Training in progress, step 9500, 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 sha256:34fef366053370529b7b3d8c01bb5e1cd9783a7cb2da67ff2f5cd2c9459084d3
|
| 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 sha256:2b50aa5954af53482c66764b46603c1491761b9838578e735e8c98a3d5959c97
|
| 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:d773548ce3e810c81a53c2e7e438410131c817145e5d806a949844b08945b61a
|
| 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": 73.
|
| 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,
|
|
@@ -17090,6 +17090,24 @@
|
|
| 17090 |
"mean_token_accuracy": 0.6583450496196747,
|
| 17091 |
"num_tokens": 34609665.0,
|
| 17092 |
"step": 9490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17093 |
}
|
| 17094 |
],
|
| 17095 |
"logging_steps": 5,
|
|
@@ -17109,7 +17127,7 @@
|
|
| 17109 |
"attributes": {}
|
| 17110 |
}
|
| 17111 |
},
|
| 17112 |
-
"total_flos": 1.
|
| 17113 |
"train_batch_size": 4,
|
| 17114 |
"trial_name": null,
|
| 17115 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17090 |
"mean_token_accuracy": 0.6583450496196747,
|
| 17091 |
"num_tokens": 34609665.0,
|
| 17092 |
"step": 9490
|
| 17093 |
+
},
|
| 17094 |
+
{
|
| 17095 |
+
"epoch": 73.03846153846153,
|
| 17096 |
+
"grad_norm": 0.0,
|
| 17097 |
+
"learning_rate": 2.53e-06,
|
| 17098 |
+
"loss": 1.7997,
|
| 17099 |
+
"mean_token_accuracy": 0.6400972425937652,
|
| 17100 |
+
"num_tokens": 34627692.0,
|
| 17101 |
+
"step": 9495
|
| 17102 |
+
},
|
| 17103 |
+
{
|
| 17104 |
+
"epoch": 73.07692307692308,
|
| 17105 |
+
"grad_norm": 0.0,
|
| 17106 |
+
"learning_rate": 2.505e-06,
|
| 17107 |
+
"loss": 1.7601,
|
| 17108 |
+
"mean_token_accuracy": 0.6496747404336929,
|
| 17109 |
+
"num_tokens": 34645368.0,
|
| 17110 |
+
"step": 9500
|
| 17111 |
}
|
| 17112 |
],
|
| 17113 |
"logging_steps": 5,
|
|
|
|
| 17127 |
"attributes": {}
|
| 17128 |
}
|
| 17129 |
},
|
| 17130 |
+
"total_flos": 1.7568523522547712e+18,
|
| 17131 |
"train_batch_size": 4,
|
| 17132 |
"trial_name": null,
|
| 17133 |
"trial_params": null
|