Model save

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- dpo
+- llama-factory
+- generated_from_trainer
+base_model: tiiuae/falcon-7b-instruct
+model-index:
+- name: Falcon-7B-Instruct-ORPO
+  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. -->
+
+# Falcon-7B-Instruct-ORPO
+
+This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5155
+- Rewards/chosen: -0.1444
+- Rewards/rejected: -0.1539
+- Rewards/accuracies: 0.5090
+- Rewards/margins: 0.0095
+- Logps/rejected: -1.5389
+- Logps/chosen: -1.4440
+- Logits/rejected: -14.5432
+- Logits/chosen: -14.4665
+- Sft Loss: 1.4440
+- Odds Ratio Loss: 0.7143
+
+## 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-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Sft Loss | Odds Ratio Loss |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
+| 1.6309        | 0.8891 | 500  | 1.5816          | -0.1510        | -0.1599          | 0.4940             | 0.0089          | -1.5988        | -1.5096      | -14.4968        | -14.4213      | 1.5096   | 0.7192          |
+| 1.5401        | 1.7782 | 1000 | 1.5269          | -0.1455        | -0.1549          | 0.5020             | 0.0094          | -1.5492        | -1.4555      | -14.5486        | -14.4721      | 1.4555   | 0.7147          |
+| 1.4914        | 2.6673 | 1500 | 1.5155          | -0.1444        | -0.1539          | 0.5090             | 0.0095          | -1.5389        | -1.4440      | -14.5432        | -14.4665      | 1.4440   | 0.7143          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0
+- Datasets 2.19.0
+- Tokenizers 0.19.1

