初始化项目，由ModelHub XC社区提供模型

Model: simonneupane/controlled-food-recipe-generation
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+models--simonneupane--controlled-food-recipe-generation/blobs/a90f40534f604576f9df857da789f69f5554f078113862b5cc7a65d322544c44 filter=lfs diff=lfs merge=lfs -text
+models--simonneupane--controlled-food-recipe-generation/blobs/ca7d086830480ea81f7fbc4697a77f87cfdd80e26cccb0695f6a8eba0263b548 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: controlled-food-recipe-generation
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# controlled-food-recipe-generation
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,15 @@
+{
+  "<INGR_END>": 50264,
+  "<INGR_START>": 50262,
+  "<INPUT_END>": 50259,
+  "<INPUT_START>": 50257,
+  "<INSTR_END>": 50267,
+  "<INSTR_START>": 50265,
+  "<NEXT_INGR>": 50263,
+  "<NEXT_INPUT>": 50258,
+  "<NEXT_STEP>": 50266,
+  "<RECIPE_END>": 50269,
+  "<RECIPE_START>": 50268,
+  "<TITLE_END>": 50261,
+  "<TITLE_START>": 50260
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50270
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

last-checkpoint/added_tokens.json

@@ -0,0 +1,15 @@
+{
+  "<INGR_END>": 50264,
+  "<INGR_START>": 50262,
+  "<INPUT_END>": 50259,
+  "<INPUT_START>": 50257,
+  "<INSTR_END>": 50267,
+  "<INSTR_START>": 50265,
+  "<NEXT_INGR>": 50263,
+  "<NEXT_INPUT>": 50258,
+  "<NEXT_STEP>": 50266,
+  "<RECIPE_END>": 50269,
+  "<RECIPE_START>": 50268,
+  "<TITLE_END>": 50261,
+  "<TITLE_START>": 50260
+}

last-checkpoint/config.json

@@ -0,0 +1,38 @@
+{
+  "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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50270
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31374e11cab95da4335286559400d4ef35bb288afc215f0d0021f27efc3e85cc
+size 497814144

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2683f4879e9b48ffc355a648377c9029f351277f0a969be4564f844da3da4d8a
+size 995722170

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995b07f3cfc3baacff0e258cdaec63824fdb43fb33ccabe8297d597e04955aea
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
+size 988

