End of training

README.md

@@ -0,0 +1,51 @@
+---
+base_model: NousResearch/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama-7B-SFT
+  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. -->
+
+# Llama-7B-SFT
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e344ac214381f56e2448a63475f59c0193d4c9bb7a93e2921a172a3979ce308d
+size 268470272

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.256724490932224e+16,
+    "train_loss": 1.1766422537506604,
+    "train_runtime": 7172.2389,
+    "train_samples": 731,
+    "train_samples_per_second": 0.204,
+    "train_steps_per_second": 0.102
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.256724490932224e+16,
+    "train_loss": 1.1766422537506604,
+    "train_runtime": 7172.2389,
+    "train_samples": 731,
+    "train_samples_per_second": 0.204,
+    "train_steps_per_second": 0.102
+}

trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 732,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9963183634476757e-05,
+      "loss": 1.9326,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.985300562686109e-05,
+      "loss": 1.8276,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 1.8392,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.941634397659126e-05,
+      "loss": 1.3092,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.909307559292236e-05,
+      "loss": 1.1181,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 1.2467,
+      "step": 120
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8248547748594246e-05,
+      "loss": 1.0989,
+      "step": 140
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.77335067770973e-05,
+      "loss": 1.1427,
+      "step": 160
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 1.1778,
+      "step": 180
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.653680474772006e-05,
+      "loss": 1.0765,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.586395533370696e-05,
+      "loss": 1.0176,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5147928015098309e-05,
+      "loss": 1.1858,
+      "step": 240
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4393995096591415e-05,
+      "loss": 1.1799,
+      "step": 260
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3607707992167836e-05,
+      "loss": 1.1227,
+      "step": 280
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2794856348516095e-05,
+      "loss": 1.0963,
+      "step": 300
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.196142541428197e-05,
+      "loss": 1.0744,
+      "step": 320
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1113551969048088e-05,
+      "loss": 1.1303,
+      "step": 340
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0257479136549889e-05,
+      "loss": 1.1179,
+      "step": 360
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.399510414850518e-06,
+      "loss": 1.0918,
+      "step": 380
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.545963261963102e-06,
+      "loss": 1.0483,
+      "step": 400
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.703122578682047e-06,
+      "loss": 1.2234,
+      "step": 420
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.877194431142055e-06,
+      "loss": 1.1311,
+      "step": 440
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.074260353858283e-06,
+      "loss": 1.1261,
+      "step": 460
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.300232569726805e-06,
+      "loss": 1.1854,
+      "step": 480
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.560810456712754e-06,
+      "loss": 1.1388,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.86143858177388e-06,
+      "loss": 1.0478,
+      "step": 520
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.207266611027069e-06,
+      "loss": 1.1229,
+      "step": 540
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.6031113913503337e-06,
+      "loss": 0.9668,
+      "step": 560
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.0534214826237486e-06,
+      "loss": 1.1179,
+      "step": 580
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.5622444017681438e-06,
+      "loss": 1.0696,
+      "step": 600
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1331968197725985e-06,
+      "loss": 1.055,
+      "step": 620
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.694379311582401e-07,
+      "loss": 1.058,
+      "step": 640
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.73646191966175e-07,
+      "loss": 1.0865,
+      "step": 660
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.479995975541749e-07,
+      "loss": 0.9857,
+      "step": 680
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.415964542203059e-08,
+      "loss": 1.1078,
+      "step": 700
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.325910115169471e-08,
+      "loss": 1.1117,
+      "step": 720
+    },
+    {
+      "epoch": 2.0,
+      "step": 732,
+      "total_flos": 2.256724490932224e+16,
+      "train_loss": 1.1766422537506604,
+      "train_runtime": 7172.2389,
+      "train_samples_per_second": 0.204,
+      "train_steps_per_second": 0.102
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 732,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "total_flos": 2.256724490932224e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3a5267faf38b68fdd89128fe636b247d3a919cbcecd53386b6eec8ec81c6c4
+size 4664