Training in progress, step 5050, 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 sha256:11a5da7b51d6c1a3399ea8a630e8d571c78a9a6ff7244f5797f3dd5a7afea1cb
|
| 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:b3defa0731d94e64e591d9fc55c5f6a75b0790404736bf58abf09cff4dc2535e
|
| 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:d91ca35ab588d20a162ca7faeedfb520a1cc4347fe51524efe4a7cf6ad212473
|
| 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,
|
|
@@ -9080,6 +9080,24 @@
|
|
| 9080 |
"mean_token_accuracy": 0.654488143324852,
|
| 9081 |
"num_tokens": 18381290.0,
|
| 9082 |
"step": 5040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9083 |
}
|
| 9084 |
],
|
| 9085 |
"logging_steps": 5,
|
|
@@ -9099,7 +9117,7 @@
|
|
| 9099 |
"attributes": {}
|
| 9100 |
}
|
| 9101 |
},
|
| 9102 |
-
"total_flos": 9.
|
| 9103 |
"train_batch_size": 4,
|
| 9104 |
"trial_name": null,
|
| 9105 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9080 |
"mean_token_accuracy": 0.654488143324852,
|
| 9081 |
"num_tokens": 18381290.0,
|
| 9082 |
"step": 5040
|
| 9083 |
+
},
|
| 9084 |
+
{
|
| 9085 |
+
"epoch": 38.80769230769231,
|
| 9086 |
+
"grad_norm": 0.0,
|
| 9087 |
+
"learning_rate": 2.478e-05,
|
| 9088 |
+
"loss": 1.7901,
|
| 9089 |
+
"mean_token_accuracy": 0.6406182050704956,
|
| 9090 |
+
"num_tokens": 18398780.0,
|
| 9091 |
+
"step": 5045
|
| 9092 |
+
},
|
| 9093 |
+
{
|
| 9094 |
+
"epoch": 38.84615384615385,
|
| 9095 |
+
"grad_norm": 0.0,
|
| 9096 |
+
"learning_rate": 2.4755e-05,
|
| 9097 |
+
"loss": 1.7715,
|
| 9098 |
+
"mean_token_accuracy": 0.6461145460605622,
|
| 9099 |
+
"num_tokens": 18416605.0,
|
| 9100 |
+
"step": 5050
|
| 9101 |
}
|
| 9102 |
],
|
| 9103 |
"logging_steps": 5,
|
|
|
|
| 9117 |
"attributes": {}
|
| 9118 |
}
|
| 9119 |
},
|
| 9120 |
+
"total_flos": 9.331502821643059e+17,
|
| 9121 |
"train_batch_size": 4,
|
| 9122 |
"trial_name": null,
|
| 9123 |
"trial_params": null
|