Training in progress, step 5610, 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:ba86306e26f2c7f8dc0bc96afb1afb86971e84f6ed4d7447c50a099f1bcf9850
|
| 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:bdc6ad6971ddf2ac7c72ef55889e4744d4111adefd5faf6f5cd9350a4dcb9671
|
| 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 sha256:924e14353dc0e44f6525ac13c16ecdff5b343730bd79bf3bbfe281651566b82f
|
| 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": 43.
|
| 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,
|
|
@@ -10088,6 +10088,24 @@
|
|
| 10088 |
"mean_token_accuracy": 0.6514497637748718,
|
| 10089 |
"num_tokens": 20422886.0,
|
| 10090 |
"step": 5600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10091 |
}
|
| 10092 |
],
|
| 10093 |
"logging_steps": 5,
|
|
@@ -10107,7 +10125,7 @@
|
|
| 10107 |
"attributes": {}
|
| 10108 |
}
|
| 10109 |
},
|
| 10110 |
-
"total_flos": 1.
|
| 10111 |
"train_batch_size": 4,
|
| 10112 |
"trial_name": null,
|
| 10113 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10088 |
"mean_token_accuracy": 0.6514497637748718,
|
| 10089 |
"num_tokens": 20422886.0,
|
| 10090 |
"step": 5600
|
| 10091 |
+
},
|
| 10092 |
+
{
|
| 10093 |
+
"epoch": 43.11538461538461,
|
| 10094 |
+
"grad_norm": 0.0,
|
| 10095 |
+
"learning_rate": 2.198e-05,
|
| 10096 |
+
"loss": 1.7403,
|
| 10097 |
+
"mean_token_accuracy": 0.6523116052150726,
|
| 10098 |
+
"num_tokens": 20440808.0,
|
| 10099 |
+
"step": 5605
|
| 10100 |
+
},
|
| 10101 |
+
{
|
| 10102 |
+
"epoch": 43.15384615384615,
|
| 10103 |
+
"grad_norm": 0.0,
|
| 10104 |
+
"learning_rate": 2.1955e-05,
|
| 10105 |
+
"loss": 1.6582,
|
| 10106 |
+
"mean_token_accuracy": 0.6698237389326096,
|
| 10107 |
+
"num_tokens": 20459519.0,
|
| 10108 |
+
"step": 5610
|
| 10109 |
}
|
| 10110 |
],
|
| 10111 |
"logging_steps": 5,
|
|
|
|
| 10125 |
"attributes": {}
|
| 10126 |
}
|
| 10127 |
},
|
| 10128 |
+
"total_flos": 1.0367638369512653e+18,
|
| 10129 |
"train_batch_size": 4,
|
| 10130 |
"trial_name": null,
|
| 10131 |
"trial_params": null
|