Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_five_function_53
+  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_five_function_53
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.6064
+- Accuracy: 0.4052
+
+## 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: 53
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 4.7541        | 1.0   | 6408  | 4.5598          | 0.3268   |
+| 4.1833        | 2.0   | 12816 | 4.0602          | 0.3599   |
+| 3.9344        | 3.0   | 19224 | 3.8742          | 0.3767   |
+| 3.8132        | 4.0   | 25632 | 3.7790          | 0.3858   |
+| 3.7206        | 5.0   | 32040 | 3.7182          | 0.3915   |
+| 3.6507        | 6.0   | 38448 | 3.6788          | 0.3954   |
+| 3.5926        | 7.0   | 44856 | 3.6508          | 0.3991   |
+| 3.5419        | 8.0   | 51264 | 3.6279          | 0.4019   |
+| 3.499         | 9.0   | 57672 | 3.6127          | 0.4039   |
+| 3.4548        | 10.0  | 64080 | 3.6064          | 0.4052   |
+
+
+### 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": 0.40520433672446293,
+    "eval_loss": 3.606384038925171,
+    "eval_runtime": 1.9789,
+    "eval_samples": 1178,
+    "eval_samples_per_second": 595.269,
+    "eval_steps_per_second": 5.053,
+    "perplexity": 36.83262638452431,
+    "train_loss": 3.9053353675146973,
+    "train_runtime": 28136.2427,
+    "train_samples": 820126,
+    "train_samples_per_second": 291.484,
+    "train_steps_per_second": 2.277
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_five_function_53",
+  "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": 0.40520433672446293,
+    "eval_loss": 3.606384038925171,
+    "eval_runtime": 1.9789,
+    "eval_samples": 1178,
+    "eval_samples_per_second": 595.269,
+    "eval_steps_per_second": 5.053,
+    "perplexity": 36.83262638452431
+}

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:cf155314b686d47bb9a16c89d2ea73eab5f37a94395b6c41a845ddd98cb375d6
+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": 3.9053353675146973,
+    "train_runtime": 28136.2427,
+    "train_samples": 820126,
+    "train_samples_per_second": 291.484,
+    "train_steps_per_second": 2.277
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 3.606384038925171,
+  "best_model_checkpoint": "models/GPT2_five_function_53/checkpoint-64080",
+  "epoch": 10.0,
+  "global_step": 64080,
+  "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": 6.9756,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 5.7447,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 5.4075,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 5.1398,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 4.9277,
+      "step": 5000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6e-05,
+      "loss": 4.7541,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3268384957822547,
+      "eval_loss": 4.559751510620117,
+      "eval_runtime": 1.9727,
+      "eval_samples_per_second": 597.157,
+      "eval_steps_per_second": 5.069,
+      "step": 6408
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 4.6042,
+      "step": 7000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8e-05,
+      "loss": 4.4833,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 4.3875,
+      "step": 9000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001,
+      "loss": 4.311,
+      "step": 10000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.815273668639054e-05,
+      "loss": 4.2427,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.630362426035503e-05,
+      "loss": 4.1833,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3599320882852292,
+      "eval_loss": 4.060220718383789,
+      "eval_runtime": 1.9924,
+      "eval_samples_per_second": 591.24,
+      "eval_steps_per_second": 5.019,
+      "step": 12816
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.445636094674557e-05,
+      "loss": 4.1256,
+      "step": 13000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.260724852071006e-05,
+      "loss": 4.0557,
+      "step": 14000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.07599852071006e-05,
+      "loss": 4.0268,
+      "step": 15000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.891087278106509e-05,
+      "loss": 4.0018,
+      "step": 16000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.706360946745562e-05,
+      "loss": 3.9761,
+      "step": 17000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.521449704142012e-05,
+      "loss": 3.9549,
+      "step": 18000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 8.336723372781065e-05,
+      "loss": 3.9344,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3767429113805596,
+      "eval_loss": 3.8741631507873535,
+      "eval_runtime": 1.9758,
+      "eval_samples_per_second": 596.205,
+      "eval_steps_per_second": 5.061,
+      "step": 19224
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 8.151812130177516e-05,
+      "loss": 3.8697,
+      "step": 20000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 7.967085798816568e-05,
+      "loss": 3.8502,
+      "step": 21000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 7.782174556213018e-05,
+      "loss": 3.8434,
+      "step": 22000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 7.597633136094676e-05,
+      "loss": 3.8327,
+      "step": 23000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 7.412721893491125e-05,
+      "loss": 3.8223,
+      "step": 24000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 7.227810650887574e-05,
+      "loss": 3.8132,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.38580671898185903,
+      "eval_loss": 3.77901291847229,
+      "eval_runtime": 1.9793,
+      "eval_samples_per_second": 595.173,
+      "eval_steps_per_second": 5.052,
+      "step": 25632
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 7.043084319526627e-05,
+      "loss": 3.7795,
+      "step": 26000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 6.858173076923077e-05,
+      "loss": 3.7361,
+      "step": 27000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 6.67344674556213e-05,
+      "loss": 3.7368,
+      "step": 28000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 6.488535502958581e-05,
