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: 1.1259
-- eval_runtime: 17.8768
-- eval_samples_per_second: 111.877
-- eval_steps_per_second: 1.79
+- eval_loss: 1.1242
+- eval_runtime: 17.8962
+- eval_samples_per_second: 111.756
+- eval_steps_per_second: 1.788
 - epoch: 0.01
-- step: 40
+- step: 45
 
 ## Model description
 

logs/events.out.tfevents.1702892983.c87f45a5aed4.42.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e49af1f1bac3d15763763630c59e684ea568b41c80bf27910feb9dcac98dc1
-size 6331
+oid sha256:c6b59e6436b272d280410208bdc36d59fef679a50ea1cfcc33bbeb57c34b9bb2
+size 6751

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf91abf8c49f3c8dcb5c8d33a3992e3e3a76829568f75daa4052d64033de42e
+oid sha256:502efa3e70ac250c4b4511ccdb38f16d1c8af9b3b9af6be779726d8d2c3e8305
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1247614622116089,
   "best_model_checkpoint": "food-recipe-generation/checkpoint-25",
-  "epoch": 0.01305909239307868,
+  "epoch": 0.014691478942213516,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 111.877,
       "eval_steps_per_second": 1.79,
       "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.592833876221499e-05,
+      "loss": 1.16,
+      "step": 45
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.124158501625061,
+      "eval_runtime": 17.8962,
+      "eval_samples_per_second": 111.756,
+      "eval_steps_per_second": 1.788,
+      "step": 45
     }
   ],
   "logging_steps": 5,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 83613450240000.0,
+  "total_flos": 94065131520000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null