Model save

README.md

@@ -3,15 +3,11 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -22,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9934
+- Loss: 1.0243
 
 ## Model description
 
@@ -44,43 +40,43 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 16
-- total_train_batch_size: 256
+- total_train_batch_size: 128
 - total_eval_batch_size: 256
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3.0
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.9681        | 0.1845 | 100  | 0.9788          |
-| 0.9962        | 0.3690 | 200  | 1.0030          |
-| 0.9917        | 0.5535 | 300  | 1.0008          |
-| 0.9652        | 0.7380 | 400  | 0.9939          |
-| 0.9666        | 0.9225 | 500  | 0.9816          |
-| 0.7366        | 1.1070 | 600  | 0.9852          |
-| 0.7228        | 1.2915 | 700  | 0.9835          |
-| 0.7319        | 1.4760 | 800  | 0.9644          |
-| 0.7177        | 1.6605 | 900  | 0.9529          |
-| 0.7095        | 1.8450 | 1000 | 0.9394          |
-| 0.4465        | 2.0295 | 1100 | 0.9917          |
-| 0.4341        | 2.2140 | 1200 | 0.9979          |
-| 0.432         | 2.3985 | 1300 | 0.9954          |
-| 0.4301        | 2.5830 | 1400 | 0.9943          |
-| 0.4361        | 2.7675 | 1500 | 0.9931          |
-| 0.4256        | 2.9520 | 1600 | 0.9934          |
+| 0.9838        | 0.1845 | 200  | 0.9937          |
+| 1.0162        | 0.3690 | 400  | 1.0329          |
+| 1.0095        | 0.5535 | 600  | 1.0302          |
+| 0.9857        | 0.7380 | 800  | 1.0204          |
+| 0.9803        | 0.9225 | 1000 | 1.0051          |
+| 0.736         | 1.1070 | 1200 | 1.0061          |
+| 0.7249        | 1.2915 | 1400 | 1.0004          |
+| 0.7355        | 1.4760 | 1600 | 0.9855          |
+| 0.7151        | 1.6605 | 1800 | 0.9713          |
+| 0.7023        | 1.8450 | 2000 | 0.9557          |
+| 0.3925        | 2.0295 | 2200 | 1.0150          |
+| 0.3871        | 2.2140 | 2400 | 1.0319          |
+| 0.3927        | 2.3985 | 2600 | 1.0269          |
+| 0.3872        | 2.5830 | 2800 | 1.0267          |
+| 0.3918        | 2.7675 | 3000 | 1.0242          |
+| 0.3764        | 2.9520 | 3200 | 1.0243          |
 
 
 ### Framework versions
 
-- Transformers 4.45.2
-- Pytorch 2.2.2+rocm5.7
-- Datasets 3.2.0
-- Tokenizers 0.20.3
+- Transformers 4.51.3
+- Pytorch 2.5.1+rocm6.2
+- Datasets 3.5.0
+- Tokenizers 0.21.1

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.9934042692184448,
-    "eval_runtime": 518.8262,
-    "eval_samples": 23109,
-    "eval_samples_per_second": 29.586,
-    "eval_steps_per_second": 0.116,
     "total_flos": 1361805280542720.0,
-    "train_loss": 0.713569560815634,
-    "train_runtime": 59769.2599,
+    "train_loss": 0.7043063408920832,
+    "train_runtime": 81819.3933,
     "train_samples": 207864,
-    "train_samples_per_second": 6.961,
-    "train_steps_per_second": 0.027
+    "train_samples_per_second": 5.085,
+    "train_steps_per_second": 0.04
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.45.2"
+  "transformers_version": "4.51.3"
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 1361805280542720.0,
-    "train_loss": 0.713569560815634,
-    "train_runtime": 59769.2599,
+    "train_loss": 0.7043063408920832,
+    "train_runtime": 81819.3933,
     "train_samples": 207864,
-    "train_samples_per_second": 6.961,
-    "train_steps_per_second": 0.027
+    "train_samples_per_second": 5.085,
+    "train_steps_per_second": 0.04
 }