End of training

README.md

@@ -5,18 +5,18 @@ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
 - generated_from_trainer
 model-index:
-- name: tinyllama-form-gen-v2-10epoch
+- name: tinyllama-form-gen-v2-15epoch
   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. -->
 
-# tinyllama-form-gen-v2-10epoch
+# tinyllama-form-gen-v2-15epoch
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2711
+- Loss: 0.2239
 
 ## Model description
 
@@ -43,23 +43,28 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 4
 - 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: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6432        | 1.0   | 11   | 0.5982          |
-| 0.5264        | 2.0   | 22   | 0.4917          |
-| 0.4407        | 3.0   | 33   | 0.3981          |
-| 0.3384        | 4.0   | 44   | 0.3466          |
-| 0.3049        | 5.0   | 55   | 0.3172          |
-| 0.262         | 6.0   | 66   | 0.2967          |
-| 0.2537        | 7.0   | 77   | 0.2852          |
-| 0.2436        | 8.0   | 88   | 0.2772          |
-| 0.2109        | 9.0   | 99   | 0.2718          |
-| 0.2099        | 10.0  | 110  | 0.2711          |
+| 0.6428        | 1.0   | 11   | 0.5965          |
+| 0.5231        | 2.0   | 22   | 0.4848          |
+| 0.4323        | 3.0   | 33   | 0.3889          |
+| 0.3284        | 4.0   | 44   | 0.3361          |
+| 0.2941        | 5.0   | 55   | 0.3050          |
+| 0.2494        | 6.0   | 66   | 0.2824          |
+| 0.2379        | 7.0   | 77   | 0.2704          |
+| 0.2247        | 8.0   | 88   | 0.2578          |
+| 0.1871        | 9.0   | 99   | 0.2466          |
+| 0.1724        | 10.0  | 110  | 0.2404          |
+| 0.1624        | 11.0  | 121  | 0.2320          |
+| 0.1544        | 12.0  | 132  | 0.2295          |
+| 0.1492        | 13.0  | 143  | 0.2278          |
+| 0.149         | 14.0  | 154  | 0.2250          |
+| 0.1514        | 15.0  | 165  | 0.2239          |
 
 
 ### Framework versions

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {