End of training

README.md

@@ -12,6 +12,13 @@ should probably proofread and complete it, then remove this comment. -->
 # food-recipe-generation
 
 This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.1495
+- eval_runtime: 18.2071
+- eval_samples_per_second: 109.847
+- eval_steps_per_second: 1.758
+- epoch: 0.0
+- step: 5
 
 ## Model description
 
@@ -36,16 +43,12 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 0.09
+- num_epochs: 0.1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.15.0
+- Transformers 4.36.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.15.0

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.36.0"
 }

logs/events.out.tfevents.1702890312.94ffa4c68314.42.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64630dbc23c9b85c3ea4f4960fcc89424ccba04711292b1fe9e52329b172817b
-size 6334
+oid sha256:1bf6db4b1bd629a6a7ae0e4599e4400c583db86e41f54f160c93a3d6ba088c27
+size 6488

logs/events.out.tfevents.1702890871.94ffa4c68314.42.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cd43d76757476261ba2f4f4e61ff10a288ff29d524db52b754393270508a68
+size 5071

logs/events.out.tfevents.1702891019.94ffa4c68314.42.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbc75e4a6673145f1c5354bfa7cbab2cf6ea0b0698bb1201737678ca4c06f46
+size 5071

logs/events.out.tfevents.1702891302.94ffa4c68314.42.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1154511ab0129c857aa272addb8906154993b185869d60e5a905de4e7fc768ba
+size 5071

logs/events.out.tfevents.1702891424.94ffa4c68314.42.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e1ac97fb5a6ac92cd7be0bf00839a741c50d6032ec9701e1d240ac574a47dc
+size 5071

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5515811da6e7d576cec17f762b6688e514cb8bb198a4b6ea46af5673262df3fe
+oid sha256:666cbb5e59aaee04ea8170f35956d96e7095a86374ac8b9475767573c0d09143
 size 497918592

trainer_state.json

@@ -1,28 +1,35 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09375,
-  "eval_steps": 10,
-  "global_step": 3,
+  "epoch": 0.001632386549134835,
+  "eval_steps": 5,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.09,
-      "step": 3,
-      "total_flos": 6271008768000.0,
-      "train_loss": 1.1875303586324055,
-      "train_runtime": 2.2971,
-      "train_samples_per_second": 39.179,
-      "train_steps_per_second": 1.306
+      "epoch": 0.0,
+      "learning_rate": 4.9185667752443e-05,
+      "loss": 1.1026,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.1494640111923218,
+      "eval_runtime": 18.2071,
+      "eval_samples_per_second": 109.847,
+      "eval_steps_per_second": 1.758,
+      "step": 5
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 3,
+  "logging_steps": 5,
+  "max_steps": 307,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 10,
-  "total_flos": 6271008768000.0,
+  "save_steps": 5,
+  "total_flos": 10451681280000.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0719ac2c3857521eb0237bb6745188bdf600048244b2e607ab1613757631299
+oid sha256:24f7cc470173209200fa7833aefd3c6f1ea8b6b4e8765bc96a7ce199e4c5e43d
 size 4283