Training in progress, step 9100, 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 sha256:54457a139bf1733b4fecf8d30368fc850320fd3d20f7cd18874c08ca6afb5527
|
| 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 sha256:8251b0ab286186ee7864a7b7141b011d508ab3ffc48ce78cebf0876cdda4268c
|
| 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:cefe6b15651009d3b799f791dc92ce329639b12c1457eedc6a4c0312f1a56791
|
| 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":
|
| 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,
|
|
@@ -16370,6 +16370,24 @@
|
|
| 16370 |
"mean_token_accuracy": 0.6561585962772369,
|
| 16371 |
"num_tokens": 33150722.0,
|
| 16372 |
"step": 9090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16373 |
}
|
| 16374 |
],
|
| 16375 |
"logging_steps": 5,
|
|
@@ -16389,7 +16407,7 @@
|
|
| 16389 |
"attributes": {}
|
| 16390 |
}
|
| 16391 |
},
|
| 16392 |
-
"total_flos": 1.
|
| 16393 |
"train_batch_size": 4,
|
| 16394 |
"trial_name": null,
|
| 16395 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16370 |
"mean_token_accuracy": 0.6561585962772369,
|
| 16371 |
"num_tokens": 33150722.0,
|
| 16372 |
"step": 9090
|
| 16373 |
+
},
|
| 16374 |
+
{
|
| 16375 |
+
"epoch": 69.96153846153847,
|
| 16376 |
+
"grad_norm": 0.0,
|
| 16377 |
+
"learning_rate": 4.53e-06,
|
| 16378 |
+
"loss": 1.6798,
|
| 16379 |
+
"mean_token_accuracy": 0.6648322910070419,
|
| 16380 |
+
"num_tokens": 33169488.0,
|
| 16381 |
+
"step": 9095
|
| 16382 |
+
},
|
| 16383 |
+
{
|
| 16384 |
+
"epoch": 70.0,
|
| 16385 |
+
"grad_norm": 0.0,
|
| 16386 |
+
"learning_rate": 4.505e-06,
|
| 16387 |
+
"loss": 1.7484,
|
| 16388 |
+
"mean_token_accuracy": 0.6524565041065216,
|
| 16389 |
+
"num_tokens": 33187350.0,
|
| 16390 |
+
"step": 9100
|
| 16391 |
}
|
| 16392 |
],
|
| 16393 |
"logging_steps": 5,
|
|
|
|
| 16407 |
"attributes": {}
|
| 16408 |
}
|
| 16409 |
},
|
| 16410 |
+
"total_flos": 1.6828460273088922e+18,
|
| 16411 |
"train_batch_size": 4,
|
| 16412 |
"trial_name": null,
|
| 16413 |
"trial_params": null
|