Training in progress, step 2110, 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:aad38a2ea91884d3fc54ddaf3709127c96ba9459fc80296983fa50a3c204c503
|
| 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:ef9e6d9ba3360bb1a0aea5f8917d1b80543bcf6248690cecb090f2407830e255
|
| 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 sha256:33ac8e51f80aa63a5e6fa52ab0f78b4a2680475f1b1c0ec6c1b764ae42414bc5
|
| 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": 16.
|
| 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,
|
|
@@ -3788,6 +3788,24 @@
|
|
| 3788 |
"mean_token_accuracy": 0.6566350907087326,
|
| 3789 |
"num_tokens": 7658920.0,
|
| 3790 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3791 |
}
|
| 3792 |
],
|
| 3793 |
"logging_steps": 5,
|
|
@@ -3807,7 +3825,7 @@
|
|
| 3807 |
"attributes": {}
|
| 3808 |
}
|
| 3809 |
},
|
| 3810 |
-
"total_flos": 3.
|
| 3811 |
"train_batch_size": 4,
|
| 3812 |
"trial_name": null,
|
| 3813 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3788 |
"mean_token_accuracy": 0.6566350907087326,
|
| 3789 |
"num_tokens": 7658920.0,
|
| 3790 |
"step": 2100
|
| 3791 |
+
},
|
| 3792 |
+
{
|
| 3793 |
+
"epoch": 16.192307692307693,
|
| 3794 |
+
"grad_norm": 0.0,
|
| 3795 |
+
"learning_rate": 3.948e-05,
|
| 3796 |
+
"loss": 1.8121,
|
| 3797 |
+
"mean_token_accuracy": 0.6355432808399201,
|
| 3798 |
+
"num_tokens": 7676608.0,
|
| 3799 |
+
"step": 2105
|
| 3800 |
+
},
|
| 3801 |
+
{
|
| 3802 |
+
"epoch": 16.23076923076923,
|
| 3803 |
+
"grad_norm": 0.0,
|
| 3804 |
+
"learning_rate": 3.9455e-05,
|
| 3805 |
+
"loss": 1.7127,
|
| 3806 |
+
"mean_token_accuracy": 0.65393525660038,
|
| 3807 |
+
"num_tokens": 7695148.0,
|
| 3808 |
+
"step": 2110
|
| 3809 |
}
|
| 3810 |
],
|
| 3811 |
"logging_steps": 5,
|
|
|
|
| 3825 |
"attributes": {}
|
| 3826 |
}
|
| 3827 |
},
|
| 3828 |
+
"total_flos": 3.8989076766621696e+17,
|
| 3829 |
"train_batch_size": 4,
|
| 3830 |
"trial_name": null,
|
| 3831 |
"trial_params": null
|