Training in progress, epoch 1

README.md

@@ -0,0 +1,110 @@
+---
+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: 0.6695
+
+## 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- 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: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.7209        | 1.0   | 5717   | 0.7060          |
+| 0.7027        | 2.0   | 11434  | 0.6916          |
+| 0.7005        | 3.0   | 17151  | 0.6865          |
+| 0.7009        | 4.0   | 22868  | 0.6858          |
+| 0.6933        | 5.0   | 28585  | 0.6854          |
+| 0.6922        | 6.0   | 34302  | 0.6825          |
+| 0.6859        | 7.0   | 40019  | 0.6810          |
+| 0.6923        | 8.0   | 45736  | 0.6812          |
+| 0.6919        | 9.0   | 51453  | 0.6809          |
+| 0.6871        | 10.0  | 57170  | 0.6795          |
+| 0.6844        | 11.0  | 62887  | 0.6776          |
+| 0.6923        | 12.0  | 68604  | 0.6780          |
+| 0.6878        | 13.0  | 74321  | 0.6785          |
+| 0.6765        | 14.0  | 80038  | 0.6775          |
+| 0.6864        | 15.0  | 85755  | 0.6769          |
+| 0.6776        | 16.0  | 91472  | 0.6761          |
+| 0.6823        | 17.0  | 97189  | 0.6768          |
+| 0.6743        | 18.0  | 102906 | 0.6751          |
+| 0.682         | 19.0  | 108623 | 0.6776          |
+| 0.6902        | 20.0  | 114340 | 0.6762          |
+| 0.6774        | 21.0  | 120057 | 0.6751          |
+| 0.6748        | 22.0  | 125774 | 0.6747          |
+| 0.6864        | 23.0  | 131491 | 0.6745          |
+| 0.6819        | 24.0  | 137208 | 0.6756          |
+| 0.6818        | 25.0  | 142925 | 0.6745          |
+| 0.6757        | 26.0  | 148642 | 0.6737          |
+| 0.6801        | 27.0  | 154359 | 0.6734          |
+| 0.6717        | 28.0  | 160076 | 0.6724          |
+| 0.6717        | 29.0  | 165793 | 0.6722          |
+| 0.6802        | 30.0  | 171510 | 0.6723          |
+| 0.677         | 31.0  | 177227 | 0.6725          |
+| 0.6764        | 32.0  | 182944 | 0.6712          |
+| 0.6767        | 33.0  | 188661 | 0.6712          |
+| 0.6758        | 34.0  | 194378 | 0.6716          |
+| 0.6772        | 35.0  | 200095 | 0.6715          |
+| 0.679         | 36.0  | 205812 | 0.6717          |
+| 0.6744        | 37.0  | 211529 | 0.6702          |
+| 0.6654        | 38.0  | 217246 | 0.6707          |
+| 0.6723        | 39.0  | 222963 | 0.6704          |
+| 0.6758        | 40.0  | 228680 | 0.6701          |
+| 0.6795        | 41.0  | 234397 | 0.6701          |
+| 0.6681        | 42.0  | 240114 | 0.6698          |
+| 0.6761        | 43.0  | 245831 | 0.6700          |
+| 0.673         | 44.0  | 251548 | 0.6697          |
+| 0.6736        | 45.0  | 257265 | 0.6698          |
+| 0.673         | 46.0  | 262982 | 0.6695          |
+| 0.6686        | 47.0  | 268699 | 0.6695          |
+| 0.666         | 48.0  | 274416 | 0.6696          |
+| 0.663         | 49.0  | 280133 | 0.6695          |
+| 0.6667        | 50.0  | 285850 | 0.6695          |
+
+
+### 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 sha256:9eb51483cf968b82b0cf9c54f3b758fd80d876bc377ad9e2c2eb5508cf6ce063
+size 309980480

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<endofex>": 50257,
+  "<pad>": 50258,
+  "<startofex>": 50259
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.6694793105125427,
+    "eval_runtime": 16.9169,
+    "eval_samples_per_second": 577.411,
+    "eval_steps_per_second": 72.176,
+    "perplexity": 1.953220034675124,
+    "total_flos": 1.49878932701184e+17,
+    "train_loss": 0.6821009000064568,
+    "train_runtime": 10227.5107,
+    "train_samples_per_second": 223.564,
+    "train_steps_per_second": 27.949
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.6694793105125427,
+    "eval_runtime": 16.9169,
+    "eval_samples_per_second": 577.411,
+    "eval_steps_per_second": 72.176,
+    "perplexity": 1.953220034675124
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<startofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<endofex>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<endofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<startofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<startofex>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<endofex>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "total_flos": 1.49878932701184e+17,
+    "train_loss": 0.6821009000064568,
+    "train_runtime": 10227.5107,
+    "train_samples_per_second": 223.564,
+    "train_steps_per_second": 27.949
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc7dd218a4a2076a719892745d51eaf36a902a1f4a6f10e22d336f1f236a845
+size 5432