Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: GPT2_more_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_more_function_53
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3533
+- Accuracy: 0.2671
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 5.6324        | 1.0   | 6417  | 5.4069          | 0.1901   |
+| 4.9863        | 2.0   | 12834 | 4.8399          | 0.2250   |
+| 4.7128        | 3.0   | 19251 | 4.6418          | 0.2408   |
+| 4.5849        | 4.0   | 25668 | 4.5399          | 0.2498   |
+| 4.485         | 5.0   | 32085 | 4.4786          | 0.2551   |
+| 4.4117        | 6.0   | 38502 | 4.4334          | 0.2588   |
+| 4.3507        | 7.0   | 44919 | 4.4014          | 0.2623   |
+| 4.2955        | 8.0   | 51336 | 4.3777          | 0.2646   |
+| 4.2474        | 9.0   | 57753 | 4.3611          | 0.2660   |
+| 4.2047        | 10.0  | 64170 | 4.3533          | 0.2671   |
+
+
+### 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": 0.267075394201679,
+    "eval_loss": 4.353286266326904,
+    "eval_runtime": 1.9498,
+    "eval_samples": 1179,
+    "eval_samples_per_second": 604.666,
+    "eval_steps_per_second": 5.129,
+    "perplexity": 77.73349661382329,
+    "train_loss": 4.69663484373326,
+    "train_runtime": 28007.947,
+    "train_samples": 821300,
+    "train_samples_per_second": 293.238,
+    "train_steps_per_second": 2.291
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "models/GPT2_more_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": 0.267075394201679,
+    "eval_loss": 4.353286266326904,
+    "eval_runtime": 1.9498,
+    "eval_samples": 1179,
+    "eval_samples_per_second": 604.666,
+    "eval_steps_per_second": 5.129,
+    "perplexity": 77.73349661382329
+}

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:b282d71743b09ea30ce9c16607d3a96ef9b39879055d442dfdb47f56dd379e11
+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": 4.69663484373326,
+    "train_runtime": 28007.947,
+    "train_samples": 821300,
+    "train_samples_per_second": 293.238,
+    "train_steps_per_second": 2.291
+}

trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_metric": 4.353286266326904,
+  "best_model_checkpoint": "models/GPT2_more_function_53/checkpoint-64170",
+  "epoch": 10.0,
+  "global_step": 64170,
+  "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": 8.1886,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2e-05,
+      "loss": 6.8727,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3e-05,
+      "loss": 6.4088,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4e-05,
+      "loss": 6.0857,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 5.8321,
+      "step": 5000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6e-05,
+      "loss": 5.6324,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1900583037807297,
+      "eval_loss": 5.406868934631348,
+      "eval_runtime": 1.9656,
+      "eval_samples_per_second": 599.816,
+      "eval_steps_per_second": 5.088,
+      "step": 6417
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7e-05,
+      "loss": 5.464,
+      "step": 7000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8e-05,
+      "loss": 5.328,
+      "step": 8000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9e-05,
+      "loss": 5.2203,
+      "step": 9000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001,
+      "loss": 5.1311,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.815580579656637e-05,
+      "loss": 5.0538,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.630976555288906e-05,
+      "loss": 4.9863,
+      "step": 12000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.22501385800057436,
+      "eval_loss": 4.839901924133301,
+      "eval_runtime": 1.9549,
+      "eval_samples_per_second": 603.101,
+      "eval_steps_per_second": 5.115,
+      "step": 12834
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.446557134945542e-05,
+      "loss": 4.9247,
+      "step": 13000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.26195311057781e-05,
+      "loss": 4.8477,
+      "step": 14000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 9.077533690234448e-05,
+      "loss": 4.8179,
+      "step": 15000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.892929665866716e-05,
+      "loss": 4.7877,
+      "step": 16000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 8.708510245523353e-05,
+      "loss": 4.7605,
+      "step": 17000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.523906221155622e-05,
+      "loss": 4.7362,
+      "step": 18000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 8.339486800812258e-05,
+      "loss": 4.7128,
+      "step": 19000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.24079528226910568,
+      "eval_loss": 4.641803741455078,
+      "eval_runtime": 1.9635,
+      "eval_samples_per_second": 600.449,
+      "eval_steps_per_second": 5.093,
+      "step": 19251
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 8.154882776444527e-05,
+      "loss": 4.6461,
+      "step": 20000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 7.970463356101163e-05,
+      "loss": 4.6251,
+      "step": 21000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 7.785859331733432e-05,
+      "loss": 4.6154,
+      "step": 22000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 7.60143991139007e-05,
+      "loss": 4.606,
+      "step": 23000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 7.416835887022337e-05,
+      "loss": 4.5953,
+      "step": 24000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 7.232416466678975e-05,
+      "loss": 4.5849,
+      "step": 25000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24978461661757928,
+      "eval_loss": 4.5399394035339355,
+      "eval_runtime": 1.9869,
+      "eval_samples_per_second": 593.401,
+      "eval_steps_per_second": 5.033,
+      "step": 25668
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 7.047812442311242e-05,
+      "loss": 4.547,
+      "step": 26000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 6.863393021967878e-05,
+      "loss": 4.502,
+      "step": 27000
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 6.678788997600149e-05,
+      "loss": 4.5043,
