Training in progress, step 3910, 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 sha256:86e999d9dce206d29c6083e2100268f7db52594d3217113a4a1442dcc341873e
|
| 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 sha256:515317c7b48a34c9d8a714b77f4fb3bfc96aba17045da2c399e5279b725411f6
|
| 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 sha256:51cd31abd14cbbbb2318009c0815cccd797697338dd1ad88e899d79abb4bdc9a
|
| 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": 30.
|
| 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,
|
|
@@ -7028,6 +7028,24 @@
|
|
| 7028 |
"mean_token_accuracy": 0.6565341949462891,
|
| 7029 |
"num_tokens": 14223150.0,
|
| 7030 |
"step": 3900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7031 |
}
|
| 7032 |
],
|
| 7033 |
"logging_steps": 5,
|
|
@@ -7047,7 +7065,7 @@
|
|
| 7047 |
"attributes": {}
|
| 7048 |
}
|
| 7049 |
},
|
| 7050 |
-
"total_flos": 7.
|
| 7051 |
"train_batch_size": 4,
|
| 7052 |
"trial_name": null,
|
| 7053 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7028 |
"mean_token_accuracy": 0.6565341949462891,
|
| 7029 |
"num_tokens": 14223150.0,
|
| 7030 |
"step": 3900
|
| 7031 |
+
},
|
| 7032 |
+
{
|
| 7033 |
+
"epoch": 30.03846153846154,
|
| 7034 |
+
"grad_norm": 0.0,
|
| 7035 |
+
"learning_rate": 3.0480000000000003e-05,
|
| 7036 |
+
"loss": 1.7284,
|
| 7037 |
+
"mean_token_accuracy": 0.6489845454692841,
|
| 7038 |
+
"num_tokens": 14241996.0,
|
| 7039 |
+
"step": 3905
|
| 7040 |
+
},
|
| 7041 |
+
{
|
| 7042 |
+
"epoch": 30.076923076923077,
|
| 7043 |
+
"grad_norm": 0.0,
|
| 7044 |
+
"learning_rate": 3.0455e-05,
|
| 7045 |
+
"loss": 1.6848,
|
| 7046 |
+
"mean_token_accuracy": 0.6612500458955765,
|
| 7047 |
+
"num_tokens": 14260761.0,
|
| 7048 |
+
"step": 3910
|
| 7049 |
}
|
| 7050 |
],
|
| 7051 |
"logging_steps": 5,
|
|
|
|
| 7065 |
"attributes": {}
|
| 7066 |
}
|
| 7067 |
},
|
| 7068 |
+
"total_flos": 7.226882062648934e+17,
|
| 7069 |
"train_batch_size": 4,
|
| 7070 |
"trial_name": null,
|
| 7071 |
"trial_params": null
|