ninagroot/Llama-360Mtest

README.md

@@ -0,0 +1,98 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama-360M
+  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. -->
+
+# Llama-360M
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.6562
+
+## 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: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 40
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 8.3864        | 0.98  | 7    | 8.4700          |
+| 7.2228        | 1.96  | 14   | 7.6525          |
+| 6.2754        | 2.95  | 21   | 6.9672          |
+| 5.444         | 3.93  | 28   | 6.3528          |
+| 4.6376        | 4.91  | 35   | 5.8872          |
+| 3.7271        | 5.89  | 42   | 5.4730          |
+| 3.211         | 6.88  | 49   | 5.2839          |
+| 2.563         | 8.0   | 57   | 5.1826          |
+| 1.9961        | 8.98  | 64   | 5.1621          |
+| 1.4468        | 9.96  | 71   | 5.2455          |
+| 1.0269        | 10.95 | 78   | 5.3081          |
+| 0.7106        | 11.93 | 85   | 5.2484          |
+| 0.4967        | 12.91 | 92   | 5.3469          |
+| 0.3478        | 13.89 | 99   | 5.3402          |
+| 0.2494        | 14.88 | 106  | 5.4144          |
+| 0.1696        | 16.0  | 114  | 5.4190          |
+| 0.1245        | 16.98 | 121  | 5.4780          |
+| 0.0799        | 17.96 | 128  | 5.5194          |
+| 0.0618        | 18.95 | 135  | 5.5302          |
+| 0.0375        | 19.93 | 142  | 5.5205          |
+| 0.032         | 20.91 | 149  | 5.5534          |
+| 0.0275        | 21.89 | 156  | 5.5555          |
+| 0.0218        | 22.88 | 163  | 5.6052          |
+| 0.0196        | 24.0  | 171  | 5.6138          |
+| 0.0203        | 24.98 | 178  | 5.6179          |
+| 0.018         | 25.96 | 185  | 5.6200          |
+| 0.0189        | 26.95 | 192  | 5.6299          |
+| 0.0181        | 27.93 | 199  | 5.6347          |
+| 0.016         | 28.91 | 206  | 5.6402          |
+| 0.018         | 29.89 | 213  | 5.6432          |
+| 0.016         | 30.88 | 220  | 5.6474          |
+| 0.0166        | 32.0  | 228  | 5.6500          |
+| 0.0169        | 32.98 | 235  | 5.6515          |
+| 0.0166        | 33.96 | 242  | 5.6531          |
+| 0.0159        | 34.95 | 249  | 5.6547          |
+| 0.0164        | 35.93 | 256  | 5.6556          |
+| 0.0159        | 36.91 | 263  | 5.6561          |
+| 0.0144        | 37.89 | 270  | 5.6562          |
+| 0.0142        | 38.88 | 277  | 5.6562          |
+| 0.016         | 39.3  | 280  | 5.6562          |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 256,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 12198
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b95ad33b4c61898cfeefbb8d0b7ca9fc5382ef0d8973ded4d712bd15e7caa49
+size 1408774432

runs/Apr18_09-41-00_gcn66.local.snellius.surf.nl/events.out.tfevents.1713426070.gcn66.local.snellius.surf.nl.151482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950a43945d7f4d97d574e1ccffd06717228dead7fa9d2f2f2685c60d5533d03e
+size 74243

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13f80659633a7cbcc67700eb6a8ea06b718482efadb08dd4e23b49b007f61b6
+size 4984