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: 1.1248
-- eval_runtime: 18.0737
-- eval_samples_per_second: 110.658
-- eval_steps_per_second: 1.771
+- eval_loss: 1.1253
+- eval_runtime: 17.9015
+- eval_samples_per_second: 111.722
+- eval_steps_per_second: 1.788
 - epoch: 0.01
-- step: 25
+- step: 30
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea702a24314946f92467438aff883338d086d47b57a079511642c601f29ddf5
-size 5071
+oid sha256:f60b19c41deb5a295a4c31755061d6efbaef785573dee8fe083782fc58461a86
+size 5491

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedddfce999d785930cda46ba5039fb11f40804527336adc043a90eb5babe4c1
+oid sha256:1a9d2f50b1ec70a7f9f965d6c23fb17f132f0f94e902901696715e5e56a02d6d
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.142299771308899,
-  "best_model_checkpoint": "food-recipe-generation/checkpoint-5",
-  "epoch": 0.008161932745674175,
+  "best_metric": 1.1247614622116089,
+  "best_model_checkpoint": "food-recipe-generation/checkpoint-25",
+  "epoch": 0.009794319294809012,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 110.658,
       "eval_steps_per_second": 1.771,
       "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.8371335504885994e-05,
+      "loss": 1.1589,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.1252552270889282,
+      "eval_runtime": 17.9015,
+      "eval_samples_per_second": 111.722,
+      "eval_steps_per_second": 1.788,
+      "step": 30
     }
   ],
   "logging_steps": 5,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 52258406400000.0,
+  "total_flos": 62710087680000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null