End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: microsoft/git-base
+base_model: TeeA/git-base-pokemon
 tags:
 - generated_from_trainer
 model-index:
@@ -13,15 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # git-base-pokemon
 
-This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
+This model is a fine-tuned version of [TeeA/git-base-pokemon](https://huggingface.co/TeeA/git-base-pokemon) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1249
-- eval_wer_score: 4.5964
-- eval_runtime: 45.9726
-- eval_samples_per_second: 15.923
-- eval_steps_per_second: 1.001
-- epoch: 6.0
-- step: 913
+- eval_loss: 0.2101
+- eval_wer_score: 4.6548
+- eval_runtime: 25.4225
+- eval_samples_per_second: 28.793
+- eval_steps_per_second: 1.809
+- epoch: 22.0
+- step: 3349
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 50
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/git-base",
+  "_name_or_path": "TeeA/git-base-pokemon",
   "architectures": [
     "GitForCausalLM"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be7909c5602523eec4f7e645408a67fe15aac65cc03dbc987000af72783b2a9
+oid sha256:50f619992c107ba41105da92e4899cf63b56aecfe66751ed1c670c0b1a8fca0c
 size 706516040

runs/Jan02_05-26-00_22a4f9b1e50c/events.out.tfevents.1704173166.22a4f9b1e50c.373.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fb03d3d9971591efeb08baa98fa25b36590895dad30b61e02a644cb23b8ba7
+size 15165

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102422a0b453cd54d9934528f07e9236480d2f67ca822d3626b07badcb9e197c
+oid sha256:b838674edfbce67ac24e7e5b38f26440e5649bd7d041f4c228eeb69a318867bb
 size 4728