Training in progress, step 5690, 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:f3dddab8f050378dfaddc22e593a9dd65857aa6640de4c1d05ff9a99272fe86f
|
| 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 sha256:95c853879d7773f3287f77163222115626a77c85af389384acd83bad80fa5bfd
|
| 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:aad328efcbd4ee96b944c88a6923a43ba529b318ed688f5d04245121fb4c6ac1
|
| 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": 43.
|
| 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,
|
|
@@ -10232,6 +10232,24 @@
|
|
| 10232 |
"mean_token_accuracy": 0.6438897788524628,
|
| 10233 |
"num_tokens": 20717346.0,
|
| 10234 |
"step": 5680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10235 |
}
|
| 10236 |
],
|
| 10237 |
"logging_steps": 5,
|
|
@@ -10251,7 +10269,7 @@
|
|
| 10251 |
"attributes": {}
|
| 10252 |
}
|
| 10253 |
},
|
| 10254 |
-
"total_flos": 1.
|
| 10255 |
"train_batch_size": 4,
|
| 10256 |
"trial_name": null,
|
| 10257 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10232 |
"mean_token_accuracy": 0.6438897788524628,
|
| 10233 |
"num_tokens": 20717346.0,
|
| 10234 |
"step": 5680
|
| 10235 |
+
},
|
| 10236 |
+
{
|
| 10237 |
+
"epoch": 43.73076923076923,
|
| 10238 |
+
"grad_norm": 0.0,
|
| 10239 |
+
"learning_rate": 2.158e-05,
|
| 10240 |
+
"loss": 1.7388,
|
| 10241 |
+
"mean_token_accuracy": 0.6525939971208572,
|
| 10242 |
+
"num_tokens": 20735654.0,
|
| 10243 |
+
"step": 5685
|
| 10244 |
+
},
|
| 10245 |
+
{
|
| 10246 |
+
"epoch": 43.76923076923077,
|
| 10247 |
+
"grad_norm": 0.0,
|
| 10248 |
+
"learning_rate": 2.1555e-05,
|
| 10249 |
+
"loss": 1.7583,
|
| 10250 |
+
"mean_token_accuracy": 0.649162980914116,
|
| 10251 |
+
"num_tokens": 20753638.0,
|
| 10252 |
+
"step": 5690
|
| 10253 |
}
|
| 10254 |
],
|
| 10255 |
"logging_steps": 5,
|
|
|
|
| 10269 |
"attributes": {}
|
| 10270 |
}
|
| 10271 |
},
|
| 10272 |
+
"total_flos": 1.0517708479581389e+18,
|
| 10273 |
"train_batch_size": 4,
|
| 10274 |
"trial_name": null,
|
| 10275 |
"trial_params": null
|