End of training

README.md

@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 9.1700
-- eval_runtime: 0.0227
-- eval_samples_per_second: 44.006
-- eval_steps_per_second: 44.006
-- epoch: 14.0
-- step: 14
+- eval_loss: 6.9974
+- eval_runtime: 0.0211
+- eval_samples_per_second: 47.457
+- eval_steps_per_second: 47.457
+- epoch: 15.0
+- step: 15
 
 ## Model description
 

logs/events.out.tfevents.1707026005.d77ab3a64c5c.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b30f62ec1847ca76b405ad57c309dfc4c520836c677baa7de39b200b3a6488fb
-size 10513
+oid sha256:8ba3d6e581aab74637b693922b066f79ffe151620bbe2904e337fe6d48bb02b4
+size 10933

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64eb868bc0c790fa98f05c5b534049b2379eb16ba7ecb9fe98cf7ea826e77cde
+oid sha256:0f0f5d17dafec3300164ff2ba0d1d63fbe9d86331d49f4e267f4f76e9f82cadf
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.201495170593262,
-  "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-12",
-  "epoch": 14.0,
+  "best_metric": 9.170014381408691,
+  "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-14",
+  "epoch": 15.0,
   "eval_steps": 1,
-  "global_step": 14,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 44.006,
       "eval_steps_per_second": 44.006,
       "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 4.6500000000000005e-05,
+      "loss": 6.3525,
+      "step": 15
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 6.997350215911865,
+      "eval_runtime": 0.0211,
+      "eval_samples_per_second": 47.457,
+      "eval_steps_per_second": 47.457,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 1,
-  "total_flos": 8230699008000.0,
+  "total_flos": 8818606080000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null