Training in progress, step 110, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c344b69b2bc0161e279605d84105dd8716da620a0d86fda29e004039defb2525
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8f132fb156c462c6f737820d081354d4d75eda6d6bb178c61bf35ef0448b4c
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28eb7c73593f2896e0c50f2ea61fe8fd08a826a5dfcd5cdd78b9085b057596ec
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 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,
|
|
@@ -188,6 +188,24 @@
|
|
| 188 |
"mean_token_accuracy": 0.6630265355110169,
|
| 189 |
"num_tokens": 364985.0,
|
| 190 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 191 |
}
|
| 192 |
],
|
| 193 |
"logging_steps": 5,
|
|
@@ -207,7 +225,7 @@
|
|
| 207 |
"attributes": {}
|
| 208 |
}
|
| 209 |
},
|
| 210 |
-
"total_flos":
|
| 211 |
"train_batch_size": 4,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8461538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 188 |
"mean_token_accuracy": 0.6630265355110169,
|
| 189 |
"num_tokens": 364985.0,
|
| 190 |
"step": 100
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.8076923076923077,
|
| 194 |
+
"grad_norm": 0.0,
|
| 195 |
+
"learning_rate": 4.948000000000001e-05,
|
| 196 |
+
"loss": 1.7477,
|
| 197 |
+
"mean_token_accuracy": 0.6559244930744171,
|
| 198 |
+
"num_tokens": 382893.0,
|
| 199 |
+
"step": 105
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8461538461538461,
|
| 203 |
+
"grad_norm": 0.0,
|
| 204 |
+
"learning_rate": 4.9455e-05,
|
| 205 |
+
"loss": 1.7006,
|
| 206 |
+
"mean_token_accuracy": 0.6579539209604264,
|
| 207 |
+
"num_tokens": 401596.0,
|
| 208 |
+
"step": 110
|
| 209 |
}
|
| 210 |
],
|
| 211 |
"logging_steps": 5,
|
|
|
|
| 225 |
"attributes": {}
|
| 226 |
}
|
| 227 |
},
|
| 228 |
+
"total_flos": 2.033436892151808e+16,
|
| 229 |
"train_batch_size": 4,
|
| 230 |
"trial_name": null,
|
| 231 |
"trial_params": null
|