
-
"eval_precision": 0.
|
| 8 |
-
"eval_recall": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second": 0.
|
| 11 |
-
"eval_steps_per_second": 0.
|
| 12 |
-
"total_flos": 1.
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second": 0.
|
| 16 |
-
"train_steps_per_second": 0.
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.99,
|
| 3 |
+
"eval_accuracy": 0.84,
|
| 4 |
+
"eval_f1_score": 0.8423376623376623,
|
| 5 |
+
"eval_gmean": 0.8605301007689224,
|
| 6 |
+
"eval_loss": 0.3891015648841858,
|
| 7 |
+
"eval_precision": 0.8687999999999999,
|
| 8 |
+
"eval_recall": 0.84,
|
| 9 |
+
"eval_runtime": 156.3274,
|
| 10 |
+
"eval_samples_per_second": 0.32,
|
| 11 |
+
"eval_steps_per_second": 0.045,
|
| 12 |
+
"total_flos": 1.171238676922368e+17,
|
| 13 |
+
"train_loss": 0.9641927083333334,
|
| 14 |
+
"train_runtime": 18930.2986,
|
| 15 |
+
"train_samples_per_second": 0.317,
|
| 16 |
+
"train_steps_per_second": 0.005
|
| 17 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_score": 0.
|
| 5 |
-
"eval_gmean": 0.
|
| 6 |
-
"eval_loss": 0.
|
| 7 |
-
"eval_precision": 0.
|
| 8 |
-
"eval_recall": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second": 0.
|
| 11 |
-
"eval_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.99,
|
| 3 |
+
"eval_accuracy": 0.84,
|
| 4 |
+
"eval_f1_score": 0.8423376623376623,
|
| 5 |
+
"eval_gmean": 0.8605301007689224,
|
| 6 |
+
"eval_loss": 0.3891015648841858,
|
| 7 |
+
"eval_precision": 0.8687999999999999,
|
| 8 |
+
"eval_recall": 0.84,
|
| 9 |
+
"eval_runtime": 156.3274,
|
| 10 |
+
"eval_samples_per_second": 0.32,
|
| 11 |
+
"eval_steps_per_second": 0.045
|
| 12 |
}
|
runs/Mar31_00-08-10_a67b165e443d/events.out.tfevents.1711843692.a67b165e443d.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b7a1a0cb5f8040ad8c4dcd07d9a78b1fe78c847cbe32b10144f0fbf81c6bec3
|
| 3 |
+
size 4919
|
runs/Mar31_00-13-11_a67b165e443d/events.out.tfevents.1711843992.a67b165e443d.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32887d276cf285148292e7134729f00a457bddcb533578fc2b61d2bbd63f61dd
|
| 3 |
+
size 9095
|
runs/Mar31_00-13-11_a67b165e443d/events.out.tfevents.1711863078.a67b165e443d.34.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62af20f2ac529efff6289f4571b270ba4b39f7fb509e997638675b8df412ad02
|
| 3 |
+
size 605
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.99,
|
| 3 |
+
"total_flos": 1.171238676922368e+17,
|
| 4 |
+
"train_loss": 0.9641927083333334,
|
| 5 |
+
"train_runtime": 18930.2986,
|
| 6 |
+
"train_samples_per_second": 0.317,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,229 +1,145 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 1.
|
| 15 |
-
"loss":
|
| 16 |
"step": 8
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"eval_loss": 0.2664209008216858,
|
| 24 |
-
"eval_precision": 0.8726060606060605,
|
| 25 |
-
"eval_recall": 0.87,
|
| 26 |
-
"eval_runtime": 325.1061,
|
| 27 |
-
"eval_samples_per_second": 0.308,
|
| 28 |
-
"eval_steps_per_second": 0.04,
|
| 29 |
-
"step": 8
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"epoch": 0.19,
|
| 33 |
-
"grad_norm": 7.4375,
|
| 34 |
-
"learning_rate": 1.65e-05,
|
| 35 |
-
"loss": 0.3261,
|
| 36 |
"step": 16
|
| 37 |
},
|
| 38 |
{
|
| 39 |
-
"epoch": 0.
