End of training

README.md

@@ -0,0 +1,100 @@
+---
+library_name: peft
+base_model: roneneldan/TinyStories-1M
+tags:
+- generated_from_trainer
+model-index:
+- name: test_1M_1-2025-02-13-16-57
+  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. -->
+
+# test_1M_1-2025-02-13-16-57
+
+This model is a fine-tuned version of [roneneldan/TinyStories-1M](https://huggingface.co/roneneldan/TinyStories-1M) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5458
+
+## 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: 2.5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.5623        | 0.5   | 297   | 2.6254          |
+| 2.6957        | 1.0   | 594   | 2.6033          |
+| 2.533         | 1.5   | 891   | 2.5928          |
+| 2.583         | 2.0   | 1188  | 2.5871          |
+| 2.4467        | 2.5   | 1485  | 2.5803          |
+| 2.5157        | 3.0   | 1782  | 2.5742          |
+| 2.5378        | 3.5   | 2079  | 2.5718          |
+| 2.4285        | 4.0   | 2376  | 2.5732          |
+| 2.4606        | 4.5   | 2673  | 2.5643          |
+| 2.5373        | 5.0   | 2970  | 2.5660          |
+| 2.5087        | 5.5   | 3267  | 2.5616          |
+| 2.5158        | 6.0   | 3564  | 2.5620          |
+| 2.4755        | 6.5   | 3861  | 2.5607          |
+| 2.5964        | 7.0   | 4158  | 2.5595          |
+| 2.54          | 7.5   | 4455  | 2.5608          |
+| 2.5001        | 8.0   | 4752  | 2.5558          |
+| 2.4152        | 8.5   | 5049  | 2.5562          |
+| 2.5635        | 9.0   | 5346  | 2.5559          |
+| 2.5722        | 9.5   | 5643  | 2.5550          |
+| 2.5334        | 10.0  | 5940  | 2.5533          |
+| 2.5433        | 10.5  | 6237  | 2.5540          |
+| 2.4406        | 11.0  | 6534  | 2.5531          |
+| 2.5045        | 11.5  | 6831  | 2.5528          |
+| 2.5424        | 12.0  | 7128  | 2.5529          |
+| 2.4114        | 12.5  | 7425  | 2.5508          |
+| 2.4601        | 13.0  | 7722  | 2.5494          |
+| 2.4751        | 13.5  | 8019  | 2.5519          |
+| 2.4457        | 14.0  | 8316  | 2.5519          |
+| 2.5539        | 14.5  | 8613  | 2.5500          |
+| 2.6792        | 15.0  | 8910  | 2.5500          |
+| 2.5712        | 15.5  | 9207  | 2.5498          |
+| 2.4492        | 16.0  | 9504  | 2.5476          |
+| 2.4512        | 16.5  | 9801  | 2.5481          |
+| 2.417         | 17.0  | 10098 | 2.5482          |
+| 2.5693        | 17.5  | 10395 | 2.5478          |
+| 2.5358        | 18.0  | 10692 | 2.5482          |
+| 2.4265        | 18.5  | 10989 | 2.5477          |
+| 2.4858        | 19.0  | 11286 | 2.5475          |
+| 2.4319        | 19.5  | 11583 | 2.5471          |
+| 2.4089        | 20.0  | 11880 | 2.5458          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roneneldan/TinyStories-1M",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "wte"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b27bd07b6d3fd0434e6144146e2e1b6dd61cdfd1e2abaa05c5cef05794a8fc5
+size 51684320

added_tokens.json

@@ -0,0 +1,19 @@
+{
+  "<cluster_0>": 50268,
+  "<cluster_10>": 50264,
+  "<cluster_11>": 50261,
+  "<cluster_12>": 50257,
+  "<cluster_13>": 50265,
+  "<cluster_14>": 50262,
+  "<cluster_15>": 50272,
+  "<cluster_16>": 50273,
+  "<cluster_1>": 50260,
+  "<cluster_2>": 50259,
+  "<cluster_3>": 50269,
+  "<cluster_4>": 50267,
+  "<cluster_5>": 50270,
+  "<cluster_6>": 50266,
+  "<cluster_7>": 50263,
+  "<cluster_8>": 50271,
+  "<cluster_9>": 50258
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,161 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<cluster_12>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<cluster_9>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<cluster_2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "<cluster_1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "<cluster_11>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "<cluster_14>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "<cluster_7>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "<cluster_10>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "<cluster_13>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "<cluster_6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "<cluster_4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "<cluster_0>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "<cluster_3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "<cluster_5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "<cluster_8>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "<cluster_15>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "<cluster_16>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f30d5158b89db2a166ec747d99e6f1f2bd04def6b58332631e13dd544c22400
+size 5368