Training in progress, step 1000, 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:fe49e42d2a302fdbcf09ea92f07fe293c8a2bb0395d8aa383cabbfd0daa5d35a
|
| 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 sha256:84f336374c73eaa3e0cffed8db4372651cf36e031d49c3a3793598ee23bfe1cd
|
| 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:d9df127ffff72d847710ffee4153c8826030d8229752a93a09e90ab015bde8e0
|
| 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 sha256:12bcd1ca048dbaba0d04fdf16b335c31344751cacaba7e0f860e95741fdac905
|
| 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,
|
|
@@ -1008,6 +1008,16 @@
|
|
| 1008 |
"mean_token_accuracy": 0.7708485037088394,
|
| 1009 |
"num_tokens": 4623275.0,
|
| 1010 |
"step": 990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 10,
|
|
@@ -1027,7 +1037,7 @@
|
|
| 1027 |
"attributes": {}
|
| 1028 |
}
|
| 1029 |
},
|
| 1030 |
-
"total_flos": 2.
|
| 1031 |
"train_batch_size": 4,
|
| 1032 |
"trial_name": null,
|
| 1033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.21333333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1008 |
"mean_token_accuracy": 0.7708485037088394,
|
| 1009 |
"num_tokens": 4623275.0,
|
| 1010 |
"step": 990
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 0.9400355100631714,
|
| 1014 |
+
"epoch": 0.21333333333333335,
|
| 1015 |
+
"grad_norm": 0.2274121642112732,
|
| 1016 |
+
"learning_rate": 9.85435841294036e-05,
|
| 1017 |
+
"loss": 1.051990795135498,
|
| 1018 |
+
"mean_token_accuracy": 0.762999877333641,
|
| 1019 |
+
"num_tokens": 4670070.0,
|
| 1020 |
+
"step": 1000
|
| 1021 |
}
|
| 1022 |
],
|
| 1023 |
"logging_steps": 10,
|
|
|
|
| 1037 |
"attributes": {}
|
| 1038 |
}
|
| 1039 |
},
|
| 1040 |
+
"total_flos": 2.2093569331224576e+16,
|
| 1041 |
"train_batch_size": 4,
|
| 1042 |
"trial_name": null,
|
| 1043 |
"trial_params": null
|