Training in progress, epoch 8, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 283195372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dffdaa18d490862a5baa34f1aa1bc200d0d828239d6937759dba871204f96647
|
| 3 |
size 283195372
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 566510586
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4058832662a554684058259749c60029406d0e939fd4f2354ba6001345e6670b
|
| 3 |
size 566510586
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0403b973607a11ec8e102f5d54893b1b4bd95322e3f79eb6b0f5e4a601f67d63
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97cf51aabce7093c5fba6ba591e23e2496121cbddbeffe19a8366acfe3aafef1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.34553440702781846,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-24",
|
| 4 |
-
"epoch": 8.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -79,6 +79,15 @@
|
|
| 79 |
"eval_samples_per_second": 139.235,
|
| 80 |
"eval_steps_per_second": 8.766,
|
| 81 |
"step": 199
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 500,
|
|
@@ -98,7 +107,7 @@
|
|
| 98 |
"attributes": {}
|
| 99 |
}
|
| 100 |
},
|
| 101 |
-
"total_flos":
|
| 102 |
"train_batch_size": 16,
|
| 103 |
"trial_name": null,
|
| 104 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.34553440702781846,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-24",
|
| 4 |
+
"epoch": 8.964824120603016,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 223,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 79 |
"eval_samples_per_second": 139.235,
|
| 80 |
"eval_steps_per_second": 8.766,
|
| 81 |
"step": 199
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 8.964824120603016,
|
| 85 |
+
"eval_accuracy": 0.4128843338213763,
|
| 86 |
+
"eval_loss": 1.072035551071167,
|
| 87 |
+
"eval_runtime": 9.4031,
|
| 88 |
+
"eval_samples_per_second": 145.27,
|
| 89 |
+
"eval_steps_per_second": 9.146,
|
| 90 |
+
"step": 223
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"logging_steps": 500,
|
|
|
|
| 107 |
"attributes": {}
|
| 108 |
}
|
| 109 |
},
|
| 110 |
+
"total_flos": 1880376428888640.0,
|
| 111 |
"train_batch_size": 16,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|