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: 1.1222
-- eval_runtime: 17.8085
-- eval_samples_per_second: 112.306
-- eval_steps_per_second: 1.797
+- eval_loss: 1.1328
+- eval_runtime: 18.2169
+- eval_samples_per_second: 109.788
+- eval_steps_per_second: 1.757
 - epoch: 0.02
-- step: 50
+- step: 55
 
 ## Model description
 

logs/events.out.tfevents.1702893748.c87f45a5aed4.42.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b745c560d58f901442361f39e390fc2160c183eb0f8c06e4143c1ecb00ca03d
+size 5071

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db25361201f94ee4603c3730182d977d0a4d9f1bc5f98ae095777c4e48f5691
+oid sha256:7704850a36e6d5a6cfee818b88972a342e7735882cd0b07fd42504b010b0da80
 size 497918592

tmp-checkpoint-50/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/kaggle/working/food-recipe-generation",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

tmp-checkpoint-50/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.36.0"
+}

tmp-checkpoint-50/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db25361201f94ee4603c3730182d977d0a4d9f1bc5f98ae095777c4e48f5691
+size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.124158501625061,
   "best_model_checkpoint": "food-recipe-generation/checkpoint-45",
-  "epoch": 0.01632386549134835,
+  "epoch": 0.017956252040483185,
   "eval_steps": 5,
-  "global_step": 50,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 112.306,
       "eval_steps_per_second": 1.797,
       "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9185667752443e-05,
+      "loss": 1.1619,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.1328459978103638,
+      "eval_runtime": 18.2169,
+      "eval_samples_per_second": 109.788,
+      "eval_steps_per_second": 1.757,
+      "step": 55
     }
   ],
   "logging_steps": 5,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 104516812800000.0,
+  "total_flos": 114968494080000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null