Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_natural_function_67
+  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_natural_function_67
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.6758
+- Accuracy: 0.3762
+
+## 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: 67
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 4.9145        | 1.0   | 6439  | 4.6882          | 0.2902   |
+| 4.2877        | 2.0   | 12878 | 4.1479          | 0.3278   |
+| 4.0279        | 3.0   | 19317 | 3.9541          | 0.3454   |
+| 3.9003        | 4.0   | 25756 | 3.8561          | 0.3553   |
+| 3.8034        | 5.0   | 32195 | 3.7953          | 0.3616   |
+| 3.731         | 6.0   | 38634 | 3.7539          | 0.3663   |
+| 3.6709        | 7.0   | 45073 | 3.7236          | 0.3700   |
+| 3.6162        | 8.0   | 51512 | 3.7010          | 0.3734   |
+| 3.5698        | 9.0   | 57951 | 3.6846          | 0.3751   |
+| 3.5258        | 10.0  | 64390 | 3.6758          | 0.3762   |
+
+
+### 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": 0.3762155470211194,
+    "eval_loss": 3.675755739212036,
+    "eval_runtime": 2.0024,
+    "eval_samples": 1183,
+    "eval_samples_per_second": 590.784,
+    "eval_steps_per_second": 4.994,
+    "perplexity": 39.47848102227569,
+    "train_loss": 4.008237893900936,
+    "train_runtime": 29754.0363,
+    "train_samples": 824154,
+    "train_samples_per_second": 276.989,
+    "train_steps_per_second": 2.164
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_natural_function_67",
+  "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": 0.3762155470211194,
+    "eval_loss": 3.675755739212036,
+    "eval_runtime": 2.0024,
+    "eval_samples": 1183,
+    "eval_samples_per_second": 590.784,
+    "eval_steps_per_second": 4.994,
+    "perplexity": 39.47848102227569
+}

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:b2e5db6627fa25967ed39cdbf558593be65ec0869516a49a6f9d5156f1e6a32e
+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": 4.008237893900936,
+    "train_runtime": 29754.0363,
+    "train_samples": 824154,
+    "train_samples_per_second": 276.989,
+    "train_steps_per_second": 2.164
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 3.675755739212036,
+  "best_model_checkpoint": "models/GPT2_natural_function_67/checkpoint-64390",
+  "epoch": 10.0,
+  "global_step": 64390,
+  "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": 7.5832,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 6.0927,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 5.6579,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 5.3482,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 5.1066,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6e-05,
+      "loss": 4.9145,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.29016047550269236,
+      "eval_loss": 4.688190937042236,
+      "eval_runtime": 1.9998,
+      "eval_samples_per_second": 591.551,
+      "eval_steps_per_second": 5.0,
+      "step": 6439
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 4.7467,
+      "step": 7000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 8e-05,
+      "loss": 4.6193,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 4.5146,
+      "step": 9000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0001,
+      "loss": 4.4312,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.816326530612245e-05,
+      "loss": 4.3532,
+      "step": 11000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 9.632469203897775e-05,
+      "loss": 4.2877,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.32783993716761733,
+      "eval_loss": 4.14790153503418,
+      "eval_runtime": 2.0061,
+      "eval_samples_per_second": 589.709,
+      "eval_steps_per_second": 4.985,
+      "step": 12878
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.448795734510021e-05,
+      "loss": 4.2314,
+      "step": 13000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.264938407795552e-05,
+      "loss": 4.1519,
+      "step": 14000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.081264938407796e-05,
+      "loss": 4.1216,
+      "step": 15000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.897407611693326e-05,
+      "loss": 4.0984,
+      "step": 16000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 8.713734142305572e-05,
+      "loss": 4.0698,
+      "step": 17000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.529876815591101e-05,
+      "loss": 4.049,
+      "step": 18000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.346203346203346e-05,
+      "loss": 4.0279,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3453651133844956,
+      "eval_loss": 3.954080820083618,
+      "eval_runtime": 2.0088,
+      "eval_samples_per_second": 588.916,
+      "eval_steps_per_second": 4.978,
+      "step": 19317
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 8.162346019488876e-05,
+      "loss": 3.9655,
+      "step": 20000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 7.978672550101122e-05,
+      "loss": 3.9369,
+      "step": 21000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.794815223386652e-05,
+      "loss": 3.9293,
+      "step": 22000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 7.611325611325611e-05,
+      "loss": 3.9213,
+      "step": 23000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 7.427468284611142e-05,
+      "loss": 3.9107,
+      "step": 24000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 7.243610957896673e-05,
+      "loss": 3.9003,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3553157926265134,
+      "eval_loss": 3.856142044067383,
+      "eval_runtime": 2.0123,
+      "eval_samples_per_second": 587.87,
+      "eval_steps_per_second": 4.969,
+      "step": 25756
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 7.059937488508918e-05,
+      "loss": 3.8711,
+      "step": 26000
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 6.876080161794448e-05,
+      "loss": 3.8186,
+      "step": 27000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 6.692406692406693e-05,
+      "loss": 3.8207,
