Training in progress, step 9960, 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 sha256:9abb2da57c0370b1f14aa563b68ddec35263d994da8cae1e7932066cff64c462
|
| 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 sha256:2c2dc023be3ca362601ab3f8e11e9042b1276b01b6df27ff4330c647c55b2394
|
| 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 sha256:4d1028be78b68d90fd2885810eacd8831cc358fd14f37f26d78823fdf07cb424
|
| 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": 76.
|
| 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,
|
|
@@ -17918,6 +17918,24 @@
|
|
| 17918 |
"mean_token_accuracy": 0.6507739454507828,
|
| 17919 |
"num_tokens": 36286936.0,
|
| 17920 |
"step": 9950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17921 |
}
|
| 17922 |
],
|
| 17923 |
"logging_steps": 5,
|
|
@@ -17937,7 +17955,7 @@
|
|
| 17937 |
"attributes": {}
|
| 17938 |
}
|
| 17939 |
},
|
| 17940 |
-
"total_flos": 1.
|
| 17941 |
"train_batch_size": 4,
|
| 17942 |
"trial_name": null,
|
| 17943 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 76.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17918 |
"mean_token_accuracy": 0.6507739454507828,
|
| 17919 |
"num_tokens": 36286936.0,
|
| 17920 |
"step": 9950
|
| 17921 |
+
},
|
| 17922 |
+
{
|
| 17923 |
+
"epoch": 76.57692307692308,
|
| 17924 |
+
"grad_norm": 0.0,
|
| 17925 |
+
"learning_rate": 2.3e-07,
|
| 17926 |
+
"loss": 1.6551,
|
| 17927 |
+
"mean_token_accuracy": 0.6698577493429184,
|
| 17928 |
+
"num_tokens": 36305937.0,
|
| 17929 |
+
"step": 9955
|
| 17930 |
+
},
|
| 17931 |
+
{
|
| 17932 |
+
"epoch": 76.61538461538461,
|
| 17933 |
+
"grad_norm": 0.0,
|
| 17934 |
+
"learning_rate": 2.0500000000000002e-07,
|
| 17935 |
+
"loss": 1.7305,
|
| 17936 |
+
"mean_token_accuracy": 0.6495934307575226,
|
| 17937 |
+
"num_tokens": 36324168.0,
|
| 17938 |
+
"step": 9960
|
| 17939 |
}
|
| 17940 |
],
|
| 17941 |
"logging_steps": 5,
|
|
|
|
| 17955 |
"attributes": {}
|
| 17956 |
}
|
| 17957 |
},
|
| 17958 |
+
"total_flos": 1.8420394283414323e+18,
|
| 17959 |
"train_batch_size": 4,
|
| 17960 |
"trial_name": null,
|
| 17961 |
"trial_params": null
|