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-8bit-3B-4Epoch-EmbToken
+  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-3B-4Epoch-EmbToken
+
+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: 6
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 96
+- 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 0.13.1
+- Transformers 4.45.2
+- Pytorch 2.4.1
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "embed_tokens",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_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:cf6847e67fdd1b83c32120770d7367723d4f1b6f62bf197a51009c84c6eb3ae9
+size 846556736

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 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.999089792017476,
+  "eval_steps": 500,
+  "global_step": 5492,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18204159650480134,
+      "grad_norm": 3.854499101638794,
+      "learning_rate": 9.548269581056467e-05,
+      "loss": 1.0014,
+      "step": 250
+    },
+    {
+      "epoch": 0.3640831930096027,
+      "grad_norm": 3.5418713092803955,
+      "learning_rate": 9.092896174863389e-05,
+      "loss": 0.5401,
+      "step": 500
+    },
+    {
+      "epoch": 0.546124789514404,
+      "grad_norm": 3.089492082595825,
+      "learning_rate": 8.63752276867031e-05,
+      "loss": 0.4797,
+      "step": 750
+    },
+    {
+      "epoch": 0.7281663860192054,
+      "grad_norm": 3.0062525272369385,
+      "learning_rate": 8.182149362477231e-05,
+      "loss": 0.4598,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9102079825240067,
+      "grad_norm": 2.703545093536377,
+      "learning_rate": 7.726775956284153e-05,
+      "loss": 0.4454,
+      "step": 1250
+    },
+    {
+      "epoch": 1.092249579028808,
+      "grad_norm": 2.665408134460449,
+      "learning_rate": 7.271402550091076e-05,
+      "loss": 0.4338,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2742911755336095,
+      "grad_norm": 2.8605291843414307,
+      "learning_rate": 6.816029143897996e-05,
+      "loss": 0.4224,
+      "step": 1750
+    },
+    {
+      "epoch": 1.4563327720384107,
+      "grad_norm": 3.0206186771392822,
+      "learning_rate": 6.360655737704918e-05,
+      "loss": 0.4147,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6383743685432122,
+      "grad_norm": 3.633958578109741,
+      "learning_rate": 5.90528233151184e-05,
+      "loss": 0.3983,
+      "step": 2250
+    },
+    {
+      "epoch": 1.8204159650480136,
+      "grad_norm": 3.535999059677124,
+      "learning_rate": 5.449908925318762e-05,
+      "loss": 0.3808,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0024575615528146,
+      "grad_norm": 3.919354200363159,
+      "learning_rate": 4.994535519125683e-05,
+      "loss": 0.3642,
+      "step": 2750
+    },
+    {
+      "epoch": 2.184499158057616,
+      "grad_norm": 4.2734246253967285,
+      "learning_rate": 4.539162112932605e-05,
+      "loss": 0.3377,
+      "step": 3000
+    },
+    {
+      "epoch": 2.3665407545624175,
+      "grad_norm": 4.275780200958252,
+      "learning_rate": 4.083788706739526e-05,
+      "loss": 0.3261,
+      "step": 3250
+    },
+    {
+      "epoch": 2.548582351067219,
+      "grad_norm": 4.408421516418457,
+      "learning_rate": 3.6284153005464486e-05,
+      "loss": 0.31,
+      "step": 3500
+    },
+    {
+      "epoch": 2.7306239475720204,
+      "grad_norm": 4.726068019866943,
+      "learning_rate": 3.17304189435337e-05,
+      "loss": 0.2998,
+      "step": 3750
+    },
+    {
+      "epoch": 2.9126655440768214,
+      "grad_norm": 4.753103733062744,
+      "learning_rate": 2.7176684881602916e-05,
+      "loss": 0.2897,
+      "step": 4000
+    },
+    {
+      "epoch": 3.094707140581623,
+      "grad_norm": 4.001144886016846,
+      "learning_rate": 2.262295081967213e-05,
+      "loss": 0.2744,
+      "step": 4250
+    },
+    {
+      "epoch": 3.2767487370864243,
+      "grad_norm": 4.412220001220703,
+      "learning_rate": 1.806921675774135e-05,
+      "loss": 0.2619,
+      "step": 4500
+    },
+    {
+      "epoch": 3.458790333591226,
+      "grad_norm": 4.553833961486816,
+      "learning_rate": 1.3515482695810567e-05,
+      "loss": 0.2578,
+      "step": 4750
+    },
+    {
+      "epoch": 3.640831930096027,
+      "grad_norm": 4.323617458343506,
+      "learning_rate": 8.961748633879782e-06,
+      "loss": 0.2533,
+      "step": 5000
+    },
+    {
+      "epoch": 3.8228735266008282,
+      "grad_norm": 4.197403430938721,
+      "learning_rate": 4.408014571948998e-06,
+      "loss": 0.2489,
+      "step": 5250
+    },
+    {
+      "epoch": 3.999089792017476,
+      "step": 5492,
+      "total_flos": 1.2115246643852867e+18,
+      "train_loss": 0.38415815321442337,
+      "train_runtime": 38374.2384,
+      "train_samples_per_second": 13.742,
+      "train_steps_per_second": 0.143
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 5492,
+  "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": 1.2115246643852867e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c8222790fef3f0776422283ef24dd960e466ce88e6130609f3777dd2dcfa8a
+size 5240