Training in progress, epoch 1

README.md

@@ -0,0 +1,106 @@
+---
+library_name: peft
+license: mit
+base_model: gpt2-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: Se124M100KInfPrompt_WT_EOS_medium
+  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. -->
+
+# Se124M100KInfPrompt_WT_EOS_medium
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7127
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.8652        | 0.0655 | 20   | 2.6742          |
+| 2.6735        | 0.1309 | 40   | 2.4205          |
+| 2.3498        | 0.1964 | 60   | 2.0554          |
+| 1.9542        | 0.2619 | 80   | 1.6239          |
+| 1.5661        | 0.3273 | 100  | 1.2791          |
+| 1.3052        | 0.3928 | 120  | 1.0776          |
+| 1.1291        | 0.4583 | 140  | 0.9537          |
+| 1.0151        | 0.5237 | 160  | 0.8837          |
+| 0.9431        | 0.5892 | 180  | 0.8324          |
+| 0.8821        | 0.6547 | 200  | 0.8044          |
+| 0.8536        | 0.7201 | 220  | 0.7846          |
+| 0.8371        | 0.7856 | 240  | 0.7712          |
+| 0.8281        | 0.8511 | 260  | 0.7628          |
+| 0.8077        | 0.9165 | 280  | 0.7553          |
+| 0.8013        | 0.9820 | 300  | 0.7501          |
+| 0.7948        | 1.0458 | 320  | 0.7447          |
+| 0.783         | 1.1113 | 340  | 0.7394          |
+| 0.7727        | 1.1768 | 360  | 0.7372          |
+| 0.777         | 1.2422 | 380  | 0.7331          |
+| 0.7711        | 1.3077 | 400  | 0.7309          |
+| 0.7642        | 1.3732 | 420  | 0.7289          |
+| 0.7631        | 1.4386 | 440  | 0.7267          |
+| 0.7581        | 1.5041 | 460  | 0.7250          |
+| 0.7606        | 1.5696 | 480  | 0.7233          |
+| 0.7578        | 1.6350 | 500  | 0.7223          |
+| 0.7562        | 1.7005 | 520  | 0.7208          |
+| 0.7497        | 1.7660 | 540  | 0.7195          |
+| 0.7508        | 1.8314 | 560  | 0.7179          |
+| 0.7476        | 1.8969 | 580  | 0.7168          |
+| 0.7503        | 1.9624 | 600  | 0.7165          |
+| 0.7414        | 2.0262 | 620  | 0.7164          |
+| 0.7425        | 2.0917 | 640  | 0.7159          |
+| 0.7451        | 2.1571 | 660  | 0.7146          |
+| 0.7452        | 2.2226 | 680  | 0.7147          |
+| 0.7446        | 2.2881 | 700  | 0.7138          |
+| 0.7437        | 2.3535 | 720  | 0.7140          |
+| 0.7397        | 2.4190 | 740  | 0.7131          |
+| 0.7426        | 2.4845 | 760  | 0.7130          |
+| 0.7421        | 2.5499 | 780  | 0.7127          |
+| 0.7408        | 2.6154 | 800  | 0.7135          |
+| 0.7413        | 2.6809 | 820  | 0.7135          |
+| 0.7404        | 2.7463 | 840  | 0.7131          |
+| 0.7373        | 2.8118 | 860  | 0.7128          |
+| 0.7451        | 2.8773 | 880  | 0.7134          |
+| 0.7407        | 2.9427 | 900  | 0.7127          |
+
+
+### 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:f5e4d16223937ec23e6388b5af4dc21f45b35c0a5b2a89989d809852f9b4d759
+size 309968192

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 50257
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.9918166939443536,
+    "eval_loss": 0.7127311825752258,
+    "eval_runtime": 27.5772,
+    "eval_samples_per_second": 607.423,
+    "eval_steps_per_second": 9.501,
+    "perplexity": 2.0395540531763667,
+    "total_flos": 5.437860691102925e+16,
+    "train_loss": 0.9607737994584881,
+    "train_runtime": 2198.2213,
+    "train_samples_per_second": 106.683,
+    "train_steps_per_second": 0.416
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9918166939443536,
+    "eval_loss": 0.7127311825752258,
+    "eval_runtime": 27.5772,
+    "eval_samples_per_second": 607.423,
+    "eval_steps_per_second": 9.501,
+    "perplexity": 2.0395540531763667
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9918166939443536,
+    "total_flos": 5.437860691102925e+16,
+    "train_loss": 0.9607737994584881,
+    "train_runtime": 2198.2213,
+    "train_samples_per_second": 106.683,
+    "train_steps_per_second": 0.416
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292ef2eeddd76334ea82363d42b3c3eb46d89a0bd2f36e844b0fa811524abef8
+size 5432