Model save

README.md

@@ -0,0 +1,60 @@
+---
+base_model: HuggingFaceTB/cosmo2-350M-webinst-sc2
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: cosmo2-350M-webinst-sc2-dpo-argilla-ep1
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/z5gb262b)
+# cosmo2-350M-webinst-sc2-dpo-argilla-ep1
+
+This model is a fine-tuned version of [HuggingFaceTB/cosmo2-350M-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-350M-webinst-sc2) on an unknown 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: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.985781990521327,
+    "total_flos": 0.0,
+    "train_loss": 0.6860739244864538,
+    "train_runtime": 316.322,
+    "train_samples": 6750,
+    "train_samples_per_second": 21.339,
+    "train_steps_per_second": 0.164
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "HuggingFaceTB/cosmo2-350M-webinst-sc2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c109192ffddcfc2be1ba4ae52a01e5713a98de94e98d90167e218aeebf919cc
+size 723674912

runs/Jul15_21-49-55_ip-26-0-167-245/events.out.tfevents.1721080291.ip-26-0-167-245.4053728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5dce01aa2e28781812105dc503156ef6f8285cc8c15e77a4b2f17cbfb8eb53
+size 9608

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "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|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.985781990521327,
+    "total_flos": 0.0,
+    "train_loss": 0.6860739244864538,
+    "train_runtime": 316.322,
+    "train_samples": 6750,
+    "train_samples_per_second": 21.339,
+    "train_steps_per_second": 0.164
+}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.985781990521327,
+  "eval_steps": 100,
+  "global_step": 52,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018957345971563982,
+      "grad_norm": 3.021558692298453,
+      "learning_rate": 8.333333333333333e-07,
+      "logits/chosen": -0.5616407990455627,
+      "logits/rejected": -0.42516714334487915,
+      "logps/chosen": -373.83282470703125,
+      "logps/rejected": -493.9554748535156,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 3.23447571449701,
+      "learning_rate": 4.907293218369499e-06,
+      "logits/chosen": -0.1685400903224945,
+      "logits/rejected": -0.19170813262462616,
+      "logps/chosen": -464.29693603515625,
+      "logps/rejected": -501.8587341308594,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4097222089767456,
+      "rewards/chosen": 0.0008683237829245627,
+      "rewards/margins": 0.0007554867188446224,
+      "rewards/rejected": 0.00011283738422207534,
+      "step": 10
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 3.9389946840001264,
+      "learning_rate": 3.941700805287169e-06,
+      "logits/chosen": -0.27595698833465576,
+      "logits/rejected": -0.21783480048179626,
+      "logps/chosen": -438.6907653808594,
+      "logps/rejected": -475.0658264160156,
+      "loss": 0.6894,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -0.003008360043168068,
+      "rewards/margins": 0.0011918289819732308,
+      "rewards/rejected": -0.00420018844306469,
+      "step": 20
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 3.2779169381175386,
+      "learning_rate": 2.3293939665883233e-06,
+      "logits/chosen": -0.012437907047569752,
+      "logits/rejected": -0.20707044005393982,
+      "logps/chosen": -476.6265563964844,
+      "logps/rejected": -474.9481506347656,
+      "loss": 0.6873,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.01446505170315504,
+      "rewards/margins": 0.007696834392845631,
+      "rewards/rejected": -0.02216188609600067,
+      "step": 30
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 2.8592366061141954,
+      "learning_rate": 7.936171419533653e-07,
+      "logits/chosen": -0.4586310386657715,
+      "logits/rejected": -0.5929983854293823,
+      "logps/chosen": -422.44293212890625,
+      "logps/rejected": -402.6429748535156,
+      "loss": 0.6827,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.018473980948328972,
+      "rewards/margins": 0.014362658374011517,
+      "rewards/rejected": -0.03283664211630821,
+      "step": 40
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 3.296382116125289,
+      "learning_rate": 2.3285134909173113e-08,
+      "logits/chosen": 0.08067023754119873,
+      "logits/rejected": 0.19673587381839752,
+      "logps/chosen": -483.49212646484375,
+      "logps/rejected": -536.2080688476562,
+      "loss": 0.679,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.017066333442926407,
+      "rewards/margins": 0.01992700807750225,
+      "rewards/rejected": -0.03699334338307381,
+      "step": 50
+    },
+    {
+      "epoch": 0.985781990521327,
+      "step": 52,
+      "total_flos": 0.0,
+      "train_loss": 0.6860739244864538,
+      "train_runtime": 316.322,
+      "train_samples_per_second": 21.339,
+      "train_steps_per_second": 0.164
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 52,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "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 sha256:753772c371abf783b3f96c5ddc2c75471f7281c7efc51b1f2c0c1b6ddd4988f7
+size 6520