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: Instruments-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. -->
+
+# Instruments-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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- 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": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_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:a8bce6d4ec6a0f34111d3772420ebde5ae226586cd843179904361d3360a1a09
+size 1103312056

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": 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 +1,497 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 16480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06067961165048544,
+      "grad_norm": 1.0428600311279297,
+      "learning_rate": 4.9241504854368934e-05,
+      "loss": 1.1077,
+      "step": 250
+    },
+    {
+      "epoch": 0.12135922330097088,
+      "grad_norm": 1.5115264654159546,
+      "learning_rate": 4.8483009708737866e-05,
+      "loss": 0.657,
+      "step": 500
+    },
+    {
+      "epoch": 0.1820388349514563,
+      "grad_norm": 1.4269579648971558,
+      "learning_rate": 4.77245145631068e-05,
+      "loss": 0.543,
+      "step": 750
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 1.7683141231536865,
+      "learning_rate": 4.696601941747573e-05,
+      "loss": 0.4856,
+      "step": 1000
+    },
+    {
+      "epoch": 0.30339805825242716,
+      "grad_norm": 1.7940973043441772,
+      "learning_rate": 4.620752427184466e-05,
+      "loss": 0.4484,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3640776699029126,
+      "grad_norm": 1.5501463413238525,
+      "learning_rate": 4.544902912621359e-05,
+      "loss": 0.4257,
+      "step": 1500
+    },
+    {
+      "epoch": 0.42475728155339804,
+      "grad_norm": 1.4384820461273193,
+      "learning_rate": 4.469053398058253e-05,
+      "loss": 0.4041,
+      "step": 1750
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 1.443152904510498,
+      "learning_rate": 4.393203883495146e-05,
+      "loss": 0.3986,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5461165048543689,
+      "grad_norm": 1.1744354963302612,
+      "learning_rate": 4.3173543689320386e-05,
+      "loss": 0.3886,
+      "step": 2250
+    },
+    {
+      "epoch": 0.6067961165048543,
+      "grad_norm": 1.3900296688079834,
+      "learning_rate": 4.2415048543689325e-05,
+      "loss": 0.3894,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6674757281553398,
+      "grad_norm": 1.3115075826644897,
+      "learning_rate": 4.1656553398058256e-05,
+      "loss": 0.3803,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7281553398058253,
+      "grad_norm": 1.1693966388702393,
+      "learning_rate": 4.089805825242719e-05,
+      "loss": 0.3749,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7888349514563107,
+      "grad_norm": 1.2021554708480835,
+      "learning_rate": 4.013956310679612e-05,
+      "loss": 0.3678,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8495145631067961,
+      "grad_norm": 1.1241698265075684,
+      "learning_rate": 3.938106796116505e-05,
+      "loss": 0.3666,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9101941747572816,
+      "grad_norm": 1.2042889595031738,
+      "learning_rate": 3.862257281553398e-05,
+      "loss": 0.3681,
+      "step": 3750
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 1.1275087594985962,
+      "learning_rate": 3.7864077669902914e-05,
+      "loss": 0.3646,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0315533980582525,
+      "grad_norm": 1.1873338222503662,
+      "learning_rate": 3.7105582524271846e-05,
+      "loss": 0.3612,
+      "step": 4250
+    },
+    {
+      "epoch": 1.0922330097087378,
+      "grad_norm": 0.9657476544380188,
+      "learning_rate": 3.634708737864078e-05,
+      "loss": 0.358,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1529126213592233,
+      "grad_norm": 1.0361531972885132,
+      "learning_rate": 3.558859223300971e-05,
+      "loss": 0.3526,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2135922330097086,
+      "grad_norm": 1.3572288751602173,
+      "learning_rate": 3.483009708737864e-05,
