Training in progress, epoch 1

README.md

@@ -0,0 +1,84 @@
+---
+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: 0.6872
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.8085        | 1.0   | 610   | 0.7760          |
+| 0.7801        | 2.0   | 1220  | 0.7436          |
+| 0.7608        | 3.0   | 1830  | 0.7269          |
+| 0.7438        | 4.0   | 2440  | 0.7199          |
+| 0.7413        | 5.0   | 3050  | 0.7118          |
+| 0.7343        | 6.0   | 3660  | 0.7121          |
+| 0.7332        | 7.0   | 4270  | 0.7089          |
+| 0.7319        | 8.0   | 4880  | 0.7025          |
+| 0.7289        | 9.0   | 5490  | 0.7001          |
+| 0.7236        | 10.0  | 6100  | 0.6965          |
+| 0.7147        | 11.0  | 6710  | 0.6970          |
+| 0.7126        | 12.0  | 7320  | 0.6973          |
+| 0.7167        | 13.0  | 7930  | 0.6935          |
+| 0.711         | 14.0  | 8540  | 0.6927          |
+| 0.7057        | 15.0  | 9150  | 0.6940          |
+| 0.7109        | 16.0  | 9760  | 0.6924          |
+| 0.7117        | 17.0  | 10370 | 0.6928          |
+| 0.7086        | 18.0  | 10980 | 0.6882          |
+| 0.7004        | 19.0  | 11590 | 0.6872          |
+| 0.7016        | 20.0  | 12200 | 0.6895          |
+| 0.7027        | 21.0  | 12810 | 0.6884          |
+| 0.6928        | 22.0  | 13420 | 0.6885          |
+| 0.7059        | 23.0  | 14030 | 0.6894          |
+| 0.6916        | 24.0  | 14640 | 0.6875          |
+
+
+### 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 sha256:51db2ec4a47bd18d996717e015fa3067dc9afa2b9ed7637bc76f69320bc02532
+size 309980480

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 24.0,
+    "eval_loss": 0.6872262954711914,
+    "eval_runtime": 1.8886,
+    "eval_samples_per_second": 559.678,
+    "eval_steps_per_second": 70.423,
+    "perplexity": 1.9881932176157675,
+    "total_flos": 7672437924691968.0,
+    "train_loss": 0.7372308338926138,
+    "train_runtime": 572.2889,
+    "train_samples_per_second": 426.096,
+    "train_steps_per_second": 53.295
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 24.0,
+    "eval_loss": 0.6872262954711914,
+    "eval_runtime": 1.8886,
+    "eval_samples_per_second": 559.678,
+    "eval_steps_per_second": 70.423,
+    "perplexity": 1.9881932176157675
+}

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": 24.0,
+    "total_flos": 7672437924691968.0,
+    "train_loss": 0.7372308338926138,
+    "train_runtime": 572.2889,
+    "train_samples_per_second": 426.096,
+    "train_steps_per_second": 53.295
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f55b4e66571daf6f19dab0928d3c98956c4ff5ac9849dd910f0d3be8a7519d
+size 5432