Training in progress, step 1800, 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 sha256:0637a2f3b8b916b3a7273be86ef3aa72b85120a3f356a8cbebfbdb558008ad1e
|
| 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 sha256:9fac2b8b3b01b830606810f81be50bbaff1108c20363dc56f4e02a027ed085a9
|
| 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 sha256:2f7099b1bddab2a83a5971353a97c6e3e1ada93db7d64762e2ec568600e3e64c
|
| 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,
|
|
@@ -3230,6 +3230,24 @@
|
|
| 3230 |
"mean_token_accuracy": 0.6555010586977005,
|
| 3231 |
"num_tokens": 6526939.0,
|
| 3232 |
"step": 1790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3233 |
}
|
| 3234 |
],
|
| 3235 |
"logging_steps": 5,
|
|
@@ -3249,7 +3267,7 @@
|
|
| 3249 |
"attributes": {}
|
| 3250 |
}
|
| 3251 |
},
|
| 3252 |
-
"total_flos": 3.
|
| 3253 |
"train_batch_size": 4,
|
| 3254 |
"trial_name": null,
|
| 3255 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3230 |
"mean_token_accuracy": 0.6555010586977005,
|
| 3231 |
"num_tokens": 6526939.0,
|
| 3232 |
"step": 1790
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 13.807692307692308,
|
| 3236 |
+
"grad_norm": 0.0,
|
| 3237 |
+
"learning_rate": 4.103e-05,
|
| 3238 |
+
"loss": 1.7877,
|
| 3239 |
+
"mean_token_accuracy": 0.6444415628910065,
|
| 3240 |
+
"num_tokens": 6544917.0,
|
| 3241 |
+
"step": 1795
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 13.846153846153847,
|
| 3245 |
+
"grad_norm": 0.0,
|
| 3246 |
+
"learning_rate": 4.1005000000000005e-05,
|
| 3247 |
+
"loss": 1.6953,
|
| 3248 |
+
"mean_token_accuracy": 0.6559826284646988,
|
| 3249 |
+
"num_tokens": 6563694.0,
|
| 3250 |
+
"step": 1800
|
| 3251 |
}
|
| 3252 |
],
|
| 3253 |
"logging_steps": 5,
|
|
|
|
| 3267 |
"attributes": {}
|
| 3268 |
}
|
| 3269 |
},
|
| 3270 |
+
"total_flos": 3.3257101953613824e+17,
|
| 3271 |
"train_batch_size": 4,
|
| 3272 |
"trial_name": null,
|
| 3273 |
"trial_params": null
|