Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
text-embeddings-inference
Instructions to use avsolatorio/doc-topic-model_eval-02_train-04 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use avsolatorio/doc-topic-model_eval-02_train-04 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="avsolatorio/doc-topic-model_eval-02_train-04")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("avsolatorio/doc-topic-model_eval-02_train-04") model = AutoModelForSequenceClassification.from_pretrained("avsolatorio/doc-topic-model_eval-02_train-04", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 17000, 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 567860028
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feafb2107affe6fdf4c45264861a1909ef3735a26a9c5ada27dbc7dc8ba845d9
|
| 3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1135783354
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ccbbfeea057fc532f3d46d99f6f4f20db7279e6a5eb62846aee8e261f1d659b
|
| 3 |
size 1135783354
|
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:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
|
| 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 sha256:6da7d5a2ae8f209d8c7dd162056a124c933df3dbc8839879a1816c27a0c4446e
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.03750571236014366,
|
| 3 |
"best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-13000",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -423,6 +423,32 @@
|
|
| 423 |
"eval_samples_per_second": 571.194,
|
| 424 |
"eval_steps_per_second": 2.254,
|
| 425 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 426 |
}
|
| 427 |
],
|
| 428 |
"logging_steps": 500,
|
|
@@ -451,7 +477,7 @@
|
|
| 451 |
"attributes": {}
|
| 452 |
}
|
| 453 |
},
|
| 454 |
-
"total_flos":
|
| 455 |
"train_batch_size": 4,
|
| 456 |
"trial_name": null,
|
| 457 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.03750571236014366,
|
| 3 |
"best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-13000",
|
| 4 |
+
"epoch": 8.378511582060128,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 17000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 423 |
"eval_samples_per_second": 571.194,
|
| 424 |
"eval_steps_per_second": 2.254,
|
| 425 |
"step": 16000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 8.132084770823065,
|
| 429 |
+
"grad_norm": 0.48524007201194763,
|
| 430 |
+
"learning_rate": 1.8373878758008873e-05,
|
| 431 |
+
"loss": 0.0217,
|
| 432 |
+
"step": 16500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 8.378511582060128,
|
| 436 |
+
"grad_norm": 0.3671877384185791,
|
| 437 |
+
"learning_rate": 1.8324593395761462e-05,
|
| 438 |
+
"loss": 0.0208,
|
| 439 |
+
"step": 17000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 8.378511582060128,
|
| 443 |
+
"eval_accuracy": 0.9877219836444293,
|
| 444 |
+
"eval_f1": 0.6341484015372271,
|
| 445 |
+
"eval_loss": 0.037882279604673386,
|
| 446 |
+
"eval_precision": 0.7129427404804862,
|
| 447 |
+
"eval_recall": 0.5710374201399452,
|
| 448 |
+
"eval_runtime": 14.1368,
|
| 449 |
+
"eval_samples_per_second": 573.681,
|
| 450 |
+
"eval_steps_per_second": 2.264,
|
| 451 |
+
"step": 17000
|
| 452 |
}
|
| 453 |
],
|
| 454 |
"logging_steps": 500,
|
|
|
|
| 477 |
"attributes": {}
|
| 478 |
}
|
| 479 |
},
|
| 480 |
+
"total_flos": 385542059579694.0,
|
| 481 |
"train_batch_size": 4,
|
| 482 |
"trial_name": null,
|
| 483 |
"trial_params": null
|