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: 1.1423
-- eval_runtime: 18.2229
-- eval_samples_per_second: 109.752
+- eval_loss: 1.1526
+- eval_runtime: 18.2243
+- eval_samples_per_second: 109.744
 - eval_steps_per_second: 1.756
 - epoch: 0.0
-- step: 5
+- step: 15
 
 ## Model description
 

logs/events.out.tfevents.1702892360.82d5b6822809.42.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b731f489539729ca489d9f14794e43f6410b766b6914000b9675dc117820e8
-size 5071
+oid sha256:665bd13cf70bd896026d07b64a9a9163b7760281767a496ec63619223b9ef07d
+size 5491

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ad33be7d0485b15516b8569d1a5beb0cb8ff4e4b63a6739ebc3c0e37d8f4b2
+size 5071

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876ea86b9abcb1b2de8746622b8968d50f0dee582e9aa4b133c809b475d5c880
+oid sha256:786a50d8d4ce0218d11987ec66734818f9045dfe55fad3d78997f5a0a8bc34fb
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.001632386549134835,
+  "best_metric": 1.142299771308899,
+  "best_model_checkpoint": "food-recipe-generation/checkpoint-5",
+  "epoch": 0.004897159647404506,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,34 @@
       "eval_samples_per_second": 109.752,
       "eval_steps_per_second": 1.756,
       "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.8371335504885994e-05,
+      "loss": 1.2427,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.1404472589492798,
+      "eval_runtime": 17.9113,
+      "eval_samples_per_second": 111.662,
+      "eval_steps_per_second": 1.787,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9185667752443e-05,
+      "loss": 1.1104,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.1525651216506958,
+      "eval_runtime": 18.2243,
+      "eval_samples_per_second": 109.744,
+      "eval_steps_per_second": 1.756,
+      "step": 15
     }
   ],
   "logging_steps": 5,
@@ -28,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 10451681280000.0,
+  "total_flos": 31355043840000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null