Training in progress, epoch 1

README.md

@@ -0,0 +1,88 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M500KInfSimple
+  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. -->
+
+# Se124M500KInfSimple
+
+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: 0.4475
+
+## 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 |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.1287        | 1.0   | 8317   | 0.5023          |
+| 0.1249        | 2.0   | 16634  | 0.4836          |
+| 0.1214        | 3.0   | 24951  | 0.4746          |
+| 0.1225        | 4.0   | 33268  | 0.4691          |
+| 0.1212        | 5.0   | 41585  | 0.4653          |
+| 0.1192        | 6.0   | 49902  | 0.4625          |
+| 0.1203        | 7.0   | 58219  | 0.4595          |
+| 0.1182        | 8.0   | 66536  | 0.4579          |
+| 0.117         | 9.0   | 74853  | 0.4565          |
+| 0.1184        | 10.0  | 83170  | 0.4543          |
+| 0.1165        | 11.0  | 91487  | 0.4539          |
+| 0.116         | 12.0  | 99804  | 0.4528          |
+| 0.117         | 13.0  | 108121 | 0.4515          |
+| 0.1161        | 14.0  | 116438 | 0.4512          |
+| 0.1149        | 15.0  | 124755 | 0.4510          |
+| 0.1157        | 16.0  | 133072 | 0.4503          |
+| 0.1162        | 17.0  | 141389 | 0.4497          |
+| 0.1155        | 18.0  | 149706 | 0.4497          |
+| 0.115         | 19.0  | 158023 | 0.4496          |
+| 0.1156        | 20.0  | 166340 | 0.4488          |
+| 0.1156        | 21.0  | 174657 | 0.4492          |
+| 0.114         | 22.0  | 182974 | 0.4483          |
+| 0.1122        | 23.0  | 191291 | 0.4488          |
+| 0.1134        | 24.0  | 199608 | 0.4480          |
+| 0.114         | 25.0  | 207925 | 0.4476          |
+| 0.1159        | 26.0  | 216242 | 0.4481          |
+| 0.115         | 27.0  | 224559 | 0.4475          |
+| 0.1145        | 28.0  | 232876 | 0.4475          |
+| 0.1141        | 29.0  | 241193 | 0.4477          |
+
+
+### 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:c259a1f54ff9ff83eed89265acd803ac570851054be5fddf199bbf32b3c509a9
+size 309974336

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 29.0,
+    "eval_loss": 0.4475274682044983,
+    "eval_runtime": 362.3481,
+    "eval_samples_per_second": 157.114,
+    "eval_steps_per_second": 4.912,
+    "perplexity": 1.5644392736681412,
+    "total_flos": 5.058807603414958e+17,
+    "train_loss": 0.11824046083851339,
+    "train_runtime": 25872.5126,
+    "train_samples_per_second": 514.295,
+    "train_steps_per_second": 16.073
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 29.0,
+    "eval_loss": 0.4475274682044983,
+    "eval_runtime": 362.3481,
+    "eval_samples_per_second": 157.114,
+    "eval_steps_per_second": 4.912,
+    "perplexity": 1.5644392736681412
+}

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": 29.0,
+    "total_flos": 5.058807603414958e+17,
+    "train_loss": 0.11824046083851339,
+    "train_runtime": 25872.5126,
+    "train_samples_per_second": 514.295,
+    "train_steps_per_second": 16.073
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f2d25c850399c646c236c39f3ec487e3c380f1174232e2fcbece86f800d0f6
+size 5432