Training in progress, step 790, 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 sha256:0e2494ffdf63bf22327553c4bb55e852175014ff33dff9daedab169a57bb6f7a
|
| 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 sha256:6def35174fba19fddbd1fbc01159935c523dc04fd26db6a5deaf3b862edc82b4
|
| 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:fdc561fcb0454540f2c70b4e670e9c553e4361d10c10a8586dcf2c98e6374da7
|
| 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 sha256:2ae3588707c67138d3df6e5970c2e06dbec86d28723537e7e2192c4a3a9f3b48
|
| 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,
|
|
@@ -798,6 +798,16 @@
|
|
| 798 |
"mean_token_accuracy": 0.7623399093747139,
|
| 799 |
"num_tokens": 3625602.0,
|
| 800 |
"step": 780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 801 |
}
|
| 802 |
],
|
| 803 |
"logging_steps": 10,
|
|
@@ -817,7 +827,7 @@
|
|
| 817 |
"attributes": {}
|
| 818 |
}
|
| 819 |
},
|
| 820 |
-
"total_flos": 1.
|
| 821 |
"train_batch_size": 4,
|
| 822 |
"trial_name": null,
|
| 823 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.16853333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 798 |
"mean_token_accuracy": 0.7623399093747139,
|
| 799 |
"num_tokens": 3625602.0,
|
| 800 |
"step": 780
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 0.8914617538452149,
|
| 804 |
+
"epoch": 0.16853333333333334,
|
| 805 |
+
"grad_norm": 0.2739625573158264,
|
| 806 |
+
"learning_rate": 9.928545207415675e-05,
|
| 807 |
+
"loss": 1.014828872680664,
|
| 808 |
+
"mean_token_accuracy": 0.7721783280372619,
|
| 809 |
+
"num_tokens": 3671375.0,
|
| 810 |
+
"step": 790
|
| 811 |
}
|
| 812 |
],
|
| 813 |
"logging_steps": 10,
|
|
|
|
| 827 |
"attributes": {}
|
| 828 |
}
|
| 829 |
},
|
| 830 |
+
"total_flos": 1.7370304770330624e+16,
|
| 831 |
"train_batch_size": 4,
|
| 832 |
"trial_name": null,
|
| 833 |
"trial_params": null
|