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c910fc6b91130eeca68181cc3c87a2e24b14e94547f06fd96621073d501c834
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,127 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<INPUT_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<NEXT_INPUT>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<INPUT_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "<TITLE_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "<TITLE_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "<INGR_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "<NEXT_INGR>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "<INGR_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "<INSTR_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "<NEXT_STEP>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "<INSTR_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "<RECIPE_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "<RECIPE_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,804 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8764800560947236,
+  "eval_steps": 500,
+  "global_step": 55000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007968000509952033,
+      "grad_norm": 118280.5625,
+      "learning_rate": 2.9936381561814055e-05,
+      "loss": 1.2421,
+      "step": 500
+    },
+    {
+      "epoch": 0.015936001019904066,
+      "grad_norm": 93972.8125,
+      "learning_rate": 2.9856659208197584e-05,
+      "loss": 0.7745,
+      "step": 1000
+    },
+    {
+      "epoch": 0.023904001529856098,
+      "grad_norm": 78047.78125,
+      "learning_rate": 2.9776936854581113e-05,
+      "loss": 0.73,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03187200203980813,
+      "grad_norm": 72831.09375,
+      "learning_rate": 2.9697214500964642e-05,
+      "loss": 0.7087,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03984000254976016,
+      "grad_norm": 62310.4453125,
+      "learning_rate": 2.961749214734817e-05,
+      "loss": 0.6964,
+      "step": 2500
+    },
+    {
+      "epoch": 0.047808003059712195,
+      "grad_norm": 65517.09375,
+      "learning_rate": 2.9537769793731697e-05,
+      "loss": 0.6858,
+      "step": 3000
+    },
+    {
+      "epoch": 0.05577600356966423,
+      "grad_norm": 57505.90625,
+      "learning_rate": 2.9458047440115226e-05,
+      "loss": 0.6761,
+      "step": 3500
+    },
+    {
+      "epoch": 0.06374400407961626,
+      "grad_norm": 55419.26171875,
+      "learning_rate": 2.9378325086498752e-05,
+      "loss": 0.6679,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07171200458956829,
+      "grad_norm": 51254.3671875,
+      "learning_rate": 2.929860273288228e-05,
+      "loss": 0.6602,
+      "step": 4500
+    },
+    {
+      "epoch": 0.07968000509952032,
+      "grad_norm": 51469.9765625,
+      "learning_rate": 2.9218880379265813e-05,
+      "loss": 0.6554,
+      "step": 5000
+    },
+    {
+      "epoch": 0.08764800560947236,
+      "grad_norm": 69357.2265625,
+      "learning_rate": 2.913915802564934e-05,
+      "loss": 0.6516,
+      "step": 5500
+    },
+    {
+      "epoch": 0.09561600611942439,
+      "grad_norm": 48255.7890625,
+      "learning_rate": 2.9059435672032868e-05,
+      "loss": 0.6482,
+      "step": 6000
+    },
+    {
+      "epoch": 0.10358400662937642,
+      "grad_norm": 59810.20703125,
+      "learning_rate": 2.8979713318416394e-05,
+      "loss": 0.6397,
+      "step": 6500
+    },
+    {
