Training in progress, step 50, 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:ef43c0b08777e4cf58436345057a4ac19f5ea6f7dc29094a654f94375a978e10
|
| 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 sha256:085a4898d4ccf1d6a3e9c720ae3b9edaa8266c978faa9cfc1ed3fe6ae8d232b3
|
| 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 sha256:4a8cfb859be6f4f67e3504bcce2b8892e0f6d9a16445c5c4c136cb8a3220508e
|
| 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": 0.
|
| 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,
|
|
@@ -80,6 +80,24 @@
|
|
| 80 |
"mean_token_accuracy": 0.6348982483148575,
|
| 81 |
"num_tokens": 144478.0,
|
| 82 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
}
|
| 84 |
],
|
| 85 |
"logging_steps": 5,
|
|
@@ -99,7 +117,7 @@
|
|
| 99 |
"attributes": {}
|
| 100 |
}
|
| 101 |
},
|
| 102 |
-
"total_flos":
|
| 103 |
"train_batch_size": 4,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.38461538461538464,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 80 |
"mean_token_accuracy": 0.6348982483148575,
|
| 81 |
"num_tokens": 144478.0,
|
| 82 |
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.34615384615384615,
|
| 86 |
+
"grad_norm": 0.0,
|
| 87 |
+
"learning_rate": 4.978e-05,
|
| 88 |
+
"loss": 1.7499,
|
| 89 |
+
"mean_token_accuracy": 0.6513226598501205,
|
| 90 |
+
"num_tokens": 163267.0,
|
| 91 |
+
"step": 45
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.38461538461538464,
|
| 95 |
+
"grad_norm": 0.0,
|
| 96 |
+
"learning_rate": 4.9755e-05,
|
| 97 |
+
"loss": 1.8227,
|
| 98 |
+
"mean_token_accuracy": 0.6310899078845977,
|
| 99 |
+
"num_tokens": 181224.0,
|
| 100 |
+
"step": 50
|
| 101 |
}
|
| 102 |
],
|
| 103 |
"logging_steps": 5,
|
|
|
|
| 117 |
"attributes": {}
|
| 118 |
}
|
| 119 |
},
|
| 120 |
+
"total_flos": 9080579373465600.0,
|
| 121 |
"train_batch_size": 4,
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|