+      "loss": 3.7341,
+      "step": 29000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.30362426035503e-05,
+      "loss": 3.7308,
+      "step": 30000
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 6.118897928994083e-05,
+      "loss": 3.7239,
+      "step": 31000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 5.9339866863905326e-05,
+      "loss": 3.7206,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3915150461879871,
+      "eval_loss": 3.7181639671325684,
+      "eval_runtime": 1.9928,
+      "eval_samples_per_second": 591.139,
+      "eval_steps_per_second": 5.018,
+      "step": 32040
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 5.749075443786982e-05,
+      "loss": 3.6524,
+      "step": 33000
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 5.564349112426036e-05,
+      "loss": 3.656,
+      "step": 34000
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 5.379437869822486e-05,
+      "loss": 3.6564,
+      "step": 35000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 5.1947115384615385e-05,
+      "loss": 3.6575,
+      "step": 36000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 5.009800295857988e-05,
+      "loss": 3.6561,
+      "step": 37000
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 4.8250739644970414e-05,
+      "loss": 3.6507,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3954253171664238,
+      "eval_loss": 3.6788344383239746,
+      "eval_runtime": 1.9827,
+      "eval_samples_per_second": 594.145,
+      "eval_steps_per_second": 5.044,
+      "step": 38448
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 4.640162721893491e-05,
+      "loss": 3.6138,
+      "step": 39000
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 4.4552514792899406e-05,
+      "loss": 3.5906,
+      "step": 40000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 4.2705251479289946e-05,
+      "loss": 3.5945,
+      "step": 41000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 4.0856139053254435e-05,
+      "loss": 3.5952,
+      "step": 42000
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 3.9008875739644975e-05,
+      "loss": 3.5956,
+      "step": 43000
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 3.715976331360947e-05,
+      "loss": 3.5926,
+      "step": 44000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3990749034129647,
+      "eval_loss": 3.650787353515625,
+      "eval_runtime": 1.9767,
+      "eval_samples_per_second": 595.946,
+      "eval_steps_per_second": 5.059,
+      "step": 44856
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 3.5312500000000005e-05,
+      "loss": 3.5838,
+      "step": 45000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 3.34633875739645e-05,
+      "loss": 3.534,
+      "step": 46000
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 3.1614275147928997e-05,
+      "loss": 3.5398,
+      "step": 47000
+    },
+    {
+      "epoch": 7.49,
+      "learning_rate": 2.976701183431953e-05,
+      "loss": 3.5422,
+      "step": 48000
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 2.7917899408284026e-05,
+      "loss": 3.5428,
+      "step": 49000
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 2.6070636094674556e-05,
+      "loss": 3.5444,
+      "step": 50000
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 2.4221523668639055e-05,
+      "loss": 3.5419,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.401922382792134,
+      "eval_loss": 3.6278560161590576,
+      "eval_runtime": 2.0031,
+      "eval_samples_per_second": 588.082,
+      "eval_steps_per_second": 4.992,
+      "step": 51264
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 2.237241124260355e-05,
+      "loss": 3.5004,
+      "step": 52000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 2.0523298816568047e-05,
+      "loss": 3.4936,
+      "step": 53000
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 1.867603550295858e-05,
+      "loss": 3.4955,
+      "step": 54000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 1.682692307692308e-05,
+      "loss": 3.4964,
+      "step": 55000
+    },
+    {
+      "epoch": 8.74,
+      "learning_rate": 1.4977810650887576e-05,
+      "loss": 3.4961,
+      "step": 56000
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 1.3130547337278107e-05,
+      "loss": 3.499,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4038942288410893,
+      "eval_loss": 3.6126561164855957,
+      "eval_runtime": 1.9751,
+      "eval_samples_per_second": 596.417,
+      "eval_steps_per_second": 5.063,
+      "step": 57672
+    },
+    {
+      "epoch": 9.05,
+      "learning_rate": 1.1281434911242605e-05,
+      "loss": 3.4819,
+      "step": 58000
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 9.432322485207101e-06,
+      "loss": 3.4571,
+      "step": 59000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 7.5832100591715985e-06,
+      "loss": 3.459,
+      "step": 60000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 5.73594674556213e-06,
+      "loss": 3.4586,
+      "step": 61000
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 3.886834319526628e-06,
+      "loss": 3.4583,
+      "step": 62000
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 2.03957100591716e-06,
+      "loss": 3.4568,
+      "step": 63000
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 1.9045857988165683e-07,
+      "loss": 3.4548,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.40520433672446293,
+      "eval_loss": 3.606384038925171,
+      "eval_runtime": 1.9874,
+      "eval_samples_per_second": 592.729,
+      "eval_steps_per_second": 5.032,
+      "step": 64080
+    },
+    {
+      "epoch": 10.0,
+      "step": 64080,
+      "total_flos": 5.3573097259008e+17,
+      "train_loss": 3.9053353675146973,
+      "train_runtime": 28136.2427,
+      "train_samples_per_second": 291.484,
+      "train_steps_per_second": 2.277
+    }
+  ],
+  "max_steps": 64080,
+  "num_train_epochs": 10,
+  "total_flos": 5.3573097259008e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163ba4dab3da9de53d869bb2df8a1ca21cab1999f8f79cda6754d5f0f2775b94
+size 4881