Training in progress, step 6740, 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:cc332b588b3b986823108a4f8d7c3568e564ea9ff3a3217236399e234ee718e9
|
| 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 sha256:07972f7ca464ee57dc8b5332d367a3acbcff97f58d4e6b4a73838ae5b623f0df
|
| 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:f63968b5877168b630f154ce53d23ad9bd35d00ecd762c5a19cb20ed274edeb6
|
| 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": 51.
|
| 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,
|
|
@@ -12122,6 +12122,24 @@
|
|
| 12122 |
"mean_token_accuracy": 0.6629273265600204,
|
| 12123 |
"num_tokens": 24544388.0,
|
| 12124 |
"step": 6730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12125 |
}
|
| 12126 |
],
|
| 12127 |
"logging_steps": 5,
|
|
@@ -12141,7 +12159,7 @@
|
|
| 12141 |
"attributes": {}
|
| 12142 |
}
|
| 12143 |
},
|
| 12144 |
-
"total_flos": 1.
|
| 12145 |
"train_batch_size": 4,
|
| 12146 |
"trial_name": null,
|
| 12147 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12122 |
"mean_token_accuracy": 0.6629273265600204,
|
| 12123 |
"num_tokens": 24544388.0,
|
| 12124 |
"step": 6730
|
| 12125 |
+
},
|
| 12126 |
+
{
|
| 12127 |
+
"epoch": 51.80769230769231,
|
| 12128 |
+
"grad_norm": 0.0,
|
| 12129 |
+
"learning_rate": 1.633e-05,
|
| 12130 |
+
"loss": 1.7177,
|
| 12131 |
+
"mean_token_accuracy": 0.653970816731453,
|
| 12132 |
+
"num_tokens": 24563413.0,
|
| 12133 |
+
"step": 6735
|
| 12134 |
+
},
|
| 12135 |
+
{
|
| 12136 |
+
"epoch": 51.84615384615385,
|
| 12137 |
+
"grad_norm": 0.0,
|
| 12138 |
+
"learning_rate": 1.6305e-05,
|
| 12139 |
+
"loss": 1.7994,
|
| 12140 |
+
"mean_token_accuracy": 0.6389773488044739,
|
| 12141 |
+
"num_tokens": 24581168.0,
|
| 12142 |
+
"step": 6740
|
| 12143 |
}
|
| 12144 |
],
|
| 12145 |
"logging_steps": 5,
|
|
|
|
| 12159 |
"attributes": {}
|
| 12160 |
}
|
| 12161 |
},
|
| 12162 |
+
"total_flos": 1.2462829235011584e+18,
|
| 12163 |
"train_batch_size": 4,
|
| 12164 |
"trial_name": null,
|
| 12165 |
"trial_params": null
|