Model save

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-dpo-full
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-lora-romantic
+  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. -->
+
+# zephyr-7b-sft-lora-romantic
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-dpo-full](https://huggingface.co/alignment-handbook/zephyr-7b-dpo-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2856
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3053        | 0.3   | 3    | 1.2856          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alignment-handbook/zephyr-7b-dpo-full",
+  "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",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705a20456aba38389db84ff4676571e109581ac88f196fc2263e6d83b3102768
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.3,
+    "eval_loss": 1.2855873107910156,
+    "eval_runtime": 54.5166,
+    "eval_samples": 575,
+    "eval_samples_per_second": 10.547,
+    "eval_steps_per_second": 1.321,
+    "train_loss": 1.6732101043065388,
+    "train_runtime": 1592.7916,
+    "train_samples": 5169,
+    "train_samples_per_second": 3.245,
+    "train_steps_per_second": 0.006
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.3,
+    "eval_loss": 1.2855873107910156,
+    "eval_runtime": 54.5166,
+    "eval_samples": 575,
+    "eval_samples_per_second": 10.547,
+    "eval_steps_per_second": 1.321
+}

runs/Jan09_02-23-08_c77bb60b6e11/events.out.tfevents.1704767057.c77bb60b6e11.1155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6707c1f9e86412ae09d2890f295cf95606e089183621a0d7d59a3551aa074100
+size 4464

runs/Jan09_02-32-37_c77bb60b6e11/events.out.tfevents.1704767629.c77bb60b6e11.1252.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae79a35bc2d3a6b1341647fe0e945c2735d6a5c97eedb0dbf04b22020565aad
+size 5077

runs/Jan09_02-32-37_c77bb60b6e11/events.out.tfevents.1704769276.c77bb60b6e11.1252.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46fb99e154368b724dd9c9b6c78e2b707143696c8e8d0434f78cb9c89e41369
+size 354

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.3,
+    "train_loss": 1.6732101043065388,
+    "train_runtime": 1592.7916,
+    "train_samples": 5169,
+    "train_samples_per_second": 3.245,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.29698375870069604,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 1.3053,
+      "step": 1
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.2855874300003052,
+      "eval_runtime": 54.5811,
+      "eval_samples_per_second": 10.535,
+      "eval_steps_per_second": 1.319,
+      "step": 3
+    },
+    {
+      "epoch": 0.3,
+      "step": 3,
+      "total_flos": 1.7380242293260288e+17,
+      "train_loss": 1.6732101043065388,
+      "train_runtime": 1592.7916,
+      "train_samples_per_second": 3.245,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 10,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.7380242293260288e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696af519da54fe8afce4a1a49353afed8ff62ba24ae4030ab746be24b2d22c9c
+size 4664