+      "epoch": 0.11155200713932846,
+      "grad_norm": 54012.7109375,
+      "learning_rate": 2.8899990964799923e-05,
+      "loss": 0.6425,
+      "step": 7000
+    },
+    {
+      "epoch": 0.11952000764928049,
+      "grad_norm": 47228.74609375,
+      "learning_rate": 2.8820268611183452e-05,
+      "loss": 0.6392,
+      "step": 7500
+    },
+    {
+      "epoch": 0.12748800815923253,
+      "grad_norm": 55561.9453125,
+      "learning_rate": 2.874054625756698e-05,
+      "loss": 0.6342,
+      "step": 8000
+    },
+    {
+      "epoch": 0.13545600866918456,
+      "grad_norm": 50830.77734375,
+      "learning_rate": 2.866082390395051e-05,
+      "loss": 0.6288,
+      "step": 8500
+    },
+    {
+      "epoch": 0.14342400917913659,
+      "grad_norm": 45037.15234375,
+      "learning_rate": 2.858110155033404e-05,
+      "loss": 0.6283,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1513920096890886,
+      "grad_norm": 42729.57421875,
+      "learning_rate": 2.8501379196717565e-05,
+      "loss": 0.6252,
+      "step": 9500
+    },
+    {
+      "epoch": 0.15936001019904064,
+      "grad_norm": 46592.18359375,
+      "learning_rate": 2.8421656843101094e-05,
+      "loss": 0.6199,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1673280107089927,
+      "grad_norm": 40794.70703125,
+      "learning_rate": 2.834193448948462e-05,
+      "loss": 0.6237,
+      "step": 10500
+    },
+    {
+      "epoch": 0.17529601121894473,
+      "grad_norm": 40227.96484375,
+      "learning_rate": 2.8262212135868152e-05,
+      "loss": 0.6174,
+      "step": 11000
+    },
+    {
+      "epoch": 0.18326401172889675,
+      "grad_norm": 49994.6015625,
+      "learning_rate": 2.818248978225168e-05,
+      "loss": 0.6151,
+      "step": 11500
+    },
+    {
+      "epoch": 0.19123201223884878,
+      "grad_norm": 55100.75390625,
+      "learning_rate": 2.8102767428635207e-05,
+      "loss": 0.6117,
+      "step": 12000
+    },
+    {
+      "epoch": 0.1992000127488008,
+      "grad_norm": 93011.546875,
+      "learning_rate": 2.8023045075018736e-05,
+      "loss": 0.6122,
+      "step": 12500
+    },
+    {
+      "epoch": 0.20716801325875284,
+      "grad_norm": 47631.09375,
+      "learning_rate": 2.794332272140226e-05,
+      "loss": 0.6133,
+      "step": 13000
+    },
+    {
+      "epoch": 0.2151360137687049,
+      "grad_norm": 42235.15625,
+      "learning_rate": 2.786360036778579e-05,
+      "loss": 0.6038,
+      "step": 13500
+    },
+    {
+      "epoch": 0.22310401427865692,
+      "grad_norm": 41144.3359375,
+      "learning_rate": 2.7783878014169323e-05,
+      "loss": 0.6074,
+      "step": 14000
+    },
+    {
+      "epoch": 0.23107201478860895,
+      "grad_norm": 47137.19921875,
+      "learning_rate": 2.770415566055285e-05,
+      "loss": 0.6047,
+      "step": 14500
+    },
+    {
+      "epoch": 0.23904001529856098,
+      "grad_norm": 37974.65625,
+      "learning_rate": 2.7624433306936378e-05,
+      "loss": 0.6058,
+      "step": 15000
+    },
+    {
+      "epoch": 0.247008015808513,
+      "grad_norm": 49424.44140625,
+      "learning_rate": 2.7544710953319903e-05,
+      "loss": 0.6014,
+      "step": 15500
+    },
+    {
+      "epoch": 0.25497601631846506,
+      "grad_norm": 57363.96875,
+      "learning_rate": 2.7464988599703432e-05,
+      "loss": 0.6012,
+      "step": 16000
+    },
+    {
+      "epoch": 0.26294401682841706,
+      "grad_norm": 48850.90234375,
+      "learning_rate": 2.738526624608696e-05,
