Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_more_function_42
+  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. -->
+
+# GPT2_more_function_42
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3530
+- Accuracy: 0.2670
+
+## 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: 0.0001
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10000
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 5.6351        | 1.0   | 6417  | 5.4097          | 0.1894   |
+| 4.9863        | 2.0   | 12834 | 4.8426          | 0.2244   |
+| 4.7136        | 3.0   | 19251 | 4.6423          | 0.2405   |
+| 4.584         | 4.0   | 25668 | 4.5398          | 0.2492   |
+| 4.4834        | 5.0   | 32085 | 4.4778          | 0.2548   |
+| 4.4098        | 6.0   | 38502 | 4.4340          | 0.2588   |
+| 4.3491        | 7.0   | 44919 | 4.4003          | 0.2622   |
+| 4.2949        | 8.0   | 51336 | 4.3788          | 0.2642   |
+| 4.2459        | 9.0   | 57753 | 4.3607          | 0.2667   |
+| 4.2045        | 10.0  | 64170 | 4.3530          | 0.2670   |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.9.1+cu128
+- Datasets 4.1.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2669818944387677,
+    "eval_loss": 4.352972984313965,
+    "eval_runtime": 1.9443,
+    "eval_samples": 1179,
+    "eval_samples_per_second": 606.385,
+    "eval_steps_per_second": 5.143,
+    "perplexity": 77.70914792173406,
+    "train_loss": 4.696024066056532,
+    "train_runtime": 27954.6258,
+    "train_samples": 821300,
+    "train_samples_per_second": 293.798,
+    "train_steps_per_second": 2.296
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_more_function_42",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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": 128,
+  "pad_token_id": 1,
+  "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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2669818944387677,
+    "eval_loss": 4.352972984313965,
+    "eval_runtime": 1.9443,
+    "eval_samples": 1179,
+    "eval_samples_per_second": 606.385,
+    "eval_steps_per_second": 5.143,
+    "perplexity": 77.70914792173406
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.30.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc29cf47f00c50c70d7b3484a5cb493e44e322213fe9b3646ef3f1ebb19584c
+size 441329395

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "token": null,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 4.696024066056532,
+    "train_runtime": 27954.6258,
+    "train_samples": 821300,
+    "train_samples_per_second": 293.798,
+    "train_steps_per_second": 2.296
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 4.352972984313965,
+  "best_model_checkpoint": "models/GPT2_more_function_42/checkpoint-64170",
+  "epoch": 10.0,
+  "global_step": 64170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 8.1748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 6.8699,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 6.4168,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 6.0866,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 5.833,
+      "step": 5000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6e-05,
+      "loss": 5.6351,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.18935705555889484,
+      "eval_loss": 5.409687519073486,
+      "eval_runtime": 1.9348,
+      "eval_samples_per_second": 609.359,
+      "eval_steps_per_second": 5.168,
+      "step": 6417
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 5.4639,
+      "step": 7000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8e-05,
+      "loss": 5.329,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 5.2228,
+      "step": 9000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001,
+      "loss": 5.1325,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.815580579656637e-05,
+      "loss": 5.0529,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.630976555288906e-05,
+      "loss": 4.9863,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.22439943098715714,
+      "eval_loss": 4.842624187469482,
+      "eval_runtime": 1.9956,
+      "eval_samples_per_second": 590.792,
+      "eval_steps_per_second": 5.011,
+      "step": 12834
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.446557134945542e-05,
+      "loss": 4.9242,
+      "step": 13000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.26195311057781e-05,
+      "loss": 4.8479,
+      "step": 14000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.077533690234448e-05,
+      "loss": 4.8167,
+      "step": 15000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.892929665866716e-05,
+      "loss": 4.7852,
+      "step": 16000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.708510245523353e-05,
+      "loss": 4.7617,
+      "step": 17000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.523906221155622e-05,
+      "loss": 4.7371,
+      "step": 18000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.339486800812258e-05,
+      "loss": 4.7136,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.24054817575284004,
+      "eval_loss": 4.642277240753174,
+      "eval_runtime": 2.2287,
+      "eval_samples_per_second": 529.009,
+      "eval_steps_per_second": 4.487,
+      "step": 19251
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 8.154882776444527e-05,
+      "loss": 4.6459,
+      "step": 20000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 7.970463356101163e-05,
+      "loss": 4.6241,
+      "step": 21000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 7.785859331733432e-05,
+      "loss": 4.6143,
+      "step": 22000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 7.60143991139007e-05,
+      "loss": 4.6051,
+      "step": 23000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 7.416835887022337e-05,
+      "loss": 4.5945,
+      "step": 24000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 7.232416466678975e-05,
+      "loss": 4.584,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24919690382213674,
+      "eval_loss": 4.539839267730713,
+      "eval_runtime": 1.952,
+      "eval_samples_per_second": 603.996,
+      "eval_steps_per_second": 5.123,
+      "step": 25668
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 7.047812442311242e-05,
+      "loss": 4.5485,
+      "step": 26000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 6.863393021967878e-05,
