Skyler215/Finetune2

README.md

@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1590
-- Rouge1: 0.3875
-- Rouge2: 0.1212
-- Rougel: 0.3156
-- Rougelsum: 0.3166
+- Loss: 2.0461
+- Rouge1: 0.4850
+- Rouge2: 0.2566
+- Rougel: 0.3589
+- Rougelsum: 0.3595
 
 ## Model description
 
@@ -46,23 +46,28 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1024
-- num_epochs: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| No log        | 1.0   | 13   | 4.3037          | 0.3448 | 0.0437 | 0.2181 | 0.2186    |
-| No log        | 2.0   | 26   | 4.2507          | 0.3448 | 0.0437 | 0.2181 | 0.2186    |
-| No log        | 3.0   | 39   | 4.1702          | 0.3448 | 0.0437 | 0.2181 | 0.2186    |
-| No log        | 4.0   | 52   | 4.0673          | 0.3448 | 0.0437 | 0.2181 | 0.2186    |
-| No log        | 5.0   | 65   | 3.9448          | 0.3643 | 0.0496 | 0.2480 | 0.2481    |
-| No log        | 6.0   | 78   | 3.8053          | 0.3653 | 0.0499 | 0.2464 | 0.2466    |
-| No log        | 7.0   | 91   | 3.6485          | 0.3653 | 0.0499 | 0.2464 | 0.2466    |
-| No log        | 8.0   | 104  | 3.4774          | 0.4061 | 0.0678 | 0.2583 | 0.2586    |
-| No log        | 9.0   | 117  | 3.3057          | 0.3700 | 0.0443 | 0.2441 | 0.2448    |
-| No log        | 10.0  | 130  | 3.1590          | 0.3875 | 0.1212 | 0.3156 | 0.3166    |
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 2.4042        | 1.0   | 1828  | 1.7451          | 0.4622 | 0.1906 | 0.3370 | 0.3422    |
+| 1.5875        | 2.0   | 3656  | 1.5933          | 0.4599 | 0.2060 | 0.3451 | 0.3472    |
+| 1.3882        | 3.0   | 5484  | 1.5322          | 0.4606 | 0.2082 | 0.3422 | 0.3442    |
+| 1.2415        | 4.0   | 7312  | 1.5130          | 0.4687 | 0.2208 | 0.3458 | 0.3476    |
+| 1.1113        | 5.0   | 9140  | 1.5186          | 0.4630 | 0.2146 | 0.3398 | 0.3402    |
+| 0.9671        | 6.0   | 10968 | 1.5683          | 0.4720 | 0.2290 | 0.3517 | 0.3520    |
+| 0.8528        | 7.0   | 12796 | 1.6352          | 0.4704 | 0.2281 | 0.3491 | 0.3496    |
+| 0.7555        | 8.0   | 14624 | 1.7122          | 0.4725 | 0.2305 | 0.3477 | 0.3481    |
+| 0.6567        | 9.0   | 16452 | 1.7814          | 0.4763 | 0.2389 | 0.3537 | 0.3543    |
+| 0.5612        | 10.0  | 18280 | 1.8528          | 0.4777 | 0.2410 | 0.3515 | 0.3516    |
+| 0.4953        | 11.0  | 20108 | 1.9072          | 0.4799 | 0.2487 | 0.3562 | 0.3565    |
+| 0.4445        | 12.0  | 21936 | 1.9503          | 0.4829 | 0.2514 | 0.3571 | 0.3574    |
+| 0.3976        | 13.0  | 23764 | 1.9928          | 0.4834 | 0.2543 | 0.3569 | 0.3573    |
+| 0.3643        | 14.0  | 25592 | 2.0249          | 0.4820 | 0.2520 | 0.3575 | 0.3581    |
+| 0.3263        | 15.0  | 27420 | 2.0461          | 0.4850 | 0.2566 | 0.3589 | 0.3595    |
 
 
 ### Framework versions

config.json

@@ -185,21 +185,6 @@
   "no_repeat_ngram_size": null,
   "num_beams": null,
   "pad_token_id": 50259,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "tie_encoder_decoder": true,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08b62e0db86d85d9385c5e51409d7af7f172ba1d5b0776b62014e22f2998f66
+oid sha256:6ac4967b9e428e1d0cd5d8131a809c357f99733b0d702f90d22ee83a7015a9d8
 size 956847808

runs/Nov25_14-02-34_b1ac11fd3836/events.out.tfevents.1732543354.b1ac11fd3836.814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665beba30094b6e409a40941c559c94c60b3b09afda932cb2dad3aa9f92a9c73
+size 9832

runs/Nov25_14-20-26_b1ac11fd3836/events.out.tfevents.1732544426.b1ac11fd3836.814.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d063b03dd9043c8bfcb803416b90652aa5fa75bf8dc952a64ad115d5a99e1bbb
+size 22684

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3250168532d7a398ffe371b69ed5814ef5808e6d1166e9f0afc312e49f36e8e7
+oid sha256:63dabb376ec66b07ca97ed2e5a31a3f89c482d325417e5a1636bbca97377c0d6
 size 5432