SmolLM-360M-Instruct-dpo-16k

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM-360M-Instruct
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: SmolLM-360M-Instruct-dpo-16k
+  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. -->
+
+# SmolLM-360M-Instruct-dpo-16k
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8873
+- Rewards/chosen: 0.0047
+- Rewards/rejected: 0.3539
+- Rewards/accuracies: 0.0326
+- Rewards/margins: -0.3493
+- Logps/rejected: -470.7575
+- Logps/chosen: -546.0133
+- Logits/rejected: 0.3014
+- Logits/chosen: 0.6045
+
+## 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: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5225        | 0.9999 | 3368  | 0.8679          | 0.0092         | 0.3258           | 0.0337             | -0.3166         | -471.0385      | -545.9679    | 0.3212          | 0.6250        |
+| 0.4511        | 2.0    | 6737  | 0.8863          | 0.0171         | 0.3649           | 0.0283             | -0.3477         | -470.6477      | -545.8885    | 0.2889          | 0.5939        |
+| 0.4453        | 2.9999 | 10105 | 0.8880          | 0.0006         | 0.3516           | 0.0304             | -0.3510         | -470.7807      | -546.0537    | 0.3259          | 0.6291        |
+| 0.4439        | 4.0    | 13474 | 0.8894          | 0.0067         | 0.3598           | 0.0228             | -0.3531         | -470.6990      | -545.9932    | 0.2699          | 0.5815        |
+| 0.4441        | 4.9999 | 16842 | 0.8881          | 0.0058         | 0.3569           | 0.0293             | -0.3511         | -470.7278      | -546.0020    | 0.2999          | 0.6028        |
+| 0.4442        | 5.9991 | 20208 | 0.8873          | 0.0047         | 0.3539           | 0.0326             | -0.3493         | -470.7575      | -546.0133    | 0.3014          | 0.6045        |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.2.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM-360M-Instruct",
+  "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": "4.41.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_new_tokens": 40,
+  "pad_token_id": 2,
+  "transformers_version": "4.41.0"
+}

logs/evaluation_data/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e279d6438642c72a3f2bcb8a85ee7d146c084c3aee6bed8d67382dec817e8c2
+size 4200008

logs/evaluation_data/dataset_info.json

@@ -0,0 +1,46 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "test-dpo-plaba",
+  "dataset_size": 4033369,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/dmariko/test-dpo-plaba@df3f28196a1828595fc34a68a7903693de3f4dac/data/train-00000-of-00001.parquet": {
+      "num_bytes": 1846723,
+      "checksum": null
+    }
+  },
+  "download_size": 1846723,
+  "features": {
+    "prompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "chosen": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "rejected": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 5880092,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 4033369,
+      "num_examples": 921,
+      "dataset_name": "test-dpo-plaba"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

logs/evaluation_data/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "9fbf7da8a292f424",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

logs/training_args.json

@@ -0,0 +1 @@
+{"output_dir": "SmolLM-360M-Instruct-dpo-16k", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "eval_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 2, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 2, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 5e-06, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 6, "max_steps": -1, "lr_scheduler_type": "cosine", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 2, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "SmolLM-360M-Instruct-dpo-16k/runs/Sep11_18-08-40_ip-172-16-93-96.eu-west-1.compute.internal", "logging_strategy": "epoch", "logging_first_step": false, "logging_steps": 1, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "SmolLM-360M-Instruct-dpo-16k", "disable_tqdm": false, "remove_unused_columns": false, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": {"split_batches": false, "dispatch_batches": null, "even_batches": true, "use_seedable_sampler": true, "non_blocking": false, "gradient_accumulation_kwargs": null}, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "paged_adamw_32bit", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": {"use_reentrant": false}, "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": null, "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false}

logs/training_data/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2292d7ceaf1c87890c4be79a2be8e6e048d3117be8ab511d99495c947fa61385
+size 47906296

logs/training_data/dataset_info.json

@@ -0,0 +1,46 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "test-dpo",
+  "dataset_size": 52930157,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/dmariko/test-dpo@73d3c2ff5fe5b5dab3d2019469a00d00bdfb0742/data/train-00000-of-00001.parquet": {
+      "num_bytes": 25553882,
+      "checksum": null
+    }
+  },
+  "download_size": 25553882,
+  "features": {
+    "prompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "chosen": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "rejected": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 78484039,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 52930157,
+      "num_examples": 14954,
+      "dataset_name": "test-dpo"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

logs/training_data/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "85df5ed416154a2b",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b41f9492973ff642a1599f3566393c47f227fc9c7c3cc79c90bf78b8997065
+size 723674912

runs/Sep11_18-08-40_ip-172-16-93-96.eu-west-1.compute.internal/events.out.tfevents.1726078190.ip-172-16-93-96.eu-west-1.compute.internal.23166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c17050487340751900e2b14589a7167045e458745e6eed7a57ad3710c7a14c7
+size 13969

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "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": "<|im_end|>",
+  "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24f4543a30df0b19abb3a048eb5094ab6aae933a6073d6ec2773a336e3c9d28
+size 5176