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"eval_loss": 0.26719239354133606,
|
| 44 |
-
"eval_precision": 0.8726060606060605,
|
| 45 |
-
"eval_recall": 0.87,
|
| 46 |
-
"eval_runtime": 325.6461,
|
| 47 |
-
"eval_samples_per_second": 0.307,
|
| 48 |
-
"eval_steps_per_second": 0.04,
|
| 49 |
-
"step": 16
|
| 50 |
-
},
|
| 51 |
-
{
|
| 52 |
-
"epoch": 0.29,
|
| 53 |
-
"grad_norm": 10.5625,
|
| 54 |
-
"learning_rate": 1.45e-05,
|
| 55 |
-
"loss": 0.3721,
|
| 56 |
-
"step": 24
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.29,
|
| 60 |
-
"eval_accuracy": 0.87,
|
| 61 |
-
"eval_f1_score": 0.8705157155935307,
|
| 62 |
-
"eval_gmean": 0.8715093639362524,
|
| 63 |
-
"eval_loss": 0.2671875059604645,
|
| 64 |
-
"eval_precision": 0.8726060606060605,
|
| 65 |
-
"eval_recall": 0.87,
|
| 66 |
-
"eval_runtime": 325.3707,
|
| 67 |
-
"eval_samples_per_second": 0.307,
|
| 68 |
-
"eval_steps_per_second": 0.04,
|
| 69 |
"step": 24
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch": 0.
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"eval_loss": 0.2667529284954071,
|
| 84 |
-
"eval_precision": 0.8726060606060605,
|
| 85 |
-
"eval_recall": 0.87,
|
| 86 |
-
"eval_runtime": 325.8406,
|
| 87 |
-
"eval_samples_per_second": 0.307,
|
| 88 |
-
"eval_steps_per_second": 0.04,
|
| 89 |
"step": 32
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch": 0.
|
| 93 |
-
"grad_norm":
|
| 94 |
-
"learning_rate": 1.
|
| 95 |
-
"loss": 0.
|
| 96 |
"step": 40
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"epoch": 0.
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"eval_loss": 0.26649415493011475,
|
| 104 |
-
"eval_precision": 0.8726060606060605,
|
| 105 |
-
"eval_recall": 0.87,
|
| 106 |
-
"eval_runtime": 325.6291,
|
| 107 |
-
"eval_samples_per_second": 0.307,
|
| 108 |
-
"eval_steps_per_second": 0.04,
|
| 109 |
-
"step": 40
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 0.58,
|
| 113 |
-
"grad_norm": 4.90625,
|
| 114 |
-
"learning_rate": 8.5e-06,
|
| 115 |
-
"loss": 0.2994,
|
| 116 |
-
"step": 48
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.58,
|
| 120 |
-
"eval_accuracy": 0.87,
|
| 121 |
-
"eval_f1_score": 0.8705157155935307,
|
| 122 |
-
"eval_gmean": 0.8715093639362524,
|
| 123 |
-
"eval_loss": 0.2669140696525574,
|
| 124 |
-
"eval_precision": 0.8726060606060605,
|
| 125 |
-
"eval_recall": 0.87,
|
| 126 |
-
"eval_runtime": 325.6436,
|
| 127 |
-
"eval_samples_per_second": 0.307,
|
| 128 |
-
"eval_steps_per_second": 0.04,
|
| 129 |
"step": 48
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"grad_norm":
|
| 134 |
-
"learning_rate":
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 56
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 0.
|
| 140 |
-
"eval_accuracy": 0.
|
| 141 |
-
"eval_f1_score": 0.
|
| 142 |
-
"eval_gmean": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_precision": 0.
|
| 145 |
-
"eval_recall": 0.
