ninagroot/Llama-450Mtest

README.md

@@ -0,0 +1,72 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama-450M
+  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-450M
+
+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: 5.3443
+
+## 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: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 8.6203        | 0.89  | 2    | 8.5191          |
+| 8.0999        | 1.78  | 4    | 8.1511          |
+| 7.3266        | 2.67  | 6    | 7.6165          |
+| 6.4407        | 4.0   | 9    | 6.9793          |
+| 5.9683        | 4.89  | 11   | 6.7137          |
+| 5.5381        | 5.78  | 13   | 6.4971          |
+| 5.1411        | 6.67  | 15   | 6.2243          |
+| 4.6555        | 8.0   | 18   | 6.0123          |
+| 4.1495        | 8.89  | 20   | 5.7939          |
+| 3.7822        | 9.78  | 22   | 5.6854          |
+| 3.2967        | 10.67 | 24   | 5.6039          |
+| 2.733         | 12.0  | 27   | 5.4239          |
+| 2.2935        | 12.89 | 29   | 5.3576          |
+| 2.0496        | 13.33 | 30   | 5.3443          |
+
+
+### 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": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "max_position_embeddings": 256,
+  "model_type": "llama",
+  "num_attention_heads": 10,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 10,
+  "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": 4312
+}

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:cdb1cc402213adaa1dc4942691fe6aa4fe65a8752d8e0d915cd4f6a446178640
+size 2875619784

runs/Apr22_10-59-08_gcn52.local.snellius.surf.nl/events.out.tfevents.1713776358.gcn52.local.snellius.surf.nl.2827063.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95cdf1526470758094fa43232ddafb957b48c5bac23e1d31c9e9ffaf448ea3ec
+size 14845

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c11001d733bbb619359b62337e11ec9cd3afd24dbb623c8a89682cdc9a309e
+size 4984