End of training

README.md

@@ -4,8 +4,6 @@ tags:
 - generated_from_trainer
 datasets:
 - pubmed-summarization
-metrics:
-- rouge
 model-index:
 - name: lsg-bart-base-16384-pubmed-finetuned-pubmed-16394
   results: []
@@ -14,16 +12,21 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/thanhkt27507-vsu/huggingface/runs/uh54ybef)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/thanhkt27507-vsu/huggingface/runs/056l8muj)
 # lsg-bart-base-16384-pubmed-finetuned-pubmed-16394
 
 This model is a fine-tuned version of [ccdv/lsg-bart-base-16384-pubmed](https://huggingface.co/ccdv/lsg-bart-base-16384-pubmed) on the pubmed-summarization dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3006
-- Rouge1: 0.406
-- Rouge2: 0.1651
-- Rougel: 0.2662
-- Rougelsum: 0.3547
+- eval_loss: 5.6482
+- eval_rouge1: 0.451
+- eval_rouge2: 0.2128
+- eval_rougeL: 0.2772
+- eval_rougeLsum: 0.4174
+- eval_runtime: 484.657
+- eval_samples_per_second: 0.413
+- eval_steps_per_second: 0.206
+- epoch: 1.6
+- step: 100
 
 ## Model description
 
@@ -42,7 +45,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8e-05
+- learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
@@ -51,25 +54,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 6
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 12.4753       | 0.48  | 30   | 9.7449          | 0.3279 | 0.1346 | 0.2161 | 0.2938    |
-| 7.5448        | 0.96  | 60   | 4.3875          | 0.3249 | 0.1325 | 0.215  | 0.2898    |
-| 3.8253        | 1.44  | 90   | 2.4496          | 0.3388 | 0.1393 | 0.2243 | 0.301     |
-| 2.2909        | 1.92  | 120  | 1.3377          | 0.3446 | 0.1424 | 0.2263 | 0.3069    |
-| 1.1711        | 2.4   | 150  | 0.5844          | 0.3476 | 0.1447 | 0.2284 | 0.3093    |
-| 0.4808        | 2.88  | 180  | 0.3227          | 0.3677 | 0.1532 | 0.2395 | 0.3284    |
-| 0.2757        | 3.36  | 210  | 0.2896          | 0.3705 | 0.1465 | 0.2385 | 0.3282    |
-| 0.2491        | 3.84  | 240  | 0.2863          | 0.3975 | 0.1666 | 0.2617 | 0.3517    |
-| 0.2346        | 4.32  | 270  | 0.2911          | 0.3962 | 0.1663 | 0.262  | 0.3517    |
-| 0.2207        | 4.8   | 300  | 0.2919          | 0.3918 | 0.1614 | 0.259  | 0.3466    |
-| 0.2098        | 5.28  | 330  | 0.2989          | 0.3955 | 0.1611 | 0.2568 | 0.3495    |
-| 0.1985        | 5.76  | 360  | 0.3006          | 0.406  | 0.1651 | 0.2662 | 0.3547    |
-
+- num_epochs: 9
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5895e123cb0da321d4f5c854701ff55ba0b1696d0965f985f23c6ba2dc2302
+oid sha256:7992feaeda807fa29cc86c1e3a712b0a1d88c03fe1cb066befffc849fecc9500
 size 653857508

runs/Jul19_10-30-21_3be8174ee72b/events.out.tfevents.1721385021.3be8174ee72b.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9f176e6be2c97e402311ef9bb47d192ee0ec61fd79a0f73412a56ea942ccfe
+size 8341

tokenizer_config.json

@@ -48,7 +48,7 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 512,
+  "max_length": 4096,
   "model_max_length": 16384,
   "pad_token": "<pad>",
   "sep_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09d24bdf34a09b0d0ed8efe040563dbacb630a2557e7f6ba3730bbbf9b21bb8
+oid sha256:99c3adba772b0b22dc1b0279283daa3e869a9ae4e216aa76ad3171065715e55c
 size 4923