+      "loss": 4.501,
+      "step": 27000
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.678788997600149e-05,
+      "loss": 4.5013,
+      "step": 28000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.494369577256785e-05,
+      "loss": 4.4983,
+      "step": 29000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.309765552889054e-05,
+      "loss": 4.4939,
+      "step": 30000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 6.12534613254569e-05,
+      "loss": 4.4905,
+      "step": 31000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 5.940742108177959e-05,
+      "loss": 4.4834,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.25477349682434736,
+      "eval_loss": 4.477753639221191,
+      "eval_runtime": 1.951,
+      "eval_samples_per_second": 604.311,
+      "eval_steps_per_second": 5.126,
+      "step": 32085
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 5.7563226878345955e-05,
+      "loss": 4.4151,
+      "step": 33000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 5.571718663466864e-05,
+      "loss": 4.4147,
+      "step": 34000
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 5.3872992431235006e-05,
+      "loss": 4.4158,
+      "step": 35000
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 5.202695218755769e-05,
+      "loss": 4.4175,
+      "step": 36000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 5.018275798412405e-05,
+      "loss": 4.4135,
+      "step": 37000
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 4.833671774044675e-05,
+      "loss": 4.4098,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.25882737940200223,
+      "eval_loss": 4.433998107910156,
+      "eval_runtime": 1.9481,
+      "eval_samples_per_second": 605.217,
+      "eval_steps_per_second": 5.133,
+      "step": 38502
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 4.6492523537013114e-05,
+      "loss": 4.3737,
+      "step": 39000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 4.46464832933358e-05,
+      "loss": 4.344,
+      "step": 40000
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 4.2802289089902164e-05,
+      "loss": 4.3508,
+      "step": 41000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 4.095624884622485e-05,
+      "loss": 4.3525,
+      "step": 42000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 3.9112054642791215e-05,
+      "loss": 4.3499,
+      "step": 43000
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 3.7266014399113905e-05,
+      "loss": 4.3491,
+      "step": 44000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.26216665664883493,
+      "eval_loss": 4.400253772735596,
+      "eval_runtime": 1.9465,
+      "eval_samples_per_second": 605.701,
+      "eval_steps_per_second": 5.137,
+      "step": 44919
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 3.5421820195680266e-05,
+      "loss": 4.3435,
+      "step": 45000
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 3.3575779952002956e-05,
+      "loss": 4.2852,
+      "step": 46000
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 3.173158574856932e-05,
+      "loss": 4.293,
+      "step": 47000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 2.988554550489201e-05,
+      "loss": 4.292,
+      "step": 48000
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 2.8041351301458374e-05,
+      "loss": 4.296,
+      "step": 49000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 2.6195311057781064e-05,
+      "loss": 4.2944,
+      "step": 50000
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 2.4351116854347424e-05,
+      "loss": 4.2949,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.26415686588794723,
+      "eval_loss": 4.378811359405518,
+      "eval_runtime": 1.9499,
+      "eval_samples_per_second": 604.653,
+      "eval_steps_per_second": 5.129,
+      "step": 51336
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 2.2505076610670114e-05,
+      "loss": 4.2537,
+      "step": 52000
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 2.0660882407236478e-05,
+      "loss": 4.2437,
+      "step": 53000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 1.8814842163559165e-05,
+      "loss": 4.2463,
+      "step": 54000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 1.6970647960125532e-05,
+      "loss": 4.2466,
+      "step": 55000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 1.5124607716448219e-05,
+      "loss": 4.2481,
+      "step": 56000
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 1.3280413513014583e-05,
+      "loss": 4.2459,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2666880380410464,
+      "eval_loss": 4.360716819763184,
+      "eval_runtime": 1.9472,
+      "eval_samples_per_second": 605.483,
+      "eval_steps_per_second": 5.136,
+      "step": 57753
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 1.1434373269337271e-05,
+      "loss": 4.234,
+      "step": 58000
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 9.590179065903637e-06,
+      "loss": 4.2034,
+      "step": 59000
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 7.744138822226325e-06,
+      "loss": 4.2049,
+      "step": 60000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 5.899944618792691e-06,
+      "loss": 4.2057,
+      "step": 61000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 4.0539043751153775e-06,
+      "loss": 4.2062,
+      "step": 62000
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 2.209710171681743e-06,
+      "loss": 4.2061,
+      "step": 63000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 3.636699280044305e-07,
+      "loss": 4.2045,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2669818944387677,
+      "eval_loss": 4.352972984313965,
+      "eval_runtime": 1.9405,
+      "eval_samples_per_second": 607.582,
+      "eval_steps_per_second": 5.153,
+      "step": 64170
+    },
+    {
+      "epoch": 10.0,
+      "step": 64170,
+      "total_flos": 5.36497864704e+17,
+      "train_loss": 4.696024066056532,
+      "train_runtime": 27954.6258,
+      "train_samples_per_second": 293.798,
+      "train_steps_per_second": 2.296
+    }
+  ],
+  "max_steps": 64170,
+  "num_train_epochs": 10,
+  "total_flos": 5.36497864704e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc08c539fa2d96e7dd937dc8259020bd829a6796393d71dcb4a71d8ff84b8cab
+size 4881