+      "loss": 0.5969,
+      "step": 16500
+    },
+    {
+      "epoch": 0.2709120173383691,
+      "grad_norm": 60200.43359375,
+      "learning_rate": 2.730554389247049e-05,
+      "loss": 0.5958,
+      "step": 17000
+    },
+    {
+      "epoch": 0.2788800178483211,
+      "grad_norm": 48039.16015625,
+      "learning_rate": 2.722582153885402e-05,
+      "loss": 0.598,
+      "step": 17500
+    },
+    {
+      "epoch": 0.28684801835827317,
+      "grad_norm": 34431.2265625,
+      "learning_rate": 2.7146099185237545e-05,
+      "loss": 0.5953,
+      "step": 18000
+    },
+    {
+      "epoch": 0.2948160188682252,
+      "grad_norm": 34913.16015625,
+      "learning_rate": 2.7066376831621074e-05,
+      "loss": 0.5932,
+      "step": 18500
+    },
+    {
+      "epoch": 0.3027840193781772,
+      "grad_norm": 36192.234375,
+      "learning_rate": 2.6986654478004603e-05,
+      "loss": 0.5939,
+      "step": 19000
+    },
+    {
+      "epoch": 0.3107520198881293,
+      "grad_norm": 46195.62890625,
+      "learning_rate": 2.690693212438813e-05,
+      "loss": 0.5914,
+      "step": 19500
+    },
+    {
+      "epoch": 0.3187200203980813,
+      "grad_norm": 43815.43359375,
+      "learning_rate": 2.682720977077166e-05,
+      "loss": 0.5904,
+      "step": 20000
+    },
+    {
+      "epoch": 0.32668802090803334,
+      "grad_norm": 35572.34375,
+      "learning_rate": 2.674748741715519e-05,
+      "loss": 0.5865,
+      "step": 20500
+    },
+    {
+      "epoch": 0.3346560214179854,
+      "grad_norm": 36805.02734375,
+      "learning_rate": 2.6667765063538716e-05,
+      "loss": 0.5904,
+      "step": 21000
+    },
+    {
+      "epoch": 0.3426240219279374,
+      "grad_norm": 45271.30078125,
+      "learning_rate": 2.6588042709922245e-05,
+      "loss": 0.5873,
+      "step": 21500
+    },
+    {
+      "epoch": 0.35059202243788945,
+      "grad_norm": 35245.0234375,
+      "learning_rate": 2.650832035630577e-05,
+      "loss": 0.5856,
+      "step": 22000
+    },
+    {
+      "epoch": 0.35856002294784145,
+      "grad_norm": 34578.25,
+      "learning_rate": 2.64285980026893e-05,
+      "loss": 0.5795,
+      "step": 22500
+    },
+    {
+      "epoch": 0.3665280234577935,
+      "grad_norm": 40504.375,
+      "learning_rate": 2.6348875649072832e-05,
+      "loss": 0.5846,
+      "step": 23000
+    },
+    {
+      "epoch": 0.37449602396774556,
+      "grad_norm": 37683.4453125,
+      "learning_rate": 2.6269153295456358e-05,
+      "loss": 0.5792,
+      "step": 23500
+    },
+    {
+      "epoch": 0.38246402447769756,
+      "grad_norm": 35323.41015625,
+      "learning_rate": 2.6189430941839887e-05,
+      "loss": 0.5803,
+      "step": 24000
+    },
+    {
+      "epoch": 0.3904320249876496,
+      "grad_norm": 47546.1953125,
+      "learning_rate": 2.6109708588223413e-05,
+      "loss": 0.5805,
+      "step": 24500
+    },
+    {
+      "epoch": 0.3984000254976016,
+      "grad_norm": 44604.859375,
+      "learning_rate": 2.6029986234606942e-05,
+      "loss": 0.5773,
+      "step": 25000
+    },
+    {
+      "epoch": 0.4063680260075537,
+      "grad_norm": 47108.78125,
+      "learning_rate": 2.595026388099047e-05,
+      "loss": 0.5825,
+      "step": 25500
+    },
+    {
+      "epoch": 0.4143360265175057,
+      "grad_norm": 42788.87109375,
+      "learning_rate": 2.5870541527374e-05,
+      "loss": 0.578,
+      "step": 26000
+    },
+    {
+      "epoch": 0.42230402702745773,
+      "grad_norm": 33550.89453125,
