Training in progress, step 60, 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:af353f5f2c79b6691eb32d4de5c2391053a28b93350db7518ed0d1123a35ca8e
|
| 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:f346c9a195a4e197f1cf474c7ffdfbbff9fb5f952073d9f523270a0379fe558f
|
| 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:d94a4d3080d5fb4684be61069502ffa1667a231eb92e0376d9c94cf1c87d96af
|
| 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,
|
|
@@ -98,6 +98,24 @@
|
|
| 98 |
"mean_token_accuracy": 0.6310899078845977,
|
| 99 |
"num_tokens": 181224.0,
|
| 100 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
}
|
| 102 |
],
|
| 103 |
"logging_steps": 5,
|
|
@@ -117,7 +135,7 @@
|
|
| 117 |
"attributes": {}
|
| 118 |
}
|
| 119 |
},
|
| 120 |
-
"total_flos":
|
| 121 |
"train_batch_size": 4,
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.46153846153846156,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 60,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 98 |
"mean_token_accuracy": 0.6310899078845977,
|
| 99 |
"num_tokens": 181224.0,
|
| 100 |
"step": 50
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4230769230769231,
|
| 104 |
+
"grad_norm": 0.0,
|
| 105 |
+
"learning_rate": 4.973000000000001e-05,
|
| 106 |
+
"loss": 1.7641,
|
| 107 |
+
"mean_token_accuracy": 0.6496782422065734,
|
| 108 |
+
"num_tokens": 199090.0,
|
| 109 |
+
"step": 55
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.46153846153846156,
|
| 113 |
+
"grad_norm": 0.0,
|
| 114 |
+
"learning_rate": 4.9705e-05,
|
| 115 |
+
"loss": 1.7405,
|
| 116 |
+
"mean_token_accuracy": 0.6453521817922592,
|
| 117 |
+
"num_tokens": 217701.0,
|
| 118 |
+
"step": 60
|
| 119 |
}
|
| 120 |
],
|
| 121 |
"logging_steps": 5,
|
|
|
|
| 135 |
"attributes": {}
|
| 136 |
}
|
| 137 |
},
|
| 138 |
+
"total_flos": 1.092940375228416e+16,
|
| 139 |
"train_batch_size": 4,
|
| 140 |
"trial_name": null,
|
| 141 |
"trial_params": null
|