Training in progress, epoch 1

README.md

@@ -0,0 +1,104 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M10KInfPrompt_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. -->
+
+# Se124M10KInfPrompt_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: 0.7552
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6082        | 1.0   | 153  | 1.4745          |
+| 0.3175        | 2.0   | 306  | 1.0258          |
+| 0.2798        | 3.0   | 459  | 0.9099          |
+| 0.244         | 4.0   | 612  | 0.8688          |
+| 0.2373        | 5.0   | 765  | 0.8479          |
+| 0.2252        | 6.0   | 918  | 0.8343          |
+| 0.2289        | 7.0   | 1071 | 0.8216          |
+| 0.2209        | 8.0   | 1224 | 0.8143          |
+| 0.2211        | 9.0   | 1377 | 0.8082          |
+| 0.2176        | 10.0  | 1530 | 0.8029          |
+| 0.2157        | 11.0  | 1683 | 0.7990          |
+| 0.2097        | 12.0  | 1836 | 0.7945          |
+| 0.2113        | 13.0  | 1989 | 0.7921          |
+| 0.2099        | 14.0  | 2142 | 0.7891          |
+| 0.2073        | 15.0  | 2295 | 0.7863          |
+| 0.2055        | 16.0  | 2448 | 0.7805          |
+| 0.2051        | 17.0  | 2601 | 0.7806          |
+| 0.2031        | 18.0  | 2754 | 0.7776          |
+| 0.2046        | 19.0  | 2907 | 0.7760          |
+| 0.206         | 20.0  | 3060 | 0.7720          |
+| 0.2043        | 21.0  | 3213 | 0.7725          |
+| 0.204         | 22.0  | 3366 | 0.7707          |
+| 0.2032        | 23.0  | 3519 | 0.7681          |
+| 0.2026        | 24.0  | 3672 | 0.7678          |
+| 0.1991        | 25.0  | 3825 | 0.7665          |
+| 0.2037        | 26.0  | 3978 | 0.7660          |
+| 0.2011        | 27.0  | 4131 | 0.7634          |
+| 0.2015        | 28.0  | 4284 | 0.7635          |
+| 0.2006        | 29.0  | 4437 | 0.7620          |
+| 0.2014        | 30.0  | 4590 | 0.7640          |
+| 0.2           | 31.0  | 4743 | 0.7609          |
+| 0.202         | 32.0  | 4896 | 0.7606          |
+| 0.1989        | 33.0  | 5049 | 0.7599          |
+| 0.1983        | 34.0  | 5202 | 0.7594          |
+| 0.2           | 35.0  | 5355 | 0.7596          |
+| 0.1991        | 36.0  | 5508 | 0.7588          |
+| 0.1978        | 37.0  | 5661 | 0.7576          |
+| 0.1975        | 38.0  | 5814 | 0.7572          |
+| 0.2007        | 39.0  | 5967 | 0.7569          |
+| 0.1987        | 40.0  | 6120 | 0.7563          |
+| 0.2002        | 41.0  | 6273 | 0.7561          |
+| 0.1961        | 42.0  | 6426 | 0.7563          |
+| 0.201         | 43.0  | 6579 | 0.7552          |
+| 0.1993        | 44.0  | 6732 | 0.7553          |
+| 0.1969        | 45.0  | 6885 | 0.7553          |
+
+
+### 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:a6eb1878e595d65bb27367a30d55fd8865df77dba28498c606af68a0bb41d6df
+size 309974336

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 45.0,
+    "eval_loss": 0.7551774382591248,
+    "eval_runtime": 6.5379,
+    "eval_samples_per_second": 161.672,
+    "eval_steps_per_second": 5.2,
+    "perplexity": 2.127989076535295,
+    "total_flos": 1.438582110879744e+16,
+    "train_loss": 0.2186263353822884,
+    "train_runtime": 769.5598,
+    "train_samples_per_second": 316.869,
+    "train_steps_per_second": 9.941
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 45.0,
+    "eval_loss": 0.7551774382591248,
+    "eval_runtime": 6.5379,
+    "eval_samples_per_second": 161.672,
+    "eval_steps_per_second": 5.2,
+    "perplexity": 2.127989076535295
+}

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": 45.0,
+    "total_flos": 1.438582110879744e+16,
+    "train_loss": 0.2186263353822884,
+    "train_runtime": 769.5598,
+    "train_samples_per_second": 316.869,
+    "train_steps_per_second": 9.941
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bd0190032b8576fa67d50e424c4c48cd36048fc82231e1db1117e678eb5423
+size 5432