Training in progress, step 8910, 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:d54aa9901d836a0af6e49ce0c993968660bbdba86ecd083642d494ec8b06bc9f
|
| 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 sha256:0390eabefd832e640892a71a4d1527fd765c97a0624eb768443d8fe3d071c5ca
|
| 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 sha256:56f2878ed789ba24943bfce07ddee00d8ab39e139149970c086bdfe73083c433
|
| 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": 68.
|
| 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,
|
|
@@ -16028,6 +16028,24 @@
|
|
| 16028 |
"mean_token_accuracy": 0.6481510013341903,
|
| 16029 |
"num_tokens": 32455486.0,
|
| 16030 |
"step": 8900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16031 |
}
|
| 16032 |
],
|
| 16033 |
"logging_steps": 5,
|
|
@@ -16047,7 +16065,7 @@
|
|
| 16047 |
"attributes": {}
|
| 16048 |
}
|
| 16049 |
},
|
| 16050 |
-
"total_flos": 1.
|
| 16051 |
"train_batch_size": 4,
|
| 16052 |
"trial_name": null,
|
| 16053 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16028 |
"mean_token_accuracy": 0.6481510013341903,
|
| 16029 |
"num_tokens": 32455486.0,
|
| 16030 |
"step": 8900
|
| 16031 |
+
},
|
| 16032 |
+
{
|
| 16033 |
+
"epoch": 68.5,
|
| 16034 |
+
"grad_norm": 0.0,
|
| 16035 |
+
"learning_rate": 5.48e-06,
|
| 16036 |
+
"loss": 1.6469,
|
| 16037 |
+
"mean_token_accuracy": 0.6719613999128342,
|
| 16038 |
+
"num_tokens": 32475172.0,
|
| 16039 |
+
"step": 8905
|
| 16040 |
+
},
|
| 16041 |
+
{
|
| 16042 |
+
"epoch": 68.53846153846153,
|
| 16043 |
+
"grad_norm": 0.0,
|
| 16044 |
+
"learning_rate": 5.455e-06,
|
| 16045 |
+
"loss": 1.7171,
|
| 16046 |
+
"mean_token_accuracy": 0.6506960332393646,
|
| 16047 |
+
"num_tokens": 32493791.0,
|
| 16048 |
+
"step": 8910
|
| 16049 |
}
|
| 16050 |
],
|
| 16051 |
"logging_steps": 5,
|
|
|
|
| 16065 |
"attributes": {}
|
| 16066 |
}
|
| 16067 |
},
|
| 16068 |
+
"total_flos": 1.6476381806424883e+18,
|
| 16069 |
"train_batch_size": 4,
|
| 16070 |
"trial_name": null,
|
| 16071 |
"trial_params": null
|