End of training

README.md

@@ -13,7 +13,7 @@ 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: 1.6773
+- Loss: 0.9871
 
 ## Model description
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -53,6 +53,11 @@ The following hyperparameters were used during training:
 | 2.0204        | 3.0   | 11601 | 2.0694          |
 | 1.6845        | 4.0   | 15468 | 1.7321          |
 | 1.5994        | 5.0   | 19335 | 1.6773          |
+| 1.3579        | 6.0   | 23202 | 1.3416          |
+| 1.0921        | 7.0   | 27069 | 1.1302          |
+| 0.975         | 8.0   | 30936 | 1.0375          |
+| 0.9599        | 9.0   | 34803 | 0.9928          |
+| 0.9228        | 10.0  | 38670 | 0.9871          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0535ed3ab84bc2141732a3bba63920207461aaed5c048fce195c35101f114c90
+oid sha256:79c468ba0cd9b6a689dde131aa146da7e5dfe0bebfa010669ef76fcd76d783c3
 size 2324348896

runs/Mar30_21-05-46_2fb5a5160ba6/events.out.tfevents.1711832784.2fb5a5160ba6.2205.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519c850c2117820864f0265c9f89361580a86672730309f560fd656aed7a5843
-size 16563
+oid sha256:599270e2bc1073a77539145022ae97abf1e725b57ade4d2cf4f86126bbf14d72
+size 18919

runs/Mar30_21-05-46_2fb5a5160ba6/events.out.tfevents.1711862585.2fb5a5160ba6.2205.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ccf871dd7fe4ab7975775733788b2bb84533f7d58f4cb82f9e344fb96d6086
+size 364