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: Se124M10KInfSimple
+  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. -->
+
+# Se124M10KInfSimple
+
+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: 0.5177
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.3959        | 1.0   | 237   | 0.9383          |
+| 0.2182        | 2.0   | 474   | 0.6835          |
+| 0.1772        | 3.0   | 711   | 0.6222          |
+| 0.1676        | 4.0   | 948   | 0.5980          |
+| 0.1609        | 5.0   | 1185  | 0.5840          |
+| 0.1519        | 6.0   | 1422  | 0.5740          |
+| 0.1535        | 7.0   | 1659  | 0.5659          |
+| 0.1492        | 8.0   | 1896  | 0.5587          |
+| 0.1456        | 9.0   | 2133  | 0.5575          |
+| 0.1427        | 10.0  | 2370  | 0.5528          |
+| 0.1442        | 11.0  | 2607  | 0.5499          |
+| 0.1403        | 12.0  | 2844  | 0.5466          |
+| 0.1425        | 13.0  | 3081  | 0.5449          |
+| 0.1403        | 14.0  | 3318  | 0.5414          |
+| 0.1405        | 15.0  | 3555  | 0.5399          |
+| 0.1387        | 16.0  | 3792  | 0.5383          |
+| 0.1377        | 17.0  | 4029  | 0.5368          |
+| 0.1379        | 18.0  | 4266  | 0.5376          |
+| 0.1353        | 19.0  | 4503  | 0.5349          |
+| 0.1378        | 20.0  | 4740  | 0.5313          |
+| 0.1372        | 21.0  | 4977  | 0.5320          |
+| 0.135         | 22.0  | 5214  | 0.5286          |
+| 0.1361        | 23.0  | 5451  | 0.5282          |
+| 0.1357        | 24.0  | 5688  | 0.5287          |
+| 0.1372        | 25.0  | 5925  | 0.5269          |
+| 0.1343        | 26.0  | 6162  | 0.5271          |
+| 0.1321        | 27.0  | 6399  | 0.5255          |
+| 0.1341        | 28.0  | 6636  | 0.5240          |
+| 0.1346        | 29.0  | 6873  | 0.5235          |
+| 0.1327        | 30.0  | 7110  | 0.5239          |
+| 0.1335        | 31.0  | 7347  | 0.5230          |
+| 0.1332        | 32.0  | 7584  | 0.5228          |
+| 0.1317        | 33.0  | 7821  | 0.5234          |
+| 0.1331        | 34.0  | 8058  | 0.5220          |
+| 0.1327        | 35.0  | 8295  | 0.5213          |
+| 0.1338        | 36.0  | 8532  | 0.5204          |
+| 0.1306        | 37.0  | 8769  | 0.5206          |
+| 0.1317        | 38.0  | 9006  | 0.5208          |
+| 0.1327        | 39.0  | 9243  | 0.5196          |
+| 0.1337        | 40.0  | 9480  | 0.5195          |
+| 0.1325        | 41.0  | 9717  | 0.5187          |
+| 0.1308        | 42.0  | 9954  | 0.5189          |
+| 0.1304        | 43.0  | 10191 | 0.5184          |
+| 0.1305        | 44.0  | 10428 | 0.5185          |
+| 0.1316        | 45.0  | 10665 | 0.5179          |
+| 0.1298        | 46.0  | 10902 | 0.5182          |
+| 0.1334        | 47.0  | 11139 | 0.5179          |
+| 0.1315        | 48.0  | 11376 | 0.5178          |
+| 0.131         | 49.0  | 11613 | 0.5176          |
+| 0.1302        | 50.0  | 11850 | 0.5177          |
+
+
+### 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:abac890932b5782fba3c3b36eea1226943c7a3d91228bccab0ee1599abe00330
+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": 0.5177325010299683,
+    "eval_runtime": 10.0034,
+    "eval_samples_per_second": 158.647,
+    "eval_steps_per_second": 4.998,
+    "perplexity": 1.678217974585131,
+    "total_flos": 2.48235958075392e+16,
+    "train_loss": 0.14677102237814085,
+    "train_runtime": 1298.068,
+    "train_samples_per_second": 291.741,
+    "train_steps_per_second": 9.129
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.5177325010299683,
+    "eval_runtime": 10.0034,
+    "eval_samples_per_second": 158.647,
+    "eval_steps_per_second": 4.998,
+    "perplexity": 1.678217974585131
+}

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": 2.48235958075392e+16,
+    "train_loss": 0.14677102237814085,
+    "train_runtime": 1298.068,
+    "train_samples_per_second": 291.741,
+    "train_steps_per_second": 9.129
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd3763eccf86d5e8593cb977781c5263f8dc208cb5f591c6c0cde2570adb9a5
+size 5368