Training in progress, step 1530, 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:fa8c929b2353be068090a0d3edb7a2c3a8c3aa1178a010b3aee7b57ed4f8593c
|
| 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 sha256:3709b7e6232088b3c7530872514b47b9a50aa253dc7b229a3510ab6dba279ed9
|
| 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 sha256:3517b15e4c3e3b404bcc53fc212dea14c448a5ebc1283ab0a7253d287f3abf76
|
| 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": 11.
|
| 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,
|
|
@@ -2744,6 +2744,24 @@
|
|
| 2744 |
"mean_token_accuracy": 0.6412011951208114,
|
| 2745 |
"num_tokens": 5542986.0,
|
| 2746 |
"step": 1520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2747 |
}
|
| 2748 |
],
|
| 2749 |
"logging_steps": 5,
|
|
@@ -2763,7 +2781,7 @@
|
|
| 2763 |
"attributes": {}
|
| 2764 |
}
|
| 2765 |
},
|
| 2766 |
-
"total_flos": 2.
|
| 2767 |
"train_batch_size": 4,
|
| 2768 |
"trial_name": null,
|
| 2769 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2744 |
"mean_token_accuracy": 0.6412011951208114,
|
| 2745 |
"num_tokens": 5542986.0,
|
| 2746 |
"step": 1520
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 11.73076923076923,
|
| 2750 |
+
"grad_norm": 0.0,
|
| 2751 |
+
"learning_rate": 4.2380000000000004e-05,
|
| 2752 |
+
"loss": 1.7368,
|
| 2753 |
+
"mean_token_accuracy": 0.6486877024173736,
|
| 2754 |
+
"num_tokens": 5560991.0,
|
| 2755 |
+
"step": 1525
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 11.76923076923077,
|
| 2759 |
+
"grad_norm": 0.0,
|
| 2760 |
+
"learning_rate": 4.2355000000000004e-05,
|
| 2761 |
+
"loss": 1.7506,
|
| 2762 |
+
"mean_token_accuracy": 0.6509437531232833,
|
| 2763 |
+
"num_tokens": 5579072.0,
|
| 2764 |
+
"step": 1530
|
| 2765 |
}
|
| 2766 |
],
|
| 2767 |
"logging_steps": 5,
|
|
|
|
| 2781 |
"attributes": {}
|
| 2782 |
}
|
| 2783 |
},
|
| 2784 |
+
"total_flos": 2.8266863922266112e+17,
|
| 2785 |
"train_batch_size": 4,
|
| 2786 |
"trial_name": null,
|
| 2787 |
"trial_params": null
|