+      "loss": 0.3492,
+      "step": 5000
+    },
+    {
+      "epoch": 1.2742718446601942,
+      "grad_norm": 1.227097988128662,
+      "learning_rate": 3.407160194174757e-05,
+      "loss": 0.3522,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 1.0761758089065552,
+      "learning_rate": 3.3313106796116504e-05,
+      "loss": 0.3533,
+      "step": 5500
+    },
+    {
+      "epoch": 1.395631067961165,
+      "grad_norm": 1.1308465003967285,
+      "learning_rate": 3.255461165048544e-05,
+      "loss": 0.3495,
+      "step": 5750
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 1.0873249769210815,
+      "learning_rate": 3.1796116504854373e-05,
+      "loss": 0.3427,
+      "step": 6000
+    },
+    {
+      "epoch": 1.516990291262136,
+      "grad_norm": 1.1765254735946655,
+      "learning_rate": 3.10376213592233e-05,
+      "loss": 0.3373,
+      "step": 6250
+    },
+    {
+      "epoch": 1.5776699029126213,
+      "grad_norm": 1.1217211484909058,
+      "learning_rate": 3.0279126213592237e-05,
+      "loss": 0.3337,
+      "step": 6500
+    },
+    {
+      "epoch": 1.6383495145631068,
+      "grad_norm": 1.388096809387207,
+      "learning_rate": 2.9520631067961168e-05,
+      "loss": 0.3367,
+      "step": 6750
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 1.2720024585723877,
+      "learning_rate": 2.8762135922330096e-05,
+      "loss": 0.3281,
+      "step": 7000
+    },
+    {
+      "epoch": 1.7597087378640777,
+      "grad_norm": 1.3721733093261719,
+      "learning_rate": 2.800364077669903e-05,
+      "loss": 0.3261,
+      "step": 7250
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 1.1529369354248047,
+      "learning_rate": 2.7245145631067963e-05,
+      "loss": 0.3252,
+      "step": 7500
+    },
+    {
+      "epoch": 1.8810679611650487,
+      "grad_norm": 1.326474905014038,
+      "learning_rate": 2.648665048543689e-05,
+      "loss": 0.323,
+      "step": 7750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 1.332924723625183,
+      "learning_rate": 2.5728155339805826e-05,
+      "loss": 0.3155,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0024271844660193,
+      "grad_norm": 1.4862456321716309,
+      "learning_rate": 2.4969660194174758e-05,
+      "loss": 0.3102,
+      "step": 8250
+    },
+    {
+      "epoch": 2.063106796116505,
+      "grad_norm": 1.576427698135376,
+      "learning_rate": 2.4211165048543692e-05,
+      "loss": 0.304,
+      "step": 8500
+    },
+    {
+      "epoch": 2.1237864077669903,
+      "grad_norm": 1.5153827667236328,
+      "learning_rate": 2.345266990291262e-05,
+      "loss": 0.3,
+      "step": 8750
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 1.6367888450622559,
+      "learning_rate": 2.2694174757281556e-05,
+      "loss": 0.2972,
+      "step": 9000
+    },
+    {
+      "epoch": 2.2451456310679614,
+      "grad_norm": 1.6072200536727905,
+      "learning_rate": 2.1935679611650487e-05,
+      "loss": 0.2946,
+      "step": 9250
+    },
+    {
+      "epoch": 2.3058252427184467,
+      "grad_norm": 1.5894421339035034,
+      "learning_rate": 2.117718446601942e-05,
+      "loss": 0.2918,
+      "step": 9500
+    },
+    {
+      "epoch": 2.366504854368932,
+      "grad_norm": 1.3856350183486938,
+      "learning_rate": 2.041868932038835e-05,
+      "loss": 0.2847,
+      "step": 9750
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 1.8990323543548584,
+      "learning_rate": 1.9660194174757282e-05,
+      "loss": 0.281,
+      "step": 10000
+    },
+    {
+      "epoch": 2.487864077669903,
+      "grad_norm": 1.4469305276870728,
+      "learning_rate": 1.8901699029126217e-05,
+      "loss": 0.277,
+      "step": 10250
+    },
+    {
+      "epoch": 2.5485436893203883,
+      "grad_norm": 1.591465711593628,
+      "learning_rate": 1.814320388349515e-05,
+      "loss": 0.2762,
+      "step": 10500
+    },
+    {
+      "epoch": 2.6092233009708736,
+      "grad_norm": 1.799155831336975,
+      "learning_rate": 1.7384708737864077e-05,
+      "loss": 0.2728,
+      "step": 10750
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 1.9380991458892822,
+      "learning_rate": 1.662621359223301e-05,
+      "loss": 0.2726,
+      "step": 11000
+    },
