Training in progress, step 5040, 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 sha256:0fcc819f48f1d6754522a1682bb875759e81aab67c41e40f8fffe12f8074f482
|
| 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 sha256:57136672ce72da80c2bb7be44c036c1ddcbeb12f452061c556c9eb9162383ab2
|
| 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 sha256:2cae13b35c48c50f9e9f546cffc774f294ece4bf240645e151432e5febb28886
|
| 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": 38.
|
| 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,
|
|
@@ -9062,6 +9062,24 @@
|
|
| 9062 |
"mean_token_accuracy": 0.6517604231834412,
|
| 9063 |
"num_tokens": 18344113.0,
|
| 9064 |
"step": 5030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9065 |
}
|
| 9066 |
],
|
| 9067 |
"logging_steps": 5,
|
|
@@ -9081,7 +9099,7 @@
|
|
| 9081 |
"attributes": {}
|
| 9082 |
}
|
| 9083 |
},
|
| 9084 |
-
"total_flos": 9.
|
| 9085 |
"train_batch_size": 4,
|
| 9086 |
"trial_name": null,
|
| 9087 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9062 |
"mean_token_accuracy": 0.6517604231834412,
|
| 9063 |
"num_tokens": 18344113.0,
|
| 9064 |
"step": 5030
|
| 9065 |
+
},
|
| 9066 |
+
{
|
| 9067 |
+
"epoch": 38.73076923076923,
|
| 9068 |
+
"grad_norm": 0.0,
|
| 9069 |
+
"learning_rate": 2.483e-05,
|
| 9070 |
+
"loss": 1.6998,
|
| 9071 |
+
"mean_token_accuracy": 0.6589053481817245,
|
| 9072 |
+
"num_tokens": 18362753.0,
|
| 9073 |
+
"step": 5035
|
| 9074 |
+
},
|
| 9075 |
+
{
|
| 9076 |
+
"epoch": 38.76923076923077,
|
| 9077 |
+
"grad_norm": 0.0,
|
| 9078 |
+
"learning_rate": 2.4805e-05,
|
| 9079 |
+
"loss": 1.7194,
|
| 9080 |
+
"mean_token_accuracy": 0.654488143324852,
|
| 9081 |
+
"num_tokens": 18381290.0,
|
| 9082 |
+
"step": 5040
|
| 9083 |
}
|
| 9084 |
],
|
| 9085 |
"logging_steps": 5,
|
|
|
|
| 9099 |
"attributes": {}
|
| 9100 |
}
|
| 9101 |
},
|
| 9102 |
+
"total_flos": 9.314027588807885e+17,
|
| 9103 |
"train_batch_size": 4,
|
| 9104 |
"trial_name": null,
|
| 9105 |
"trial_params": null
|