Training in progress, epoch 1

README.md

@@ -0,0 +1,109 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M100KInfKeyValue
+  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. -->
+
+# Se124M100KInfKeyValue
+
+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: 0.4826
+
+## 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 |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.1533        | 1.0   | 2090   | 0.5677          |
+| 0.141         | 2.0   | 4180   | 0.5401          |
+| 0.1401        | 3.0   | 6270   | 0.5321          |
+| 0.1351        | 4.0   | 8360   | 0.5224          |
+| 0.1361        | 5.0   | 10450  | 0.5209          |
+| 0.134         | 6.0   | 12540  | 0.5155          |
+| 0.1315        | 7.0   | 14630  | 0.5118          |
+| 0.1304        | 8.0   | 16720  | 0.5085          |
+| 0.1299        | 9.0   | 18810  | 0.5067          |
+| 0.1294        | 10.0  | 20900  | 0.5066          |
+| 0.1309        | 11.0  | 22990  | 0.5030          |
+| 0.129         | 12.0  | 25080  | 0.5004          |
+| 0.1292        | 13.0  | 27170  | 0.4999          |
+| 0.1309        | 14.0  | 29260  | 0.4985          |
+| 0.1312        | 15.0  | 31350  | 0.4974          |
+| 0.1275        | 16.0  | 33440  | 0.4963          |
+| 0.1265        | 17.0  | 35530  | 0.4950          |
+| 0.1276        | 18.0  | 37620  | 0.4936          |
+| 0.1247        | 19.0  | 39710  | 0.4931          |
+| 0.1268        | 20.0  | 41800  | 0.4919          |
+| 0.1273        | 21.0  | 43890  | 0.4914          |
+| 0.1284        | 22.0  | 45980  | 0.4907          |
+| 0.1276        | 23.0  | 48070  | 0.4898          |
+| 0.1284        | 24.0  | 50160  | 0.4894          |
+| 0.1263        | 25.0  | 52250  | 0.4894          |
+| 0.1264        | 26.0  | 54340  | 0.4888          |
+| 0.1257        | 27.0  | 56430  | 0.4881          |
+| 0.1292        | 28.0  | 58520  | 0.4875          |
+| 0.1262        | 29.0  | 60610  | 0.4874          |
+| 0.1272        | 30.0  | 62700  | 0.4867          |
+| 0.1252        | 31.0  | 64790  | 0.4864          |
+| 0.1261        | 32.0  | 66880  | 0.4859          |
+| 0.1262        | 33.0  | 68970  | 0.4858          |
+| 0.1256        | 34.0  | 71060  | 0.4849          |
+| 0.1251        | 35.0  | 73150  | 0.4847          |
+| 0.1263        | 36.0  | 75240  | 0.4843          |
+| 0.1266        | 37.0  | 77330  | 0.4843          |
+| 0.125         | 38.0  | 79420  | 0.4842          |
+| 0.1248        | 39.0  | 81510  | 0.4840          |
+| 0.126         | 40.0  | 83600  | 0.4837          |
+| 0.1239        | 41.0  | 85690  | 0.4831          |
+| 0.1246        | 42.0  | 87780  | 0.4837          |
+| 0.1241        | 43.0  | 89870  | 0.4830          |
+| 0.1259        | 44.0  | 91960  | 0.4829          |
+| 0.1275        | 45.0  | 94050  | 0.4828          |
+| 0.1258        | 46.0  | 96140  | 0.4826          |
+| 0.1265        | 47.0  | 98230  | 0.4828          |
+| 0.1235        | 48.0  | 100320 | 0.4827          |
+| 0.1255        | 49.0  | 102410 | 0.4827          |
+| 0.1245        | 50.0  | 104500 | 0.4826          |
+
+
+### 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 sha256:9a8c3ccac9a4c9df5fe9bf87e10022ff745ccf254adf28137b1f4fd68fdf9925
+size 309974336

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.4826192259788513,
+    "eval_runtime": 90.5563,
+    "eval_samples_per_second": 158.62,
+    "eval_steps_per_second": 4.958,
+    "perplexity": 1.620312814507615,
+    "total_flos": 2.191516447408128e+17,
+    "train_loss": 0.12956011656254673,
+    "train_runtime": 10667.5849,
+    "train_samples_per_second": 313.407,
+    "train_steps_per_second": 9.796
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.4826192259788513,
+    "eval_runtime": 90.5563,
+    "eval_samples_per_second": 158.62,
+    "eval_steps_per_second": 4.958,
+    "perplexity": 1.620312814507615
+}

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": "<|endoftext|>",
+  "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": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "total_flos": 2.191516447408128e+17,
+    "train_loss": 0.12956011656254673,
+    "train_runtime": 10667.5849,
+    "train_samples_per_second": 313.407,
+    "train_steps_per_second": 9.796
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668c38419b555312b47d9feb0caa9b47cff44adb7267ae12d90fd02e8b10ce5b
+size 5368