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: Se124M10KInfMinimalist
+  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. -->
+
+# Se124M10KInfMinimalist
+
+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: 0.6063
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.3678        | 1.0   | 200   | 1.1110          |
+| 0.2364        | 2.0   | 400   | 0.7918          |
+| 0.2048        | 3.0   | 600   | 0.7298          |
+| 0.1916        | 4.0   | 800   | 0.7019          |
+| 0.1861        | 5.0   | 1000  | 0.6841          |
+| 0.179         | 6.0   | 1200  | 0.6719          |
+| 0.1767        | 7.0   | 1400  | 0.6665          |
+| 0.1722        | 8.0   | 1600  | 0.6568          |
+| 0.1714        | 9.0   | 1800  | 0.6538          |
+| 0.1651        | 10.0  | 2000  | 0.6493          |
+| 0.1674        | 11.0  | 2200  | 0.6446          |
+| 0.1655        | 12.0  | 2400  | 0.6407          |
+| 0.1643        | 13.0  | 2600  | 0.6384          |
+| 0.1638        | 14.0  | 2800  | 0.6346          |
+| 0.1619        | 15.0  | 3000  | 0.6347          |
+| 0.1618        | 16.0  | 3200  | 0.6299          |
+| 0.1625        | 17.0  | 3400  | 0.6292          |
+| 0.1586        | 18.0  | 3600  | 0.6262          |
+| 0.1589        | 19.0  | 3800  | 0.6235          |
+| 0.1616        | 20.0  | 4000  | 0.6229          |
+| 0.1609        | 21.0  | 4200  | 0.6218          |
+| 0.1575        | 22.0  | 4400  | 0.6195          |
+| 0.1601        | 23.0  | 4600  | 0.6200          |
+| 0.1577        | 24.0  | 4800  | 0.6159          |
+| 0.1593        | 25.0  | 5000  | 0.6171          |
+| 0.1574        | 26.0  | 5200  | 0.6185          |
+| 0.1582        | 27.0  | 5400  | 0.6139          |
+| 0.1563        | 28.0  | 5600  | 0.6141          |
+| 0.1563        | 29.0  | 5800  | 0.6146          |
+| 0.1595        | 30.0  | 6000  | 0.6124          |
+| 0.1575        | 31.0  | 6200  | 0.6126          |
+| 0.1537        | 32.0  | 6400  | 0.6121          |
+| 0.1559        | 33.0  | 6600  | 0.6104          |
+| 0.1543        | 34.0  | 6800  | 0.6116          |
+| 0.1562        | 35.0  | 7000  | 0.6098          |
+| 0.1558        | 36.0  | 7200  | 0.6089          |
+| 0.1551        | 37.0  | 7400  | 0.6089          |
+| 0.1537        | 38.0  | 7600  | 0.6085          |
+| 0.1526        | 39.0  | 7800  | 0.6084          |
+| 0.1556        | 40.0  | 8000  | 0.6085          |
+| 0.1548        | 41.0  | 8200  | 0.6080          |
+| 0.1542        | 42.0  | 8400  | 0.6078          |
+| 0.1581        | 43.0  | 8600  | 0.6071          |
+| 0.1555        | 44.0  | 8800  | 0.6066          |
+| 0.1547        | 45.0  | 9000  | 0.6064          |
+| 0.1569        | 46.0  | 9200  | 0.6067          |
+| 0.1524        | 47.0  | 9400  | 0.6063          |
+| 0.1555        | 48.0  | 9600  | 0.6065          |
+| 0.1543        | 49.0  | 9800  | 0.6065          |
+| 0.1559        | 50.0  | 10000 | 0.6063          |
+
+
+### 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:a78c9981790e22ca5560fa13bb076320a68e57434dbfd19a99d76a6262ab3693
+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": 0.606285572052002,
+    "eval_runtime": 8.6215,
+    "eval_samples_per_second": 154.382,
+    "eval_steps_per_second": 4.872,
+    "perplexity": 1.8336079294454999,
+    "total_flos": 2.08971807326208e+16,
+    "train_loss": 0.16982314805984497,
+    "train_runtime": 1086.9473,
+    "train_samples_per_second": 293.298,
+    "train_steps_per_second": 9.2
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.606285572052002,
+    "eval_runtime": 8.6215,
+    "eval_samples_per_second": 154.382,
+    "eval_steps_per_second": 4.872,
+    "perplexity": 1.8336079294454999
+}

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": 2.08971807326208e+16,
+    "train_loss": 0.16982314805984497,
+    "train_runtime": 1086.9473,
+    "train_samples_per_second": 293.298,
+    "train_steps_per_second": 9.2
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac5c30321826240e4eb338d1d4efb0fb7f809cfe97cdcf395b09d4b16acb5f1
+size 5368