Training in progress, epoch 1

README.md

@@ -0,0 +1,106 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M10KInfPrompt
+  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
+
+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: 0.7128
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.4014        | 1.0   | 267   | 1.0141          |
+| 0.2422        | 2.0   | 534   | 0.8523          |
+| 0.2202        | 3.0   | 801   | 0.8168          |
+| 0.2129        | 4.0   | 1068  | 0.7993          |
+| 0.2059        | 5.0   | 1335  | 0.7837          |
+| 0.2041        | 6.0   | 1602  | 0.7695          |
+| 0.2031        | 7.0   | 1869  | 0.7635          |
+| 0.1982        | 8.0   | 2136  | 0.7586          |
+| 0.1975        | 9.0   | 2403  | 0.7532          |
+| 0.1974        | 10.0  | 2670  | 0.7483          |
+| 0.1978        | 11.0  | 2937  | 0.7467          |
+| 0.1939        | 12.0  | 3204  | 0.7445          |
+| 0.1953        | 13.0  | 3471  | 0.7439          |
+| 0.1929        | 14.0  | 3738  | 0.7362          |
+| 0.1937        | 15.0  | 4005  | 0.7328          |
+| 0.1934        | 16.0  | 4272  | 0.7329          |
+| 0.1927        | 17.0  | 4539  | 0.7323          |
+| 0.1927        | 18.0  | 4806  | 0.7257          |
+| 0.1909        | 19.0  | 5073  | 0.7276          |
+| 0.1919        | 20.0  | 5340  | 0.7251          |
+| 0.1919        | 21.0  | 5607  | 0.7239          |
+| 0.1912        | 22.0  | 5874  | 0.7260          |
+| 0.1897        | 23.0  | 6141  | 0.7241          |
+| 0.1916        | 24.0  | 6408  | 0.7235          |
+| 0.1905        | 25.0  | 6675  | 0.7225          |
+| 0.1919        | 26.0  | 6942  | 0.7188          |
+| 0.1883        | 27.0  | 7209  | 0.7207          |
+| 0.1898        | 28.0  | 7476  | 0.7198          |
+| 0.1874        | 29.0  | 7743  | 0.7195          |
+| 0.188         | 30.0  | 8010  | 0.7194          |
+| 0.1873        | 31.0  | 8277  | 0.7182          |
+| 0.1878        | 32.0  | 8544  | 0.7212          |
+| 0.1866        | 33.0  | 8811  | 0.7171          |
+| 0.1883        | 34.0  | 9078  | 0.7151          |
+| 0.1881        | 35.0  | 9345  | 0.7176          |
+| 0.1868        | 36.0  | 9612  | 0.7149          |
+| 0.1871        | 37.0  | 9879  | 0.7157          |
+| 0.1876        | 38.0  | 10146 | 0.7162          |
+| 0.188         | 39.0  | 10413 | 0.7142          |
+| 0.1861        | 40.0  | 10680 | 0.7149          |
+| 0.1862        | 41.0  | 10947 | 0.7144          |
+| 0.1862        | 42.0  | 11214 | 0.7128          |
+| 0.186         | 43.0  | 11481 | 0.7136          |
+| 0.1868        | 44.0  | 11748 | 0.7137          |
+| 0.1837        | 45.0  | 12015 | 0.7138          |
+| 0.1868        | 46.0  | 12282 | 0.7141          |
+| 0.187         | 47.0  | 12549 | 0.7133          |
+
+
+### 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:cf9cd31ca462580715e5d6d00620cdda0650d86cf17c817bdb5eb3e63f7b13f6
+size 309980480

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 47.0,
+    "eval_loss": 0.7128096222877502,
+    "eval_runtime": 11.4031,
+    "eval_samples_per_second": 160.307,
+    "eval_steps_per_second": 5.086,
+    "perplexity": 2.039714041484612,
+    "total_flos": 2.5044104326938624e+16,
+    "train_loss": 0.1997737506061201,
+    "train_runtime": 1307.9406,
+    "train_samples_per_second": 326.009,
+    "train_steps_per_second": 10.207
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 47.0,
+    "eval_loss": 0.7128096222877502,
+    "eval_runtime": 11.4031,
+    "eval_samples_per_second": 160.307,
+    "eval_steps_per_second": 5.086,
+    "perplexity": 2.039714041484612
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "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": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<startofex>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "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": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 47.0,
+    "total_flos": 2.5044104326938624e+16,
+    "train_loss": 0.1997737506061201,
+    "train_runtime": 1307.9406,
+    "train_samples_per_second": 326.009,
+    "train_steps_per_second": 10.207
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc6f617ab1966ae5de1fbddfdf3b998b680d42983701a40b2dccf33f67d0711
+size 5432