Upload 14 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77aff4290a4cc52d71f0dde3425ad8cd7aba3cbc61c62b9f38c5a1658b113a1d
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90a74b6f2804dc63003d5d3383e01e31a4d1b41a54eb11fe22b1cd8abd13d00
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372010c33f15d586b91174490010376899886b6fb8f25f6df4ad722a385ca854
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468c7deb41f53c0d0b135af65f6e03d06758293f4a8fceff1aa7408685b2495c
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_full_config.json

@@ -0,0 +1,14 @@
+{
+  "model_max_length": 1024,
+  "padding_side": "right",
+  "pad_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "gpt2",
+  "tokenizer_class": "GPT2Tokenizer",
+  "special_tokens": {
+    "bos_token": "<|endoftext|>",
+    "eos_token": "<|endoftext|>",
+    "unk_token": "<|endoftext|>",
+    "pad_token": "<|endoftext|>"
+  }
+}

trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": 3.256429433822632,
+  "best_model_checkpoint": "/content/drive/MyDrive/Hugh Mann/GPT2/GPT2-LyricsDec8/checkpoint-1600",
+  "epoch": 9.907120743034056,
+  "eval_steps": 100,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6191950464396285,
+      "grad_norm": 7.51154088973999,
+      "learning_rate": 9.7e-06,
+      "loss": 3.9524,
+      "step": 100
+    },
+    {
+      "epoch": 0.6191950464396285,
+      "eval_loss": 3.506685733795166,
+      "eval_runtime": 2.2552,
+      "eval_samples_per_second": 254.077,
+      "eval_steps_per_second": 15.963,
+      "step": 100
+    },
+    {
+      "epoch": 1.238390092879257,
+      "grad_norm": 6.163869857788086,
+      "learning_rate": 9.58099352051836e-06,
+      "loss": 3.598,
+      "step": 200
+    },
+    {
+      "epoch": 1.238390092879257,
+      "eval_loss": 3.4033825397491455,
+      "eval_runtime": 2.2344,
+      "eval_samples_per_second": 256.441,
+      "eval_steps_per_second": 16.111,
+      "step": 200
+    },
+    {
+      "epoch": 1.8575851393188856,
+      "grad_norm": 5.917358875274658,
+      "learning_rate": 9.14902807775378e-06,
+      "loss": 3.5138,
+      "step": 300
+    },
+    {
+      "epoch": 1.8575851393188856,
+      "eval_loss": 3.360402822494507,
+      "eval_runtime": 2.2391,
+      "eval_samples_per_second": 255.912,
+      "eval_steps_per_second": 16.078,
+      "step": 300
+    },
+    {
+      "epoch": 2.476780185758514,
+      "grad_norm": 5.890804290771484,
+      "learning_rate": 8.717062634989202e-06,
+      "loss": 3.4766,
+      "step": 400
+    },
+    {
+      "epoch": 2.476780185758514,
+      "eval_loss": 3.3368523120880127,
+      "eval_runtime": 2.2358,
+      "eval_samples_per_second": 256.287,
+      "eval_steps_per_second": 16.102,
+      "step": 400
+    },
+    {
+      "epoch": 3.0959752321981426,
+      "grad_norm": 6.225989818572998,
+      "learning_rate": 8.285097192224622e-06,
+      "loss": 3.4229,
+      "step": 500
+    },
+    {
+      "epoch": 3.0959752321981426,
+      "eval_loss": 3.319918394088745,
+      "eval_runtime": 2.2394,
+      "eval_samples_per_second": 255.87,
+      "eval_steps_per_second": 16.076,
+      "step": 500
+    },
+    {
+      "epoch": 3.715170278637771,
+      "grad_norm": 6.0069499015808105,
+      "learning_rate": 7.853131749460043e-06,
+      "loss": 3.4022,
+      "step": 600
+    },
+    {
+      "epoch": 3.715170278637771,
+      "eval_loss": 3.306849718093872,
+      "eval_runtime": 2.3091,
+      "eval_samples_per_second": 248.153,
+      "eval_steps_per_second": 15.591,
+      "step": 600
+    },
+    {
+      "epoch": 4.3343653250774,
+      "grad_norm": 7.3684492111206055,
+      "learning_rate": 7.4211663066954655e-06,
+      "loss": 3.3725,
+      "step": 700
+    },
+    {
+      "epoch": 4.3343653250774,
+      "eval_loss": 3.297823667526245,
+      "eval_runtime": 2.2288,
+      "eval_samples_per_second": 257.086,
+      "eval_steps_per_second": 16.152,
+      "step": 700
+    },
+    {
+      "epoch": 4.953560371517028,
+      "grad_norm": 6.168036460876465,
+      "learning_rate": 6.989200863930886e-06,
+      "loss": 3.3689,
+      "step": 800
+    },
+    {
+      "epoch": 4.953560371517028,
+      "eval_loss": 3.2880301475524902,
+      "eval_runtime": 2.226,
+      "eval_samples_per_second": 257.41,
+      "eval_steps_per_second": 16.172,
+      "step": 800
+    },
+    {
+      "epoch": 5.572755417956657,
+      "grad_norm": 6.212117671966553,
+      "learning_rate": 6.557235421166307e-06,
+      "loss": 3.3332,
+      "step": 900
+    },
+    {
+      "epoch": 5.572755417956657,
+      "eval_loss": 3.2826037406921387,
+      "eval_runtime": 2.2453,
