Training in progress, step 6700, 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 sha256:8be1a27415d625b99fddad373e06a4a5905f9e91fab01b79508d2ded3ff512af
|
| 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:b1392a9caf93162555d83ea2ad01bdcde3c0de8bee5c647b2d190afb8ff493e3
|
| 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:d2dae866eaa8105257bbbb5e6ec54c0d1c5415220a665f863a7d6341dab04b00
|
| 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": 51.
|
| 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,
|
|
@@ -12050,6 +12050,24 @@
|
|
| 12050 |
"mean_token_accuracy": 0.650789025425911,
|
| 12051 |
"num_tokens": 24398752.0,
|
| 12052 |
"step": 6690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12053 |
}
|
| 12054 |
],
|
| 12055 |
"logging_steps": 5,
|
|
@@ -12069,7 +12087,7 @@
|
|
| 12069 |
"attributes": {}
|
| 12070 |
}
|
| 12071 |
},
|
| 12072 |
-
"total_flos": 1.
|
| 12073 |
"train_batch_size": 4,
|
| 12074 |
"trial_name": null,
|
| 12075 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12050 |
"mean_token_accuracy": 0.650789025425911,
|
| 12051 |
"num_tokens": 24398752.0,
|
| 12052 |
"step": 6690
|
| 12053 |
+
},
|
| 12054 |
+
{
|
| 12055 |
+
"epoch": 51.5,
|
| 12056 |
+
"grad_norm": 0.0,
|
| 12057 |
+
"learning_rate": 1.6530000000000003e-05,
|
| 12058 |
+
"loss": 1.8203,
|
| 12059 |
+
"mean_token_accuracy": 0.6345427900552749,
|
| 12060 |
+
"num_tokens": 24416377.0,
|
| 12061 |
+
"step": 6695
|
| 12062 |
+
},
|
| 12063 |
+
{
|
| 12064 |
+
"epoch": 51.53846153846154,
|
| 12065 |
+
"grad_norm": 0.0,
|
| 12066 |
+
"learning_rate": 1.6505000000000002e-05,
|
| 12067 |
+
"loss": 1.7334,
|
| 12068 |
+
"mean_token_accuracy": 0.6506275236606598,
|
| 12069 |
+
"num_tokens": 24435235.0,
|
| 12070 |
+
"step": 6700
|
| 12071 |
}
|
| 12072 |
],
|
| 12073 |
"logging_steps": 5,
|
|
|
|
| 12087 |
"attributes": {}
|
| 12088 |
}
|
| 12089 |
},
|
| 12090 |
+
"total_flos": 1.238742025508782e+18,
|
| 12091 |
"train_batch_size": 4,
|
| 12092 |
"trial_name": null,
|
| 12093 |
"trial_params": null
|