+      "step": 28000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 6.508549365692223e-05,
+      "loss": 3.8165,
+      "step": 29000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 6.324692038977753e-05,
+      "loss": 3.8114,
+      "step": 30000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 6.141018569589998e-05,
+      "loss": 3.8074,
+      "step": 31000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 5.957161242875529e-05,
+      "loss": 3.8034,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.36155243908120954,
+      "eval_loss": 3.7953288555145264,
+      "eval_runtime": 1.9992,
+      "eval_samples_per_second": 591.726,
+      "eval_steps_per_second": 5.002,
+      "step": 32195
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 5.7734877734877734e-05,
+      "loss": 3.7432,
+      "step": 33000
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 5.589630446773304e-05,
+      "loss": 3.7348,
+      "step": 34000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 5.4057731200588346e-05,
+      "loss": 3.7356,
+      "step": 35000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 5.222099650671079e-05,
+      "loss": 3.7344,
+      "step": 36000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 5.03824232395661e-05,
+      "loss": 3.735,
+      "step": 37000
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 4.854568854568855e-05,
+      "loss": 3.731,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.36634473945194723,
+      "eval_loss": 3.753897190093994,
+      "eval_runtime": 2.0037,
+      "eval_samples_per_second": 590.407,
+      "eval_steps_per_second": 4.991,
+      "step": 38634
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 4.670711527854385e-05,
+      "loss": 3.7019,
+      "step": 39000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 4.486854201139915e-05,
+      "loss": 3.6644,
+      "step": 40000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 4.3031807317521606e-05,
+      "loss": 3.6718,
+      "step": 41000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 4.119323405037691e-05,
+      "loss": 3.6717,
+      "step": 42000
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 3.935466078323221e-05,
+      "loss": 3.6718,
+      "step": 43000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 3.751792608935466e-05,
+      "loss": 3.6713,
+      "step": 44000
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 3.567935282220997e-05,
+      "loss": 3.6709,
+      "step": 45000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3699988684846347,
+      "eval_loss": 3.72359037399292,
+      "eval_runtime": 2.0134,
+      "eval_samples_per_second": 587.554,
+      "eval_steps_per_second": 4.967,
+      "step": 45073
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 3.384261812833241e-05,
+      "loss": 3.6101,
+      "step": 46000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 3.200404486118772e-05,
+      "loss": 3.6119,
+      "step": 47000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 3.0165471594043025e-05,
+      "loss": 3.6167,
+      "step": 48000
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 2.8326898326898328e-05,
+      "loss": 3.618,
+      "step": 49000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 2.6490163633020777e-05,
+      "loss": 3.6183,
+      "step": 50000
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 2.465159036587608e-05,
+      "loss": 3.6162,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3734133824987853,
+      "eval_loss": 3.7009902000427246,
+      "eval_runtime": 2.0145,
+      "eval_samples_per_second": 587.246,
+      "eval_steps_per_second": 4.964,
+      "step": 51512
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 2.281485567199853e-05,
+      "loss": 3.5874,
+      "step": 52000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 2.0976282404853832e-05,
+      "loss": 3.5646,
+      "step": 53000
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 1.913954771097628e-05,
+      "loss": 3.5686,
+      "step": 54000
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 1.7300974443831588e-05,
+      "loss": 3.5686,
+      "step": 55000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 1.546240117668689e-05,
+      "loss": 3.5705,
+      "step": 56000
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 1.3623827909542197e-05,
+      "loss": 3.5698,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3750973436012806,
+      "eval_loss": 3.684567928314209,
+      "eval_runtime": 2.0058,
+      "eval_samples_per_second": 589.776,
+      "eval_steps_per_second": 4.985,
+      "step": 57951
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 1.1787093215664645e-05,
+      "loss": 3.566,
+      "step": 58000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 9.948519948519949e-06,
+      "loss": 3.5272,
+      "step": 59000
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 8.111785254642398e-06,
+      "loss": 3.5296,
+      "step": 60000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 6.273211987497703e-06,
+      "loss": 3.5308,
+      "step": 61000
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 4.436477293620151e-06,
+      "loss": 3.5305,
+      "step": 62000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.597904026475455e-06,
+      "loss": 3.527,
+      "step": 63000
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 7.61169332597904e-07,
+      "loss": 3.5258,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3762155470211194,
+      "eval_loss": 3.675755739212036,
+      "eval_runtime": 2.0114,
+      "eval_samples_per_second": 588.151,
+      "eval_steps_per_second": 4.972,
+      "step": 64390
+    },
+    {
+      "epoch": 10.0,
+      "step": 64390,
+      "total_flos": 5.3836218335232e+17,
+      "train_loss": 4.008237893900936,
+      "train_runtime": 29754.0363,
+      "train_samples_per_second": 276.989,
+      "train_steps_per_second": 2.164
+    }
+  ],
+  "max_steps": 64390,
+  "num_train_epochs": 10,
+  "total_flos": 5.3836218335232e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f0327ced918c711c8c6f3d26809f84b546d71e9c9be63d7dab4ae96001eb8a
+size 4881