Training in progress, step 1840, 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:a1e46e1875e09c0f8711e501642d0cb2bc21143f46b68405e5799e5be646a253
|
| 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:ef94e4b78ddf6bf9d27ea08c6add9da82470736e0d02865d89af93c7bf2b63ac
|
| 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 sha256:7ce1dd15d720d5ca48b2b9582f767b4bf005ba4fcca32cc35205c9c52bfb779c
|
| 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": 14.
|
| 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,
|
|
@@ -3302,6 +3302,24 @@
|
|
| 3302 |
"mean_token_accuracy": 0.6526720136404037,
|
| 3303 |
"num_tokens": 6675746.0,
|
| 3304 |
"step": 1830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3305 |
}
|
| 3306 |
],
|
| 3307 |
"logging_steps": 5,
|
|
@@ -3321,7 +3339,7 @@
|
|
| 3321 |
"attributes": {}
|
| 3322 |
}
|
| 3323 |
},
|
| 3324 |
-
"total_flos": 3.
|
| 3325 |
"train_batch_size": 4,
|
| 3326 |
"trial_name": null,
|
| 3327 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3302 |
"mean_token_accuracy": 0.6526720136404037,
|
| 3303 |
"num_tokens": 6675746.0,
|
| 3304 |
"step": 1830
|
| 3305 |
+
},
|
| 3306 |
+
{
|
| 3307 |
+
"epoch": 14.115384615384615,
|
| 3308 |
+
"grad_norm": 0.0,
|
| 3309 |
+
"learning_rate": 4.083e-05,
|
| 3310 |
+
"loss": 1.6588,
|
| 3311 |
+
"mean_token_accuracy": 0.663616544008255,
|
| 3312 |
+
"num_tokens": 6695210.0,
|
| 3313 |
+
"step": 1835
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 14.153846153846153,
|
| 3317 |
+
"grad_norm": 0.0,
|
| 3318 |
+
"learning_rate": 4.0805000000000007e-05,
|
| 3319 |
+
"loss": 1.7722,
|
| 3320 |
+
"mean_token_accuracy": 0.6440047711133957,
|
| 3321 |
+
"num_tokens": 6713034.0,
|
| 3322 |
+
"step": 1840
|
| 3323 |
}
|
| 3324 |
],
|
| 3325 |
"logging_steps": 5,
|
|
|
|
| 3339 |
"attributes": {}
|
| 3340 |
}
|
| 3341 |
},
|
| 3342 |
+
"total_flos": 3.400898472271872e+17,
|
| 3343 |
"train_batch_size": 4,
|
| 3344 |
"trial_name": null,
|
| 3345 |
"trial_params": null
|