Model save

README.md

@@ -0,0 +1,59 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: results_scratch
+  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_scratch
+
+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: 2.4991
+
+## 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: 120
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 3.4563        | 5.5310  | 10000 | 3.3200          |
+| 2.7398        | 11.0619 | 20000 | 2.7421          |
+| 2.441         | 16.5929 | 30000 | 2.4991          |
+
+
+### 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": 30,
+  "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 sha256:3af3853781745c18b4e3af7b4ca4186118327b45e3a030f4567aaca520ceb809
+size 249315352

best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e385559fe1f6b91ddbe17b5fc24e5ddf29f1fbf91482403210c09ef6ff4ec38
+size 5112

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "TransformerNet"
+  ],
+  "d_model": 512,
+  "dim_feedforward": 1024,
+  "dropout": 0.1,
+  "input_dim": 30000,
+  "max_seq_len": 30,
+  "model_type": "transformer",
+  "nhead": 8,
+  "num_decoder_layers": 6,
+  "num_encoder_layers": 6,
+  "output_dim": 30000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af3853781745c18b4e3af7b4ca4186118327b45e3a030f4567aaca520ceb809
+size 249315352

results_scratch/best/config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "TransformerNet"
+  ],
+  "d_model": 512,
+  "dim_feedforward": 1024,
+  "dropout": 0.1,
+  "input_dim": 30000,
+  "max_seq_len": 30,
+  "model_type": "transformer",
+  "nhead": 8,
+  "num_decoder_layers": 6,
+  "num_encoder_layers": 6,
+  "output_dim": 30000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

results_scratch/best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf1c069b04cd7e92e2ddd3932d0a186745262be56298ec36247cab2b9e3bc80
+size 249315352

results_scratch/best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651030923a67daeafba93404f006f73ebcd9a1a6446146e326aef99307e383bc
+size 5112

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e385559fe1f6b91ddbe17b5fc24e5ddf29f1fbf91482403210c09ef6ff4ec38
+size 5112