+      "learning_rate": 2.579081917375753e-05,
+      "loss": 0.5779,
+      "step": 26500
+    },
+    {
+      "epoch": 0.4302720275374098,
+      "grad_norm": 36036.8984375,
+      "learning_rate": 2.5711096820141055e-05,
+      "loss": 0.574,
+      "step": 27000
+    },
+    {
+      "epoch": 0.4382400280473618,
+      "grad_norm": 61990.4296875,
+      "learning_rate": 2.5631374466524584e-05,
+      "loss": 0.5751,
+      "step": 27500
+    },
+    {
+      "epoch": 0.44620802855731384,
+      "grad_norm": 35250.4375,
+      "learning_rate": 2.5551652112908113e-05,
+      "loss": 0.5761,
+      "step": 28000
+    },
+    {
+      "epoch": 0.45417602906726584,
+      "grad_norm": 40302.27734375,
+      "learning_rate": 2.547192975929164e-05,
+      "loss": 0.5723,
+      "step": 28500
+    },
+    {
+      "epoch": 0.4621440295772179,
+      "grad_norm": 40248.03515625,
+      "learning_rate": 2.539220740567517e-05,
+      "loss": 0.5754,
+      "step": 29000
+    },
+    {
+      "epoch": 0.47011203008716995,
+      "grad_norm": 38083.6484375,
+      "learning_rate": 2.5312485052058697e-05,
+      "loss": 0.5719,
+      "step": 29500
+    },
+    {
+      "epoch": 0.47808003059712195,
+      "grad_norm": 32291.21484375,
+      "learning_rate": 2.5232762698442226e-05,
+      "loss": 0.5726,
+      "step": 30000
+    },
+    {
+      "epoch": 0.486048031107074,
+      "grad_norm": 39065.84375,
+      "learning_rate": 2.5153040344825755e-05,
+      "loss": 0.5716,
+      "step": 30500
+    },
+    {
+      "epoch": 0.494016031617026,
+      "grad_norm": 46160.44921875,
+      "learning_rate": 2.507331799120928e-05,
+      "loss": 0.5723,
+      "step": 31000
+    },
+    {
+      "epoch": 0.5019840321269781,
+      "grad_norm": 36111.65625,
+      "learning_rate": 2.499359563759281e-05,
+      "loss": 0.569,
+      "step": 31500
+    },
+    {
+      "epoch": 0.5099520326369301,
+      "grad_norm": 33012.55859375,
+      "learning_rate": 2.4913873283976342e-05,
+      "loss": 0.5692,
+      "step": 32000
+    },
+    {
+      "epoch": 0.5179200331468822,
+      "grad_norm": 40300.83203125,
+      "learning_rate": 2.4834150930359868e-05,
+      "loss": 0.5686,
+      "step": 32500
+    },
+    {
+      "epoch": 0.5258880336568341,
+      "grad_norm": 38612.78515625,
+      "learning_rate": 2.4754428576743397e-05,
+      "loss": 0.5663,
+      "step": 33000
+    },
+    {
+      "epoch": 0.5338560341667862,
+      "grad_norm": 52813.0234375,
+      "learning_rate": 2.4674706223126922e-05,
+      "loss": 0.5662,
+      "step": 33500
+    },
+    {
+      "epoch": 0.5418240346767382,
+      "grad_norm": 36266.23046875,
+      "learning_rate": 2.459498386951045e-05,
+      "loss": 0.5635,
+      "step": 34000
+    },
+    {
+      "epoch": 0.5497920351866903,
+      "grad_norm": 38791.453125,
+      "learning_rate": 2.451526151589398e-05,
+      "loss": 0.5677,
+      "step": 34500
+    },
+    {
+      "epoch": 0.5577600356966422,
+      "grad_norm": 43926.4296875,
+      "learning_rate": 2.443553916227751e-05,
+      "loss": 0.5688,
+      "step": 35000
+    },
+    {
+      "epoch": 0.5657280362065943,
+      "grad_norm": 32247.173828125,
+      "learning_rate": 2.435581680866104e-05,
+      "loss": 0.5686,
+      "step": 35500
+    },
+    {
+      "epoch": 0.5736960367165463,
+      "grad_norm": 35230.44140625,
+      "learning_rate": 2.4276094455044564e-05,
+      "loss": 0.566,
+      "step": 36000
+    },
+    {
