Training in progress, epoch 7, 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 669458436
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53fda658b8a32fb0f72b7d1a523991f0fc8fdbcb198ceeef683c7396e3b81bba
|
| 3 |
size 669458436
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1339037946
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715e7b8fc35521cd994f22c00e4547ff637e4e53893ae30267fc2833e21bc435
|
| 3 |
size 1339037946
|
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:cfe701a24e29fba2f6b4e441c550568c67f9395cca7bed012512b5a39db2e59f
|
| 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:d3b26beaada53dc7406693046bc1ae99fadf1d058e1ad68b87ff1014eb39062c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-
|
| 4 |
-
"epoch":
|
| 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,
|
|
@@ -70,6 +70,15 @@
|
|
| 70 |
"eval_samples_per_second": 103.932,
|
| 71 |
"eval_steps_per_second": 3.272,
|
| 72 |
"step": 87
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
}
|
| 74 |
],
|
| 75 |
"logging_steps": 500,
|
|
@@ -89,7 +98,7 @@
|
|
| 89 |
"attributes": {}
|
| 90 |
}
|
| 91 |
},
|
| 92 |
-
"total_flos":
|
| 93 |
"train_batch_size": 32,
|
| 94 |
"trial_name": null,
|
| 95 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6251830161054173,
|
| 3 |
+
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-99",
|
| 4 |
+
"epoch": 7.959798994974874,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 99,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 70 |
"eval_samples_per_second": 103.932,
|
| 71 |
"eval_steps_per_second": 3.272,
|
| 72 |
"step": 87
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.959798994974874,
|
| 76 |
+
"eval_accuracy": 0.6251830161054173,
|
| 77 |
+
"eval_loss": 0.8302316665649414,
|
| 78 |
+
"eval_runtime": 12.8468,
|
| 79 |
+
"eval_samples_per_second": 106.33,
|
| 80 |
+
"eval_steps_per_second": 3.347,
|
| 81 |
+
"step": 99
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 500,
|
|
|
|
| 98 |
"attributes": {}
|
| 99 |
}
|
| 100 |
},
|
| 101 |
+
"total_flos": 6675845191303680.0,
|
| 102 |
"train_batch_size": 32,
|
| 103 |
"trial_name": null,
|
| 104 |
"trial_params": null
|