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: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: Mistral-7B-Instruct-v0.2-ORPO-SALT
+  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. -->
+
+# Mistral-7B-Instruct-v0.2-ORPO-SALT
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8630
+- Rewards/chosen: -0.0798
+- Rewards/rejected: -0.1033
+- Rewards/accuracies: 0.5618
+- Rewards/margins: 0.0235
+- Logps/rejected: -1.0328
+- Logps/chosen: -0.7975
+- Logits/rejected: -2.8558
+- Logits/chosen: -2.8473
+- Sft Loss: 0.7975
+- Odds Ratio Loss: 0.6547
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
+| 0.93          | 0.8082 | 500  | 0.8928          | -0.0828        | -0.1057          | 0.5773             | 0.0229          | -1.0567        | -0.8278      | -2.8442         | -2.8368       | 0.8278   | 0.6496          |
+| 0.7571        | 1.6165 | 1000 | 0.8679          | -0.0803        | -0.1034          | 0.5700             | 0.0231          | -1.0337        | -0.8028      | -2.8729         | -2.8644       | 0.8028   | 0.6510          |
+| 0.8035        | 2.4247 | 1500 | 0.8630          | -0.0798        | -0.1033          | 0.5618             | 0.0235          | -1.0328        | -0.7975      | -2.8558         | -2.8473       | 0.7975   | 0.6547          |
+
+
+### 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 +151,39 @@
 {"current_steps": 1490, "total_steps": 1854, "loss": 0.8935, "accuracy": 0.543749988079071, "learning_rate": 4.607082849092523e-07, "epoch": 2.40856738735098, "percentage": 80.37, "elapsed_time": "4:02:11", "remaining_time": "0:59:09"}
 {"current_steps": 1500, "total_steps": 1854, "loss": 0.8035, "accuracy": 0.5562499761581421, "learning_rate": 4.3649635614901405e-07, "epoch": 2.4247322691452817, "percentage": 80.91, "elapsed_time": "4:03:47", "remaining_time": "0:57:32"}
 {"current_steps": 1500, "total_steps": 1854, "eval_loss": 0.8629826903343201, "epoch": 2.4247322691452817, "percentage": 80.91, "elapsed_time": "4:07:01", "remaining_time": "0:58:17"}
+{"current_steps": 1510, "total_steps": 1854, "loss": 0.8304, "accuracy": 0.59375, "learning_rate": 4.128769732701973e-07, "epoch": 2.4408971509395836, "percentage": 81.45, "elapsed_time": "4:08:37", "remaining_time": "0:56:38"}
+{"current_steps": 1520, "total_steps": 1854, "loss": 0.8284, "accuracy": 0.581250011920929, "learning_rate": 3.8985691870233046e-07, "epoch": 2.4570620327338855, "percentage": 81.98, "elapsed_time": "4:10:10", "remaining_time": "0:54:58"}
+{"current_steps": 1530, "total_steps": 1854, "loss": 0.8392, "accuracy": 0.59375, "learning_rate": 3.6744280277467904e-07, "epoch": 2.4732269145281873, "percentage": 82.52, "elapsed_time": "4:11:42", "remaining_time": "0:53:18"}
+{"current_steps": 1540, "total_steps": 1854, "loss": 0.7646, "accuracy": 0.6499999761581421, "learning_rate": 3.456410618180503e-07, "epoch": 2.489391796322489, "percentage": 83.06, "elapsed_time": "4:13:17", "remaining_time": "0:51:38"}
+{"current_steps": 1550, "total_steps": 1854, "loss": 0.8173, "accuracy": 0.59375, "learning_rate": 3.244579563165753e-07, "epoch": 2.5055566781167915, "percentage": 83.6, "elapsed_time": "4:14:49", "remaining_time": "0:49:58"}
+{"current_steps": 1560, "total_steps": 1854, "loss": 0.8503, "accuracy": 0.6187499761581421, "learning_rate": 3.038995691099697e-07, "epoch": 2.521721559911093, "percentage": 84.14, "elapsed_time": "4:16:19", "remaining_time": "0:48:18"}
