Training in progress, step 140, 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 sha256:382fe43fb4816a0f80dd227cebaaabf1dbc8c60ffff9394f8bff9a321525c329
|
| 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:f2c9b3be05f69b66da14166a1fcb375ffa9d94b6d1ef2c20bc1a23aa16da9b04
|
| 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 sha256:196b1dc060d632e761356f79c6c55ba0ad1f244fcc04f06ab282f68fff9533cf
|
| 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": 1.
|
| 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,
|
|
@@ -242,6 +242,24 @@
|
|
| 242 |
"mean_token_accuracy": 0.6529789954423905,
|
| 243 |
"num_tokens": 474105.0,
|
| 244 |
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 245 |
}
|
| 246 |
],
|
| 247 |
"logging_steps": 5,
|
|
@@ -261,7 +279,7 @@
|
|
| 261 |
"attributes": {}
|
| 262 |
}
|
| 263 |
},
|
| 264 |
-
"total_flos": 2.
|
| 265 |
"train_batch_size": 4,
|
| 266 |
"trial_name": null,
|
| 267 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 242 |
"mean_token_accuracy": 0.6529789954423905,
|
| 243 |
"num_tokens": 474105.0,
|
| 244 |
"step": 130
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.0384615384615385,
|
| 248 |
+
"grad_norm": 0.0,
|
| 249 |
+
"learning_rate": 4.9330000000000004e-05,
|
| 250 |
+
"loss": 1.7308,
|
| 251 |
+
"mean_token_accuracy": 0.6532562792301178,
|
| 252 |
+
"num_tokens": 492861.0,
|
| 253 |
+
"step": 135
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.0769230769230769,
|
| 257 |
+
"grad_norm": 0.0,
|
| 258 |
+
"learning_rate": 4.9305e-05,
|
| 259 |
+
"loss": 1.7815,
|
| 260 |
+
"mean_token_accuracy": 0.6435200899839402,
|
| 261 |
+
"num_tokens": 510988.0,
|
| 262 |
+
"step": 140
|
| 263 |
}
|
| 264 |
],
|
| 265 |
"logging_steps": 5,
|
|
|
|
| 279 |
"attributes": {}
|
| 280 |
}
|
| 281 |
},
|
| 282 |
+
"total_flos": 2.58159013871616e+16,
|
| 283 |
"train_batch_size": 4,
|
| 284 |
"trial_name": null,
|
| 285 |
"trial_params": null
|