Training in progress, step 4320, 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 sha256:929026d2ba579145ba5dc6baf4cc7ac3d54c9699a3c84f321658e0c2b0b460ca
|
| 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 sha256:0a25b7694f0c6ffe4ae906d96379aaca41385b739400fd07425888974f189c83
|
| 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:ae977300cb3db8c6b489d921e6b00c4c1a561593c0a427710de3b8c4c4056548
|
| 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": 33.
|
| 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,
|
|
@@ -7766,6 +7766,24 @@
|
|
| 7766 |
"mean_token_accuracy": 0.6517443567514419,
|
| 7767 |
"num_tokens": 15718054.0,
|
| 7768 |
"step": 4310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7769 |
}
|
| 7770 |
],
|
| 7771 |
"logging_steps": 5,
|
|
@@ -7785,7 +7803,7 @@
|
|
| 7785 |
"attributes": {}
|
| 7786 |
}
|
| 7787 |
},
|
| 7788 |
-
"total_flos": 7.
|
| 7789 |
"train_batch_size": 4,
|
| 7790 |
"trial_name": null,
|
| 7791 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7766 |
"mean_token_accuracy": 0.6517443567514419,
|
| 7767 |
"num_tokens": 15718054.0,
|
| 7768 |
"step": 4310
|
| 7769 |
+
},
|
| 7770 |
+
{
|
| 7771 |
+
"epoch": 33.19230769230769,
|
| 7772 |
+
"grad_norm": 0.0,
|
| 7773 |
+
"learning_rate": 2.843e-05,
|
| 7774 |
+
"loss": 1.7484,
|
| 7775 |
+
"mean_token_accuracy": 0.6458596080541611,
|
| 7776 |
+
"num_tokens": 15736292.0,
|
| 7777 |
+
"step": 4315
|
| 7778 |
+
},
|
| 7779 |
+
{
|
| 7780 |
+
"epoch": 33.23076923076923,
|
| 7781 |
+
"grad_norm": 0.0,
|
| 7782 |
+
"learning_rate": 2.8405000000000003e-05,
|
| 7783 |
+
"loss": 1.715,
|
| 7784 |
+
"mean_token_accuracy": 0.6541249454021454,
|
| 7785 |
+
"num_tokens": 15755018.0,
|
| 7786 |
+
"step": 4320
|
| 7787 |
}
|
| 7788 |
],
|
| 7789 |
"logging_steps": 5,
|
|
|
|
| 7803 |
"attributes": {}
|
| 7804 |
}
|
| 7805 |
},
|
| 7806 |
+
"total_flos": 7.983790191732326e+17,
|
| 7807 |
"train_batch_size": 4,
|
| 7808 |
"trial_name": null,
|
| 7809 |
"trial_params": null
|