Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_no_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_no_function_67
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.7260
+- 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: 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 6.3673        | 1.0   | 4702  | 6.0093          | 0.2210   |
+| 5.5122        | 2.0   | 9404  | 5.3627          | 0.2531   |
+| 5.1637        | 3.0   | 14106 | 5.0803          | 0.2754   |
+| 5.0001        | 4.0   | 18808 | 4.9437          | 0.2882   |
+| 4.8699        | 5.0   | 23510 | 4.8652          | 0.2950   |
+| 4.7738        | 6.0   | 28212 | 4.8127          | 0.3002   |
+| 4.6966        | 7.0   | 32914 | 4.7762          | 0.3044   |
+| 4.6296        | 8.0   | 37616 | 4.7499          | 0.3069   |
+| 4.5712        | 9.0   | 42318 | 4.7333          | 0.3087   |
+| 4.5227        | 10.0  | 47020 | 4.7260          | 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": 0.31029623029222964,
+    "eval_loss": 4.725980758666992,
+    "eval_runtime": 1.4649,
+    "eval_samples": 866,
+    "eval_samples_per_second": 591.179,
+    "eval_steps_per_second": 4.779,
+    "perplexity": 112.841114022145,
+    "train_loss": 5.095248515795566,
+    "train_runtime": 20611.3432,
+    "train_samples": 601770,
+    "train_samples_per_second": 291.961,
+    "train_steps_per_second": 2.281
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_no_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": 0.31029623029222964,
+    "eval_loss": 4.725980758666992,
+    "eval_runtime": 1.4649,
+    "eval_samples": 866,
+    "eval_samples_per_second": 591.179,
+    "eval_steps_per_second": 4.779,
+    "perplexity": 112.841114022145
+}

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 sha256:4867ca683ee98891feef7b38a97c92b57059d3737c1ca6c5dab0e126eecf6418
+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": 5.095248515795566,
+    "train_runtime": 20611.3432,
+    "train_samples": 601770,
+    "train_samples_per_second": 291.961,
+    "train_steps_per_second": 2.281
+}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": 4.725980758666992,
+  "best_model_checkpoint": "models/GPT2_no_function_67/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": 8.0666,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2e-05,
+      "loss": 7.0832,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3e-05,
+      "loss": 6.6789,
+      "step": 3000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4e-05,
+      "loss": 6.3673,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22100889236420504,
+      "eval_loss": 6.009326934814453,
+      "eval_runtime": 1.4336,
+      "eval_samples_per_second": 604.067,
+      "eval_steps_per_second": 4.883,
+      "step": 4702
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 5e-05,
+      "loss": 6.1194,
+      "step": 5000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6e-05,
+      "loss": 5.9118,
+      "step": 6000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7e-05,
+      "loss": 5.7482,
+      "step": 7000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8e-05,
+      "loss": 5.6171,
+      "step": 8000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9e-05,
+      "loss": 5.5122,
+      "step": 9000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2530959611572803,
+      "eval_loss": 5.362746238708496,
+      "eval_runtime": 1.4445,
+      "eval_samples_per_second": 599.499,
+      "eval_steps_per_second": 4.846,
+      "step": 9404
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0001,
+      "loss": 5.3993,
+      "step": 10000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.730145867098865e-05,
+      "loss": 5.3202,
+      "step": 11000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 9.460021609940574e-05,
+      "loss": 5.2575,
+      "step": 12000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 9.190167477039439e-05,
+      "loss": 5.2089,
+      "step": 13000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.920043219881146e-05,
+      "loss": 5.1637,
+      "step": 14000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2754268880362241,
+      "eval_loss": 5.0802507400512695,
+      "eval_runtime": 1.4537,
+      "eval_samples_per_second": 595.734,
+      "eval_steps_per_second": 4.815,
+      "step": 14106
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.650189086980012e-05,
+      "loss": 5.0658,
+      "step": 15000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 8.380064829821718e-05,
+      "loss": 5.0423,
+      "step": 16000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 8.110210696920584e-05,
+      "loss": 5.0206,
+      "step": 17000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 7.84008643976229e-05,
+      "loss": 5.0001,
+      "step": 18000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.2882471677183539,
+      "eval_loss": 4.943727970123291,
+      "eval_runtime": 1.5715,
+      "eval_samples_per_second": 551.081,
+      "eval_steps_per_second": 4.454,
+      "step": 18808
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 7.570232306861156e-05,
+      "loss": 4.9618,
+      "step": 19000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 7.300108049702864e-05,
