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 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+license: llama3.2
+tags:
+- generated_from_trainer
+model-index:
+- name: Instruments-16bit-3B-4Epoch
+  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. -->
+
+# Instruments-16bit-3B-4Epoch
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- 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 0.13.2
+- Transformers 4.45.2
+- Pytorch 2.4.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_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 sha256:1ffedf39ab0597bf940bb98f1009ed114ebfc7b401e0c2d440df3c5d27932e69
+size 1684597880

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": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "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": 129174
+}

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 sha256:6cdb5a41c4ff365aaf322d31b46b6ce2c9f8493fa398bd5ad4fbe6179ebfa53e
+size 17378691

trainer_state.json

@@ -0,0 +1,266 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12135922330097088,
+      "grad_norm": 1.0393857955932617,
+      "learning_rate": 9.698956057295461e-05,
+      "loss": 1.1954,
+      "step": 250
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 0.9956526756286621,
+      "learning_rate": 9.395484340859432e-05,
+      "loss": 0.6506,
+      "step": 500
+    },
+    {
+      "epoch": 0.3640776699029126,
+      "grad_norm": 0.8538560271263123,
+      "learning_rate": 9.092012624423404e-05,
+      "loss": 0.551,
+      "step": 750
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.7631779909133911,
+      "learning_rate": 8.788540907987377e-05,
+      "loss": 0.5112,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6067961165048543,
+      "grad_norm": 0.6782851219177246,
+      "learning_rate": 8.485069191551348e-05,
+      "loss": 0.4978,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7281553398058253,
+      "grad_norm": 0.6814644932746887,
+      "learning_rate": 8.181597475115321e-05,
+      "loss": 0.4818,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8495145631067961,
+      "grad_norm": 0.6583015322685242,
+      "learning_rate": 7.878125758679291e-05,
+      "loss": 0.4743,
+      "step": 1750
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.5943029522895813,
+      "learning_rate": 7.574654042243264e-05,
+      "loss": 0.4671,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0922330097087378,
+      "grad_norm": 0.6358692646026611,
+      "learning_rate": 7.271182325807235e-05,
+      "loss": 0.4576,
+      "step": 2250
+    },
+    {
+      "epoch": 1.2135922330097086,
+      "grad_norm": 0.6650794148445129,
+      "learning_rate": 6.967710609371208e-05,
+      "loss": 0.4466,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 0.6177652478218079,
+      "learning_rate": 6.664238892935178e-05,
+      "loss": 0.4414,
+      "step": 2750
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 0.7465215921401978,
+      "learning_rate": 6.360767176499151e-05,
+      "loss": 0.4272,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5776699029126213,
+      "grad_norm": 0.8073906302452087,
+      "learning_rate": 6.0572954600631224e-05,
+      "loss": 0.4104,
+      "step": 3250
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 0.8686108589172363,
+      "learning_rate": 5.7538237436270945e-05,
+      "loss": 0.3943,
+      "step": 3500
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 0.7997599840164185,
+      "learning_rate": 5.450352027191066e-05,
+      "loss": 0.3759,
+      "step": 3750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.8568466305732727,
+      "learning_rate": 5.146880310755038e-05,
+      "loss": 0.3588,
+      "step": 4000
+    },
+    {
+      "epoch": 2.063106796116505,
+      "grad_norm": 0.9695954322814941,
+      "learning_rate": 4.84340859431901e-05,
+      "loss": 0.3308,
+      "step": 4250
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 0.9294792413711548,
+      "learning_rate": 4.539936877882982e-05,
+      "loss": 0.3118,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3058252427184467,
+      "grad_norm": 0.9838653206825256,
+      "learning_rate": 4.236465161446954e-05,
+      "loss": 0.3022,
+      "step": 4750
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 1.043236255645752,
+      "learning_rate": 3.932993445010925e-05,
+      "loss": 0.2916,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5485436893203883,
+      "grad_norm": 0.9233840703964233,
+      "learning_rate": 3.6295217285748975e-05,
+      "loss": 0.2817,
+      "step": 5250
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 1.0206633806228638,
+      "learning_rate": 3.326050012138869e-05,
+      "loss": 0.2717,
+      "step": 5500
+    },
+    {
+      "epoch": 2.79126213592233,
+      "grad_norm": 1.0079368352890015,
+      "learning_rate": 3.022578295702841e-05,
+      "loss": 0.268,
+      "step": 5750
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.9239732623100281,
+      "learning_rate": 2.7191065792668125e-05,
+      "loss": 0.2594,
+      "step": 6000
+    },
+    {
+      "epoch": 3.033980582524272,
+      "grad_norm": 0.9461367726325989,
+      "learning_rate": 2.4156348628307843e-05,
+      "loss": 0.2478,
+      "step": 6250
+    },
+    {
+      "epoch": 3.1553398058252426,
+      "grad_norm": 0.9437795877456665,
+      "learning_rate": 2.112163146394756e-05,
+      "loss": 0.2338,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2766990291262137,
+      "grad_norm": 0.9600566625595093,
+      "learning_rate": 1.808691429958728e-05,
+      "loss": 0.2303,
+      "step": 6750
+    },
+    {
+      "epoch": 3.3980582524271843,
+      "grad_norm": 1.0476354360580444,
+      "learning_rate": 1.5052197135226997e-05,
+      "loss": 0.2274,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5194174757281553,
+      "grad_norm": 0.9463278651237488,
+      "learning_rate": 1.2017479970866715e-05,
+      "loss": 0.2254,
+      "step": 7250
+    },
+    {
+      "epoch": 3.6407766990291264,
+      "grad_norm": 0.9192850589752197,
+      "learning_rate": 8.982762806506435e-06,
+      "loss": 0.2232,
+      "step": 7500
+    },
+    {
+      "epoch": 3.762135922330097,
+      "grad_norm": 0.9748009443283081,
+      "learning_rate": 5.948045642146152e-06,
+      "loss": 0.2199,
+      "step": 7750
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 0.9270649552345276,
+      "learning_rate": 2.9133284777858704e-06,
+      "loss": 0.2201,
+      "step": 8000
+    },
+    {
+      "epoch": 4.0,
+      "step": 8240,
+      "total_flos": 1.1079720316327956e+18,
+      "train_loss": 0.3791189865001197,
+      "train_runtime": 14726.9623,
+      "train_samples_per_second": 35.808,
+      "train_steps_per_second": 0.56
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 8240,
+  "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": 1.1079720316327956e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac98a665fe707fe94a20db3f47d62ea7c31846737e65457326b6b755afe26e04
+size 5240