Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: allenai/scitulu-7b
+library_name: transformers
+model_name: review_evaluation_all
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for review_evaluation_all
+
+This model is a fine-tuned version of [allenai/scitulu-7b](https://huggingface.co/allenai/scitulu-7b).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="boda/review_evaluation_all", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bodasadallah2/review_evaluation/runs/qh4fwvyk) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.1
+- Transformers: 4.49.0
+- Pytorch: 2.4.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/scitulu-7b",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_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:a47a4671015ecaf760615c3f90857a849eadf11cf80466d56259a25f006b15b3
+size 80014016

all_results.json

@@ -0,0 +1,13 @@
+{
+    "eval_loss": 2.0348782539367676,
+    "eval_runtime": 1.2317,
+    "eval_samples": 100,
+    "eval_samples_per_second": 4.059,
+    "eval_steps_per_second": 0.812,
+    "total_flos": 7336072979677184.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0077,
+    "train_samples": 898,
+    "train_samples_per_second": 25878.664,
+    "train_steps_per_second": 3136.808
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "allenai/scitulu-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 2.0348782539367676,
+    "eval_runtime": 1.2317,
+    "eval_samples": 100,
+    "eval_samples_per_second": 4.059,
+    "eval_steps_per_second": 0.812
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\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>",
+  "extra_special_tokens": {},
+  "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 @@
+{
+    "total_flos": 7336072979677184.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0077,
+    "train_samples": 898,
+    "train_samples_per_second": 25878.664,
+    "train_steps_per_second": 3136.808
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7058823529411766,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.5514968283268096,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 2.103,
+      "mean_token_accuracy": 0.6410358250141144,
+      "step": 1
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.5564948741796076,
+      "learning_rate": 0.0001955572805786141,
+      "loss": 1.95,
+      "mean_token_accuracy": 0.6562966406345367,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.2298309803009033,
+      "eval_mean_token_accuracy": 0.6953375414013863,
+      "eval_runtime": 1.1412,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 0.876,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.3550428109424067,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5318,
+      "mean_token_accuracy": 0.6940737068653107,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.15172839418805506,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 1.4025,
+      "mean_token_accuracy": 0.7238408386707306,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.040649652481079,
+      "eval_mean_token_accuracy": 0.6979705393314362,
+      "eval_runtime": 1.278,
+      "eval_samples_per_second": 3.912,
+      "eval_steps_per_second": 0.782,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.16155482865148485,
+      "learning_rate": 1.7376122568400532e-05,
+      "loss": 1.4263,
+      "mean_token_accuracy": 0.7188252657651901,
+      "step": 20
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "step": 24,
+      "total_flos": 7336072979677184.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.0077,
+      "train_samples_per_second": 25878.664,
+      "train_steps_per_second": 3136.808
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 7336072979677184.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15422a8cc312f27243bbe037d59674ce9812dd2538bb912d4172e959462e158
+size 7288