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: Se124M100KInfMinimalist
+  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. -->
+
+# Se124M100KInfMinimalist
+
+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: 0.5392
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1691        | 1.0   | 1860  | 0.6314          |
+| 0.1598        | 2.0   | 3720  | 0.6036          |
+| 0.1539        | 3.0   | 5580  | 0.5906          |
+| 0.153         | 4.0   | 7440  | 0.5836          |
+| 0.1507        | 5.0   | 9300  | 0.5790          |
+| 0.1483        | 6.0   | 11160 | 0.5746          |
+| 0.149         | 7.0   | 13020 | 0.5703          |
+| 0.1485        | 8.0   | 14880 | 0.5684          |
+| 0.1462        | 9.0   | 16740 | 0.5656          |
+| 0.1469        | 10.0  | 18600 | 0.5630          |
+| 0.1449        | 11.0  | 20460 | 0.5617          |
+| 0.1469        | 12.0  | 22320 | 0.5581          |
+| 0.1456        | 13.0  | 24180 | 0.5575          |
+| 0.1459        | 14.0  | 26040 | 0.5547          |
+| 0.1432        | 15.0  | 27900 | 0.5544          |
+| 0.1429        | 16.0  | 29760 | 0.5540          |
+| 0.1431        | 17.0  | 31620 | 0.5523          |
+| 0.1432        | 18.0  | 33480 | 0.5512          |
+| 0.1423        | 19.0  | 35340 | 0.5519          |
+| 0.1429        | 20.0  | 37200 | 0.5506          |
+| 0.1429        | 21.0  | 39060 | 0.5490          |
+| 0.1441        | 22.0  | 40920 | 0.5477          |
+| 0.1426        | 23.0  | 42780 | 0.5476          |
+| 0.1436        | 24.0  | 44640 | 0.5463          |
+| 0.1419        | 25.0  | 46500 | 0.5462          |
+| 0.1399        | 26.0  | 48360 | 0.5449          |
+| 0.1412        | 27.0  | 50220 | 0.5452          |
+| 0.14          | 28.0  | 52080 | 0.5440          |
+| 0.1396        | 29.0  | 53940 | 0.5440          |
+| 0.1402        | 30.0  | 55800 | 0.5440          |
+| 0.1404        | 31.0  | 57660 | 0.5437          |
+| 0.1415        | 32.0  | 59520 | 0.5427          |
+| 0.1406        | 33.0  | 61380 | 0.5420          |
+| 0.1387        | 34.0  | 63240 | 0.5422          |
+| 0.1392        | 35.0  | 65100 | 0.5420          |
+| 0.1404        | 36.0  | 66960 | 0.5420          |
+| 0.1436        | 37.0  | 68820 | 0.5411          |
+| 0.1424        | 38.0  | 70680 | 0.5415          |
+| 0.141         | 39.0  | 72540 | 0.5407          |
+| 0.1402        | 40.0  | 74400 | 0.5403          |
+| 0.1412        | 41.0  | 76260 | 0.5407          |
+| 0.139         | 42.0  | 78120 | 0.5403          |
+| 0.1357        | 43.0  | 79980 | 0.5401          |
+| 0.1396        | 44.0  | 81840 | 0.5397          |
+| 0.1398        | 45.0  | 83700 | 0.5394          |
+| 0.1385        | 46.0  | 85560 | 0.5395          |
+| 0.1408        | 47.0  | 87420 | 0.5396          |
+| 0.1371        | 48.0  | 89280 | 0.5392          |
+| 0.1418        | 49.0  | 91140 | 0.5393          |
+| 0.1382        | 50.0  | 93000 | 0.5392          |
+
+
+### 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 sha256:6ed3f57f2acfde18959030e0b27638eae2b1ec5e94d02eab7e71bb065955c7a1
+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": 0.5392394065856934,
+    "eval_runtime": 80.8454,
+    "eval_samples_per_second": 158.154,
+    "eval_steps_per_second": 4.948,
+    "perplexity": 1.7147021748977518,
+    "total_flos": 1.950556483878912e+17,
+    "train_loss": 0.14462488290315034,
+    "train_runtime": 9614.4477,
+    "train_samples_per_second": 309.503,
+    "train_steps_per_second": 9.673
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 50.0,
+    "eval_loss": 0.5392394065856934,
+    "eval_runtime": 80.8454,
+    "eval_samples_per_second": 158.154,
+    "eval_steps_per_second": 4.948,
+    "perplexity": 1.7147021748977518
+}

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": 1.950556483878912e+17,
+    "train_loss": 0.14462488290315034,
+    "train_runtime": 9614.4477,
+    "train_samples_per_second": 309.503,
+    "train_steps_per_second": 9.673
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0426832942c50610ac436828fa8c166ebacacdf1b75d24835dff50e7467b4f5
+size 5368