Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_natural_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_natural_function_42
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.6743
+- Accuracy: 0.3760
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 4.9122        | 1.0   | 6439  | 4.6831          | 0.2912   |
+| 4.2912        | 2.0   | 12878 | 4.1456          | 0.3270   |
+| 4.0258        | 3.0   | 19317 | 3.9543          | 0.3454   |
+| 3.8998        | 4.0   | 25756 | 3.8565          | 0.3544   |
+| 3.8025        | 5.0   | 32195 | 3.7955          | 0.3619   |
+| 3.7321        | 6.0   | 38634 | 3.7518          | 0.3656   |
+| 3.6704        | 7.0   | 45073 | 3.7216          | 0.3702   |
+| 3.6185        | 8.0   | 51512 | 3.6979          | 0.3726   |
+| 3.5692        | 9.0   | 57951 | 3.6816          | 0.3746   |
+| 3.5276        | 10.0  | 64390 | 3.6743          | 0.3760   |
+
+
+### 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": 0.3759892439480568,
+    "eval_loss": 3.674250841140747,
+    "eval_runtime": 1.9817,
+    "eval_samples": 1183,
+    "eval_samples_per_second": 596.958,
+    "eval_steps_per_second": 5.046,
+    "perplexity": 39.41911461372872,
+    "train_loss": 4.00796840269015,
+    "train_runtime": 29832.6906,
+    "train_samples": 824154,
+    "train_samples_per_second": 276.259,
+    "train_steps_per_second": 2.158
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_natural_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": 0.3759892439480568,
+    "eval_loss": 3.674250841140747,
+    "eval_runtime": 1.9817,
+    "eval_samples": 1183,
+    "eval_samples_per_second": 596.958,
+    "eval_steps_per_second": 5.046,
+    "perplexity": 39.41911461372872
+}

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 sha256:6fe05cf4466e2b2fea68be7d0f70c66dafb57b6569b31c4cff572fa23c35674e
+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": 4.00796840269015,
+    "train_runtime": 29832.6906,
+    "train_samples": 824154,
+    "train_samples_per_second": 276.259,
+    "train_steps_per_second": 2.158
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 3.674250841140747,
+  "best_model_checkpoint": "models/GPT2_natural_function_42/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": 7.5617,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 6.0924,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 5.6562,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 5.3462,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 5.1032,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6e-05,
+      "loss": 4.9122,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2911988072496855,
+      "eval_loss": 4.683091640472412,
+      "eval_runtime": 2.016,
+      "eval_samples_per_second": 586.819,
+      "eval_steps_per_second": 4.96,
+      "step": 6439
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 4.7481,
+      "step": 7000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 8e-05,
+      "loss": 4.6153,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 4.5141,
+      "step": 9000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0001,
+      "loss": 4.4281,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.816326530612245e-05,
+      "loss": 4.3533,
+      "step": 11000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 9.632469203897775e-05,
+      "loss": 4.2912,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.32702125252094966,
+      "eval_loss": 4.145557403564453,
+      "eval_runtime": 2.0315,
+      "eval_samples_per_second": 582.318,
+      "eval_steps_per_second": 4.922,
+      "step": 12878
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.448795734510021e-05,
+      "loss": 4.2316,
+      "step": 13000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.264938407795552e-05,
+      "loss": 4.1534,
+      "step": 14000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.081264938407796e-05,
+      "loss": 4.1261,
+      "step": 15000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.897407611693326e-05,
+      "loss": 4.0963,
+      "step": 16000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 8.713734142305572e-05,
+      "loss": 4.0713,
+      "step": 17000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.529876815591101e-05,
+      "loss": 4.0484,
+      "step": 18000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.346203346203346e-05,
+      "loss": 4.0258,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3454050492209184,
+      "eval_loss": 3.9542500972747803,
+      "eval_runtime": 2.0276,
+      "eval_samples_per_second": 583.446,
+      "eval_steps_per_second": 4.932,
+      "step": 19317
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 8.162346019488876e-05,
+      "loss": 3.9666,
+      "step": 20000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 7.978672550101122e-05,
+      "loss": 3.9382,
+      "step": 21000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.794815223386652e-05,
+      "loss": 3.9307,
+      "step": 22000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 7.611141753998897e-05,
+      "loss": 3.9198,
+      "step": 23000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 7.427284427284427e-05,
+      "loss": 3.9101,
+      "step": 24000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 7.243610957896673e-05,
+      "loss": 3.8998,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.35441723630700006,
+      "eval_loss": 3.8564870357513428,
+      "eval_runtime": 2.0237,
+      "eval_samples_per_second": 584.57,
+      "eval_steps_per_second": 4.941,
+      "step": 25756
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 7.059753631182204e-05,
+      "loss": 3.8732,
+      "step": 26000
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 6.876080161794448e-05,
+      "loss": 3.8189,
+      "step": 27000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 6.692222835079978e-05,
+      "loss": 3.8169,
+      "step": 28000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 6.508549365692223e-05,
