Training in progress, epoch 5, 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 2239622772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e2337c930e5288017078419835a4c9b9706ad66b3b34977cc787152fe1ded7b
|
| 3 |
size 2239622772
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4479480977
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f50495d912cdaddfcb82e677cc6e0d987ec2e02e77be13b3bcd2c8cba06979e
|
| 3 |
size 4479480977
|
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:eef7d497557c6acde0df57c8664dd739dd3dccf6a195816d7c89ef72a0524e04
|
| 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 sha256:7f900f8e7ee0be53449615890cf1fad12ae456f7e5275907b8f6bf1d6c1480ab
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7774524158125915,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
|
| 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,
|
|
@@ -50,6 +50,15 @@
|
|
| 50 |
"eval_samples_per_second": 11.044,
|
| 51 |
"eval_steps_per_second": 5.522,
|
| 52 |
"step": 796
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
}
|
| 54 |
],
|
| 55 |
"logging_steps": 500,
|
|
@@ -69,7 +78,7 @@
|
|
| 69 |
"attributes": {}
|
| 70 |
}
|
| 71 |
},
|
| 72 |
-
"total_flos": 1.
|
| 73 |
"train_batch_size": 2,
|
| 74 |
"trial_name": null,
|
| 75 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7774524158125915,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 995,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 50 |
"eval_samples_per_second": 11.044,
|
| 51 |
"eval_steps_per_second": 5.522,
|
| 52 |
"step": 796
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 5.0,
|
| 56 |
+
"eval_accuracy": 0.7693997071742313,
|
| 57 |
+
"eval_loss": 0.8647988438606262,
|
| 58 |
+
"eval_runtime": 112.0996,
|
| 59 |
+
"eval_samples_per_second": 12.186,
|
| 60 |
+
"eval_steps_per_second": 6.093,
|
| 61 |
+
"step": 995
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"logging_steps": 500,
|
|
|
|
| 78 |
"attributes": {}
|
| 79 |
}
|
| 80 |
},
|
| 81 |
+
"total_flos": 1.47784427556048e+16,
|
| 82 |
"train_batch_size": 2,
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|