End of training

README.md

@@ -13,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.4277
-- eval_runtime: 0.0432
-- eval_samples_per_second: 46.32
-- eval_steps_per_second: 23.16
+- eval_loss: 4.4161
+- eval_runtime: 0.0471
+- eval_samples_per_second: 42.424
+- eval_steps_per_second: 21.212
 - epoch: 1.0
 - step: 1
 
@@ -44,6 +44,7 @@ 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
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc3b0a6ffd5b8f17378f6012aefc278f489bb7233780f269eb1cabd977a5237
+oid sha256:57c96db9d72fa11361de659173136028f7c98934637d89b5f50a34f0c4d7a41e
 size 435820636

runs/Jan05_08-13-40_414819e23027/events.out.tfevents.1704442424.414819e23027.9579.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfcb1fd4472ae9300d3e268820e10cbe3fbdc809768f742fc89f460f8c31d72
-size 7847
+oid sha256:3d5157e976a6c0bdfd0a3264cdbbda96d2b8287516e29c3ea1dfa6732ed71e2c
+size 8267

runs/Jan05_08-15-17_414819e23027/events.out.tfevents.1704442521.414819e23027.9579.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef06bc349a69160ba31249b711101a42ea1e9a342205f04cb0869354d3de3dac
+size 7846

trainer_state.json

@@ -11,15 +11,15 @@
     {
       "epoch": 1.0,
       "learning_rate": 4.9e-05,
-      "loss": 1.7032,
+      "loss": 1.6172,
       "step": 1
     },
     {
       "epoch": 1.0,
-      "eval_loss": 4.427746772766113,
-      "eval_runtime": 0.0432,
-      "eval_samples_per_second": 46.32,
-      "eval_steps_per_second": 23.16,
+      "eval_loss": 4.416090965270996,
+      "eval_runtime": 0.0471,
+      "eval_samples_per_second": 42.424,
+      "eval_steps_per_second": 21.212,
       "step": 1
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b554a0f7ab4b7d3244fac3afa1785f5d08bd92fbd8650dc39823806b8d9c0513
+oid sha256:b966ffecbed91c5a0f2c413b6fea27a6d5dcd1ad5d43f2d92aea5836886021b2
 size 4600