+{"current_steps": 1570, "total_steps": 1854, "loss": 0.9513, "accuracy": 0.59375, "learning_rate": 2.839718036468192e-07, "epoch": 2.5378864417053952, "percentage": 84.68, "elapsed_time": "4:17:54", "remaining_time": "0:46:39"}
+{"current_steps": 1580, "total_steps": 1854, "loss": 0.8627, "accuracy": 0.5687500238418579, "learning_rate": 2.646803822893723e-07, "epoch": 2.5540513234996967, "percentage": 85.22, "elapsed_time": "4:19:27", "remaining_time": "0:44:59"}
+{"current_steps": 1590, "total_steps": 1854, "loss": 0.8556, "accuracy": 0.5874999761581421, "learning_rate": 2.460308446703341e-07, "epoch": 2.570216205293999, "percentage": 85.76, "elapsed_time": "4:21:00", "remaining_time": "0:43:20"}
+{"current_steps": 1600, "total_steps": 1854, "loss": 0.7531, "accuracy": 0.6312500238418579, "learning_rate": 2.2802854610213143e-07, "epoch": 2.5863810870883004, "percentage": 86.3, "elapsed_time": "4:22:33", "remaining_time": "0:41:40"}
+{"current_steps": 1610, "total_steps": 1854, "loss": 0.8638, "accuracy": 0.612500011920929, "learning_rate": 2.106786560391072e-07, "epoch": 2.6025459688826027, "percentage": 86.84, "elapsed_time": "4:24:04", "remaining_time": "0:40:01"}
+{"current_steps": 1620, "total_steps": 1854, "loss": 0.8181, "accuracy": 0.581250011920929, "learning_rate": 1.9398615659308255e-07, "epoch": 2.6187108506769046, "percentage": 87.38, "elapsed_time": "4:25:39", "remaining_time": "0:38:22"}
+{"current_steps": 1630, "total_steps": 1854, "loss": 0.8594, "accuracy": 0.574999988079071, "learning_rate": 1.7795584110272184e-07, "epoch": 2.6348757324712064, "percentage": 87.92, "elapsed_time": "4:27:18", "remaining_time": "0:36:44"}
+{"current_steps": 1640, "total_steps": 1854, "loss": 0.8356, "accuracy": 0.5625, "learning_rate": 1.6259231275709636e-07, "epoch": 2.6510406142655083, "percentage": 88.46, "elapsed_time": "4:28:54", "remaining_time": "0:35:05"}
+{"current_steps": 1650, "total_steps": 1854, "loss": 0.82, "accuracy": 0.606249988079071, "learning_rate": 1.478999832738548e-07, "epoch": 2.66720549605981, "percentage": 89.0, "elapsed_time": "4:30:27", "remaining_time": "0:33:26"}
+{"current_steps": 1660, "total_steps": 1854, "loss": 0.8687, "accuracy": 0.59375, "learning_rate": 1.338830716323769e-07, "epoch": 2.683370377854112, "percentage": 89.54, "elapsed_time": "4:32:03", "remaining_time": "0:31:47"}
+{"current_steps": 1670, "total_steps": 1854, "loss": 0.7835, "accuracy": 0.6312500238418579, "learning_rate": 1.205456028622723e-07, "epoch": 2.699535259648414, "percentage": 90.08, "elapsed_time": "4:33:32", "remaining_time": "0:30:08"}
+{"current_steps": 1680, "total_steps": 1854, "loss": 0.8217, "accuracy": 0.5874999761581421, "learning_rate": 1.0789140688756805e-07, "epoch": 2.7157001414427158, "percentage": 90.61, "elapsed_time": "4:35:05", "remaining_time": "0:28:29"}
+{"current_steps": 1690, "total_steps": 1854, "loss": 0.845, "accuracy": 0.5562499761581421, "learning_rate": 9.592411742693098e-08, "epoch": 2.7318650232370176, "percentage": 91.15, "elapsed_time": "4:36:35", "remaining_time": "0:26:50"}
+{"current_steps": 1700, "total_steps": 1854, "loss": 0.805, "accuracy": 0.65625, "learning_rate": 8.464717095022168e-08, "epoch": 2.7480299050313195, "percentage": 91.69, "elapsed_time": "4:38:07", "remaining_time": "0:25:11"}
+{"current_steps": 1710, "total_steps": 1854, "loss": 0.8593, "accuracy": 0.581250011920929, "learning_rate": 7.406380569169841e-08, "epoch": 2.7641947868256214, "percentage": 92.23, "elapsed_time": "4:39:41", "remaining_time": "0:23:33"}
