Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+license: llama2
+base_model: meta-llama/Llama-2-13b-hf
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: llama2-13b-lora-classification-11-v1
+  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. -->
+
+# llama2-13b-lora-classification-11-v1
+
+This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0208
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8348        | 1.0   | 72   | 2.0208          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "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": 16,
+  "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": [
+    "v_proj",
+    "q_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 sha256:70b0bfb2699dd7f2843c27faa3c0536c5e07f75b0358a928bc277e0cbc655cb8
+size 681636888

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.280931693081395e+17,
+    "train_loss": 2.938576486375597,
+    "train_runtime": 504.3487,
+    "train_samples": 92634,
+    "train_samples_per_second": 36.431,
+    "train_steps_per_second": 0.143
+}

runs/Nov22_14-35-18_metallic-vm-falls-fin-02/events.out.tfevents.1732286447.metallic-vm-falls-fin-02.50699.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338a894fd66b64cb241c3cfdfb19682299b804dc040a5ec796f16ed1fd3c2302
+size 9356

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.280931693081395e+17,
+    "train_loss": 2.938576486375597,
+    "train_runtime": 504.3487,
+    "train_samples": 92634,
+    "train_samples_per_second": 36.431,
+    "train_steps_per_second": 0.143
+}

trainer_state.json

@@ -0,0 +1,155 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013888888888888888,
+      "grad_norm": 2.69645357131958,
+      "learning_rate": 2.5e-05,
+      "loss": 6.4485,
+      "step": 1
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 3.235274076461792,
+      "learning_rate": 0.000125,
+      "loss": 6.3994,
+      "step": 5
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 3.4826488494873047,
+      "learning_rate": 0.0001995184726672197,
+      "loss": 5.6587,
+      "step": 10
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 4.541069984436035,
+      "learning_rate": 0.00019415440651830208,
+      "loss": 4.6657,
+      "step": 15
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 4.04740047454834,
+      "learning_rate": 0.00018314696123025454,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 1.9904128313064575,
+      "learning_rate": 0.00016715589548470185,
+      "loss": 3.0269,
+      "step": 25
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.2599273920059204,
+      "learning_rate": 0.0001471396736825998,
+      "loss": 2.541,
+      "step": 30
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 0.848343014717102,
+      "learning_rate": 0.0001242980179903264,
+      "loss": 2.2349,
+      "step": 35
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.7984316349029541,
+      "learning_rate": 0.0001,
+      "loss": 2.0682,
+      "step": 40
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.6735253930091858,
+      "learning_rate": 7.570198200967362e-05,
+      "loss": 1.9724,
+      "step": 45
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.6062337160110474,
+      "learning_rate": 5.286032631740023e-05,
+      "loss": 1.9033,
+      "step": 50
+    },
+    {
+      "epoch": 0.7638888888888888,
+      "grad_norm": 0.5750789046287537,
+      "learning_rate": 3.2844104515298155e-05,
+      "loss": 1.8667,
+      "step": 55
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6575501561164856,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.8513,
+      "step": 60
+    },
+    {
+      "epoch": 0.9027777777777778,
+      "grad_norm": 0.5935372710227966,
+      "learning_rate": 5.8455934816979305e-06,
+      "loss": 1.8311,
+      "step": 65
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.527962327003479,
+      "learning_rate": 4.815273327803182e-07,
+      "loss": 1.8348,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.020827293395996,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 3.49,
+      "eval_steps_per_second": 0.873,
+      "step": 72
+    },
+    {
+      "epoch": 1.0,
+      "step": 72,
+      "total_flos": 7.280931693081395e+17,
+      "train_loss": 2.938576486375597,
+      "train_runtime": 504.3487,
+      "train_samples_per_second": 36.431,
+      "train_steps_per_second": 0.143
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.280931693081395e+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:f81cc204c8e68a5222c2718f077187272a4271c4d41914fe62fdb1b06ac80dd4
+size 5688