Training in progress, step 3900, 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 sha256:8ee834049211ea114776fb1acf078e1582f5f644859391df5d0efe9b5f49136c
|
| 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 sha256:62e0a516aa1c02ac3ecd06fd7b7962ddc98d01d953621acdc241d938be3026cc
|
| 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:bd1757f54becd3ea47d9afbf9f5b9fb16e2e517b21bdd80d8a4e7fbaf7197aa2
|
| 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,
|
|
@@ -7010,6 +7010,24 @@
|
|
| 7010 |
"mean_token_accuracy": 0.6312504172325134,
|
| 7011 |
"num_tokens": 14185905.0,
|
| 7012 |
"step": 3890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7013 |
}
|
| 7014 |
],
|
| 7015 |
"logging_steps": 5,
|
|
@@ -7029,7 +7047,7 @@
|
|
| 7029 |
"attributes": {}
|
| 7030 |
}
|
| 7031 |
},
|
| 7032 |
-
"total_flos": 7.
|
| 7033 |
"train_batch_size": 4,
|
| 7034 |
"trial_name": null,
|
| 7035 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7010 |
"mean_token_accuracy": 0.6312504172325134,
|
| 7011 |
"num_tokens": 14185905.0,
|
| 7012 |
"step": 3890
|
| 7013 |
+
},
|
| 7014 |
+
{
|
| 7015 |
+
"epoch": 29.96153846153846,
|
| 7016 |
+
"grad_norm": 0.0,
|
| 7017 |
+
"learning_rate": 3.053e-05,
|
| 7018 |
+
"loss": 1.7589,
|
| 7019 |
+
"mean_token_accuracy": 0.6496811449527741,
|
| 7020 |
+
"num_tokens": 14203685.0,
|
| 7021 |
+
"step": 3895
|
| 7022 |
+
},
|
| 7023 |
+
{
|
| 7024 |
+
"epoch": 30.0,
|
| 7025 |
+
"grad_norm": 0.0,
|
| 7026 |
+
"learning_rate": 3.0505e-05,
|
| 7027 |
+
"loss": 1.6956,
|
| 7028 |
+
"mean_token_accuracy": 0.6565341949462891,
|
| 7029 |
+
"num_tokens": 14223150.0,
|
| 7030 |
+
"step": 3900
|
| 7031 |
}
|
| 7032 |
],
|
| 7033 |
"logging_steps": 5,
|
|
|
|
| 7047 |
"attributes": {}
|
| 7048 |
}
|
| 7049 |
},
|
| 7050 |
+
"total_flos": 7.207518945764966e+17,
|
| 7051 |
"train_batch_size": 4,
|
| 7052 |
"trial_name": null,
|
| 7053 |
"trial_params": null
|