+      "step": 28000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.494369577256785e-05,
+      "loss": 4.4988,
+      "step": 29000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.309765552889054e-05,
+      "loss": 4.4946,
+      "step": 30000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 6.12534613254569e-05,
+      "loss": 4.4897,
+      "step": 31000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 5.940742108177959e-05,
+      "loss": 4.485,
+      "step": 32000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.2550740317765623,
+      "eval_loss": 4.478567600250244,
+      "eval_runtime": 1.9498,
+      "eval_samples_per_second": 604.677,
+      "eval_steps_per_second": 5.129,
+      "step": 32085
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 5.7563226878345955e-05,
+      "loss": 4.4151,
+      "step": 33000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 5.571718663466864e-05,
+      "loss": 4.416,
+      "step": 34000
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 5.3872992431235006e-05,
+      "loss": 4.4179,
+      "step": 35000
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 5.202695218755769e-05,
+      "loss": 4.4176,
+      "step": 36000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 5.018275798412405e-05,
+      "loss": 4.4149,
+      "step": 37000
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 4.833671774044675e-05,
+      "loss": 4.4117,
+      "step": 38000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.2587672724115592,
+      "eval_loss": 4.433353424072266,
+      "eval_runtime": 1.9414,
+      "eval_samples_per_second": 607.287,
+      "eval_steps_per_second": 5.151,
+      "step": 38502
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 4.6492523537013114e-05,
+      "loss": 4.3737,
+      "step": 39000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 4.46464832933358e-05,
+      "loss": 4.3457,
+      "step": 40000
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 4.2802289089902164e-05,
+      "loss": 4.351,
+      "step": 41000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 4.095624884622485e-05,
+      "loss": 4.3507,
+      "step": 42000
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 3.9112054642791215e-05,
+      "loss": 4.353,
+      "step": 43000
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 3.7266014399113905e-05,
+      "loss": 4.3507,
+      "step": 44000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.26234029906567025,
+      "eval_loss": 4.401378154754639,
+      "eval_runtime": 1.9509,
+      "eval_samples_per_second": 604.326,
+      "eval_steps_per_second": 5.126,
+      "step": 44919
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 3.5421820195680266e-05,
+      "loss": 4.3421,
+      "step": 45000
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 3.3575779952002956e-05,
+      "loss": 4.2851,
+      "step": 46000
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 3.173158574856932e-05,
+      "loss": 4.292,
+      "step": 47000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 2.988554550489201e-05,
+      "loss": 4.2954,
+      "step": 48000
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 2.8041351301458374e-05,
+      "loss": 4.2978,
+      "step": 49000
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 2.6195311057781064e-05,
+      "loss": 4.2961,
+      "step": 50000
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 2.4351116854347424e-05,
+      "loss": 4.2955,
+      "step": 51000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.26463772181149114,
+      "eval_loss": 4.3776960372924805,
+      "eval_runtime": 1.9467,
+      "eval_samples_per_second": 605.639,
+      "eval_steps_per_second": 5.137,
+      "step": 51336
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 2.2505076610670114e-05,
+      "loss": 4.2564,
+      "step": 52000
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 2.06590363669928e-05,
+      "loss": 4.242,
+      "step": 53000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 1.8814842163559165e-05,
+      "loss": 4.2455,
+      "step": 54000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 1.6968801919881855e-05,
+      "loss": 4.2465,
+      "step": 55000
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 1.5124607716448219e-05,
+      "loss": 4.2493,
+      "step": 56000
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 1.3278567472770906e-05,
+      "loss": 4.2474,
+      "step": 57000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2660068254826925,
+      "eval_loss": 4.361112594604492,
+      "eval_runtime": 1.9399,
+      "eval_samples_per_second": 607.753,
+      "eval_steps_per_second": 5.155,
+      "step": 57753
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 1.1434373269337271e-05,
+      "loss": 4.2371,
+      "step": 58000
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 9.58833302565996e-06,
+      "loss": 4.2035,
+      "step": 59000
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 7.744138822226325e-06,
+      "loss": 4.2061,
+      "step": 60000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 5.898098578549013e-06,
+      "loss": 4.2083,
+      "step": 61000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 4.0539043751153775e-06,
+      "loss": 4.207,
+      "step": 62000
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 2.2078641314380656e-06,
+      "loss": 4.2071,
+      "step": 63000
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 3.636699280044305e-07,
+      "loss": 4.2047,
+      "step": 64000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.267075394201679,
+      "eval_loss": 4.353286266326904,
+      "eval_runtime": 1.9413,
+      "eval_samples_per_second": 607.324,
+      "eval_steps_per_second": 5.151,
+      "step": 64170
+    },
+    {
+      "epoch": 10.0,
+      "step": 64170,
+      "total_flos": 5.36497864704e+17,
+      "train_loss": 4.69663484373326,
+      "train_runtime": 28007.947,
+      "train_samples_per_second": 293.238,
+      "train_steps_per_second": 2.291
+    }
+  ],
+  "max_steps": 64170,
+  "num_train_epochs": 10,
+  "total_flos": 5.36497864704e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c270417da259b614911f842e7e75a62d06c13a13717fe5838b4e6fb10035d4
+size 4881