Training in progress, step 6640, 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 sha256:4dd6ba9b58063e839afb1df6fef04f7fff494d00b26fd8d8dbba56c6dc88d8d1
|
| 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 sha256:84a3c6d81f1d2373d88c2bbc0e6c93a8baf14410fe4246eeb4521ac3e328d413
|
| 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:c666e1d5949fe27ce46c63153c41a48c0c00cc23e475384ec94592220e1eda44
|
| 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,
|
|
@@ -11942,6 +11942,24 @@
|
|
| 11942 |
"mean_token_accuracy": 0.6428048938512803,
|
| 11943 |
"num_tokens": 24179355.0,
|
| 11944 |
"step": 6630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11945 |
}
|
| 11946 |
],
|
| 11947 |
"logging_steps": 5,
|
|
@@ -11961,7 +11979,7 @@
|
|
| 11961 |
"attributes": {}
|
| 11962 |
}
|
| 11963 |
},
|
| 11964 |
-
"total_flos": 1.
|
| 11965 |
"train_batch_size": 4,
|
| 11966 |
"trial_name": null,
|
| 11967 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11942 |
"mean_token_accuracy": 0.6428048938512803,
|
| 11943 |
"num_tokens": 24179355.0,
|
| 11944 |
"step": 6630
|
| 11945 |
+
},
|
| 11946 |
+
{
|
| 11947 |
+
"epoch": 51.03846153846154,
|
| 11948 |
+
"grad_norm": 0.0,
|
| 11949 |
+
"learning_rate": 1.683e-05,
|
| 11950 |
+
"loss": 1.6311,
|
| 11951 |
+
"mean_token_accuracy": 0.6698222011327744,
|
| 11952 |
+
"num_tokens": 24198872.0,
|
| 11953 |
+
"step": 6635
|
| 11954 |
+
},
|
| 11955 |
+
{
|
| 11956 |
+
"epoch": 51.07692307692308,
|
| 11957 |
+
"grad_norm": 0.0,
|
| 11958 |
+
"learning_rate": 1.6805000000000003e-05,
|
| 11959 |
+
"loss": 1.7177,
|
| 11960 |
+
"mean_token_accuracy": 0.6608267247676849,
|
| 11961 |
+
"num_tokens": 24216830.0,
|
| 11962 |
+
"step": 6640
|
| 11963 |
}
|
| 11964 |
],
|
| 11965 |
"logging_steps": 5,
|
|
|
|
| 11979 |
"attributes": {}
|
| 11980 |
}
|
| 11981 |
},
|
| 11982 |
+
"total_flos": 1.2278154797811302e+18,
|
| 11983 |
"train_batch_size": 4,
|
| 11984 |
"trial_name": null,
|
| 11985 |
"trial_params": null
|