Training in progress, step 3400, 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 sha256:95f2a56d76dc0c315b3112122217747505a17ee51c57225d840588ea80d5f86f
|
| 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 sha256:2954a43a44245fbc9d037471371ac661935f603c819f00f6f460de8bf4f174fd
|
| 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 sha256:73bffca53827c288870943f59291c6b1467e3b132d9cda373082d3385cdd1991
|
| 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": 26.
|
| 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,
|
|
@@ -6110,6 +6110,24 @@
|
|
| 6110 |
"mean_token_accuracy": 0.6523230075836182,
|
| 6111 |
"num_tokens": 12362936.0,
|
| 6112 |
"step": 3390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6113 |
}
|
| 6114 |
],
|
| 6115 |
"logging_steps": 5,
|
|
@@ -6129,7 +6147,7 @@
|
|
| 6129 |
"attributes": {}
|
| 6130 |
}
|
| 6131 |
},
|
| 6132 |
-
"total_flos": 6.
|
| 6133 |
"train_batch_size": 4,
|
| 6134 |
"trial_name": null,
|
| 6135 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6110 |
"mean_token_accuracy": 0.6523230075836182,
|
| 6111 |
"num_tokens": 12362936.0,
|
| 6112 |
"step": 3390
|
| 6113 |
+
},
|
| 6114 |
+
{
|
| 6115 |
+
"epoch": 26.115384615384617,
|
| 6116 |
+
"grad_norm": 0.0,
|
| 6117 |
+
"learning_rate": 3.303e-05,
|
| 6118 |
+
"loss": 1.7103,
|
| 6119 |
+
"mean_token_accuracy": 0.6539131790399552,
|
| 6120 |
+
"num_tokens": 12381863.0,
|
| 6121 |
+
"step": 3395
|
| 6122 |
+
},
|
| 6123 |
+
{
|
| 6124 |
+
"epoch": 26.153846153846153,
|
| 6125 |
+
"grad_norm": 0.0,
|
| 6126 |
+
"learning_rate": 3.3005e-05,
|
| 6127 |
+
"loss": 1.765,
|
| 6128 |
+
"mean_token_accuracy": 0.6502564907073974,
|
| 6129 |
+
"num_tokens": 12399802.0,
|
| 6130 |
+
"step": 3400
|
| 6131 |
}
|
| 6132 |
],
|
| 6133 |
"logging_steps": 5,
|
|
|
|
| 6147 |
"attributes": {}
|
| 6148 |
}
|
| 6149 |
},
|
| 6150 |
+
"total_flos": 6.281968309877146e+17,
|
| 6151 |
"train_batch_size": 4,
|
| 6152 |
"trial_name": null,
|
| 6153 |
"trial_params": null
|