Training in progress, step 5150, 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 sha256:19f060e0a6cd6a44a032d2bb630cdc33098e8bfc20e243a25607bf7a04dbed02
|
| 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:fbea0f8f7b8dd1a97a433cc38edd1c132929366adb3ff75e95a3e98032201e80
|
| 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:ad7060c39e43edd9b22272991a8a702ac1d3b662e1fe82e1b216e261b31e9ab8
|
| 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": 39.
|
| 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,
|
|
@@ -9260,6 +9260,24 @@
|
|
| 9260 |
"mean_token_accuracy": 0.6536213010549545,
|
| 9261 |
"num_tokens": 18747486.0,
|
| 9262 |
"step": 5140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9263 |
}
|
| 9264 |
],
|
| 9265 |
"logging_steps": 5,
|
|
@@ -9279,7 +9297,7 @@
|
|
| 9279 |
"attributes": {}
|
| 9280 |
}
|
| 9281 |
},
|
| 9282 |
-
"total_flos": 9.
|
| 9283 |
"train_batch_size": 4,
|
| 9284 |
"trial_name": null,
|
| 9285 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9260 |
"mean_token_accuracy": 0.6536213010549545,
|
| 9261 |
"num_tokens": 18747486.0,
|
| 9262 |
"step": 5140
|
| 9263 |
+
},
|
| 9264 |
+
{
|
| 9265 |
+
"epoch": 39.57692307692308,
|
| 9266 |
+
"grad_norm": 0.0,
|
| 9267 |
+
"learning_rate": 2.428e-05,
|
| 9268 |
+
"loss": 1.7075,
|
| 9269 |
+
"mean_token_accuracy": 0.6612475931644439,
|
| 9270 |
+
"num_tokens": 18766026.0,
|
| 9271 |
+
"step": 5145
|
| 9272 |
+
},
|
| 9273 |
+
{
|
| 9274 |
+
"epoch": 39.61538461538461,
|
| 9275 |
+
"grad_norm": 0.0,
|
| 9276 |
+
"learning_rate": 2.4255e-05,
|
| 9277 |
+
"loss": 1.6588,
|
| 9278 |
+
"mean_token_accuracy": 0.6661661475896835,
|
| 9279 |
+
"num_tokens": 18785291.0,
|
| 9280 |
+
"step": 5150
|
| 9281 |
}
|
| 9282 |
],
|
| 9283 |
"logging_steps": 5,
|
|
|
|
| 9297 |
"attributes": {}
|
| 9298 |
}
|
| 9299 |
},
|
| 9300 |
+
"total_flos": 9.519003527646413e+17,
|
| 9301 |
"train_batch_size": 4,
|
| 9302 |
"trial_name": null,
|
| 9303 |
"trial_params": null
|