Training in progress, step 850, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fddc345ae6d2b73ee57370372630cb3799ae0d04076c953daffa116187dbab07
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e30b59ca469485cb4d3c1b1fd41cc3176cfa57e591993c804843ddbcebf765dd
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed7c9da09ac2e2da4726d998155ab319bdce74dc5490db2a8af114c66f110360
|
| 3 |
size 14645
|
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 sha256:4228f8bcc0f777dd374525c5543b7fd9d59767e59fc71edf11fc0a4c8e676b49
|
| 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": 0.
|
| 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,
|
|
@@ -858,6 +858,16 @@
|
|
| 858 |
"mean_token_accuracy": 0.7290896072983741,
|
| 859 |
"num_tokens": 3909965.0,
|
| 860 |
"step": 840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 861 |
}
|
| 862 |
],
|
| 863 |
"logging_steps": 10,
|
|
@@ -877,7 +887,7 @@
|
|
| 877 |
"attributes": {}
|
| 878 |
}
|
| 879 |
},
|
| 880 |
-
"total_flos": 1.
|
| 881 |
"train_batch_size": 4,
|
| 882 |
"trial_name": null,
|
| 883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.18133333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 858 |
"mean_token_accuracy": 0.7290896072983741,
|
| 859 |
"num_tokens": 3909965.0,
|
| 860 |
"step": 840
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 0.9500585079193116,
|
| 864 |
+
"epoch": 0.18133333333333335,
|
| 865 |
+
"grad_norm": 0.3055127263069153,
|
| 866 |
+
"learning_rate": 9.90999054619e-05,
|
| 867 |
+
"loss": 1.0213364601135253,
|
| 868 |
+
"mean_token_accuracy": 0.7678412273526192,
|
| 869 |
+
"num_tokens": 3948812.0,
|
| 870 |
+
"step": 850
|
| 871 |
}
|
| 872 |
],
|
| 873 |
"logging_steps": 10,
|
|
|
|
| 887 |
"attributes": {}
|
| 888 |
}
|
| 889 |
},
|
| 890 |
+
"total_flos": 1.870809865095168e+16,
|
| 891 |
"train_batch_size": 4,
|
| 892 |
"trial_name": null,
|
| 893 |
"trial_params": null
|