+      "loss": 4.8897,
+      "step": 20000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 7.030253916801729e-05,
+      "loss": 4.8867,
+      "step": 21000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.760129659643436e-05,
+      "loss": 4.8784,
+      "step": 22000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 6.490275526742302e-05,
+      "loss": 4.8699,
+      "step": 23000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.29503009583386375,
+      "eval_loss": 4.865215301513672,
+      "eval_runtime": 1.4538,
+      "eval_samples_per_second": 595.674,
+      "eval_steps_per_second": 4.815,
+      "step": 23510
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 6.22015126958401e-05,
+      "loss": 4.8168,
+      "step": 24000
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 5.950297136682874e-05,
+      "loss": 4.7782,
+      "step": 25000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 5.680172879524581e-05,
+      "loss": 4.7791,
+      "step": 26000
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 5.410318746623447e-05,
+      "loss": 4.7784,
+      "step": 27000
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 5.140194489465154e-05,
+      "loss": 4.7738,
+      "step": 28000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.30020366969140405,
+      "eval_loss": 4.812718391418457,
+      "eval_runtime": 1.4498,
+      "eval_samples_per_second": 597.338,
+      "eval_steps_per_second": 4.828,
+      "step": 28212
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 4.87034035656402e-05,
+      "loss": 4.7033,
+      "step": 29000
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 4.600216099405727e-05,
+      "loss": 4.6956,
+      "step": 30000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 4.330361966504592e-05,
+      "loss": 4.6959,
+      "step": 31000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 4.0602377093463e-05,
+      "loss": 4.6966,
+      "step": 32000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3044225418704879,
+      "eval_loss": 4.7761945724487305,
+      "eval_runtime": 1.4505,
+      "eval_samples_per_second": 597.024,
+      "eval_steps_per_second": 4.826,
+      "step": 32914
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 3.790383576445165e-05,
+      "loss": 4.6884,
+      "step": 33000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 3.520259319286872e-05,
+      "loss": 4.6182,
+      "step": 34000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 3.250405186385738e-05,
+      "loss": 4.6246,
+      "step": 35000
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 2.9802809292274448e-05,
+      "loss": 4.6318,
+      "step": 36000
+    },
+    {
+      "epoch": 7.87,
+      "learning_rate": 2.7104267963263103e-05,
+      "loss": 4.6296,
+      "step": 37000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.30685021185284866,
+      "eval_loss": 4.7499237060546875,
+      "eval_runtime": 1.4456,
+      "eval_samples_per_second": 599.074,
+      "eval_steps_per_second": 4.842,
+      "step": 37616
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 2.4403025391680173e-05,
+      "loss": 4.6027,
+      "step": 38000
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 2.170448406266883e-05,
+      "loss": 4.5656,
+      "step": 39000
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 1.9003241491085898e-05,
+      "loss": 4.5703,
+      "step": 40000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 1.6304700162074554e-05,
+      "loss": 4.5718,
+      "step": 41000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 1.3603457590491628e-05,
+      "loss": 4.5712,
+      "step": 42000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.30869596843119784,
+      "eval_loss": 4.733290195465088,
+      "eval_runtime": 1.4519,
+      "eval_samples_per_second": 596.477,
+      "eval_steps_per_second": 4.821,
+      "step": 42318
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 1.0904916261480282e-05,
+      "loss": 4.5367,
+      "step": 43000
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 8.203673689897353e-06,
+      "loss": 4.5226,
+      "step": 44000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 5.505132360886007e-06,
+      "loss": 4.5228,
+      "step": 45000
+    },
+    {
+      "epoch": 9.78,
+      "learning_rate": 2.8038897893030795e-06,
+      "loss": 4.5214,
+      "step": 46000
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.0534846029173421e-07,
+      "loss": 4.5227,
+      "step": 47000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.31029623029222964,
+      "eval_loss": 4.725980758666992,
+      "eval_runtime": 1.4835,
+      "eval_samples_per_second": 583.771,
+      "eval_steps_per_second": 4.719,
+      "step": 47020
+    },
+    {
+      "epoch": 10.0,
+      "step": 47020,
+      "total_flos": 3.930942652416e+17,
+      "train_loss": 5.095248515795566,
+      "train_runtime": 20611.3432,
+      "train_samples_per_second": 291.961,
+      "train_steps_per_second": 2.281
+    }
+  ],
+  "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 sha256:1f4ae50ed65894fec9166589317fb97f04522509c7ada2624ee28cf9d1a534d3
+size 4881