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 +1,55 @@
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+library_name: peft
+license: llama3.2
+tags:
+- generated_from_trainer
+model-index:
+- name: Instruments2-1B
+  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. -->
+
+# Instruments2-1B
+
+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
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "bias": "none",
+  "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_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",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_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 sha256:3dac350c659f9441e541fd894afcc83c5498e15e4f4fe09f05130b527e6ee0da
+size 1103410360

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": 129186
+}

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 sha256:3ccc9e779d2cddc5a8a73bd66cd555fc7a7491d76489b0c98a3fc35b10f19e4b
+size 17380886

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2060,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.7758151292800903,
+      "learning_rate": 8.786407766990292e-05,
+      "loss": 0.9558,
+      "step": 250
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.6270864009857178,
+      "learning_rate": 7.572815533980583e-05,
+      "loss": 0.4803,
+      "step": 500
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 0.5969606637954712,
+      "learning_rate": 6.359223300970875e-05,
+      "loss": 0.4064,
+      "step": 750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.5275030732154846,
+      "learning_rate": 5.145631067961165e-05,
+      "loss": 0.3821,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 0.5033597946166992,
+      "learning_rate": 3.9320388349514564e-05,
+      "loss": 0.3711,
+      "step": 1250
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.5042328238487244,
+      "learning_rate": 2.7184466019417475e-05,
+      "loss": 0.366,
+      "step": 1500
+    },
+    {
+      "epoch": 3.3980582524271843,
+      "grad_norm": 0.4678958058357239,
+      "learning_rate": 1.5048543689320387e-05,
+      "loss": 0.3593,
+      "step": 1750
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 0.46227386593818665,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 0.3563,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "step": 2060,
+      "total_flos": 5.02561395295531e+17,
+      "train_loss": 0.45658367768074704,
+      "train_runtime": 7745.2958,
+      "train_samples_per_second": 68.086,
+      "train_steps_per_second": 0.266
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 2060,
+  "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": 5.02561395295531e+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 sha256:0ee05edc987961b7c9466a1b16e55c51e60afddefbf342fd57d918ffb7a07b6a
+size 5240