End of training

README.md

@@ -13,12 +13,12 @@ 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: 1.1320
-- eval_runtime: 17.9412
-- eval_samples_per_second: 111.475
-- eval_steps_per_second: 1.784
+- eval_loss: 1.1335
+- eval_runtime: 18.0469
+- eval_samples_per_second: 110.823
+- eval_steps_per_second: 1.773
 - epoch: 0.02
-- step: 60
+- step: 65
 
 ## Model description
 

logs/events.out.tfevents.1702893748.c87f45a5aed4.42.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eca5756cd605e56bb8332681de3de0854eaaf03e7d12aae581987a174a64287
-size 5491
+oid sha256:9de95e510743adc9435e0b43123b8d3ae1d2ccb8fafa4aefe8a600a18f48f7d5
+size 5911

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebe54156db4801eb501da56abfaa820961e6fde0bee34d1fdae60c3d304fd51
+oid sha256:5e61e3bd1c996a2773a820b93fa6954cc5f60e51780cc5f1901127d1f3122031
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.124158501625061,
   "best_model_checkpoint": "food-recipe-generation/checkpoint-45",
-  "epoch": 0.019588638589618023,
+  "epoch": 0.021221025138752857,
   "eval_steps": 5,
-  "global_step": 60,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 111.475,
       "eval_steps_per_second": 1.784,
       "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.755700325732899e-05,
+      "loss": 1.1628,
+      "step": 65
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.1334753036499023,
+      "eval_runtime": 18.0469,
+      "eval_samples_per_second": 110.823,
+      "eval_steps_per_second": 1.773,
+      "step": 65
     }
   ],
   "logging_steps": 5,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 125420175360000.0,
+  "total_flos": 135871856640000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null