+      "eval_samples_per_second": 255.204,
+      "eval_steps_per_second": 16.034,
+      "step": 900
+    },
+    {
+      "epoch": 6.191950464396285,
+      "grad_norm": 5.847946643829346,
+      "learning_rate": 6.125269978401729e-06,
+      "loss": 3.3367,
+      "step": 1000
+    },
+    {
+      "epoch": 6.191950464396285,
+      "eval_loss": 3.276566505432129,
+      "eval_runtime": 2.2355,
+      "eval_samples_per_second": 256.315,
+      "eval_steps_per_second": 16.104,
+      "step": 1000
+    },
+    {
+      "epoch": 6.811145510835914,
+      "grad_norm": 6.364712238311768,
+      "learning_rate": 5.6933045356371494e-06,
+      "loss": 3.3289,
+      "step": 1100
+    },
+    {
+      "epoch": 6.811145510835914,
+      "eval_loss": 3.272658348083496,
+      "eval_runtime": 2.2297,
+      "eval_samples_per_second": 256.986,
+      "eval_steps_per_second": 16.146,
+      "step": 1100
+    },
+    {
+      "epoch": 7.430340557275541,
+      "grad_norm": 5.989032745361328,
+      "learning_rate": 5.261339092872571e-06,
+      "loss": 3.3134,
+      "step": 1200
+    },
+    {
+      "epoch": 7.430340557275541,
+      "eval_loss": 3.2689383029937744,
+      "eval_runtime": 2.2577,
+      "eval_samples_per_second": 253.799,
+      "eval_steps_per_second": 15.945,
+      "step": 1200
+    },
+    {
+      "epoch": 8.04953560371517,
+      "grad_norm": 6.310012340545654,
+      "learning_rate": 4.829373650107992e-06,
+      "loss": 3.2967,
+      "step": 1300
+    },
+    {
+      "epoch": 8.04953560371517,
+      "eval_loss": 3.265749216079712,
+      "eval_runtime": 2.247,
+      "eval_samples_per_second": 255.004,
+      "eval_steps_per_second": 16.021,
+      "step": 1300
+    },
+    {
+      "epoch": 8.6687306501548,
+      "grad_norm": 6.473470211029053,
+      "learning_rate": 4.397408207343413e-06,
+      "loss": 3.2846,
+      "step": 1400
+    },
+    {
+      "epoch": 8.6687306501548,
+      "eval_loss": 3.2619001865386963,
+      "eval_runtime": 2.2395,
+      "eval_samples_per_second": 255.862,
+      "eval_steps_per_second": 16.075,
+      "step": 1400
+    },
+    {
+      "epoch": 9.287925696594428,
+      "grad_norm": 6.593929767608643,
+      "learning_rate": 3.965442764578834e-06,
+      "loss": 3.2858,
+      "step": 1500
+    },
+    {
+      "epoch": 9.287925696594428,
+      "eval_loss": 3.2583212852478027,
+      "eval_runtime": 2.2458,
+      "eval_samples_per_second": 255.144,
+      "eval_steps_per_second": 16.03,
+      "step": 1500
+    },
+    {
+      "epoch": 9.907120743034056,
+      "grad_norm": 6.568899154663086,
+      "learning_rate": 3.5334773218142552e-06,
+      "loss": 3.2755,
+      "step": 1600
+    },
+    {
+      "epoch": 9.907120743034056,
+      "eval_loss": 3.256429433822632,
+      "eval_runtime": 2.2439,
+      "eval_samples_per_second": 255.355,
+      "eval_steps_per_second": 16.043,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2415,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3347580870656e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ffa1ba06ce21ab77fb40cb76067e70f1f7fb76ae1d4e6b7cbba1d2fe02ca2e
+size 5368

training_args_full.json

@@ -0,0 +1,148 @@
+{
+  "output_dir": "/content/drive/MyDrive/Hugh Mann/GPT2/GPT2-LyricsDec8",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 16,
+  "per_device_eval_batch_size": 16,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 1e-05,
+  "weight_decay": 0.01,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 15,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.0,
+  "warmup_steps": 100,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/content/drive/MyDrive/Hugh Mann/GPT2/GPT2-LyricsDec8/runs/Dec09_17-32-33_dec940e50fe7",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 100,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 100,
+  "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": false,
+  "fp16": true,
+  "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": 100,
+  "dataloader_num_workers": 0,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/content/drive/MyDrive/Hugh Mann/GPT2/GPT2-LyricsDec8",
+  "disable_tqdm": false,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "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": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard",
+    "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": 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": false,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "evaluation_strategy": "steps",
+  "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,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false
+}