End of training

README.md

@@ -0,0 +1,122 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
+tags:
+- generated_from_trainer
+model-index:
+- name: lemexp-task1-lemma_command_small-Llama-3.2-1B-ddp-8lr
+  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. -->
+
+# lemexp-task1-lemma_command_small-Llama-3.2-1B-ddp-8lr
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6416
+
+## 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: 0.0008
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- 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: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss |
+|:-------------:|:-------:|:-----:|:---------------:|
+| No log        | 0.2003  | 461   | 1.0440          |
+| 1.128         | 0.4005  | 922   | 0.9841          |
+| 1.0276        | 0.6008  | 1383  | 0.9573          |
+| 0.9831        | 0.8010  | 1844  | 0.9383          |
+| 0.9507        | 1.0013  | 2305  | 0.9198          |
+| 0.9196        | 1.2016  | 2766  | 0.8958          |
+| 0.8816        | 1.4018  | 3227  | 0.9029          |
+| 0.8802        | 1.6021  | 3688  | 0.8764          |
+| 0.8751        | 1.8023  | 4149  | 0.8647          |
+| 0.865         | 2.0026  | 4610  | 0.8444          |
+| 0.8264        | 2.2029  | 5071  | 0.8443          |
+| 0.8188        | 2.4031  | 5532  | 0.8321          |
+| 0.8188        | 2.6034  | 5993  | 0.8318          |
+| 0.8145        | 2.8036  | 6454  | 0.8210          |
+| 0.8142        | 3.0039  | 6915  | 0.8134          |
+| 0.7998        | 3.2042  | 7376  | 0.8051          |
+| 0.7759        | 3.4044  | 7837  | 0.8013          |
+| 0.764         | 3.6047  | 8298  | 0.7852          |
+| 0.764         | 3.8050  | 8759  | 0.7829          |
+| 0.7626        | 4.0052  | 9220  | 0.7777          |
+| 0.744         | 4.2055  | 9681  | 0.7865          |
+| 0.7304        | 4.4057  | 10142 | 0.7671          |
+| 0.7307        | 4.6060  | 10603 | 0.7595          |
+| 0.7313        | 4.8063  | 11064 | 0.7644          |
+| 0.7267        | 5.0065  | 11525 | 0.7642          |
+| 0.7267        | 5.2068  | 11986 | 0.7450          |
+| 0.6842        | 5.4070  | 12447 | 0.7489          |
+| 0.6944        | 5.6073  | 12908 | 0.7354          |
+| 0.6957        | 5.8076  | 13369 | 0.7272          |
+| 0.6855        | 6.0078  | 13830 | 0.7318          |
+| 0.6801        | 6.2081  | 14291 | 0.7291          |
+| 0.6528        | 6.4083  | 14752 | 0.7155          |
+| 0.6551        | 6.6086  | 15213 | 0.7167          |
+| 0.6576        | 6.8089  | 15674 | 0.7161          |
+| 0.6561        | 7.0091  | 16135 | 0.7076          |
+| 0.6262        | 7.2094  | 16596 | 0.7111          |
+| 0.627         | 7.4096  | 17057 | 0.7074          |
+| 0.624         | 7.6099  | 17518 | 0.6987          |
+| 0.624         | 7.8102  | 17979 | 0.6931          |
+| 0.6178        | 8.0104  | 18440 | 0.6892          |
+| 0.6116        | 8.2107  | 18901 | 0.6908          |
+| 0.5815        | 8.4109  | 19362 | 0.6831          |
+| 0.5887        | 8.6112  | 19823 | 0.6758          |
+| 0.5823        | 8.8115  | 20284 | 0.6793          |
+| 0.5885        | 9.0117  | 20745 | 0.6718          |
+| 0.5636        | 9.2120  | 21206 | 0.6703          |
+| 0.5485        | 9.4123  | 21667 | 0.6666          |
+| 0.5569        | 9.6125  | 22128 | 0.6596          |
+| 0.5534        | 9.8128  | 22589 | 0.6519          |
+| 0.5537        | 10.0130 | 23050 | 0.6631          |
+| 0.5146        | 10.2133 | 23511 | 0.6657          |
+| 0.5146        | 10.4136 | 23972 | 0.6550          |
+| 0.5212        | 10.6138 | 24433 | 0.6490          |
+| 0.5179        | 10.8141 | 24894 | 0.6483          |
+| 0.5234        | 11.0143 | 25355 | 0.6498          |
+| 0.5           | 11.2146 | 25816 | 0.6494          |
+| 0.4811        | 11.4149 | 26277 | 0.6499          |
+| 0.4849        | 11.6151 | 26738 | 0.6448          |
+| 0.497         | 11.8154 | 27199 | 0.6416          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "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": 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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fdbd6dfca568a670acb962bba756ca7361330ac6bda97c9a1e7798c67ace64
+size 1054097832

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1ad668d2dd7964f285921b32e8b935a7c49980c1a495018547599f90f168f0
+size 5432