Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_random_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_random_function_67
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.8521
+- Accuracy: 0.2485
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 5.9638        | 1.0   | 6426  | 5.7731          | 0.1802   |
+| 5.4117        | 2.0   | 12852 | 5.2853          | 0.2093   |
+| 5.1712        | 3.0   | 19278 | 5.1077          | 0.2239   |
+| 5.0518        | 4.0   | 25704 | 5.0164          | 0.2307   |
+| 4.9598        | 5.0   | 32130 | 4.9591          | 0.2361   |
+| 4.8949        | 6.0   | 38556 | 4.9221          | 0.2403   |
+| 4.8367        | 7.0   | 44982 | 4.8928          | 0.2431   |
+| 4.7866        | 8.0   | 51408 | 4.8736          | 0.2459   |
+| 4.7426        | 9.0   | 57834 | 4.8575          | 0.2472   |
+| 4.7034        | 10.0  | 64260 | 4.8521          | 0.2485   |
+
+
+### 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": 0.24854154026682312,
+    "eval_loss": 4.8520708084106445,
+    "eval_runtime": 2.2358,
+    "eval_samples": 1181,
+    "eval_samples_per_second": 528.222,
+    "eval_steps_per_second": 4.473,
+    "perplexity": 128.0051898000597,
+    "train_loss": 5.139265971416778,
+    "train_runtime": 32597.6138,
+    "train_samples": 822425,
+    "train_samples_per_second": 252.296,
+    "train_steps_per_second": 1.971
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_random_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": 0.24854154026682312,
+    "eval_loss": 4.8520708084106445,
+    "eval_runtime": 2.2358,
+    "eval_samples": 1181,
+    "eval_samples_per_second": 528.222,
+    "eval_steps_per_second": 4.473,
+    "perplexity": 128.0051898000597
+}

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 sha256:35c84b6bc1344933fcddafd80e9c6a34c2e676a92c0c231e9087402d85b5ed11
+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": 5.139265971416778,
+    "train_runtime": 32597.6138,
+    "train_samples": 822425,
+    "train_samples_per_second": 252.296,
+    "train_steps_per_second": 1.971
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 4.8520708084106445,
+  "best_model_checkpoint": "models/GPT2_random_function_67/checkpoint-64260",
+  "epoch": 10.0,
+  "global_step": 64260,
+  "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": 8.1506,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 6.9222,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 6.5898,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 6.3335,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 6.1289,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6e-05,
+      "loss": 5.9638,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.18021561868695288,
+      "eval_loss": 5.77306604385376,
+      "eval_runtime": 2.2354,
+      "eval_samples_per_second": 528.323,
+      "eval_steps_per_second": 4.474,
+      "step": 6426
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 5.8204,
+      "step": 7000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 8e-05,
+      "loss": 5.7052,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 5.6134,
+      "step": 9000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001,
+      "loss": 5.5375,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.815886472539625e-05,
+      "loss": 5.4701,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.631588647253964e-05,
+      "loss": 5.4117,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.20929813917206158,
+      "eval_loss": 5.285326957702637,
+      "eval_runtime": 2.2389,
+      "eval_samples_per_second": 527.498,
+      "eval_steps_per_second": 4.467,
+      "step": 12852
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.447475119793588e-05,
+      "loss": 5.356,
+      "step": 13000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.263177294507925e-05,
+      "loss": 5.2864,
+      "step": 14000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 9.07906376704755e-05,
+      "loss": 5.2607,
+      "step": 15000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.894765941761888e-05,
+      "loss": 5.2324,
+      "step": 16000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.710652414301511e-05,
+      "loss": 5.2124,
+      "step": 17000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.52635458901585e-05,
+      "loss": 5.1883,
+      "step": 18000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.342241061555473e-05,
+      "loss": 5.1712,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2238594011480995,
+      "eval_loss": 5.107715606689453,
+      "eval_runtime": 2.2377,
+      "eval_samples_per_second": 527.766,
+      "eval_steps_per_second": 4.469,
+      "step": 19278
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 8.157943236269813e-05,
+      "loss": 5.1086,
+      "step": 20000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 7.973829708809436e-05,
+      "loss": 5.0865,
+      "step": 21000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.789531883523775e-05,
+      "loss": 5.0799,
+      "step": 22000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 7.605418356063398e-05,
+      "loss": 5.0711,
+      "step": 23000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 7.421120530777738e-05,
+      "loss": 5.0605,
+      "step": 24000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 7.237007003317361e-05,
+      "loss": 5.0518,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.230713328488469,
+      "eval_loss": 5.016420364379883,
+      "eval_runtime": 2.2334,
+      "eval_samples_per_second": 528.784,
+      "eval_steps_per_second": 4.477,
+      "step": 25704
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 7.0527091780317e-05,
+      "loss": 5.0209,
+      "step": 26000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 6.868595650571323e-05,
+      "loss": 4.9744,
+      "step": 27000
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.684297825285662e-05,
+      "loss": 4.9767,
+      "step": 28000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 6.500184297825286e-05,
+      "loss": 4.9737,
