Training in progress, step 4050, 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:e953bdab74253bcd106499c0f2d3bc5a2c8aea34baef0396d3aa7604140a3b14
|
| 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 sha256:297bf9fae5340c684a76e1edf8fdc9d2c9f4bfb331d79f9d5a770dedcd07768e
|
| 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 sha256:4c944418db22586f9938916650cd627cd2e6fb1b31b6335d4f7306a31b5cb54b
|
| 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": 31.
|
| 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,
|
|
@@ -7280,6 +7280,24 @@
|
|
| 7280 |
"mean_token_accuracy": 0.6654754310846329,
|
| 7281 |
"num_tokens": 14734385.0,
|
| 7282 |
"step": 4040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7283 |
}
|
| 7284 |
],
|
| 7285 |
"logging_steps": 5,
|
|
@@ -7299,7 +7317,7 @@
|
|
| 7299 |
"attributes": {}
|
| 7300 |
}
|
| 7301 |
},
|
| 7302 |
-
"total_flos": 7.
|
| 7303 |
"train_batch_size": 4,
|
| 7304 |
"trial_name": null,
|
| 7305 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4050,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7280 |
"mean_token_accuracy": 0.6654754310846329,
|
| 7281 |
"num_tokens": 14734385.0,
|
| 7282 |
"step": 4040
|
| 7283 |
+
},
|
| 7284 |
+
{
|
| 7285 |
+
"epoch": 31.115384615384617,
|
| 7286 |
+
"grad_norm": 0.0,
|
| 7287 |
+
"learning_rate": 2.9780000000000003e-05,
|
| 7288 |
+
"loss": 1.7331,
|
| 7289 |
+
"mean_token_accuracy": 0.6555071473121643,
|
| 7290 |
+
"num_tokens": 14752659.0,
|
| 7291 |
+
"step": 4045
|
| 7292 |
+
},
|
| 7293 |
+
{
|
| 7294 |
+
"epoch": 31.153846153846153,
|
| 7295 |
+
"grad_norm": 0.0,
|
| 7296 |
+
"learning_rate": 2.9755e-05,
|
| 7297 |
+
"loss": 1.7449,
|
| 7298 |
+
"mean_token_accuracy": 0.6513841986656189,
|
| 7299 |
+
"num_tokens": 14770947.0,
|
| 7300 |
+
"step": 4050
|
| 7301 |
}
|
| 7302 |
],
|
| 7303 |
"logging_steps": 5,
|
|
|
|
| 7317 |
"attributes": {}
|
| 7318 |
}
|
| 7319 |
},
|
| 7320 |
+
"total_flos": 7.485372924936192e+17,
|
| 7321 |
"train_batch_size": 4,
|
| 7322 |
"trial_name": null,
|
| 7323 |
"trial_params": null
|