Final model checkpoint

README.md

@@ -0,0 +1,161 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: tfa_output_2025_m02_d02_t23h_29m_10s
+  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. -->
+
+# tfa_output_2025_m02_d02_t23h_29m_10s
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5286
+
+## 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: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| No log        | 0       | 0    | 3.1242          |
+| 3.6266        | 0.6667  | 1    | 3.1242          |
+| 1.7421        | 1.0     | 2    | 3.1070          |
+| 3.5691        | 1.6667  | 3    | 3.0863          |
+| 1.8145        | 2.0     | 4    | 3.0757          |
+| 3.5803        | 2.6667  | 5    | 3.0580          |
+| 1.7267        | 3.0     | 6    | 3.0413          |
+| 3.5001        | 3.6667  | 7    | 3.0321          |
+| 1.756         | 4.0     | 8    | 3.0203          |
+| 3.5043        | 4.6667  | 9    | 3.0064          |
+| 1.6752        | 5.0     | 10   | 2.9966          |
+| 3.449         | 5.6667  | 11   | 2.9887          |
+| 1.7513        | 6.0     | 12   | 2.9786          |
+| 3.4134        | 6.6667  | 13   | 2.9696          |
+| 1.7109        | 7.0     | 14   | 2.9604          |
+| 3.4382        | 7.6667  | 15   | 2.9518          |
+| 1.6749        | 8.0     | 16   | 2.9431          |
+| 3.3344        | 8.6667  | 17   | 2.9329          |
+| 1.7577        | 9.0     | 18   | 2.9260          |
+| 3.3458        | 9.6667  | 19   | 2.9184          |
+| 1.6737        | 10.0    | 20   | 2.9092          |
+| 3.4422        | 10.6667 | 21   | 2.8993          |
+| 1.5953        | 11.0    | 22   | 2.8892          |
+| 3.3445        | 11.6667 | 23   | 2.8819          |
+| 1.631         | 12.0    | 24   | 2.8721          |
+| 3.3118        | 12.6667 | 25   | 2.8626          |
+| 1.6067        | 13.0    | 26   | 2.8547          |
+| 3.2708        | 13.6667 | 27   | 2.8468          |
+| 1.619         | 14.0    | 28   | 2.8393          |
+| 3.3062        | 14.6667 | 29   | 2.8312          |
+| 1.6059        | 15.0    | 30   | 2.8240          |
+| 3.2822        | 15.6667 | 31   | 2.8154          |
+| 1.607         | 16.0    | 32   | 2.8071          |
+| 3.2488        | 16.6667 | 33   | 2.7995          |
+| 1.6078        | 17.0    | 34   | 2.7929          |
+| 3.2022        | 17.6667 | 35   | 2.7875          |
+| 1.5858        | 18.0    | 36   | 2.7801          |
+| 3.1965        | 18.6667 | 37   | 2.7720          |
+| 1.5955        | 19.0    | 38   | 2.7656          |
+| 3.1891        | 19.6667 | 39   | 2.7606          |
+| 1.5755        | 20.0    | 40   | 2.7527          |
+| 3.0662        | 20.6667 | 41   | 2.7467          |
+| 1.6257        | 21.0    | 42   | 2.7411          |
+| 3.1364        | 21.6667 | 43   | 2.7350          |
+| 1.5211        | 22.0    | 44   | 2.7288          |
+| 3.157         | 22.6667 | 45   | 2.7235          |
+| 1.4631        | 23.0    | 46   | 2.7158          |
+| 3.1188        | 23.6667 | 47   | 2.7099          |
+| 1.4971        | 24.0    | 48   | 2.7063          |
+| 2.98          | 24.6667 | 49   | 2.7008          |
+| 1.634         | 25.0    | 50   | 2.6942          |
+| 3.016         | 25.6667 | 51   | 2.6879          |
+| 1.5771        | 26.0    | 52   | 2.6843          |
+| 3.0495        | 26.6667 | 53   | 2.6808          |
+| 1.4922        | 27.0    | 54   | 2.6750          |