+      "step": 29000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 6.315886472539624e-05,
+      "loss": 4.9685,
+      "step": 30000
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 6.131772945079248e-05,
+      "loss": 4.9657,
+      "step": 31000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 5.947475119793586e-05,
+      "loss": 4.9598,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.23611379652903253,
+      "eval_loss": 4.959114074707031,
+      "eval_runtime": 2.2365,
+      "eval_samples_per_second": 528.054,
+      "eval_steps_per_second": 4.471,
+      "step": 32130
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 5.763361592333211e-05,
+      "loss": 4.8988,
+      "step": 33000
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 5.5790637670475484e-05,
+      "loss": 4.8962,
+      "step": 34000
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 5.394950239587173e-05,
+      "loss": 4.8977,
+      "step": 35000
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 5.2106524143015115e-05,
+      "loss": 4.897,
+      "step": 36000
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 5.0265388868411356e-05,
+      "loss": 4.8969,
+      "step": 37000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 4.842241061555474e-05,
+      "loss": 4.8949,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.24032749504957096,
+      "eval_loss": 4.922134876251221,
+      "eval_runtime": 2.2386,
+      "eval_samples_per_second": 527.554,
+      "eval_steps_per_second": 4.467,
+      "step": 38556
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 4.658127534095098e-05,
+      "loss": 4.8626,
+      "step": 39000
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 4.4738297088094364e-05,
+      "loss": 4.8332,
+      "step": 40000
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 4.2897161813490605e-05,
+      "loss": 4.8354,
+      "step": 41000
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 4.105418356063399e-05,
+      "loss": 4.8369,
+      "step": 42000
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 3.921304828603022e-05,
+      "loss": 4.8372,
+      "step": 43000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 3.737007003317361e-05,
+      "loss": 4.8367,
+      "step": 44000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.24314773947075413,
+      "eval_loss": 4.892807960510254,
+      "eval_runtime": 2.2354,
+      "eval_samples_per_second": 528.317,
+      "eval_steps_per_second": 4.473,
+      "step": 44982
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.552893475856985e-05,
+      "loss": 4.8358,
+      "step": 45000
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 3.368595650571324e-05,
+      "loss": 4.7777,
+      "step": 46000
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 3.184482123110947e-05,
+      "loss": 4.7806,
+      "step": 47000
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 3.0001842978252858e-05,
+      "loss": 4.7869,
+      "step": 48000
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 2.8160707703649096e-05,
+      "loss": 4.7867,
+      "step": 49000
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 2.6317729450792483e-05,
+      "loss": 4.7876,
+      "step": 50000
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 2.447659417618872e-05,
+      "loss": 4.7866,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.24586797522451945,
+      "eval_loss": 4.873629093170166,
+      "eval_runtime": 2.2375,
+      "eval_samples_per_second": 527.83,
+      "eval_steps_per_second": 4.469,
+      "step": 51408
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 2.2633615923332104e-05,
+      "loss": 4.7522,
+      "step": 52000
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 2.079063767047549e-05,
+      "loss": 4.7356,
+      "step": 53000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 1.8949502395871728e-05,
+      "loss": 4.7409,
+      "step": 54000
+    },
+    {
+      "epoch": 8.56,
+      "learning_rate": 1.710652414301511e-05,
+      "loss": 4.7433,
+      "step": 55000
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 1.5265388868411353e-05,
+      "loss": 4.7417,
+      "step": 56000
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 1.3422410615554738e-05,
+      "loss": 4.7426,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.24721475861241307,
+      "eval_loss": 4.857459545135498,
+      "eval_runtime": 2.2373,
+      "eval_samples_per_second": 527.865,
+      "eval_steps_per_second": 4.47,
+      "step": 57834
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 1.1581275340950977e-05,
+      "loss": 4.7339,
+      "step": 58000
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 9.738297088094362e-06,
+      "loss": 4.7004,
+      "step": 59000
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 7.897161813490601e-06,
+      "loss": 4.7038,
+      "step": 60000
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 6.054183560633985e-06,
+      "loss": 4.7041,
+      "step": 61000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 4.213048286030225e-06,
+      "loss": 4.7057,
+      "step": 62000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 2.3700700331736087e-06,
+      "loss": 4.7021,
+      "step": 63000
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 5.289347585698488e-07,
+      "loss": 4.7034,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.24854154026682312,
+      "eval_loss": 4.8520708084106445,
+      "eval_runtime": 2.2342,
+      "eval_samples_per_second": 528.599,
+      "eval_steps_per_second": 4.476,
+      "step": 64260
+    },
+    {
+      "epoch": 10.0,
+      "step": 64260,
+      "total_flos": 5.37232748544e+17,
+      "train_loss": 5.139265971416778,
+      "train_runtime": 32597.6138,
+      "train_samples_per_second": 252.296,
+      "train_steps_per_second": 1.971
+    }
+  ],
+  "max_steps": 64260,
+  "num_train_epochs": 10,
+  "total_flos": 5.37232748544e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4b530a494508e48498089ff63895ac9745f152745075a32aaa539ac3060a45
+size 4881