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_endtoken2
+  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_endtoken2
+
+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: 0.6701
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.7736        | 1.0   | 1066  | 0.7302          |
+| 0.7318        | 2.0   | 2132  | 0.7070          |
+| 0.7189        | 3.0   | 3198  | 0.7002          |
+| 0.7128        | 4.0   | 4264  | 0.6952          |
+| 0.7031        | 5.0   | 5330  | 0.6878          |
+| 0.6944        | 6.0   | 6396  | 0.6873          |
+| 0.6935        | 7.0   | 7462  | 0.6879          |
+| 0.6987        | 8.0   | 8528  | 0.6837          |
+| 0.7011        | 9.0   | 9594  | 0.6830          |
+| 0.6799        | 10.0  | 10660 | 0.6819          |
+| 0.6754        | 11.0  | 11726 | 0.6793          |
+| 0.6769        | 12.0  | 12792 | 0.6800          |
+| 0.6827        | 13.0  | 13858 | 0.6766          |
+| 0.6905        | 14.0  | 14924 | 0.6808          |
+| 0.6769        | 15.0  | 15990 | 0.6769          |
+| 0.6751        | 16.0  | 17056 | 0.6776          |
+| 0.688         | 17.0  | 18122 | 0.6739          |
+| 0.6922        | 18.0  | 19188 | 0.6772          |
+| 0.6804        | 19.0  | 20254 | 0.6743          |
+| 0.6718        | 20.0  | 21320 | 0.6738          |
+| 0.681         | 21.0  | 22386 | 0.6749          |
+| 0.6757        | 22.0  | 23452 | 0.6729          |
+| 0.6777        | 23.0  | 24518 | 0.6756          |
+| 0.6667        | 24.0  | 25584 | 0.6730          |
+| 0.6758        | 25.0  | 26650 | 0.6719          |
+| 0.6602        | 26.0  | 27716 | 0.6715          |
+| 0.6746        | 27.0  | 28782 | 0.6723          |
+| 0.6647        | 28.0  | 29848 | 0.6721          |
+| 0.6673        | 29.0  | 30914 | 0.6732          |
+| 0.6745        | 30.0  | 31980 | 0.6728          |
+| 0.6659        | 31.0  | 33046 | 0.6710          |
+| 0.6578        | 32.0  | 34112 | 0.6710          |
+| 0.6649        | 33.0  | 35178 | 0.6711          |
+| 0.6665        | 34.0  | 36244 | 0.6710          |
+| 0.6608        | 35.0  | 37310 | 0.6714          |
+| 0.6623        | 36.0  | 38376 | 0.6708          |
+| 0.6789        | 37.0  | 39442 | 0.6704          |
+| 0.6536        | 38.0  | 40508 | 0.6708          |
+| 0.6746        | 39.0  | 41574 | 0.6710          |
+| 0.6634        | 40.0  | 42640 | 0.6704          |
+| 0.65          | 41.0  | 43706 | 0.6710          |
+| 0.6638        | 42.0  | 44772 | 0.6702          |
+| 0.6586        | 43.0  | 45838 | 0.6705          |
+| 0.6546        | 44.0  | 46904 | 0.6706          |
+| 0.651         | 45.0  | 47970 | 0.6701          |
+| 0.6604        | 46.0  | 49036 | 0.6705          |
+| 0.6756        | 47.0  | 50102 | 0.6706          |
+| 0.6612        | 48.0  | 51168 | 0.6705          |
+| 0.6553        | 49.0  | 52234 | 0.6705          |
+| 0.6561        | 50.0  | 53300 | 0.6704          |
+
+
+### 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 sha256:981dd7b57c770251dfd9407451f97a9ae7840da45c17e83d68848b905fad1992
+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": 0.6701372861862183,
+    "eval_runtime": 3.1131,
+    "eval_samples_per_second": 587.189,
+    "eval_steps_per_second": 73.559,
+    "perplexity": 1.9545056288417388,
+    "total_flos": 2.3883058800820224e+16,
+    "train_loss": 0.6825056470402187,
+    "train_runtime": 1762.4542,
+    "train_samples_per_second": 241.935,
+    "train_steps_per_second": 30.242
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.6701372861862183,
+    "eval_runtime": 3.1131,
+    "eval_samples_per_second": 587.189,
+    "eval_steps_per_second": 73.559,
+    "perplexity": 1.9545056288417388
+}

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": 2.3883058800820224e+16,
+    "train_loss": 0.6825056470402187,
+    "train_runtime": 1762.4542,
+    "train_samples_per_second": 241.935,
+    "train_steps_per_second": 30.242
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48219bdfa97f4c279ac79e276a9fc8375db349454279612ebb625d7914a95a34
+size 5432