Upload 12 files

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: checkpoint_gpt2-medium_lyrics_meaning_2022-03-10-16-16-32
+  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. -->
+
+# checkpoint_gpt2-medium_lyrics_meaning_2022-03-10-16-16-32
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5896
+- Accuracy: 0.4923
+
+## 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-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.7781        | 1.01  | 128  | 2.6284          | 0.4875   |
+| 2.6217        | 2.02  | 256  | 2.6022          | 0.4908   |
+| 2.569         | 3.02  | 384  | 2.5928          | 0.4917   |
+
+
+### Framework versions
+
+- Transformers 4.18.0.dev0
+- Pytorch 1.10.1
+- Datasets 1.18.3
+- Tokenizers 0.11.6

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.49230193310949055,
+    "eval_loss": 2.589608907699585,
+    "eval_runtime": 70.704,
+    "eval_samples": 1021,
+    "eval_samples_per_second": 14.44,
+    "eval_steps_per_second": 1.81,
+    "perplexity": 13.324559451438118
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d19048d74dcd3fce959448487e9e32a5eaa54cd7e5ffe24862643f364450ac9
+size 1444582489

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 2.6286109864242433,
+    "train_runtime": 3384.5609,
+    "train_samples": 4064,
+    "train_samples_per_second": 4.803,
+    "train_steps_per_second": 0.15
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 508,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.740157480314961e-05,
+      "loss": 2.7781,
+      "step": 128
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.4874660477958952,
+      "eval_loss": 2.6284313201904297,
+      "eval_runtime": 69.4322,
+      "eval_samples_per_second": 14.705,
+      "eval_steps_per_second": 1.844,
+      "step": 128
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.4803149606299215e-05,
+      "loss": 2.6217,
+      "step": 256
+    },
+    {
+      "epoch": 2.02,
+      "eval_accuracy": 0.49078252111331633,
+      "eval_loss": 2.6022448539733887,
+      "eval_runtime": 70.8747,
+      "eval_samples_per_second": 14.406,
+      "eval_steps_per_second": 1.806,
+      "step": 256
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 1.220472440944882e-05,
+      "loss": 2.569,
+      "step": 384
+    },
+    {
+      "epoch": 3.02,
+      "eval_accuracy": 0.49170738058924846,
+      "eval_loss": 2.5927629470825195,
+      "eval_runtime": 76.8807,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.665,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "step": 508,
+      "total_flos": 3.0193916980494336e+16,
+      "train_loss": 2.6286109864242433,
+      "train_runtime": 3384.5609,
+      "train_samples_per_second": 4.803,
+      "train_steps_per_second": 0.15
+    }
+  ],
+  "max_steps": 508,
+  "num_train_epochs": 4,
+  "total_flos": 3.0193916980494336e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef767971109884443aa3fbe5fdc2fe385a2b6e6f54a82d6cee943d7408da89a6
+size 3183