+      "epoch": 0.5816640372264984,
+      "grad_norm": 33197.58203125,
+      "learning_rate": 2.4196372101428093e-05,
+      "loss": 0.5629,
+      "step": 36500
+    },
+    {
+      "epoch": 0.5896320377364505,
+      "grad_norm": 41267.5390625,
+      "learning_rate": 2.4116649747811623e-05,
+      "loss": 0.5642,
+      "step": 37000
+    },
+    {
+      "epoch": 0.5976000382464024,
+      "grad_norm": 41852.71875,
+      "learning_rate": 2.4036927394195148e-05,
+      "loss": 0.5635,
+      "step": 37500
+    },
+    {
+      "epoch": 0.6055680387563545,
+      "grad_norm": 32820.1015625,
+      "learning_rate": 2.395720504057868e-05,
+      "loss": 0.5639,
+      "step": 38000
+    },
+    {
+      "epoch": 0.6135360392663065,
+      "grad_norm": 39303.70703125,
+      "learning_rate": 2.3877482686962206e-05,
+      "loss": 0.5605,
+      "step": 38500
+    },
+    {
+      "epoch": 0.6215040397762586,
+      "grad_norm": 53008.375,
+      "learning_rate": 2.3797760333345735e-05,
+      "loss": 0.562,
+      "step": 39000
+    },
+    {
+      "epoch": 0.6294720402862106,
+      "grad_norm": 41845.28515625,
+      "learning_rate": 2.3718037979729264e-05,
+      "loss": 0.5641,
+      "step": 39500
+    },
+    {
+      "epoch": 0.6374400407961626,
+      "grad_norm": 49620.7734375,
+      "learning_rate": 2.363831562611279e-05,
+      "loss": 0.5582,
+      "step": 40000
+    },
+    {
+      "epoch": 0.6454080413061146,
+      "grad_norm": 46115.32421875,
+      "learning_rate": 2.355859327249632e-05,
+      "loss": 0.5616,
+      "step": 40500
+    },
+    {
+      "epoch": 0.6533760418160667,
+      "grad_norm": 33357.73828125,
+      "learning_rate": 2.3478870918879848e-05,
+      "loss": 0.5633,
+      "step": 41000
+    },
+    {
+      "epoch": 0.6613440423260187,
+      "grad_norm": 48345.0859375,
+      "learning_rate": 2.3399148565263377e-05,
+      "loss": 0.5588,
+      "step": 41500
+    },
+    {
+      "epoch": 0.6693120428359708,
+      "grad_norm": 46256.62890625,
+      "learning_rate": 2.3319426211646906e-05,
+      "loss": 0.5584,
+      "step": 42000
+    },
+    {
+      "epoch": 0.6772800433459227,
+      "grad_norm": 34897.8828125,
+      "learning_rate": 2.3239703858030432e-05,
+      "loss": 0.5577,
+      "step": 42500
+    },
+    {
+      "epoch": 0.6852480438558748,
+      "grad_norm": 86223.203125,
+      "learning_rate": 2.315998150441396e-05,
+      "loss": 0.5549,
+      "step": 43000
+    },
+    {
+      "epoch": 0.6932160443658268,
+      "grad_norm": 32481.861328125,
+      "learning_rate": 2.308025915079749e-05,
+      "loss": 0.5623,
+      "step": 43500
+    },
+    {
+      "epoch": 0.7011840448757789,
+      "grad_norm": 33890.0859375,
+      "learning_rate": 2.300053679718102e-05,
+      "loss": 0.5618,
+      "step": 44000
+    },
+    {
+      "epoch": 0.709152045385731,
+      "grad_norm": 32936.66015625,
+      "learning_rate": 2.2920814443564548e-05,
+      "loss": 0.5613,
+      "step": 44500
+    },
+    {
+      "epoch": 0.7171200458956829,
+      "grad_norm": 36461.4453125,
+      "learning_rate": 2.2841092089948074e-05,
+      "loss": 0.5581,
+      "step": 45000
+    },
+    {
+      "epoch": 0.725088046405635,
+      "grad_norm": 35596.3046875,
+      "learning_rate": 2.2761369736331603e-05,
+      "loss": 0.5514,
+      "step": 45500
+    },
+    {
+      "epoch": 0.733056046915587,
+      "grad_norm": 46988.7890625,
+      "learning_rate": 2.2681647382715132e-05,
