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: Se124M100KInfSimple
+  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. -->
+
+# Se124M100KInfSimple
+
+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: 0.4582
+
+## 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 |
+|:-------------:|:-----:|:------:|:---------------:|
+| 0.1445        | 1.0   | 2205   | 0.5442          |
+| 0.1358        | 2.0   | 4410   | 0.5179          |
+| 0.1317        | 3.0   | 6615   | 0.5090          |
+| 0.1297        | 4.0   | 8820   | 0.5015          |
+| 0.1299        | 5.0   | 11025  | 0.4954          |
+| 0.1301        | 6.0   | 13230  | 0.4917          |
+| 0.1258        | 7.0   | 15435  | 0.4875          |
+| 0.1254        | 8.0   | 17640  | 0.4834          |
+| 0.1231        | 9.0   | 19845  | 0.4816          |
+| 0.1254        | 10.0  | 22050  | 0.4798          |
+| 0.125         | 11.0  | 24255  | 0.4778          |
+| 0.1225        | 12.0  | 26460  | 0.4775          |
+| 0.1233        | 13.0  | 28665  | 0.4753          |
+| 0.1213        | 14.0  | 30870  | 0.4737          |
+| 0.1231        | 15.0  | 33075  | 0.4719          |
+| 0.1233        | 16.0  | 35280  | 0.4716          |
+| 0.1225        | 17.0  | 37485  | 0.4702          |
+| 0.1218        | 18.0  | 39690  | 0.4696          |
+| 0.1213        | 19.0  | 41895  | 0.4678          |
+| 0.1213        | 20.0  | 44100  | 0.4673          |
+| 0.121         | 21.0  | 46305  | 0.4675          |
+| 0.122         | 22.0  | 48510  | 0.4663          |
+| 0.1195        | 23.0  | 50715  | 0.4657          |
+| 0.1221        | 24.0  | 52920  | 0.4647          |
+| 0.1212        | 25.0  | 55125  | 0.4647          |
+| 0.121         | 26.0  | 57330  | 0.4640          |
+| 0.1213        | 27.0  | 59535  | 0.4637          |
+| 0.1184        | 28.0  | 61740  | 0.4629          |
+| 0.12          | 29.0  | 63945  | 0.4627          |
+| 0.1191        | 30.0  | 66150  | 0.4622          |
+| 0.1195        | 31.0  | 68355  | 0.4624          |
+| 0.1188        | 32.0  | 70560  | 0.4619          |
+| 0.1202        | 33.0  | 72765  | 0.4620          |
+| 0.119         | 34.0  | 74970  | 0.4605          |
+| 0.1206        | 35.0  | 77175  | 0.4608          |
+| 0.1197        | 36.0  | 79380  | 0.4601          |
+| 0.1199        | 37.0  | 81585  | 0.4597          |
+| 0.1204        | 38.0  | 83790  | 0.4601          |
+| 0.1185        | 39.0  | 85995  | 0.4596          |
+| 0.1184        | 40.0  | 88200  | 0.4591          |
+| 0.119         | 41.0  | 90405  | 0.4594          |
+| 0.1181        | 42.0  | 92610  | 0.4591          |
+| 0.1178        | 43.0  | 94815  | 0.4588          |
+| 0.1188        | 44.0  | 97020  | 0.4586          |
+| 0.1189        | 45.0  | 99225  | 0.4584          |
+| 0.1183        | 46.0  | 101430 | 0.4583          |
+| 0.1184        | 47.0  | 103635 | 0.4582          |
+| 0.1185        | 48.0  | 105840 | 0.4581          |
+| 0.1198        | 49.0  | 108045 | 0.4582          |
+| 0.1207        | 50.0  | 110250 | 0.4582          |
+
+
+### 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:a47cdf9e6524472f72a39fad7d23f4ddf68b055b0bd08213acc0e48c6338b604
+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": 0.4581778049468994,
+    "eval_runtime": 95.3302,
+    "eval_samples_per_second": 158.911,
+    "eval_steps_per_second": 4.972,
+    "perplexity": 1.5811901214941453,
+    "total_flos": 2.31193087967232e+17,
+    "train_loss": 0.1232609451103643,
+    "train_runtime": 11754.4686,
+    "train_samples_per_second": 300.056,
+    "train_steps_per_second": 9.379
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.4581778049468994,
+    "eval_runtime": 95.3302,
+    "eval_samples_per_second": 158.911,
+    "eval_steps_per_second": 4.972,
+    "perplexity": 1.5811901214941453
+}

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": 2.31193087967232e+17,
+    "train_loss": 0.1232609451103643,
+    "train_runtime": 11754.4686,
+    "train_samples_per_second": 300.056,
+    "train_steps_per_second": 9.379
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b00a61ba8a8ee8cb55a2f97fd4590cce76384951622b7c0a92626c0f3c91ce2
+size 5368