Training in progress, step 1810, 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:f3ae9a6b4e510bb3a326c0f3888b319e8a9cec205ad99d4a7599166e8d073bba
|
| 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:a8b4d8eb2dc83872f89d2aa869a206306354167bafbf65d2b7e91fe5db676003
|
| 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 sha256:3a00e50c4d74a2c3de6a5b778e7cae0929b3e86a008e0548c2f25a0833a590b2
|
| 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": 13.
|
| 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,
|
|
@@ -3248,6 +3248,24 @@
|
|
| 3248 |
"mean_token_accuracy": 0.6559826284646988,
|
| 3249 |
"num_tokens": 6563694.0,
|
| 3250 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3251 |
}
|
| 3252 |
],
|
| 3253 |
"logging_steps": 5,
|
|
@@ -3267,7 +3285,7 @@
|
|
| 3267 |
"attributes": {}
|
| 3268 |
}
|
| 3269 |
},
|
| 3270 |
-
"total_flos": 3.
|
| 3271 |
"train_batch_size": 4,
|
| 3272 |
"trial_name": null,
|
| 3273 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3248 |
"mean_token_accuracy": 0.6559826284646988,
|
| 3249 |
"num_tokens": 6563694.0,
|
| 3250 |
"step": 1800
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 13.884615384615385,
|
| 3254 |
+
"grad_norm": 0.0,
|
| 3255 |
+
"learning_rate": 4.0980000000000004e-05,
|
| 3256 |
+
"loss": 1.7663,
|
| 3257 |
+
"mean_token_accuracy": 0.6459847629070282,
|
| 3258 |
+
"num_tokens": 6581448.0,
|
| 3259 |
+
"step": 1805
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 13.923076923076923,
|
| 3263 |
+
"grad_norm": 0.0,
|
| 3264 |
+
"learning_rate": 4.0955000000000003e-05,
|
| 3265 |
+
"loss": 1.7447,
|
| 3266 |
+
"mean_token_accuracy": 0.6494243443012238,
|
| 3267 |
+
"num_tokens": 6600126.0,
|
| 3268 |
+
"step": 1810
|
| 3269 |
}
|
| 3270 |
],
|
| 3271 |
"logging_steps": 5,
|
|
|
|
| 3285 |
"attributes": {}
|
| 3286 |
}
|
| 3287 |
},
|
| 3288 |
+
"total_flos": 3.343502986489037e+17,
|
| 3289 |
"train_batch_size": 4,
|
| 3290 |
"trial_name": null,
|
| 3291 |
"trial_params": null
|