Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_no_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_no_function_53
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.7232
+- Accuracy: 0.3103
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 6.3722        | 1.0   | 4702  | 6.0131          | 0.2200   |
+| 5.5124        | 2.0   | 9404  | 5.3614          | 0.2521   |
+| 5.1637        | 3.0   | 14106 | 5.0791          | 0.2753   |
+| 4.9973        | 4.0   | 18808 | 4.9464          | 0.2873   |
+| 4.8674        | 5.0   | 23510 | 4.8657          | 0.2944   |
+| 4.7726        | 6.0   | 28212 | 4.8131          | 0.3001   |
+| 4.6943        | 7.0   | 32914 | 4.7743          | 0.3027   |
+| 4.6304        | 8.0   | 37616 | 4.7480          | 0.3064   |
+| 4.5722        | 9.0   | 42318 | 4.7303          | 0.3089   |
+| 4.5192        | 10.0  | 47020 | 4.7232          | 0.3103   |
+
+
+### 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": 0.31030532268916733,
+    "eval_loss": 4.72317361831665,
+    "eval_runtime": 1.4404,
+    "eval_samples": 866,
+    "eval_samples_per_second": 601.238,
+    "eval_steps_per_second": 4.86,
+    "perplexity": 112.52479735814698,
+    "train_loss": 5.094991286588901,
+    "train_runtime": 20565.7404,
+    "train_samples": 601770,
+    "train_samples_per_second": 292.608,
+    "train_steps_per_second": 2.286
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_no_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": 0.31030532268916733,
+    "eval_loss": 4.72317361831665,
+    "eval_runtime": 1.4404,
+    "eval_samples": 866,
+    "eval_samples_per_second": 601.238,
+    "eval_steps_per_second": 4.86,
+    "perplexity": 112.52479735814698
+}

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:eb89e149c865bab51c18c827beba7516f69500c918ec97022e8ba9999e6e7de8
+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": 5.094991286588901,
+    "train_runtime": 20565.7404,
+    "train_samples": 601770,
+    "train_samples_per_second": 292.608,
+    "train_steps_per_second": 2.286
+}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": 4.72317361831665,
+  "best_model_checkpoint": "models/GPT2_no_function_53/checkpoint-47020",
+  "epoch": 10.0,
+  "global_step": 47020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 1e-05,
+      "loss": 8.062,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2e-05,
+      "loss": 7.08,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3e-05,
+      "loss": 6.6777,
+      "step": 3000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4e-05,
+      "loss": 6.3722,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22003600589187322,
+      "eval_loss": 6.013131618499756,
+      "eval_runtime": 1.4557,
+      "eval_samples_per_second": 594.896,
+      "eval_steps_per_second": 4.809,
+      "step": 4702
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 5e-05,
+      "loss": 6.1266,
+      "step": 5000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6e-05,
+      "loss": 5.9211,
+      "step": 6000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7e-05,
+      "loss": 5.754,
+      "step": 7000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8e-05,
+      "loss": 5.6215,
+      "step": 8000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.999000000000001e-05,
+      "loss": 5.5124,
+      "step": 9000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2521412594788238,
+      "eval_loss": 5.3613715171813965,
+      "eval_runtime": 1.4497,
+      "eval_samples_per_second": 597.35,
+      "eval_steps_per_second": 4.828,
+      "step": 9404
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.999000000000001e-05,
+      "loss": 5.4015,
+      "step": 10000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.730145867098865e-05,
+      "loss": 5.3206,
+      "step": 11000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 9.460021609940574e-05,
+      "loss": 5.2587,
+      "step": 12000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 9.190167477039439e-05,
+      "loss": 5.206,
+      "step": 13000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.920043219881146e-05,
+      "loss": 5.1637,
+      "step": 14000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2752905020821589,
+      "eval_loss": 5.079057216644287,
+      "eval_runtime": 1.4555,
+      "eval_samples_per_second": 594.981,
+      "eval_steps_per_second": 4.809,
+      "step": 14106
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.650189086980012e-05,
+      "loss": 5.0665,
+      "step": 15000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 8.380064829821718e-05,
+      "loss": 5.0403,
+      "step": 16000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 8.110210696920584e-05,
+      "loss": 5.0201,
+      "step": 17000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 7.84008643976229e-05,
+      "loss": 4.9973,
+      "step": 18000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.28729246603989744,
+      "eval_loss": 4.946365833282471,
+      "eval_runtime": 1.4489,
+      "eval_samples_per_second": 597.697,
+      "eval_steps_per_second": 4.831,
+      "step": 18808
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 7.570232306861156e-05,
+      "loss": 4.9629,