+| 2.9655        | 27.6667 | 55   | 2.6711          |
+| 1.6188        | 28.0    | 56   | 2.6655          |
+| 3.0155        | 28.6667 | 57   | 2.6611          |
+| 1.4867        | 29.0    | 58   | 2.6567          |
+| 3.0117        | 29.6667 | 59   | 2.6515          |
+| 1.5069        | 30.0    | 60   | 2.6470          |
+| 3.0118        | 30.6667 | 61   | 2.6441          |
+| 1.4577        | 31.0    | 62   | 2.6375          |
+| 3.0372        | 31.6667 | 63   | 2.6350          |
+| 1.411         | 32.0    | 64   | 2.6295          |
+| 2.9611        | 32.6667 | 65   | 2.6267          |
+| 1.4289        | 33.0    | 66   | 2.6246          |
+| 2.9595        | 33.6667 | 67   | 2.6207          |
+| 1.437         | 34.0    | 68   | 2.6166          |
+| 2.9483        | 34.6667 | 69   | 2.6127          |
+| 1.4469        | 35.0    | 70   | 2.6114          |
+| 2.9291        | 35.6667 | 71   | 2.6067          |
+| 1.411         | 36.0    | 72   | 2.6021          |
+| 2.9534        | 36.6667 | 73   | 2.5988          |
+| 1.4295        | 37.0    | 74   | 2.5958          |
+| 2.9181        | 37.6667 | 75   | 2.5929          |
+| 1.4138        | 38.0    | 76   | 2.5891          |
+| 2.9133        | 38.6667 | 77   | 2.5855          |
+| 1.4172        | 39.0    | 78   | 2.5818          |
+| 2.8655        | 39.6667 | 79   | 2.5809          |
+| 1.3988        | 40.0    | 80   | 2.5780          |
+| 2.929         | 40.6667 | 81   | 2.5750          |
+| 1.3445        | 41.0    | 82   | 2.5712          |
+| 2.8141        | 41.6667 | 83   | 2.5696          |
+| 1.503         | 42.0    | 84   | 2.5668          |
+| 2.8483        | 42.6667 | 85   | 2.5636          |
+| 1.4017        | 43.0    | 86   | 2.5622          |
+| 2.8643        | 43.6667 | 87   | 2.5575          |
+| 1.3592        | 44.0    | 88   | 2.5553          |
+| 2.8332        | 44.6667 | 89   | 2.5537          |
+| 1.3675        | 45.0    | 90   | 2.5503          |
+| 2.742         | 45.6667 | 91   | 2.5478          |
+| 1.5006        | 46.0    | 92   | 2.5453          |
+| 2.7909        | 46.6667 | 93   | 2.5436          |
+| 1.4314        | 47.0    | 94   | 2.5406          |
+| 2.7937        | 47.6667 | 95   | 2.5382          |
+| 1.3617        | 48.0    | 96   | 2.5359          |
+| 2.8299        | 48.6667 | 97   | 2.5343          |
+| 1.3295        | 49.0    | 98   | 2.5306          |
+| 2.7586        | 49.6667 | 99   | 2.5297          |
+| 1.4496        | 50.0    | 100  | 2.5286          |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 1024,
+  "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": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.48.0"
+}

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700f2e892200ca09e7de5d9f4daaa137c089b77eca7ad014b066335714875d7d
+size 497774208

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

UDACA/gpt2-pn-v3-lean4-train-on-validation-2025_m02_d02_t23h_29m_10s/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273068530a8a0c8f8883f1799fd9d40600a14186bdea3ca2878219382c6bdef8
+size 5432

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 1024,
+  "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": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700f2e892200ca09e7de5d9f4daaa137c089b77eca7ad014b066335714875d7d
+size 497774208

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273068530a8a0c8f8883f1799fd9d40600a14186bdea3ca2878219382c6bdef8
+size 5432