Training in progress, step 4660, 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:bd4ddc5590933a1c8e7eab966ebd03f46c26c123502541e8cd62c740300d7cae
|
| 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 sha256:37475c8156fe6fd288c2bb807f45656ee116b06e90b44639498cdb5d24437b38
|
| 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 sha256:485ce248617331b19f9bff67b8d29a55ca3e5472a024775ea226703b99b2952c
|
| 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": 35.
|
| 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,
|
|
@@ -8378,6 +8378,24 @@
|
|
| 8378 |
"mean_token_accuracy": 0.653421950340271,
|
| 8379 |
"num_tokens": 16958067.0,
|
| 8380 |
"step": 4650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8381 |
}
|
| 8382 |
],
|
| 8383 |
"logging_steps": 5,
|
|
@@ -8397,7 +8415,7 @@
|
|
| 8397 |
"attributes": {}
|
| 8398 |
}
|
| 8399 |
},
|
| 8400 |
-
"total_flos": 8.
|
| 8401 |
"train_batch_size": 4,
|
| 8402 |
"trial_name": null,
|
| 8403 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8378 |
"mean_token_accuracy": 0.653421950340271,
|
| 8379 |
"num_tokens": 16958067.0,
|
| 8380 |
"step": 4650
|
| 8381 |
+
},
|
| 8382 |
+
{
|
| 8383 |
+
"epoch": 35.80769230769231,
|
| 8384 |
+
"grad_norm": 0.0,
|
| 8385 |
+
"learning_rate": 2.673e-05,
|
| 8386 |
+
"loss": 1.7234,
|
| 8387 |
+
"mean_token_accuracy": 0.6553035944700241,
|
| 8388 |
+
"num_tokens": 16976533.0,
|
| 8389 |
+
"step": 4655
|
| 8390 |
+
},
|
| 8391 |
+
{
|
| 8392 |
+
"epoch": 35.84615384615385,
|
| 8393 |
+
"grad_norm": 0.0,
|
| 8394 |
+
"learning_rate": 2.6705000000000003e-05,
|
| 8395 |
+
"loss": 1.7566,
|
| 8396 |
+
"mean_token_accuracy": 0.6490527987480164,
|
| 8397 |
+
"num_tokens": 16994749.0,
|
| 8398 |
+
"step": 4660
|
| 8399 |
}
|
| 8400 |
],
|
| 8401 |
"logging_steps": 5,
|
|
|
|
| 8415 |
"attributes": {}
|
| 8416 |
}
|
| 8417 |
},
|
| 8418 |
+
"total_flos": 8.612792191770624e+17,
|
| 8419 |
"train_batch_size": 4,
|
| 8420 |
"trial_name": null,
|
| 8421 |
"trial_params": null
|