Upload 14 files

README.md

@@ -1,3 +1,56 @@
 ---
-license: openrail
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wp_med
+  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. -->
+
+# wp_med
+
+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: 4.6055
+- Accuracy: 0.3032
+
+## 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: 8
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.30.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.31,
+    "eval_accuracy": 0.30315584561438536,
+    "eval_loss": 4.605535507202148,
+    "eval_runtime": 50.5416,
+    "eval_samples": 631,
+    "eval_samples_per_second": 12.485,
+    "eval_steps_per_second": 0.396,
+    "perplexity": 100.03653879519784,
+    "train_loss": 0.0,
+    "train_runtime": 72.3486,
+    "train_samples": 12194,
+    "train_samples_per_second": 505.635,
+    "train_steps_per_second": 63.235
+}

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": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.31,
+    "eval_accuracy": 0.30315584561438536,
+    "eval_loss": 4.605535507202148,
+    "eval_runtime": 50.5416,
+    "eval_samples": 631,
+    "eval_samples_per_second": 12.485,
+    "eval_steps_per_second": 0.396,
+    "perplexity": 100.03653879519784
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767f1a5b406c90574d0343673f414e07d84835fb799e37940a028af6c11957c5
+size 1419387869

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.31,
+    "train_loss": 0.0,
+    "train_runtime": 72.3486,
+    "train_samples": 12194,
+    "train_samples_per_second": 505.635,
+    "train_steps_per_second": 63.235
+}

trainer_state.json

@@ -0,0 +1,235 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.31358073359972766,
+  "global_step": 17500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.985067584114299e-05,
+      "loss": 2.6076,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.970135168228597e-05,
+      "loss": 2.5834,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.955202752342896e-05,
+      "loss": 2.5955,
+      "step": 1500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.940270336457195e-05,
+      "loss": 2.5908,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.925337920571494e-05,
+      "loss": 2.5974,
+      "step": 2500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9104055046857924e-05,
+      "loss": 3.0537,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.895473088800091e-05,
+      "loss": 3.0324,
+      "step": 3500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.88054067291439e-05,
+      "loss": 3.0167,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.865608257028688e-05,
+      "loss": 3.0234,
+      "step": 4500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.850675841142987e-05,
+      "loss": 3.0113,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.835743425257286e-05,
+      "loss": 3.0151,
+      "step": 5500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8208110093715845e-05,
+      "loss": 2.9967,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.805878593485883e-05,
+      "loss": 2.998,
+      "step": 6500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.790946177600182e-05,
+      "loss": 2.9781,
+      "step": 7000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.776013761714481e-05,
+      "loss": 2.9997,
+      "step": 7500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.761081345828779e-05,
+      "loss": 2.9812,
+      "step": 8000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.746148929943078e-05,
+      "loss": 2.97,
+      "step": 8500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7312165140573766e-05,
+      "loss": 2.9958,
+      "step": 9000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7162840981716754e-05,
+      "loss": 2.9818,
+      "step": 9500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7013516822859735e-05,
+      "loss": 2.973,
+      "step": 10000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.686419266400272e-05,
+      "loss": 2.9652,
+      "step": 10500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.671486850514572e-05,
+      "loss": 2.9503,
+      "step": 11000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.65655443462887e-05,
+      "loss": 2.9483,
+      "step": 11500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.641622018743169e-05,
+      "loss": 2.9592,
+      "step": 12000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.6266896028574675e-05,
+      "loss": 2.9615,
+      "step": 12500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.611757186971766e-05,
+      "loss": 2.9652,
+      "step": 13000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.5968247710860644e-05,
+      "loss": 2.9406,
+      "step": 13500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.581892355200363e-05,
+      "loss": 2.9328,
+      "step": 14000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.566959939314662e-05,
+      "loss": 2.939,
+      "step": 14500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.552027523428961e-05,
+      "loss": 2.9252,
+      "step": 15000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.5370951075432596e-05,
+      "loss": 2.9352,
+      "step": 15500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.5221626916575584e-05,
+      "loss": 2.9564,
+      "step": 16000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.5072302757718565e-05,
+      "loss": 2.943,
+      "step": 16500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.492297859886155e-05,
+      "loss": 2.9285,
+      "step": 17000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.477365444000454e-05,
+      "loss": 2.929,
+      "step": 17500
+    },
+    {
+      "epoch": 0.31,
+      "step": 17500,
+      "total_flos": 3.250452430848e+16,
+      "train_loss": 0.0,
+      "train_runtime": 72.3486,
+      "train_samples_per_second": 505.635,
+      "train_steps_per_second": 63.235
+    }
+  ],
+  "max_steps": 4575,
+  "num_train_epochs": 3,
+  "total_flos": 3.250452430848e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec1d37572bb2b60f9d09cf9fcc3e26cd309de0f5346c75112e857e7fe03ad5e
+size 3899