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second": 0.
|
| 148 |
-
"eval_steps_per_second": 0.
|
| 149 |
"step": 56
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
-
"step": 64
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.78,
|
| 160 |
-
"eval_accuracy": 0.87,
|
| 161 |
-
"eval_f1_score": 0.8705157155935307,
|
| 162 |
-
"eval_gmean": 0.8715093639362524,
|
| 163 |
-
"eval_loss": 0.26673829555511475,
|
| 164 |
-
"eval_precision": 0.8726060606060605,
|
| 165 |
-
"eval_recall": 0.87,
|
| 166 |
-
"eval_runtime": 327.9706,
|
| 167 |
-
"eval_samples_per_second": 0.305,
|
| 168 |
-
"eval_steps_per_second": 0.04,
|
| 169 |
"step": 64
|
| 170 |
},
|
| 171 |
{
|
| 172 |
-
"epoch": 0.
|
| 173 |
-
"grad_norm":
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
-
"step": 72
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"epoch": 0.88,
|
| 180 |
-
"eval_accuracy": 0.87,
|
| 181 |
-
"eval_f1_score": 0.8705157155935307,
|
| 182 |
-
"eval_gmean": 0.8715093639362524,
|
| 183 |
-
"eval_loss": 0.26673829555511475,
|
| 184 |
-
"eval_precision": 0.8726060606060605,
|
| 185 |
-
"eval_recall": 0.87,
|
| 186 |
-
"eval_runtime": 328.7312,
|
| 187 |
-
"eval_samples_per_second": 0.304,
|
| 188 |
-
"eval_steps_per_second": 0.04,
|
| 189 |
"step": 72
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
-
"grad_norm":
|
| 194 |
-
"learning_rate":
|
| 195 |
-
"loss": 0.
|
| 196 |
-
"step": 80
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 0.97,
|
| 200 |
-
"eval_accuracy": 0.87,
|
| 201 |
-
"eval_f1_score": 0.8705157155935307,
|
| 202 |
-
"eval_gmean": 0.8715093639362524,
|
| 203 |
-
"eval_loss": 0.26673829555511475,
|
| 204 |
-
"eval_precision": 0.8726060606060605,
|
| 205 |
-
"eval_recall": 0.87,
|
| 206 |
-
"eval_runtime": 328.568,
|
| 207 |
-
"eval_samples_per_second": 0.304,
|
| 208 |
-
"eval_steps_per_second": 0.04,
|
| 209 |
"step": 80
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
}
|
| 220 |
],
|
| 221 |
"logging_steps": 8,
|
| 222 |
-
"max_steps":
|
| 223 |
"num_input_tokens_seen": 0,
|
| 224 |
"num_train_epochs": 1,
|
| 225 |
"save_steps": 500,
|
| 226 |
-
"total_flos": 1.
|
| 227 |
"train_batch_size": 16,
|
| 228 |
"trial_name": null,
|
| 229 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.992,
|
| 5 |
+
"eval_steps": 28,
|
| 6 |
+
"global_step": 93,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 35.25,
|
| 14 |
+
"learning_rate": 1.8681318681318682e-05,
|
| 15 |
+
"loss": 1.1454,
|
| 16 |
"step": 8
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.17,
|
| 20 |
+
"grad_norm": 36.5,
|
| 21 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 22 |
+
"loss": 1.1827,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"step": 16
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.26,
|
| 27 |
+
"grad_norm": 34.0,
|
| 28 |
+
"learning_rate": 1.5164835164835166e-05,
|
| 29 |
+
"loss": 1.1057,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"step": 24
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.3,
|
| 34 |
+
"eval_accuracy": 0.82,
|
| 35 |
+
"eval_f1_score": 0.8225454545454545,
|
| 36 |
+
"eval_gmean": 0.844292130744656,
|
| 37 |
+
"eval_loss": 0.4087499976158142,
|
| 38 |
+
"eval_precision": 0.8572435897435898,
|
| 39 |
+
"eval_recall": 0.82,
|
| 40 |
+
"eval_runtime": 156.306,
|
| 41 |
+
"eval_samples_per_second": 0.32,