+      "step": 19000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 7.300108049702864e-05,
+      "loss": 4.8895,
+      "step": 20000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 7.030253916801729e-05,
+      "loss": 4.885,
+      "step": 21000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.760129659643436e-05,
+      "loss": 4.8783,
+      "step": 22000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 6.490275526742302e-05,
+      "loss": 4.8674,
+      "step": 23000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.29440272044516375,
+      "eval_loss": 4.86568546295166,
+      "eval_runtime": 1.4504,
+      "eval_samples_per_second": 597.067,
+      "eval_steps_per_second": 4.826,
+      "step": 23510
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 6.22015126958401e-05,
+      "loss": 4.8161,
+      "step": 24000
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 5.950297136682874e-05,
+      "loss": 4.7765,
+      "step": 25000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 5.680172879524581e-05,
+      "loss": 4.7805,
+      "step": 26000
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 5.410318746623447e-05,
+      "loss": 4.7762,
+      "step": 27000
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 5.140194489465154e-05,
+      "loss": 4.7726,
+      "step": 28000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3000854685312142,
+      "eval_loss": 4.8131208419799805,
+      "eval_runtime": 1.4646,
+      "eval_samples_per_second": 591.29,
+      "eval_steps_per_second": 4.779,
+      "step": 28212
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 4.87034035656402e-05,
+      "loss": 4.7026,
+      "step": 29000
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 4.600216099405727e-05,
+      "loss": 4.6946,
+      "step": 30000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 4.330091842247434e-05,
+      "loss": 4.6946,
+      "step": 31000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 4.059967585089141e-05,
+      "loss": 4.6943,
+      "step": 32000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.30274954083395467,
+      "eval_loss": 4.774256229400635,
+      "eval_runtime": 1.4492,
+      "eval_samples_per_second": 597.581,
+      "eval_steps_per_second": 4.83,
+      "step": 32914
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 3.790113452188007e-05,
+      "loss": 4.6866,
+      "step": 33000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 3.5199891950297136e-05,
+      "loss": 4.6173,
+      "step": 34000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 3.2501350621285795e-05,
+      "loss": 4.6242,
+      "step": 35000
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 2.980010804970286e-05,
+      "loss": 4.6284,
+      "step": 36000
+    },
+    {
+      "epoch": 7.87,
+      "learning_rate": 2.7101566720691517e-05,
+      "loss": 4.6304,
+      "step": 37000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3063774072120892,
+      "eval_loss": 4.747974872589111,
+      "eval_runtime": 1.4471,
+      "eval_samples_per_second": 598.423,
+      "eval_steps_per_second": 4.837,
+      "step": 37616
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 2.4400324149108593e-05,
+      "loss": 4.6011,
+      "step": 38000
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 2.1701782820097246e-05,
+      "loss": 4.5648,
+      "step": 39000
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 1.900054024851432e-05,
+      "loss": 4.567,
+      "step": 40000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 1.6301998919502974e-05,
+      "loss": 4.5702,
+      "step": 41000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 1.3600756347920043e-05,
+      "loss": 4.5722,
+      "step": 42000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.30892327835463984,
+      "eval_loss": 4.730299472808838,
+      "eval_runtime": 1.4538,
+      "eval_samples_per_second": 595.671,
+      "eval_steps_per_second": 4.815,
+      "step": 42318
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 1.0902215018908699e-05,
+      "loss": 4.5342,
+      "step": 43000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 8.20097244732577e-06,
+      "loss": 4.522,
+      "step": 44000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 5.502431118314425e-06,
+      "loss": 4.5233,
+      "step": 45000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.8011885467314965e-06,
+      "loss": 4.5216,
+      "step": 46000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.0264721772015128e-07,
+      "loss": 4.5192,
+      "step": 47000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.31030532268916733,
+      "eval_loss": 4.72317361831665,
+      "eval_runtime": 1.4615,
+      "eval_samples_per_second": 592.559,
+      "eval_steps_per_second": 4.79,
+      "step": 47020
+    },
+    {
+      "epoch": 10.0,
+      "step": 47020,
+      "total_flos": 3.930942652416e+17,
+      "train_loss": 5.094991286588901,
+      "train_runtime": 20565.7404,
+      "train_samples_per_second": 292.608,
+      "train_steps_per_second": 2.286
+    }
+  ],
+  "max_steps": 47020,
+  "num_train_epochs": 10,
+  "total_flos": 3.930942652416e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605b900c4e7be27bb43149eb52ddba0a6928b6f39b91c1c190dacecb89db2a2a
+size 4881