trainer_log.jsonl

@@ -151,3 +151,22 @@
 {"current_steps": 1490, "total_steps": 1686, "loss": 1.5003, "accuracy": 0.5062500238418579, "learning_rate": 1.6490167940538343e-07, "epoch": 2.6494776617026004, "percentage": 88.37, "elapsed_time": "5:47:26", "remaining_time": "0:45:42"}
 {"current_steps": 1500, "total_steps": 1686, "loss": 1.4914, "accuracy": 0.48124998807907104, "learning_rate": 1.4866882516191339e-07, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "5:50:45", "remaining_time": "0:43:29"}
 {"current_steps": 1500, "total_steps": 1686, "eval_loss": 1.5154520273208618, "epoch": 2.6672593909757722, "percentage": 88.97, "elapsed_time": "5:57:37", "remaining_time": "0:44:20"}
+{"current_steps": 1510, "total_steps": 1686, "loss": 1.5833, "accuracy": 0.550000011920929, "learning_rate": 1.3325243551706057e-07, "epoch": 2.685041120248944, "percentage": 89.56, "elapsed_time": "6:00:48", "remaining_time": "0:42:03"}
+{"current_steps": 1520, "total_steps": 1686, "loss": 1.4794, "accuracy": 0.4749999940395355, "learning_rate": 1.1865786358165737e-07, "epoch": 2.702822849522116, "percentage": 90.15, "elapsed_time": "6:03:55", "remaining_time": "0:39:44"}
+{"current_steps": 1530, "total_steps": 1686, "loss": 1.5615, "accuracy": 0.53125, "learning_rate": 1.0489017710262311e-07, "epoch": 2.720604578795288, "percentage": 90.75, "elapsed_time": "6:07:10", "remaining_time": "0:37:26"}
+{"current_steps": 1540, "total_steps": 1686, "loss": 1.4941, "accuracy": 0.48124998807907104, "learning_rate": 9.195415670326446e-08, "epoch": 2.73838630806846, "percentage": 91.34, "elapsed_time": "6:10:26", "remaining_time": "0:35:07"}
+{"current_steps": 1550, "total_steps": 1686, "loss": 1.4636, "accuracy": 0.4375, "learning_rate": 7.985429422327384e-08, "epoch": 2.7561680373416317, "percentage": 91.93, "elapsed_time": "6:13:32", "remaining_time": "0:32:46"}
+{"current_steps": 1560, "total_steps": 1686, "loss": 1.5068, "accuracy": 0.518750011920929, "learning_rate": 6.859479115900818e-08, "epoch": 2.773949766614803, "percentage": 92.53, "elapsed_time": "6:16:42", "remaining_time": "0:30:25"}
+{"current_steps": 1570, "total_steps": 1686, "loss": 1.5361, "accuracy": 0.48124998807907104, "learning_rate": 5.817955720457902e-08, "epoch": 2.791731495887975, "percentage": 93.12, "elapsed_time": "6:19:54", "remaining_time": "0:28:04"}
+{"current_steps": 1580, "total_steps": 1686, "loss": 1.5329, "accuracy": 0.4749999940395355, "learning_rate": 4.861220889427199e-08, "epoch": 2.809513225161147, "percentage": 93.71, "elapsed_time": "6:22:54", "remaining_time": "0:25:41"}
+{"current_steps": 1590, "total_steps": 1686, "loss": 1.519, "accuracy": 0.46875, "learning_rate": 3.9896068346758074e-08, "epoch": 2.827294954434319, "percentage": 94.31, "elapsed_time": "6:26:02", "remaining_time": "0:23:18"}
+{"current_steps": 1600, "total_steps": 1686, "loss": 1.491, "accuracy": 0.44999998807907104, "learning_rate": 3.203416211153832e-08, "epoch": 2.8450766837074903, "percentage": 94.9, "elapsed_time": "6:29:14", "remaining_time": "0:20:55"}
+{"current_steps": 1610, "total_steps": 1686, "loss": 1.6535, "accuracy": 0.39375001192092896, "learning_rate": 2.5029220118019393e-08, "epoch": 2.8628584129806622, "percentage": 95.49, "elapsed_time": "6:32:31", "remaining_time": "0:18:31"}
+{"current_steps": 1620, "total_steps": 1686, "loss": 1.4464, "accuracy": 0.5687500238418579, "learning_rate": 1.8883674727586122e-08, "epoch": 2.880640142253834, "percentage": 96.09, "elapsed_time": "6:35:36", "remaining_time": "0:16:07"}
+{"current_steps": 1630, "total_steps": 1686, "loss": 1.5093, "accuracy": 0.46875, "learning_rate": 1.3599659889000639e-08, "epoch": 2.898421871527006, "percentage": 96.68, "elapsed_time": "6:38:52", "remaining_time": "0:13:42"}
+{"current_steps": 1640, "total_steps": 1686, "loss": 1.5439, "accuracy": 0.4625000059604645, "learning_rate": 9.179010397421528e-09, "epoch": 2.916203600800178, "percentage": 97.27, "elapsed_time": "6:42:20", "remaining_time": "0:11:17"}
+{"current_steps": 1650, "total_steps": 1686, "loss": 1.461, "accuracy": 0.53125, "learning_rate": 5.623261257296509e-09, "epoch": 2.93398533007335, "percentage": 97.86, "elapsed_time": "6:45:30", "remaining_time": "0:08:50"}
+{"current_steps": 1660, "total_steps": 1686, "loss": 1.4361, "accuracy": 0.48124998807907104, "learning_rate": 2.933647149357122e-09, "epoch": 2.9517670593465217, "percentage": 98.46, "elapsed_time": "6:48:39", "remaining_time": "0:06:24"}
+{"current_steps": 1670, "total_steps": 1686, "loss": 1.5006, "accuracy": 0.40625, "learning_rate": 1.1111020018930717e-09, "epoch": 2.969548788619693, "percentage": 99.05, "elapsed_time": "6:51:52", "remaining_time": "0:03:56"}
+{"current_steps": 1680, "total_steps": 1686, "loss": 1.4799, "accuracy": 0.550000011920929, "learning_rate": 1.5625866646051813e-10, "epoch": 2.987330517892865, "percentage": 99.64, "elapsed_time": "6:54:58", "remaining_time": "0:01:28"}
+{"current_steps": 1686, "total_steps": 1686, "epoch": 2.997999555456768, "percentage": 100.0, "elapsed_time": "6:57:00", "remaining_time": "0:00:00"}