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: 1.1526
-- eval_runtime: 18.2243
-- eval_samples_per_second: 109.744
-- eval_steps_per_second: 1.756
-- epoch: 0.0
-- step: 15
+- eval_loss: 1.1525
+- eval_runtime: 17.9261
+- eval_samples_per_second: 111.569
+- eval_steps_per_second: 1.785
+- epoch: 0.01
+- step: 20
 
 ## Model description
 

logs/events.out.tfevents.1702892648.82d5b6822809.42.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ad33be7d0485b15516b8569d1a5beb0cb8ff4e4b63a6739ebc3c0e37d8f4b2
-size 5071
+oid sha256:a5bc7ba9bf0160bb974108ee13fd6e89d84e23fb462e86151f3a5523b9c82c73
+size 5491

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786a50d8d4ce0218d11987ec66734818f9045dfe55fad3d78997f5a0a8bc34fb
+oid sha256:91d0acc4d2d56f0cc48445003be031c08633d89d08448565ee65404a26feb261
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.142299771308899,
   "best_model_checkpoint": "food-recipe-generation/checkpoint-5",
-  "epoch": 0.004897159647404506,
+  "epoch": 0.00652954619653934,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 109.744,
       "eval_steps_per_second": 1.756,
       "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.8371335504885994e-05,
+      "loss": 1.0834,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.152503490447998,
+      "eval_runtime": 17.9261,
+      "eval_samples_per_second": 111.569,
+      "eval_steps_per_second": 1.785,
+      "step": 20
     }
   ],
   "logging_steps": 5,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 31355043840000.0,
+  "total_flos": 41806725120000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null