Model save

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: results_model8
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results_model8
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9686
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 30
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.3262        | 0.5570 | 10000 | 3.3012          |
+| 3.0829        | 1.1141 | 20000 | 3.1175          |
+| 2.9737        | 1.6711 | 30000 | 3.0091          |
+| 2.8584        | 2.2282 | 40000 | 2.9686          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

best/config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "TransformerNet"
+  ],
+  "d_model": 512,
+  "dim_feedforward": 1024,
+  "dropout": 0.1,
+  "input_dim": 30000,
+  "max_seq_len": 1024,
+  "model_type": "transformer",
+  "nhead": 8,
+  "num_decoder_layers": 6,
+  "num_encoder_layers": 6,
+  "output_dim": 30000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660672277faf05f23ac3149638ae4098efb87549862da00df4ac1e2e010c9b8f
+size 253386808

best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d1f0b56e7ee9a45cd041c731c8ea2ff9d2fb818348ccc86eb90faf2bc51b6f
+size 5112