End of training

README.md

@@ -36,7 +36,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 0.01
+- num_epochs: 0.09
 - mixed_precision_training: Native AMP
 
 ### Training results

logs/events.out.tfevents.1702723291.a235c334750e.1882.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f048ffa597afaafd35632cc331e084a702fcba049eab99916dfd97b2b7a8ac9d
+size 4867

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8180774615de49d3c84dedad017328807ae34a1fa2dd8168a09a13e37d932bf3
+oid sha256:4c4de7f5916f44599f9620dafeb5655aeda10ebec759dcf9c996dcdb8733eb74
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010007808640499752,
+  "epoch": 0.09000653376041816,
   "eval_steps": 8000,
-  "global_step": 628,
+  "global_step": 5648,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,13 +16,22 @@
       "train_runtime": 322.5365,
       "train_samples_per_second": 62.257,
       "train_steps_per_second": 1.947
+    },
+    {
+      "epoch": 0.09,
+      "step": 5648,
+      "total_flos": 1.1806219173888e+16,
+      "train_loss": 1.0376979406427054,
+      "train_runtime": 2474.3011,
+      "train_samples_per_second": 73.04,
+      "train_steps_per_second": 2.283
     }
   ],
   "logging_steps": 8000,
-  "max_steps": 628,
+  "max_steps": 5648,
   "num_train_epochs": 1,
   "save_steps": 8000,
-  "total_flos": 1312731168768000.0,
+  "total_flos": 1.1806219173888e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389032ed0f6b8bcc3a6d9a96855d8fd1eb395e266bb86a958b66b427d5fb188b
+oid sha256:38704735567bbcf51c349997edab9d7540450f26004fd210e7261e2de78eb5fc
 size 4600