Training in progress, step 2020, 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 sha256:37ea2dab6582711b6729815a9b8402287999be5a19597d6fc7a35c573d896b95
|
| 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 sha256:73b61f6c23a361f119607dacdc23b862f3405c0dae680fdace1ac11b472e6981
|
| 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 sha256:2926881dc3366357acb158050d0915d40563056d7e76b033655aaa395ef9f080
|
| 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 sha256:260e84a59e9fdc43c828187185121f54ac80fec74fac63175d55ac8ea669e7fe
|
| 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,
|
|
@@ -2028,6 +2028,16 @@
|
|
| 2028 |
"mean_token_accuracy": 0.7620892718434333,
|
| 2029 |
"num_tokens": 9317142.0,
|
| 2030 |
"step": 2010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2031 |
}
|
| 2032 |
],
|
| 2033 |
"logging_steps": 10,
|
|
@@ -2047,7 +2057,7 @@
|
|
| 2047 |
"attributes": {}
|
| 2048 |
}
|
| 2049 |
},
|
| 2050 |
-
"total_flos": 4.
|
| 2051 |
"train_batch_size": 4,
|
| 2052 |
"trial_name": null,
|
| 2053 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.43093333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2028 |
"mean_token_accuracy": 0.7620892718434333,
|
| 2029 |
"num_tokens": 9317142.0,
|
| 2030 |
"step": 2010
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"entropy": 0.8780575722455979,
|
| 2034 |
+
"epoch": 0.43093333333333333,
|
| 2035 |
+
"grad_norm": 0.2631659209728241,
|
| 2036 |
+
"learning_rate": 9.140687600006929e-05,
|
| 2037 |
+
"loss": 0.983364200592041,
|
| 2038 |
+
"mean_token_accuracy": 0.7832586973905563,
|
| 2039 |
+
"num_tokens": 9360075.0,
|
| 2040 |
+
"step": 2020
|
| 2041 |
}
|
| 2042 |
],
|
| 2043 |
"logging_steps": 10,
|
|
|
|
| 2057 |
"attributes": {}
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
+
"total_flos": 4.44263226688727e+16,
|
| 2061 |
"train_batch_size": 4,
|
| 2062 |
"trial_name": null,
|
| 2063 |
"trial_params": null
|