Training in progress, step 7810, 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 sha256:8f8bc3342c034759a22212c360857962c5dbf6b4a6cdd8bb280cdcb0090895ca
|
| 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 sha256:8de2b46eed2d39cec6b5a76cbb7dd7ab634f1ada379bdfcd87e3a23e39cabe0e
|
| 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 sha256:0dfbbea1d71fb1a8c1ae5b13c483dff0f341ee129c2bc5594491a0222ef2f505
|
| 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": 60.
|
| 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,
|
|
@@ -14048,6 +14048,24 @@
|
|
| 14048 |
"mean_token_accuracy": 0.6530990123748779,
|
| 14049 |
"num_tokens": 28446300.0,
|
| 14050 |
"step": 7800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14051 |
}
|
| 14052 |
],
|
| 14053 |
"logging_steps": 5,
|
|
@@ -14067,7 +14085,7 @@
|
|
| 14067 |
"attributes": {}
|
| 14068 |
}
|
| 14069 |
},
|
| 14070 |
-
"total_flos": 1.
|
| 14071 |
"train_batch_size": 4,
|
| 14072 |
"trial_name": null,
|
| 14073 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14048 |
"mean_token_accuracy": 0.6530990123748779,
|
| 14049 |
"num_tokens": 28446300.0,
|
| 14050 |
"step": 7800
|
| 14051 |
+
},
|
| 14052 |
+
{
|
| 14053 |
+
"epoch": 60.03846153846154,
|
| 14054 |
+
"grad_norm": 0.0,
|
| 14055 |
+
"learning_rate": 1.098e-05,
|
| 14056 |
+
"loss": 1.7301,
|
| 14057 |
+
"mean_token_accuracy": 0.6500816881656647,
|
| 14058 |
+
"num_tokens": 28464951.0,
|
| 14059 |
+
"step": 7805
|
| 14060 |
+
},
|
| 14061 |
+
{
|
| 14062 |
+
"epoch": 60.07692307692308,
|
| 14063 |
+
"grad_norm": 0.0,
|
| 14064 |
+
"learning_rate": 1.0955e-05,
|
| 14065 |
+
"loss": 1.7905,
|
| 14066 |
+
"mean_token_accuracy": 0.6456600069999695,
|
| 14067 |
+
"num_tokens": 28482557.0,
|
| 14068 |
+
"step": 7810
|
| 14069 |
}
|
| 14070 |
],
|
| 14071 |
"logging_steps": 5,
|
|
|
|
| 14085 |
"attributes": {}
|
| 14086 |
}
|
| 14087 |
},
|
| 14088 |
+
"total_flos": 1.444206845338583e+18,
|
| 14089 |
"train_batch_size": 4,
|
| 14090 |
"trial_name": null,
|
| 14091 |
"trial_params": null
|