+{"current_steps": 1720, "total_steps": 1854, "loss": 0.8231, "accuracy": 0.59375, "learning_rate": 6.417706072013808e-08, "epoch": 2.7803596686199232, "percentage": 92.77, "elapsed_time": "4:41:16", "remaining_time": "0:21:54"}
+{"current_steps": 1730, "total_steps": 1854, "loss": 0.8544, "accuracy": 0.59375, "learning_rate": 5.498977506615294e-08, "epoch": 2.796524550414225, "percentage": 93.31, "elapsed_time": "4:42:53", "remaining_time": "0:20:16"}
+{"current_steps": 1740, "total_steps": 1854, "loss": 0.8767, "accuracy": 0.6000000238418579, "learning_rate": 4.6504586906947756e-08, "epoch": 2.812689432208527, "percentage": 93.85, "elapsed_time": "4:44:27", "remaining_time": "0:18:38"}
+{"current_steps": 1750, "total_steps": 1854, "loss": 0.9219, "accuracy": 0.53125, "learning_rate": 3.8723932808754914e-08, "epoch": 2.828854314002829, "percentage": 94.39, "elapsed_time": "4:46:04", "remaining_time": "0:17:00"}
+{"current_steps": 1760, "total_steps": 1854, "loss": 0.828, "accuracy": 0.6312500238418579, "learning_rate": 3.1650047027158014e-08, "epoch": 2.8450191957971307, "percentage": 94.93, "elapsed_time": "4:47:42", "remaining_time": "0:15:21"}
+{"current_steps": 1770, "total_steps": 1854, "loss": 0.7798, "accuracy": 0.6000000238418579, "learning_rate": 2.5284960865517848e-08, "epoch": 2.8611840775914326, "percentage": 95.47, "elapsed_time": "4:49:20", "remaining_time": "0:13:43"}
+{"current_steps": 1780, "total_steps": 1854, "loss": 0.8054, "accuracy": 0.668749988079071, "learning_rate": 1.9630502091670388e-08, "epoch": 2.8773489593857344, "percentage": 96.01, "elapsed_time": "4:50:52", "remaining_time": "0:12:05"}
+{"current_steps": 1790, "total_steps": 1854, "loss": 0.7411, "accuracy": 0.6312500238418579, "learning_rate": 1.4688294413074677e-08, "epoch": 2.8935138411800363, "percentage": 96.55, "elapsed_time": "4:52:23", "remaining_time": "0:10:27"}
+{"current_steps": 1800, "total_steps": 1854, "loss": 0.8346, "accuracy": 0.543749988079071, "learning_rate": 1.0459757010556626e-08, "epoch": 2.909678722974338, "percentage": 97.09, "elapsed_time": "4:53:56", "remaining_time": "0:08:49"}
+{"current_steps": 1810, "total_steps": 1854, "loss": 0.8869, "accuracy": 0.6000000238418579, "learning_rate": 6.94610413078306e-09, "epoch": 2.92584360476864, "percentage": 97.63, "elapsed_time": "4:55:26", "remaining_time": "0:07:10"}
+{"current_steps": 1820, "total_steps": 1854, "loss": 0.7756, "accuracy": 0.637499988079071, "learning_rate": 4.14834473758563e-09, "epoch": 2.942008486562942, "percentage": 98.17, "elapsed_time": "4:57:01", "remaining_time": "0:05:32"}
+{"current_steps": 1830, "total_steps": 1854, "loss": 0.7943, "accuracy": 0.612500011920929, "learning_rate": 2.067282222230349e-09, "epoch": 2.9581733683572438, "percentage": 98.71, "elapsed_time": "4:58:41", "remaining_time": "0:03:55"}
+{"current_steps": 1840, "total_steps": 1854, "loss": 0.7784, "accuracy": 0.606249988079071, "learning_rate": 7.035141727212979e-10, "epoch": 2.9743382501515456, "percentage": 99.24, "elapsed_time": "5:00:10", "remaining_time": "0:02:17"}
+{"current_steps": 1850, "total_steps": 1854, "loss": 0.9404, "accuracy": 0.6187499761581421, "learning_rate": 5.743220219761592e-11, "epoch": 2.9905031319458475, "percentage": 99.78, "elapsed_time": "5:01:46", "remaining_time": "0:00:39"}
+{"current_steps": 1854, "total_steps": 1854, "epoch": 2.9969690846635686, "percentage": 100.0, "elapsed_time": "5:02:24", "remaining_time": "0:00:00"}