Training in progress, step 2400, 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 sha256:965f410174ddd799f803c84768747ec04cc82120bcd2d1dec0361f48c1059ad7
|
| 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 sha256:75d69fe53b1ecac3d0bf84ab7842a26d398492fbb7251c1a632eb17e08eb2e4f
|
| 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 sha256:8bacc835dc8bcda7dffe3b32328bfe9b863a471e2f69cf0acbf923d05a2ac760
|
| 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": 18.
|
| 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,
|
|
@@ -4310,6 +4310,24 @@
|
|
| 4310 |
"mean_token_accuracy": 0.6349106699228286,
|
| 4311 |
"num_tokens": 8714150.0,
|
| 4312 |
"step": 2390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4313 |
}
|
| 4314 |
],
|
| 4315 |
"logging_steps": 5,
|
|
@@ -4329,7 +4347,7 @@
|
|
| 4329 |
"attributes": {}
|
| 4330 |
}
|
| 4331 |
},
|
| 4332 |
-
"total_flos": 4.
|
| 4333 |
"train_batch_size": 4,
|
| 4334 |
"trial_name": null,
|
| 4335 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4310 |
"mean_token_accuracy": 0.6349106699228286,
|
| 4311 |
"num_tokens": 8714150.0,
|
| 4312 |
"step": 2390
|
| 4313 |
+
},
|
| 4314 |
+
{
|
| 4315 |
+
"epoch": 18.423076923076923,
|
| 4316 |
+
"grad_norm": 0.0,
|
| 4317 |
+
"learning_rate": 3.803000000000001e-05,
|
| 4318 |
+
"loss": 1.7805,
|
| 4319 |
+
"mean_token_accuracy": 0.6420513331890106,
|
| 4320 |
+
"num_tokens": 8732388.0,
|
| 4321 |
+
"step": 2395
|
| 4322 |
+
},
|
| 4323 |
+
{
|
| 4324 |
+
"epoch": 18.46153846153846,
|
| 4325 |
+
"grad_norm": 0.0,
|
| 4326 |
+
"learning_rate": 3.8005e-05,
|
| 4327 |
+
"loss": 1.7583,
|
| 4328 |
+
"mean_token_accuracy": 0.6472231477499009,
|
| 4329 |
+
"num_tokens": 8750733.0,
|
| 4330 |
+
"step": 2400
|
| 4331 |
}
|
| 4332 |
],
|
| 4333 |
"logging_steps": 5,
|
|
|
|
| 4347 |
"attributes": {}
|
| 4348 |
}
|
| 4349 |
},
|
| 4350 |
+
"total_flos": 4.4339219488751616e+17,
|
| 4351 |
"train_batch_size": 4,
|
| 4352 |
"trial_name": null,
|
| 4353 |
"trial_params": null
|