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: 1.1242
-- eval_runtime: 17.8962
-- eval_samples_per_second: 111.756
-- eval_steps_per_second: 1.788
-- epoch: 0.01
-- step: 45
+- eval_loss: 1.1222
+- eval_runtime: 17.8085
+- eval_samples_per_second: 112.306
+- eval_steps_per_second: 1.797
+- epoch: 0.02
+- step: 50
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b59e6436b272d280410208bdc36d59fef679a50ea1cfcc33bbeb57c34b9bb2
-size 6751
+oid sha256:455757bae7675273c4dd282d19d10ca985f4cf4abf34f31d7a0e088706efbe3a
+size 7171

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502efa3e70ac250c4b4511ccdb38f16d1c8af9b3b9af6be779726d8d2c3e8305
+oid sha256:2db25361201f94ee4603c3730182d977d0a4d9f1bc5f98ae095777c4e48f5691
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1247614622116089,
-  "best_model_checkpoint": "food-recipe-generation/checkpoint-25",
-  "epoch": 0.014691478942213516,
+  "best_metric": 1.124158501625061,
+  "best_model_checkpoint": "food-recipe-generation/checkpoint-45",
+  "epoch": 0.01632386549134835,
   "eval_steps": 5,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 111.756,
       "eval_steps_per_second": 1.788,
       "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.511400651465798e-05,
+      "loss": 1.2131,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.1221903562545776,
+      "eval_runtime": 17.8085,
+      "eval_samples_per_second": 112.306,
+      "eval_steps_per_second": 1.797,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 94065131520000.0,
+  "total_flos": 104516812800000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null