|
| 42 |
+
"eval_steps_per_second": 0.045,
|
| 43 |
+
"step": 28
|
| 44 |
},
|
| 45 |
{
|
| 46 |
+
"epoch": 0.34,
|
| 47 |
+
"grad_norm": 30.75,
|
| 48 |
+
"learning_rate": 1.3406593406593406e-05,
|
| 49 |
+
"loss": 0.9439,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"step": 32
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.43,
|
| 54 |
+
"grad_norm": 35.25,
|
| 55 |
+
"learning_rate": 1.164835164835165e-05,
|
| 56 |
+
"loss": 0.9382,
|
| 57 |
"step": 40
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.51,
|
| 61 |
+
"grad_norm": 35.25,
|
| 62 |
+
"learning_rate": 9.890109890109892e-06,
|
| 63 |
+
"loss": 0.9136,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
"step": 48
|
| 65 |
},
|
| 66 |
{
|
| 67 |
+
"epoch": 0.6,
|
| 68 |
+
"grad_norm": 35.75,
|
| 69 |
+
"learning_rate": 8.131868131868132e-06,
|
| 70 |
+
"loss": 0.8892,
|
| 71 |
"step": 56
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 0.6,
|
| 75 |
+
"eval_accuracy": 0.84,
|
| 76 |
+
"eval_f1_score": 0.8423376623376623,
|
| 77 |
+
"eval_gmean": 0.8605301007689224,
|
| 78 |
+
"eval_loss": 0.39445313811302185,
|
| 79 |
+
"eval_precision": 0.8687999999999999,
|
| 80 |
+
"eval_recall": 0.84,
|
| 81 |
+
"eval_runtime": 156.2149,
|
| 82 |
+
"eval_samples_per_second": 0.32,
|
| 83 |
+
"eval_steps_per_second": 0.045,
|
| 84 |
"step": 56
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 0.68,
|
| 88 |
+
"grad_norm": 25.0,
|
| 89 |
+
"learning_rate": 6.373626373626373e-06,
|
| 90 |
+
"loss": 0.9037,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
"step": 64
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"epoch": 0.77,
|
| 95 |
+
"grad_norm": 19.25,
|
| 96 |
+
"learning_rate": 4.615384615384616e-06,
|
| 97 |
+
"loss": 0.8933,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
"step": 72
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"grad_norm": 21.0,
|
| 103 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 104 |
+
"loss": 0.8473,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
"step": 80
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.9,
|
| 109 |
+
"eval_accuracy": 0.84,
|
| 110 |
+
"eval_f1_score": 0.8423376623376623,
|
| 111 |
+
"eval_gmean": 0.8605301007689224,
|
| 112 |
+
"eval_loss": 0.3901953101158142,
|
| 113 |
+
"eval_precision": 0.8687999999999999,
|
| 114 |
+
"eval_recall": 0.84,
|
| 115 |
+
"eval_runtime": 155.9323,
|
| 116 |
+
"eval_samples_per_second": 0.321,
|
| 117 |
+
"eval_steps_per_second": 0.045,
|
| 118 |
+
"step": 84
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.94,
|
| 122 |
+
"grad_norm": 32.5,
|
| 123 |
+
"learning_rate": 1.098901098901099e-06,
|
| 124 |
+
"loss": 0.8776,
|
| 125 |
+
"step": 88
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.99,
|
| 129 |
+
"step": 93,
|
| 130 |
+
"total_flos": 1.171238676922368e+17,
|
| 131 |
+
"train_loss": 0.9641927083333334,
|
| 132 |
+
"train_runtime": 18930.2986,
|
| 133 |
+
"train_samples_per_second": 0.317,
|
| 134 |
+
"train_steps_per_second": 0.005
|
| 135 |
}
|
| 136 |
],
|
| 137 |
"logging_steps": 8,
|
| 138 |
+
"max_steps": 93,
|
| 139 |
"num_input_tokens_seen": 0,
|
| 140 |
"num_train_epochs": 1,
|
| 141 |
"save_steps": 500,
|
| 142 |
+
"total_flos": 1.171238676922368e+17,
|
| 143 |
"train_batch_size": 16,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|