Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-1.1B-Chat-v1.0-reasoning-v2-dpo-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. -->
+
+# TinyLlama-1.1B-Chat-v1.0-reasoning-v2-dpo-romantic
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4293
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4496        | 0.4   | 4    | 1.4425          |
+| 1.4508        | 1.39  | 8    | 1.4372          |
+| 1.4458        | 2.39  | 12   | 1.4293          |
+
+
+### 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": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daccbcf3cd827eb0587dee01a7d9d0369ac16fbc99227dfb27134d1d8d13a966
+size 72113224

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.39,
+    "eval_loss": 1.4292563199996948,
+    "eval_runtime": 12.4664,
+    "eval_samples": 575,
+    "eval_samples_per_second": 46.124,
+    "eval_steps_per_second": 5.776,
+    "train_loss": 1.4526023268699646,
+    "train_runtime": 1107.1405,
+    "train_samples": 5169,
+    "train_samples_per_second": 14.006,
+    "train_steps_per_second": 0.027
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.39,
+    "eval_loss": 1.4292563199996948,
+    "eval_runtime": 12.4664,
+    "eval_samples": 575,
+    "eval_samples_per_second": 46.124,
+    "eval_steps_per_second": 5.776
+}

runs/Jan09_13-56-55_46e0bcaeaa2e/events.out.tfevents.1704808719.46e0bcaeaa2e.2235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e561af705091386cd70f057810d2b01c57d4a66c85db65772e321368e000076b
+size 5899

runs/Jan09_14-24-16_46e0bcaeaa2e/events.out.tfevents.1704810325.46e0bcaeaa2e.2537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e1509921f6193a87857b85a47fd79cad218b7554b679856bdee09b1cee23a0
+size 6047

runs/Jan09_14-24-16_46e0bcaeaa2e/events.out.tfevents.1704811445.46e0bcaeaa2e.2537.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3faed847b92e84d3ef6f728109b51f6a7ff54c08dba6b31bc750e760b8c4deb2
+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 +1,40 @@
+{
+  "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
+    }
+  },
+  "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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.39,
+    "train_loss": 1.4526023268699646,
+    "train_runtime": 1107.1405,
+    "train_samples": 5169,
+    "train_samples_per_second": 14.006,
+    "train_steps_per_second": 0.027
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3928847641144624,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.4496,
+      "step": 1
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4424513578414917,
+      "eval_runtime": 12.4902,
+      "eval_samples_per_second": 46.036,
+      "eval_steps_per_second": 5.765,
+      "step": 4
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.4508,
+      "step": 5
+    },
+    {
+      "epoch": 1.39,
+      "eval_loss": 1.437177062034607,
+      "eval_runtime": 12.4739,
+      "eval_samples_per_second": 46.096,
+      "eval_steps_per_second": 5.772,
+      "step": 8
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 1.4458,
+      "step": 10
+    },
+    {
+      "epoch": 2.39,
+      "eval_loss": 1.4292563199996948,
+      "eval_runtime": 12.4695,
+      "eval_samples_per_second": 46.113,
+      "eval_steps_per_second": 5.774,
+      "step": 12
+    },
+    {
+      "epoch": 2.39,
+      "step": 12,
+      "total_flos": 7.973531837844685e+16,
+      "train_loss": 1.4526023268699646,
+      "train_runtime": 1107.1405,
+      "train_samples_per_second": 14.006,
+      "train_steps_per_second": 0.027
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 30,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.973531837844685e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d38bb1c6d1af2def37aff4e06cf030172a35c31f9d69dc73721c592bdc4666
+size 4728