Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+0196a463-d9ba-704a-8b5b-f526785bf675.tos.temp filter=lfs diff=lfs merge=lfs -text
+0196a463-d9c8-7764-8ce3-6a8f3daafdbe.tos.temp filter=lfs diff=lfs merge=lfs -text
+0196a463-db54-75b3-a0eb-100a8d87fcd2.tos.temp filter=lfs diff=lfs merge=lfs -text
+0196a463-e469-7433-b514-35d1d7933bde.tos.temp filter=lfs diff=lfs merge=lfs -text

0196a463-d9ba-704a-8b5b-f526785bf675.tos.temp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4e3f7e5a54d641a7a2ac9ac383669f2db62369ae089ee4b85396d823c0f798
+size 4976698672

0196a463-d9c8-7764-8ce3-6a8f3daafdbe.tos.temp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9d458028913c05d083da6a62339b9e138d632b08b837e2ee6473f31b95bbf0
+size 4999802720

0196a463-db54-75b3-a0eb-100a8d87fcd2.tos.temp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f118bff3bcd2b09e249f2a5121cdf79b501079078a37ab073d9a75835d10f7
+size 4915916176

0196a463-e469-7433-b514-35d1d7933bde.tos.temp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7bbda8ba8062a0544d8eb767d098b441c68787a4a9db435e93bd5ef3608ffd
+size 1168138808

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 3_all_gpt4_5
+  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. -->
+
+# 3_all_gpt4_5
+
+This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the all_gpt4_5 dataset.
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.904458598726115,
+    "total_flos": 2648121016320.0,
+    "train_loss": 0.5501331692202049,
+    "train_runtime": 402.2806,
+    "train_samples_per_second": 18.644,
+    "train_steps_per_second": 0.142
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0"
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.904458598726115,
+    "total_flos": 2648121016320.0,
+    "train_loss": 0.5501331692202049,
+    "train_runtime": 402.2806,
+    "train_samples_per_second": 18.644,
+    "train_steps_per_second": 0.142
+}