+      "loss": 3.8181,
+      "step": 29000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 6.324692038977753e-05,
+      "loss": 3.8129,
+      "step": 30000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 6.141018569589998e-05,
+      "loss": 3.8089,
+      "step": 31000
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 5.957161242875529e-05,
+      "loss": 3.8025,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.36189854966354057,
+      "eval_loss": 3.795483112335205,
+      "eval_runtime": 2.0306,
+      "eval_samples_per_second": 582.574,
+      "eval_steps_per_second": 4.925,
+      "step": 32195
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 5.7734877734877734e-05,
+      "loss": 3.7413,
+      "step": 33000
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 5.589630446773304e-05,
+      "loss": 3.7338,
+      "step": 34000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 5.405956977385549e-05,
+      "loss": 3.7373,
+      "step": 35000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 5.222099650671079e-05,
+      "loss": 3.7383,
+      "step": 36000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 5.0384261812833245e-05,
+      "loss": 3.7345,
+      "step": 37000
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 4.854568854568855e-05,
+      "loss": 3.7321,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.36563255036907366,
+      "eval_loss": 3.7517600059509277,
+      "eval_runtime": 2.0166,
+      "eval_samples_per_second": 586.638,
+      "eval_steps_per_second": 4.959,
+      "step": 38634
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 4.6708953851811e-05,
+      "loss": 3.7007,
+      "step": 39000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 4.4870380584666296e-05,
+      "loss": 3.6644,
+      "step": 40000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 4.303364589078875e-05,
+      "loss": 3.6716,
+      "step": 41000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 4.119507262364405e-05,
+      "loss": 3.6729,
+      "step": 42000
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 3.9358337929766504e-05,
+      "loss": 3.6723,
+      "step": 43000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 3.751976466262181e-05,
+      "loss": 3.6717,
+      "step": 44000
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 3.568302996874426e-05,
+      "loss": 3.6704,
+      "step": 45000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.37023182753043443,
+      "eval_loss": 3.7216103076934814,
+      "eval_runtime": 2.024,
+      "eval_samples_per_second": 584.495,
+      "eval_steps_per_second": 4.941,
+      "step": 45073
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 3.3844456701599556e-05,
+      "loss": 3.6092,
+      "step": 46000
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 3.200772200772201e-05,
+      "loss": 3.6111,
+      "step": 47000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 3.0169148740577315e-05,
+      "loss": 3.6175,
+      "step": 48000
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 2.8332414046699764e-05,
+      "loss": 3.6178,
+      "step": 49000
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 2.6493840779555067e-05,
+      "loss": 3.6179,
+      "step": 50000
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 2.4657106085677516e-05,
+      "loss": 3.6185,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.372614665770329,
+      "eval_loss": 3.6979215145111084,
+      "eval_runtime": 2.0125,
+      "eval_samples_per_second": 587.82,
+      "eval_steps_per_second": 4.969,
+      "step": 51512
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 2.281853281853282e-05,
+      "loss": 3.5893,
+      "step": 52000
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 2.0981798124655268e-05,
+      "loss": 3.5628,
+      "step": 53000
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 1.914322485751057e-05,
+      "loss": 3.5694,
+      "step": 54000
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 1.730649016363302e-05,
+      "loss": 3.57,
+      "step": 55000
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 1.5467916896488326e-05,
+      "loss": 3.5698,
+      "step": 56000
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 1.3631182202610776e-05,
+      "loss": 3.5692,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.3745981456459954,
+      "eval_loss": 3.681605100631714,
+      "eval_runtime": 2.023,
+      "eval_samples_per_second": 584.781,
+      "eval_steps_per_second": 4.943,
+      "step": 57951
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 1.1792608935466078e-05,
+      "loss": 3.5682,
+      "step": 58000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 9.955874241588528e-06,
+      "loss": 3.5273,
+      "step": 59000
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 8.117300974443832e-06,
+      "loss": 3.5306,
+      "step": 60000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 6.2805662805662815e-06,
+      "loss": 3.5293,
+      "step": 61000
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 4.441993013421585e-06,
+      "loss": 3.529,
+      "step": 62000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.605258319544034e-06,
+      "loss": 3.5288,
+      "step": 63000
+    },
+    {
+      "epoch": 9.94,
+      "learning_rate": 7.666850523993381e-07,
+      "loss": 3.5276,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.3759892439480568,
+      "eval_loss": 3.674250841140747,
+      "eval_runtime": 2.0424,
+      "eval_samples_per_second": 579.222,
+      "eval_steps_per_second": 4.896,
+      "step": 64390
+    },
+    {
+      "epoch": 10.0,
+      "step": 64390,
+      "total_flos": 5.3836218335232e+17,
+      "train_loss": 4.00796840269015,
+      "train_runtime": 29832.6906,
+      "train_samples_per_second": 276.259,
+      "train_steps_per_second": 2.158
+    }
+  ],
+  "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:e8bbd505ea5e610958558f788f95b2d475133c78afca2a82cb4f3f97059f385d
+size 4881