Training in progress, epoch 1

README.md

@@ -0,0 +1,109 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M100KInfPrompt_endtoken
+  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. -->
+
+# Se124M100KInfPrompt_endtoken
+
+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: 0.6957
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.2129        | 1.0   | 1430  | 0.8043          |
+| 0.2018        | 2.0   | 2860  | 0.7705          |
+| 0.1949        | 3.0   | 4290  | 0.7588          |
+| 0.1913        | 4.0   | 5720  | 0.7498          |
+| 0.1921        | 5.0   | 7150  | 0.7435          |
+| 0.1903        | 6.0   | 8580  | 0.7371          |
+| 0.1888        | 7.0   | 10010 | 0.7339          |
+| 0.1881        | 8.0   | 11440 | 0.7299          |
+| 0.1872        | 9.0   | 12870 | 0.7267          |
+| 0.187         | 10.0  | 14300 | 0.7251          |
+| 0.184         | 11.0  | 15730 | 0.7229          |
+| 0.1846        | 12.0  | 17160 | 0.7212          |
+| 0.1851        | 13.0  | 18590 | 0.7182          |
+| 0.1804        | 14.0  | 20020 | 0.7153          |
+| 0.1848        | 15.0  | 21450 | 0.7141          |
+| 0.1824        | 16.0  | 22880 | 0.7144          |
+| 0.1796        | 17.0  | 24310 | 0.7116          |
+| 0.18          | 18.0  | 25740 | 0.7108          |
+| 0.1825        | 19.0  | 27170 | 0.7082          |
+| 0.1852        | 20.0  | 28600 | 0.7082          |
+| 0.1785        | 21.0  | 30030 | 0.7072          |
+| 0.1811        | 22.0  | 31460 | 0.7057          |
+| 0.178         | 23.0  | 32890 | 0.7059          |
+| 0.1827        | 24.0  | 34320 | 0.7046          |
+| 0.1813        | 25.0  | 35750 | 0.7033          |
+| 0.1825        | 26.0  | 37180 | 0.7039          |
+| 0.1795        | 27.0  | 38610 | 0.7032          |
+| 0.1801        | 28.0  | 40040 | 0.7017          |
+| 0.1781        | 29.0  | 41470 | 0.7013          |
+| 0.1823        | 30.0  | 42900 | 0.7010          |
+| 0.1781        | 31.0  | 44330 | 0.7012          |
+| 0.1809        | 32.0  | 45760 | 0.6999          |
+| 0.1764        | 33.0  | 47190 | 0.6996          |
+| 0.1791        | 34.0  | 48620 | 0.6983          |
+| 0.1793        | 35.0  | 50050 | 0.6988          |
+| 0.1785        | 36.0  | 51480 | 0.6980          |
+| 0.1777        | 37.0  | 52910 | 0.6980          |
+| 0.1774        | 38.0  | 54340 | 0.6980          |
+| 0.1795        | 39.0  | 55770 | 0.6976          |
+| 0.1772        | 40.0  | 57200 | 0.6974          |
+| 0.1793        | 41.0  | 58630 | 0.6974          |
+| 0.1777        | 42.0  | 60060 | 0.6968          |
+| 0.1777        | 43.0  | 61490 | 0.6965          |
+| 0.1779        | 44.0  | 62920 | 0.6965          |
+| 0.1782        | 45.0  | 64350 | 0.6964          |
+| 0.1765        | 46.0  | 65780 | 0.6961          |
+| 0.1758        | 47.0  | 67210 | 0.6962          |
+| 0.1763        | 48.0  | 68640 | 0.6960          |
+| 0.1788        | 49.0  | 70070 | 0.6958          |
+| 0.1776        | 50.0  | 71500 | 0.6957          |
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu118
+- Datasets 3.5.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685613b0b2848864eef3cbf6d9ca6ef3594d1b43bbe6de34e85c8d9858ba09ef
+size 309974336

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<endofex>": 50258,
+  "<startofex>": 50257
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.6956692934036255,
+    "eval_runtime": 59.8322,
+    "eval_samples_per_second": 163.257,
+    "eval_steps_per_second": 5.114,
+    "perplexity": 2.005050592091695,
+    "total_flos": 1.49878932701184e+17,
+    "train_loss": 0.18437957987751993,
+    "train_runtime": 7319.2549,
+    "train_samples_per_second": 312.395,
+    "train_steps_per_second": 9.769
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.6956692934036255,
+    "eval_runtime": 59.8322,
+    "eval_samples_per_second": 163.257,
+    "eval_steps_per_second": 5.114,
+    "perplexity": 2.005050592091695
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<startofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<endofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<endofex>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<startofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<endofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<startofex>",
+    "<endofex>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<endofex>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "total_flos": 1.49878932701184e+17,
+    "train_loss": 0.18437957987751993,
+    "train_runtime": 7319.2549,
+    "train_samples_per_second": 312.395,
+    "train_steps_per_second": 9.769
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afeebf18458521f7886066b8ec8ac963d073812d904190859301f0da630f17d
+size 5432