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-3.1-8B
+library_name: peft
+license: llama3.1
+tags:
+- generated_from_trainer
+model-index:
+- name: Instruments-8bit-8B-4Epoch-gcn
+  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-8bit-8B-4Epoch-gcn
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) 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
+- 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-3.1-8B",
+  "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": [
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_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:a196278f71574a7652a5d3317e317b6c635f21581df2ad7a0676af948975d4fd
+size 2284219288

config.json

@@ -0,0 +1,35 @@
+{
+  "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": 131072,
+  "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": {
+    "factor": 8.0,
+    "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": false,
+  "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": "<|end_of_text|>",
+    "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": 1.147416591644287,
+      "learning_rate": 9.696601941747573e-05,
+      "loss": 1.1102,
+      "step": 250
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 1.0398495197296143,
+      "learning_rate": 9.393203883495146e-05,
+      "loss": 0.5891,
+      "step": 500
+    },
+    {
+      "epoch": 0.3640776699029126,
+      "grad_norm": 0.7667867541313171,
+      "learning_rate": 9.089805825242718e-05,
+      "loss": 0.5176,
+      "step": 750
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.7023970484733582,
+      "learning_rate": 8.786407766990292e-05,
+      "loss": 0.4917,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6067961165048543,
+      "grad_norm": 0.6781546473503113,
+      "learning_rate": 8.483009708737865e-05,
+      "loss": 0.4822,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7281553398058253,
+      "grad_norm": 0.7623434066772461,
+      "learning_rate": 8.179611650485438e-05,
+      "loss": 0.4655,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8495145631067961,
+      "grad_norm": 0.8142368793487549,
+      "learning_rate": 7.87621359223301e-05,
+      "loss": 0.45,
+      "step": 1750
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.8743399381637573,
+      "learning_rate": 7.572815533980583e-05,
+      "loss": 0.4304,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0922330097087378,
+      "grad_norm": 0.9348050355911255,
+      "learning_rate": 7.269417475728155e-05,
+      "loss": 0.3979,
+      "step": 2250
+    },
+    {
+      "epoch": 1.2135922330097086,
+      "grad_norm": 1.0624396800994873,
+      "learning_rate": 6.966019417475728e-05,
+      "loss": 0.3695,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 1.0327861309051514,
+      "learning_rate": 6.662621359223301e-05,
+      "loss": 0.3452,
+      "step": 2750
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 1.0362504720687866,
+      "learning_rate": 6.359223300970875e-05,
+      "loss": 0.3194,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5776699029126213,
+      "grad_norm": 1.1497058868408203,
+      "learning_rate": 6.055825242718447e-05,
+      "loss": 0.3,
+      "step": 3250
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 1.1127945184707642,
+      "learning_rate": 5.752427184466019e-05,
+      "loss": 0.2829,
+      "step": 3500
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 1.0874605178833008,
+      "learning_rate": 5.4490291262135926e-05,
+      "loss": 0.2714,
+      "step": 3750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.965722382068634,
+      "learning_rate": 5.145631067961165e-05,
+      "loss": 0.2596,
+      "step": 4000
+    },
+    {
+      "epoch": 2.063106796116505,
+      "grad_norm": 1.0977766513824463,
+      "learning_rate": 4.8422330097087385e-05,
+      "loss": 0.2352,
+      "step": 4250
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 1.022316813468933,
+      "learning_rate": 4.538834951456311e-05,
+      "loss": 0.2209,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3058252427184467,
+      "grad_norm": 0.982537031173706,
+      "learning_rate": 4.235436893203884e-05,
+      "loss": 0.2171,
+      "step": 4750
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 1.093375563621521,
+      "learning_rate": 3.9320388349514564e-05,
+      "loss": 0.2129,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5485436893203883,
+      "grad_norm": 0.9269146919250488,
+      "learning_rate": 3.62864077669903e-05,
+      "loss": 0.2088,
+      "step": 5250
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 1.0317578315734863,
+      "learning_rate": 3.325242718446602e-05,
+      "loss": 0.2032,
+      "step": 5500
+    },
+    {
+      "epoch": 2.79126213592233,
+      "grad_norm": 0.9504765868186951,
+      "learning_rate": 3.0218446601941746e-05,
+      "loss": 0.2013,
+      "step": 5750
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.9305168390274048,
+      "learning_rate": 2.7184466019417475e-05,
+      "loss": 0.1963,
+      "step": 6000
+    },
+    {
+      "epoch": 3.033980582524272,
+      "grad_norm": 0.830916166305542,
+      "learning_rate": 2.4150485436893205e-05,
+      "loss": 0.1879,
+      "step": 6250
+    },
+    {
+      "epoch": 3.1553398058252426,
+      "grad_norm": 0.8673647046089172,
+      "learning_rate": 2.111650485436893e-05,
+      "loss": 0.1753,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2766990291262137,
+      "grad_norm": 0.8825583457946777,
+      "learning_rate": 1.808252427184466e-05,
+      "loss": 0.1739,
+      "step": 6750
+    },
+    {
+      "epoch": 3.3980582524271843,
+      "grad_norm": 1.0287333726882935,
+      "learning_rate": 1.5048543689320387e-05,
+      "loss": 0.1729,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5194174757281553,
+      "grad_norm": 0.809319794178009,
+      "learning_rate": 1.2014563106796117e-05,
+      "loss": 0.1718,
+      "step": 7250
+    },
+    {
+      "epoch": 3.6407766990291264,
+      "grad_norm": 0.8941086530685425,
+      "learning_rate": 8.980582524271845e-06,
+      "loss": 0.1702,
+      "step": 7500
+    },
+    {
+      "epoch": 3.762135922330097,
+      "grad_norm": 0.9008864760398865,
+      "learning_rate": 5.946601941747574e-06,
+      "loss": 0.1688,
+      "step": 7750
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 0.8730018138885498,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 0.1689,
+      "step": 8000
+    },
+    {
+      "epoch": 4.0,
+      "step": 8240,
+      "total_flos": 2.943708398017659e+18,
+      "train_loss": 0.31335733145186045,
+      "train_runtime": 45318.0558,
+      "train_samples_per_second": 11.637,
+      "train_steps_per_second": 0.182
+    }
+  ],
+  "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": 2.943708398017659e+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:ba374b109f4c0a2d77b4233e602229b02a2e9d7bc4549ea4d4db19694f99db10
+size 5240