Training in progress, step 3390, 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 sha256:3d18ca59ecdd1d151ae5781e096dc2e46c2da80890c7ad22f255abf28abbb9fc
|
| 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:b6a5a897872a273f8c9bd43c29bd30c61f55a8addb38c4bc95736ddbf8e67579
|
| 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 sha256:13360dc67e5b12cc12882d46ed87a0f02245afff86aeef8eee762e019d31460a
|
| 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,
|
|
@@ -6092,6 +6092,24 @@
|
|
| 6092 |
"mean_token_accuracy": 0.6661966532468796,
|
| 6093 |
"num_tokens": 12326730.0,
|
| 6094 |
"step": 3380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6095 |
}
|
| 6096 |
],
|
| 6097 |
"logging_steps": 5,
|
|
@@ -6111,7 +6129,7 @@
|
|
| 6111 |
"attributes": {}
|
| 6112 |
}
|
| 6113 |
},
|
| 6114 |
-
"total_flos": 6.
|
| 6115 |
"train_batch_size": 4,
|
| 6116 |
"trial_name": null,
|
| 6117 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6092 |
"mean_token_accuracy": 0.6661966532468796,
|
| 6093 |
"num_tokens": 12326730.0,
|
| 6094 |
"step": 3380
|
| 6095 |
+
},
|
| 6096 |
+
{
|
| 6097 |
+
"epoch": 26.03846153846154,
|
| 6098 |
+
"grad_norm": 0.0,
|
| 6099 |
+
"learning_rate": 3.308e-05,
|
| 6100 |
+
"loss": 1.7868,
|
| 6101 |
+
"mean_token_accuracy": 0.6423007547855377,
|
| 6102 |
+
"num_tokens": 12344701.0,
|
| 6103 |
+
"step": 3385
|
| 6104 |
+
},
|
| 6105 |
+
{
|
| 6106 |
+
"epoch": 26.076923076923077,
|
| 6107 |
+
"grad_norm": 0.0,
|
| 6108 |
+
"learning_rate": 3.3055e-05,
|
| 6109 |
+
"loss": 1.7293,
|
| 6110 |
+
"mean_token_accuracy": 0.6523230075836182,
|
| 6111 |
+
"num_tokens": 12362936.0,
|
| 6112 |
+
"step": 3390
|
| 6113 |
}
|
| 6114 |
],
|
| 6115 |
"logging_steps": 5,
|
|
|
|
| 6129 |
"attributes": {}
|
| 6130 |
}
|
| 6131 |
},
|
| 6132 |
+
"total_flos": 6.26327524099031e+17,
|
| 6133 |
"train_batch_size": 4,
|
| 6134 |
"trial_name": null,
|
| 6135 |
"trial_params": null
|