Training in progress, step 5140, 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:e19a2d1f57bf14a74ce11267129338832b44b41995cd2ca44a79d54f6fa3cd6d
|
| 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 sha256:0fbaa7f37f85ca8601fc7d51886701713ee2101692a6ebf3672d41a310e32d13
|
| 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:d860db4800eb1f2d7bd170996c6a27ce72d84301b80d56d30dc6f37051bd190e
|
| 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": 39.
|
| 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,
|
|
@@ -9242,6 +9242,24 @@
|
|
| 9242 |
"mean_token_accuracy": 0.6461830377578736,
|
| 9243 |
"num_tokens": 18710735.0,
|
| 9244 |
"step": 5130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9245 |
}
|
| 9246 |
],
|
| 9247 |
"logging_steps": 5,
|
|
@@ -9261,7 +9279,7 @@
|
|
| 9261 |
"attributes": {}
|
| 9262 |
}
|
| 9263 |
},
|
| 9264 |
-
"total_flos": 9.
|
| 9265 |
"train_batch_size": 4,
|
| 9266 |
"trial_name": null,
|
| 9267 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9242 |
"mean_token_accuracy": 0.6461830377578736,
|
| 9243 |
"num_tokens": 18710735.0,
|
| 9244 |
"step": 5130
|
| 9245 |
+
},
|
| 9246 |
+
{
|
| 9247 |
+
"epoch": 39.5,
|
| 9248 |
+
"grad_norm": 0.0,
|
| 9249 |
+
"learning_rate": 2.433e-05,
|
| 9250 |
+
"loss": 1.7019,
|
| 9251 |
+
"mean_token_accuracy": 0.657170632481575,
|
| 9252 |
+
"num_tokens": 18729163.0,
|
| 9253 |
+
"step": 5135
|
| 9254 |
+
},
|
| 9255 |
+
{
|
| 9256 |
+
"epoch": 39.53846153846154,
|
| 9257 |
+
"grad_norm": 0.0,
|
| 9258 |
+
"learning_rate": 2.4305e-05,
|
| 9259 |
+
"loss": 1.7227,
|
| 9260 |
+
"mean_token_accuracy": 0.6536213010549545,
|
| 9261 |
+
"num_tokens": 18747486.0,
|
| 9262 |
+
"step": 5140
|
| 9263 |
}
|
| 9264 |
],
|
| 9265 |
"logging_steps": 5,
|
|
|
|
| 9279 |
"attributes": {}
|
| 9280 |
}
|
| 9281 |
},
|
| 9282 |
+
"total_flos": 9.499602303767347e+17,
|
| 9283 |
"train_batch_size": 4,
|
| 9284 |
"trial_name": null,
|
| 9285 |
"trial_params": null
|