+    {
+      "epoch": 2.7305825242718447,
+      "grad_norm": 1.8352900743484497,
+      "learning_rate": 1.5867718446601943e-05,
+      "loss": 0.269,
+      "step": 11250
+    },
+    {
+      "epoch": 2.79126213592233,
+      "grad_norm": 1.737328052520752,
+      "learning_rate": 1.5109223300970873e-05,
+      "loss": 0.2652,
+      "step": 11500
+    },
+    {
+      "epoch": 2.8519417475728153,
+      "grad_norm": 1.819117546081543,
+      "learning_rate": 1.4350728155339808e-05,
+      "loss": 0.264,
+      "step": 11750
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 1.9015542268753052,
+      "learning_rate": 1.3592233009708738e-05,
+      "loss": 0.2586,
+      "step": 12000
+    },
+    {
+      "epoch": 2.9733009708737863,
+      "grad_norm": 1.9521596431732178,
+      "learning_rate": 1.2833737864077671e-05,
+      "loss": 0.2565,
+      "step": 12250
+    },
+    {
+      "epoch": 3.033980582524272,
+      "grad_norm": 2.0965163707733154,
+      "learning_rate": 1.2075242718446603e-05,
+      "loss": 0.2503,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0946601941747574,
+      "grad_norm": 1.7102735042572021,
+      "learning_rate": 1.1316747572815536e-05,
+      "loss": 0.2434,
+      "step": 12750
+    },
+    {
+      "epoch": 3.1553398058252426,
+      "grad_norm": 2.49703049659729,
+      "learning_rate": 1.0558252427184466e-05,
+      "loss": 0.2436,
+      "step": 13000
+    },
+    {
+      "epoch": 3.216019417475728,
+      "grad_norm": 1.7436761856079102,
+      "learning_rate": 9.799757281553399e-06,
+      "loss": 0.2398,
+      "step": 13250
+    },
+    {
+      "epoch": 3.2766990291262137,
+      "grad_norm": 1.8170946836471558,
+      "learning_rate": 9.04126213592233e-06,
+      "loss": 0.2392,
+      "step": 13500
+    },
+    {
+      "epoch": 3.337378640776699,
+      "grad_norm": 1.6467654705047607,
+      "learning_rate": 8.282766990291264e-06,
+      "loss": 0.2376,
+      "step": 13750
+    },
+    {
+      "epoch": 3.3980582524271843,
+      "grad_norm": 2.062037467956543,
+      "learning_rate": 7.524271844660194e-06,
+      "loss": 0.2372,
+      "step": 14000
+    },
+    {
+      "epoch": 3.45873786407767,
+      "grad_norm": 1.8514248132705688,
+      "learning_rate": 6.765776699029126e-06,
+      "loss": 0.2364,
+      "step": 14250
+    },
+    {
+      "epoch": 3.5194174757281553,
+      "grad_norm": 1.8037079572677612,
+      "learning_rate": 6.0072815533980584e-06,
+      "loss": 0.2356,
+      "step": 14500
+    },
+    {
+      "epoch": 3.5800970873786406,
+      "grad_norm": 1.6537799835205078,
+      "learning_rate": 5.24878640776699e-06,
+      "loss": 0.2335,
+      "step": 14750
+    },
+    {
+      "epoch": 3.6407766990291264,
+      "grad_norm": 1.7144070863723755,
+      "learning_rate": 4.490291262135922e-06,
+      "loss": 0.234,
+      "step": 15000
+    },
+    {
+      "epoch": 3.7014563106796117,
+      "grad_norm": 1.7142642736434937,
+      "learning_rate": 3.7317961165048544e-06,
+      "loss": 0.229,
+      "step": 15250
+    },
+    {
+      "epoch": 3.762135922330097,
+      "grad_norm": 1.8582273721694946,
+      "learning_rate": 2.973300970873787e-06,
+      "loss": 0.2301,
+      "step": 15500
+    },
+    {
+      "epoch": 3.8228155339805827,
+      "grad_norm": 1.7135488986968994,
+      "learning_rate": 2.2148058252427188e-06,
+      "loss": 0.2322,
+      "step": 15750
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 1.4958486557006836,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 0.2274,
+      "step": 16000
+    },
+    {
+      "epoch": 3.9441747572815533,
+      "grad_norm": 1.6569055318832397,
+      "learning_rate": 6.978155339805825e-07,
+      "loss": 0.2287,
+      "step": 16250
+    },
+    {
+      "epoch": 4.0,
+      "step": 16480,
+      "total_flos": 5.02561395295531e+17,
+      "train_loss": 0.3288965769184446,
+      "train_runtime": 7677.0205,
+      "train_samples_per_second": 68.692,
+      "train_steps_per_second": 2.147
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 16480,
+  "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 sha256:5f50ca3743d0bfc836d5a0656249dad1acffac8715644143d4f1d99cebe55f1a
+size 5240