Training in progress, step 1690, 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 sha256:438321fb138ebd3c8e62d14fe05a706dad1d3f08831db8b94c09355ebc250840
|
| 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 sha256:00f6220994b53c27808fd34cc11a115b6f11d71beaf4b14c7dddd6e0da0f2739
|
| 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:c6053545bd421fbce82fe698f1426aa04466e8ceb145041e2bbf7218525709df
|
| 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":
|
| 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,
|
|
@@ -3032,6 +3032,24 @@
|
|
| 3032 |
"mean_token_accuracy": 0.6449838757514954,
|
| 3033 |
"num_tokens": 6126273.0,
|
| 3034 |
"step": 1680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3035 |
}
|
| 3036 |
],
|
| 3037 |
"logging_steps": 5,
|
|
@@ -3051,7 +3069,7 @@
|
|
| 3051 |
"attributes": {}
|
| 3052 |
}
|
| 3053 |
},
|
| 3054 |
-
"total_flos": 3.
|
| 3055 |
"train_batch_size": 4,
|
| 3056 |
"trial_name": null,
|
| 3057 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3032 |
"mean_token_accuracy": 0.6449838757514954,
|
| 3033 |
"num_tokens": 6126273.0,
|
| 3034 |
"step": 1680
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 12.961538461538462,
|
| 3038 |
+
"grad_norm": 0.0,
|
| 3039 |
+
"learning_rate": 4.1580000000000005e-05,
|
| 3040 |
+
"loss": 1.6927,
|
| 3041 |
+
"mean_token_accuracy": 0.6574580699205399,
|
| 3042 |
+
"num_tokens": 6144991.0,
|
| 3043 |
+
"step": 1685
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 13.0,
|
| 3047 |
+
"grad_norm": 0.0,
|
| 3048 |
+
"learning_rate": 4.1555e-05,
|
| 3049 |
+
"loss": 1.7501,
|
| 3050 |
+
"mean_token_accuracy": 0.6433569133281708,
|
| 3051 |
+
"num_tokens": 6163365.0,
|
| 3052 |
+
"step": 1690
|
| 3053 |
}
|
| 3054 |
],
|
| 3055 |
"logging_steps": 5,
|
|
|
|
| 3069 |
"attributes": {}
|
| 3070 |
}
|
| 3071 |
},
|
| 3072 |
+
"total_flos": 3.122426842221773e+17,
|
| 3073 |
"train_batch_size": 4,
|
| 3074 |
"trial_name": null,
|
| 3075 |
"trial_params": null
|