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: 1.6093
-- eval_runtime: 0.0202
-- eval_samples_per_second: 49.616
-- eval_steps_per_second: 49.616
-- epoch: 63.0
-- step: 63
+- eval_loss: 1.6092
+- eval_runtime: 0.0205
+- eval_samples_per_second: 48.823
+- eval_steps_per_second: 48.823
+- epoch: 64.0
+- step: 64
 
 ## Model description
 

logs/events.out.tfevents.1707026588.d77ab3a64c5c.34.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff73fe3740fb5b99d01ef6ef1cbadab314dffc088695fad2e971a007c4f62f0
-size 24446
+oid sha256:94232f3ccf63cd83b0fd10a681fe1da1ed75cc824e16fc93d6019254ee1a2bd5
+size 24866

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ea65344f5f47340489f9baffe2718ad1c9a31a5e30646c73ddc3b7b576a4c4
+oid sha256:35477aab7a0d675972e3637322e028ad7b025b3cc2ea5013d9358f7f5b631137
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5992611646652222,
   "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-53",
-  "epoch": 63.0,
+  "epoch": 64.0,
   "eval_steps": 1,
-  "global_step": 63,
+  "global_step": 64,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -889,6 +889,20 @@
       "eval_samples_per_second": 49.616,
       "eval_steps_per_second": 49.616,
       "step": 63
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.1083,
+      "step": 64
+    },
+    {
+      "epoch": 64.0,
+      "eval_loss": 1.6092382669448853,
+      "eval_runtime": 0.0205,
+      "eval_samples_per_second": 48.823,
+      "eval_steps_per_second": 48.823,
+      "step": 64
     }
   ],
   "logging_steps": 1,
@@ -896,7 +910,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 1,
-  "total_flos": 37038145536000.0,
+  "total_flos": 37626052608000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null