Model save

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: Yelp-1B
+  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. -->
+
+# Yelp-1B
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown 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: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.45.2
+- Pytorch 2.5.1
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f55454e1526a2a3540192469c0a2a7acf0e2930445c8c382be50350443861a
+size 1104180408

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 129280
+}

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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86b1c5a1446428216066226d092e81d022c7c65a8521c675c25e559d1216e6e
+size 17398145

trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9991469396459802,
+  "eval_steps": 500,
+  "global_step": 3516,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28435345134001566,
+      "grad_norm": 0.7178500890731812,
+      "learning_rate": 9.294251565167901e-05,
+      "loss": 1.3567,
+      "step": 250
+    },
+    {
+      "epoch": 0.5687069026800313,
+      "grad_norm": 1.2267086505889893,
+      "learning_rate": 8.582811610700058e-05,
+      "loss": 0.8286,
+      "step": 500
+    },
+    {
+      "epoch": 0.8530603540200469,
+      "grad_norm": 0.9475031495094299,
+      "learning_rate": 7.871371656232215e-05,
+      "loss": 0.6149,
+      "step": 750
+    },
+    {
+      "epoch": 1.1374138053600626,
+      "grad_norm": 0.7641754150390625,
+      "learning_rate": 7.159931701764372e-05,
+      "loss": 0.5355,
+      "step": 1000
+    },
+    {
+      "epoch": 1.421767256700078,
+      "grad_norm": 0.6781603693962097,
+      "learning_rate": 6.448491747296529e-05,
+      "loss": 0.502,
+      "step": 1250
+    },
+    {
+      "epoch": 1.706120708040094,
+      "grad_norm": 0.6851858496665955,
+      "learning_rate": 5.737051792828686e-05,
+      "loss": 0.4789,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9904741593801094,
+      "grad_norm": 0.7101367712020874,
+      "learning_rate": 5.025611838360843e-05,
+      "loss": 0.4672,
+      "step": 1750
+    },
+    {
+      "epoch": 2.2748276107201253,
+      "grad_norm": 0.719354510307312,
+      "learning_rate": 4.3141718838929996e-05,
+      "loss": 0.4556,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5591810620601407,
+      "grad_norm": 0.7557260394096375,
+      "learning_rate": 3.602731929425157e-05,
+      "loss": 0.4437,
+      "step": 2250
+    },
+    {
+      "epoch": 2.843534513400156,
+      "grad_norm": 0.7026885151863098,
+      "learning_rate": 2.8912919749573137e-05,
+      "loss": 0.4346,
+      "step": 2500
+    },
+    {
+      "epoch": 3.127887964740172,
+      "grad_norm": 0.7724879384040833,
+      "learning_rate": 2.1798520204894708e-05,
+      "loss": 0.4278,
+      "step": 2750
+    },
+    {
+      "epoch": 3.4122414160801875,
+      "grad_norm": 0.726881742477417,
+      "learning_rate": 1.4684120660216277e-05,
+      "loss": 0.4204,
+      "step": 3000
+    },
+    {
+      "epoch": 3.6965948674202034,
+      "grad_norm": 0.726548969745636,
+      "learning_rate": 7.569721115537849e-06,
+      "loss": 0.4147,
+      "step": 3250
+    },
+    {
+      "epoch": 3.980948318760219,
+      "grad_norm": 0.7224068641662598,
+      "learning_rate": 4.553215708594195e-07,
+      "loss": 0.4115,
+      "step": 3500
+    },
+    {
+      "epoch": 3.9991469396459802,
+      "step": 3516,
+      "total_flos": 9.36662514312536e+17,
+      "train_loss": 0.5558986084724313,
+      "train_runtime": 21202.7076,
+      "train_samples_per_second": 42.459,
+      "train_steps_per_second": 0.166
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 3516,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.36662514312536e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a37ed115efdad59b564640085ef6e9db8dfac80498dd6c379575ad52cd92456
+size 5176