Training in progress, step 9400, 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:a0c10d922f84ae67fbe2ccfed292ee2a8783c656d35dd64e5a9035e4e02c0042
|
| 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 sha256:05350a0372af1d83d438d41c6f0c2e58118b92c21379237e5e76de2bdfb9aca7
|
| 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:f431966b9f11ea9654e78887555eac597d536ae7d5ef05c40bfa10de2905adb8
|
| 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": 72.
|
| 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,
|
|
@@ -16910,6 +16910,24 @@
|
|
| 16910 |
"mean_token_accuracy": 0.6630650132894516,
|
| 16911 |
"num_tokens": 34246818.0,
|
| 16912 |
"step": 9390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16913 |
}
|
| 16914 |
],
|
| 16915 |
"logging_steps": 5,
|
|
@@ -16929,7 +16947,7 @@
|
|
| 16929 |
"attributes": {}
|
| 16930 |
}
|
| 16931 |
},
|
| 16932 |
-
"total_flos": 1.
|
| 16933 |
"train_batch_size": 4,
|
| 16934 |
"trial_name": null,
|
| 16935 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16910 |
"mean_token_accuracy": 0.6630650132894516,
|
| 16911 |
"num_tokens": 34246818.0,
|
| 16912 |
"step": 9390
|
| 16913 |
+
},
|
| 16914 |
+
{
|
| 16915 |
+
"epoch": 72.26923076923077,
|
| 16916 |
+
"grad_norm": 0.0,
|
| 16917 |
+
"learning_rate": 3.0300000000000002e-06,
|
| 16918 |
+
"loss": 1.75,
|
| 16919 |
+
"mean_token_accuracy": 0.6472353667020798,
|
| 16920 |
+
"num_tokens": 34264967.0,
|
| 16921 |
+
"step": 9395
|
| 16922 |
+
},
|
| 16923 |
+
{
|
| 16924 |
+
"epoch": 72.3076923076923,
|
| 16925 |
+
"grad_norm": 0.0,
|
| 16926 |
+
"learning_rate": 3.005e-06,
|
| 16927 |
+
"loss": 1.7359,
|
| 16928 |
+
"mean_token_accuracy": 0.6492182224988937,
|
| 16929 |
+
"num_tokens": 34283311.0,
|
| 16930 |
+
"step": 9400
|
| 16931 |
}
|
| 16932 |
],
|
| 16933 |
"logging_steps": 5,
|
|
|
|
| 16947 |
"attributes": {}
|
| 16948 |
}
|
| 16949 |
},
|
| 16950 |
+
"total_flos": 1.7385082799313715e+18,
|
| 16951 |
"train_batch_size": 4,
|
| 16952 |
"trial_name": null,
|
| 16953 |
"trial_params": null
|