+      "loss": 0.5511,
+      "step": 46000
+    },
+    {
+      "epoch": 0.7410240474255391,
+      "grad_norm": 34446.23046875,
+      "learning_rate": 2.2601925029098658e-05,
+      "loss": 0.556,
+      "step": 46500
+    },
+    {
+      "epoch": 0.7489920479354911,
+      "grad_norm": 30729.033203125,
+      "learning_rate": 2.252220267548219e-05,
+      "loss": 0.5568,
+      "step": 47000
+    },
+    {
+      "epoch": 0.7569600484454431,
+      "grad_norm": 35997.25390625,
+      "learning_rate": 2.2442480321865716e-05,
+      "loss": 0.5538,
+      "step": 47500
+    },
+    {
+      "epoch": 0.7649280489553951,
+      "grad_norm": 36570.2578125,
+      "learning_rate": 2.2362757968249245e-05,
+      "loss": 0.5524,
+      "step": 48000
+    },
+    {
+      "epoch": 0.7728960494653472,
+      "grad_norm": 38073.46484375,
+      "learning_rate": 2.2283035614632774e-05,
+      "loss": 0.5564,
+      "step": 48500
+    },
+    {
+      "epoch": 0.7808640499752992,
+      "grad_norm": 32213.791015625,
+      "learning_rate": 2.22033132610163e-05,
+      "loss": 0.5531,
+      "step": 49000
+    },
+    {
+      "epoch": 0.7888320504852512,
+      "grad_norm": 51021.55078125,
+      "learning_rate": 2.212359090739983e-05,
+      "loss": 0.5551,
+      "step": 49500
+    },
+    {
+      "epoch": 0.7968000509952032,
+      "grad_norm": 34028.9609375,
+      "learning_rate": 2.2043868553783358e-05,
+      "loss": 0.5522,
+      "step": 50000
+    },
+    {
+      "epoch": 0.8047680515051553,
+      "grad_norm": 35102.0390625,
+      "learning_rate": 2.1964146200166887e-05,
+      "loss": 0.551,
+      "step": 50500
+    },
+    {
+      "epoch": 0.8127360520151073,
+      "grad_norm": 38054.03125,
+      "learning_rate": 2.1884423846550416e-05,
+      "loss": 0.5564,
+      "step": 51000
+    },
+    {
+      "epoch": 0.8207040525250594,
+      "grad_norm": 34621.86328125,
+      "learning_rate": 2.180470149293394e-05,
+      "loss": 0.5505,
+      "step": 51500
+    },
+    {
+      "epoch": 0.8286720530350113,
+      "grad_norm": 34099.5859375,
+      "learning_rate": 2.172497913931747e-05,
+      "loss": 0.5504,
+      "step": 52000
+    },
+    {
+      "epoch": 0.8366400535449634,
+      "grad_norm": 36866.79296875,
+      "learning_rate": 2.1645256785701e-05,
+      "loss": 0.5473,
+      "step": 52500
+    },
+    {
+      "epoch": 0.8446080540549155,
+      "grad_norm": 38420.94140625,
+      "learning_rate": 2.156553443208453e-05,
+      "loss": 0.547,
+      "step": 53000
+    },
+    {
+      "epoch": 0.8525760545648675,
+      "grad_norm": 35430.8984375,
+      "learning_rate": 2.1485812078468058e-05,
+      "loss": 0.5504,
+      "step": 53500
+    },
+    {
+      "epoch": 0.8605440550748196,
+      "grad_norm": 35433.71875,
+      "learning_rate": 2.1406089724851584e-05,
+      "loss": 0.5547,
+      "step": 54000
+    },
+    {
+      "epoch": 0.8685120555847715,
+      "grad_norm": 41701.05859375,
+      "learning_rate": 2.1326367371235113e-05,
+      "loss": 0.5517,
+      "step": 54500
+    },
+    {
+      "epoch": 0.8764800560947236,
+      "grad_norm": 34275.7265625,
+      "learning_rate": 2.124664501761864e-05,
+      "loss": 0.5496,
+      "step": 55000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 188253,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1496849408e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e7fcb26e3e3848d243625e49f36d2273fbe5c83ece34d46111c33604627a5b
+size 5368

