Training in progress, step 5520, 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 sha256:8f3afe94d63565b4748fc265814c3bec495b2a09c6835994973cda1a46581478
|
| 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:a9f6faa4bde2859a09b7910fa5a30fcead2da96fa4965eac25b6ab568a060450
|
| 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 sha256:021988b2fd784067d3daa24682144de9b35533397a31f450a8e4964250e1d577
|
| 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": 42.
|
| 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,
|
|
@@ -9926,6 +9926,24 @@
|
|
| 9926 |
"mean_token_accuracy": 0.6635800451040268,
|
| 9927 |
"num_tokens": 20094237.0,
|
| 9928 |
"step": 5510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9929 |
}
|
| 9930 |
],
|
| 9931 |
"logging_steps": 5,
|
|
@@ -9945,7 +9963,7 @@
|
|
| 9945 |
"attributes": {}
|
| 9946 |
}
|
| 9947 |
},
|
| 9948 |
-
"total_flos": 1.
|
| 9949 |
"train_batch_size": 4,
|
| 9950 |
"trial_name": null,
|
| 9951 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9926 |
"mean_token_accuracy": 0.6635800451040268,
|
| 9927 |
"num_tokens": 20094237.0,
|
| 9928 |
"step": 5510
|
| 9929 |
+
},
|
| 9930 |
+
{
|
| 9931 |
+
"epoch": 42.42307692307692,
|
| 9932 |
+
"grad_norm": 0.0,
|
| 9933 |
+
"learning_rate": 2.243e-05,
|
| 9934 |
+
"loss": 1.7268,
|
| 9935 |
+
"mean_token_accuracy": 0.6491197019815445,
|
| 9936 |
+
"num_tokens": 20112703.0,
|
| 9937 |
+
"step": 5515
|
| 9938 |
+
},
|
| 9939 |
+
{
|
| 9940 |
+
"epoch": 42.46153846153846,
|
| 9941 |
+
"grad_norm": 0.0,
|
| 9942 |
+
"learning_rate": 2.2405e-05,
|
| 9943 |
+
"loss": 1.7641,
|
| 9944 |
+
"mean_token_accuracy": 0.6478333413600922,
|
| 9945 |
+
"num_tokens": 20130707.0,
|
| 9946 |
+
"step": 5520
|
| 9947 |
}
|
| 9948 |
],
|
| 9949 |
"logging_steps": 5,
|
|
|
|
| 9963 |
"attributes": {}
|
| 9964 |
}
|
| 9965 |
},
|
| 9966 |
+
"total_flos": 1.0200963136330138e+18,
|
| 9967 |
"train_batch_size": 4,
|
| 9968 |
"trial_name": null,
|
| 9969 |
"trial_params": null
|