Upload folder using huggingface_hub

models/hh_rlhf/pythia-410m/2024-05-07_04:26/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

models/hh_rlhf/pythia-410m/2024-05-07_04:26/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.38.2"
+}

models/hh_rlhf/pythia-410m/2024-05-07_04:26/metrics.json

@@ -0,0 +1 @@
+{"eval_loss": 0.827226459980011, "eval_runtime": 866.0191, "eval_samples_per_second": 9.875, "eval_steps_per_second": 1.234, "eval_rewards/chosen": -1.4319628477096558, "eval_rewards/rejected": -1.502548098564148, "eval_rewards/accuracies": 0.5213984847068787, "eval_rewards/margins": 0.07058533281087875, "eval_logps/rejected": -161.97439575195312, "eval_logps/chosen": -167.0337371826172, "eval_logits/rejected": -0.032409653067588806, "eval_logits/chosen": -0.04287682846188545, "epoch": 0.25}

models/hh_rlhf/pythia-410m/2024-05-07_04:26/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17032eae514624f7bd15cce60b693056e65282609555b95aafecddf3c40aa90e
+size 810702192

models/hh_rlhf/pythia-410m/2024-05-07_04:26/training_args.json

@@ -0,0 +1 @@
+{"output_dir": "./test", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "evaluation_strategy": "steps", "prediction_loss_only": false, "per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 3e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": 5000, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "./test/runs/May07_02-24-12_a66c464a5008", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 500, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": 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": 3000, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "./test", "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}, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_hf", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "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": true, "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": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "fp16_backend": "auto", "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}