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da95de961c5fb3d0a3f1731fe1c2359a0c7bf25b33787bc95384f23fe090c360
+size 11353

logs/events.out.tfevents.1707026588.d77ab3a64c5c.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2bcf27210ecac6445b4fe91ea33ce8d1ef0fe1e674dface52bc3202cc443cf
+size 25286

logs/events.out.tfevents.1707056479.6b8ef76803b7.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a955400898c05287b5b58720427850d09aa1706c6a220d4c70d8cc3f13652102
+size 5081

logs/events.out.tfevents.1707102026.2f58af33d3db.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347dd1c2c3debc6a8720f970d8c810dd55f20054ed1295e0429bba74aea735c9
+size 5154

logs/events.out.tfevents.1707149028.4c55bcba7827.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de511e2aff8aec50f56506a4d453b836ad0c2e858090c2a7f49c427fc8db70de
+size 5154

logs/events.out.tfevents.1707188120.9f8b04a8a12f.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78095757d924d052f6a0cabf736b3f929c822728ce9e7dcffc693d93e41a7a7e
+size 5154

logs/events.out.tfevents.1707241207.9e0a4dd4b052.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27617536009dd3c4482fd830ce731581dea0c8c34026aa83f068c40e235dee85
+size 5154

logs/events.out.tfevents.1707840721.3d7c2fb775b8.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26657b4265609dbd747f23010ec98e121811337d0c8f206ba2295767266b7c14
+size 5142

logs/events.out.tfevents.1707910972.44fe15909855.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84635da10e4293ca98e4ab09219c605aff6a9e2063436d7c931fb11bd501e73d
+size 5142

logs/events.out.tfevents.1708010990.ecce5c21fb5d.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc65cb7013b8f2509e3def68792a819e824f8fd3fa9e417ec5982b1afb8a503f
+size 5154

logs/events.out.tfevents.1708053939.b8db41594979.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec921edbc45bb131a96af962a7f4000785f6eade03411f7facd811fb3e4d3bd
+size 5154

logs/events.out.tfevents.1708177060.d7a757208556.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dd7768d90060fd258e03f09c5cb49f5458593c5c9fb6cb986f98f9614b4f71
+size 5154

logs/events.out.tfevents.1708491210.a9eab0e53fc5.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57b35d1df50f788c981d90d40c4f5f8c18d2c72e1ff6ddbf92466411f5bae8f
+size 5154

logs/events.out.tfevents.1708534313.ef069b1332b9.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec13d99b79a44c4a0f2c21aeec46b3361a26e8f77ebe1b4f68bc8fa672281dfc
+size 5142

logs/events.out.tfevents.1708590633.624f01aff40e.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7981afeb9a7c96521b6f80565900669f7e5913c5b5b95ba5ef7d1f2116f80e59
+size 5142

logs/events.out.tfevents.1708869176.4df77956e39f.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723923dc88275cf797b3f9935b358330cd419cbfe97ccce20ca661ac1bd9fd7e
+size 5142

logs/events.out.tfevents.1708915015.2b77ed4580e3.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632879f94a9617b4774956b467f692fd563b1312e0424fdc77165c739dbf3158
+size 5142

logs/events.out.tfevents.1709140136.1603750d14c2.25.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739a6fc016aab02b7ce054e6e14a8c9a4bff35d40bed122d2e04dca553a4e4a2
+size 5154

logs/events.out.tfevents.1709182326.6f3e8825b9ca.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55546c8438f3abe1f326db166051de9ea92100eb39a408f3d23d12308b93982e
+size 5154

logs/events.out.tfevents.1709538402.34d8bbd0f97b.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2e2ab14339aa47825765627f5db692d6145b68ab9a117b6da268fe73d3666d
+size 5142

logs/events.out.tfevents.1750416459.84e4459dd5a2.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb993ae6193faa55e2f015730eb53f8965f772dcb73c6e8d12da00dbb33a0adb
+size 8566

logs/events.out.tfevents.1750417505.2cc91c265062.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf3cc064fb09acf40a630cecc6d594e3b5f3ac925b81485ab2e4553a2972f3d
+size 5728

logs/events.out.tfevents.1750417806.062e6a0e95bd.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8513af429315a463a6608a71ff04870f4d60144db6d139be5adb1cca64d81be3
+size 31743

logs/events.out.tfevents.1750780646.1e72a290e888.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae418bdfaf505ce47938674537dd3c25e6de7e4056595d73809edacaa0c1439
+size 18972

logs/events.out.tfevents.1750780683.9c68381af981.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11630ce9819438a76859567230a0a7560f20acd371d269c582e5d04723f5ac0
+size 22283

logs/events.out.tfevents.1750824635.cb560905bf5f.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba16ef1de147cd1aba034ed860027f464b2069e2aab00f268fe509181d818c1
+size 35527

logs/events.out.tfevents.1750835340.cdcfd3173f55.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674c7b15319bcc941ba9a7433a5590e72cd408db8f47dd76b3606ede6cae0fa7
+size 35527

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31374e11cab95da4335286559400d4ef35bb288afc215f0d0021f27efc3e85cc
+size 497814144

models--simonneupane--controlled-food-recipe-generation/blobs/1f8d761317686b0681739c9d758712101d6b09f4

@@ -0,0 +1,38 @@
+{
+  "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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50270
+}