Training in progress, step 1790, 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 sha256:8459e4ecc7e54386679adcdc7fd8863d784c14dfcf9e01a148b4f78901473767
|
| 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 sha256:1dcb5a2643d42e73d186608ee559fe62af8cf8f53da9ed82f7c983f95ec81685
|
| 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 sha256:303a7a25aa255038831a3c9e04cfc47f9c8906ae69214a25ca36a984c2b8d071
|
| 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,
|
|
@@ -3212,6 +3212,24 @@
|
|
| 3212 |
"mean_token_accuracy": 0.6522348582744598,
|
| 3213 |
"num_tokens": 6489689.0,
|
| 3214 |
"step": 1780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3215 |
}
|
| 3216 |
],
|
| 3217 |
"logging_steps": 5,
|
|
@@ -3231,7 +3249,7 @@
|
|
| 3231 |
"attributes": {}
|
| 3232 |
}
|
| 3233 |
},
|
| 3234 |
-
"total_flos": 3.
|
| 3235 |
"train_batch_size": 4,
|
| 3236 |
"trial_name": null,
|
| 3237 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3212 |
"mean_token_accuracy": 0.6522348582744598,
|
| 3213 |
"num_tokens": 6489689.0,
|
| 3214 |
"step": 1780
|
| 3215 |
+
},
|
| 3216 |
+
{
|
| 3217 |
+
"epoch": 13.73076923076923,
|
| 3218 |
+
"grad_norm": 0.0,
|
| 3219 |
+
"learning_rate": 4.108e-05,
|
| 3220 |
+
"loss": 1.764,
|
| 3221 |
+
"mean_token_accuracy": 0.6411303877830505,
|
| 3222 |
+
"num_tokens": 6508258.0,
|
| 3223 |
+
"step": 1785
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 13.76923076923077,
|
| 3227 |
+
"grad_norm": 0.0,
|
| 3228 |
+
"learning_rate": 4.1055000000000006e-05,
|
| 3229 |
+
"loss": 1.733,
|
| 3230 |
+
"mean_token_accuracy": 0.6555010586977005,
|
| 3231 |
+
"num_tokens": 6526939.0,
|
| 3232 |
+
"step": 1790
|
| 3233 |
}
|
| 3234 |
],
|
| 3235 |
"logging_steps": 5,
|
|
|
|
| 3249 |
"attributes": {}
|
| 3250 |
}
|
| 3251 |
},
|
| 3252 |
+
"total_flos": 3.3066408198979584e+17,
|
| 3253 |
"train_batch_size": 4,
|
| 3254 |
"trial_name": null,
|
| 3255 |
"trial_params": null
|