Training in progress, step 4480, 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 sha256:8d81e3420bf55e26733df83ae36bb05b18b6ce372efd45579081547de9dabd40
|
| 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 sha256:3f9103d5ca1a85fc1be3e9043c03bd5453afe92f1db7f1250b6234486b70e5d6
|
| 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:d2f51474a18480811b92c70471822bb28dbbee71d0f152b1fde5256b685e3b68
|
| 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": 34.
|
| 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,
|
|
@@ -8054,6 +8054,24 @@
|
|
| 8054 |
"mean_token_accuracy": 0.6550962030887604,
|
| 8055 |
"num_tokens": 16301795.0,
|
| 8056 |
"step": 4470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8057 |
}
|
| 8058 |
],
|
| 8059 |
"logging_steps": 5,
|
|
@@ -8073,7 +8091,7 @@
|
|
| 8073 |
"attributes": {}
|
| 8074 |
}
|
| 8075 |
},
|
| 8076 |
-
"total_flos": 8.
|
| 8077 |
"train_batch_size": 4,
|
| 8078 |
"trial_name": null,
|
| 8079 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8054 |
"mean_token_accuracy": 0.6550962030887604,
|
| 8055 |
"num_tokens": 16301795.0,
|
| 8056 |
"step": 4470
|
| 8057 |
+
},
|
| 8058 |
+
{
|
| 8059 |
+
"epoch": 34.42307692307692,
|
| 8060 |
+
"grad_norm": 0.0,
|
| 8061 |
+
"learning_rate": 2.763e-05,
|
| 8062 |
+
"loss": 1.7215,
|
| 8063 |
+
"mean_token_accuracy": 0.6581933110952377,
|
| 8064 |
+
"num_tokens": 16320399.0,
|
| 8065 |
+
"step": 4475
|
| 8066 |
+
},
|
| 8067 |
+
{
|
| 8068 |
+
"epoch": 34.46153846153846,
|
| 8069 |
+
"grad_norm": 0.0,
|
| 8070 |
+
"learning_rate": 2.7605000000000004e-05,
|
| 8071 |
+
"loss": 1.7164,
|
| 8072 |
+
"mean_token_accuracy": 0.6563991248607636,
|
| 8073 |
+
"num_tokens": 16338805.0,
|
| 8074 |
+
"step": 4480
|
| 8075 |
}
|
| 8076 |
],
|
| 8077 |
"logging_steps": 5,
|
|
|
|
| 8091 |
"attributes": {}
|
| 8092 |
}
|
| 8093 |
},
|
| 8094 |
+
"total_flos": 8.280280079297741e+17,
|
| 8095 |
"train_batch_size": 4,
|
| 8096 |
"trial_name": null,
|
| 8097 |
"trial_params": null
|