End of training

README.md

@@ -13,13 +13,13 @@ 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: 1.6239
-- eval_accuracy: 0.889
-- eval_runtime: 15.4204
-- eval_samples_per_second: 64.849
-- eval_steps_per_second: 4.085
-- epoch: 0.16
-- step: 10
+- eval_loss: 1.5642
+- eval_accuracy: 0.896
+- eval_runtime: 15.4357
+- eval_samples_per_second: 64.785
+- eval_steps_per_second: 4.081
+- epoch: 0.32
+- step: 20
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61232a5c671227f482ab55cfa03487da624786f4fb0cabe828f1ae2287d73e38
+oid sha256:7dd65022906a0ab5f82a88756f55cc79380928935ba4c8d864da8c5b57a3acff
 size 343528508

runs/Feb04_07-22-55_0bc3247a45bd/events.out.tfevents.1707031376.0bc3247a45bd.819.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8068d2aa1650743e6fb7f978142028a3034f52513763f6780cbe989e40d12c89
-size 9699
+oid sha256:87fcdb11e956e547ff64bf76406cffc727915dbe9e408587b61aa557e13e4440
+size 10170

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.32,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,13 +22,28 @@
       "eval_samples_per_second": 64.849,
       "eval_steps_per_second": 4.085,
       "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 1.5408,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.896,
+      "eval_loss": 1.56419038772583,
+      "eval_runtime": 15.4357,
+      "eval_samples_per_second": 64.785,
+      "eval_steps_per_second": 4.081,
+      "step": 20
     }
   ],
   "logging_steps": 10,
   "max_steps": 310,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 4.9638879166464e+16,
+  "total_flos": 9.9277758332928e+16,
   "trial_name": null,
   "trial_params": null
 }