Training in progress, epoch 10, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 390297116
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4c7aff00a5e65bc56c9bb395f90526eca09b4189f4699edd0d8200365dd9e42
|
| 3 |
size 390297116
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 780714234
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cbc75078017476c7be7e7e6a6f3d51ca403337fd2c531fc00ba7562588ebea2
|
| 3 |
size 780714234
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:975db69debf00745cff43ebb2f17ab930fe06de76881523eb59f0a5882cc78dd
|
| 3 |
size 14244
|
last-checkpoint/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:cc548a48522939f94b6987e6233137058d67af7e0a9a13b18ff79d01b9a207d6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 132,
|
| 3 |
"best_metric": 0.746761750915601,
|
| 4 |
"best_model_checkpoint": "/content/drive/MyDrive/Colab/models/vihsd-undersampling-visobert/checkpoint-132",
|
| 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,
|
|
@@ -170,6 +170,24 @@
|
|
| 170 |
"eval_samples_per_second": 209.14,
|
| 171 |
"eval_steps_per_second": 0.907,
|
| 172 |
"step": 198
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
}
|
| 174 |
],
|
| 175 |
"logging_steps": 500,
|
|
@@ -184,12 +202,12 @@
|
|
| 184 |
"should_evaluate": false,
|
| 185 |
"should_log": false,
|
| 186 |
"should_save": true,
|
| 187 |
-
"should_training_stop":
|
| 188 |
},
|
| 189 |
"attributes": {}
|
| 190 |
}
|
| 191 |
},
|
| 192 |
-
"total_flos":
|
| 193 |
"train_batch_size": 32,
|
| 194 |
"trial_name": null,
|
| 195 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 132,
|
| 3 |
"best_metric": 0.746761750915601,
|
| 4 |
"best_model_checkpoint": "/content/drive/MyDrive/Colab/models/vihsd-undersampling-visobert/checkpoint-132",
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 170 |
"eval_samples_per_second": 209.14,
|
| 171 |
"eval_steps_per_second": 0.907,
|
| 172 |
"step": 198
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 10.0,
|
| 176 |
+
"grad_norm": 1.7623181343078613,
|
| 177 |
+
"learning_rate": 9.090909090909091e-08,
|
| 178 |
+
"loss": 0.1065,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 10.0,
|
| 183 |
+
"eval_accuracy": 0.7519514310494363,
|
| 184 |
+
"eval_f1_macro": 0.7425482697194573,
|
| 185 |
+
"eval_f1_weighted": 0.7483340980964746,
|
| 186 |
+
"eval_loss": 0.8097909092903137,
|
| 187 |
+
"eval_runtime": 5.495,
|
| 188 |
+
"eval_samples_per_second": 209.826,
|
| 189 |
+
"eval_steps_per_second": 0.91,
|
| 190 |
+
"step": 220
|
| 191 |
}
|
| 192 |
],
|
| 193 |
"logging_steps": 500,
|
|
|
|
| 202 |
"should_evaluate": false,
|
| 203 |
"should_log": false,
|
| 204 |
"should_save": true,
|
| 205 |
+
"should_training_stop": true
|
| 206 |
},
|
| 207 |
"attributes": {}
|
| 208 |
}
|
| 209 |
},
|
| 210 |
+
"total_flos": 2766288139902000.0,
|
| 211 |
"train_batch_size": 32,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|