Model save

last-checkpoint/added_tokens.json

@@ -1,16 +0,0 @@
-{
-  "<INGR_END>": 50264,
-  "<INGR_START>": 50262,
-  "<INPUT_END>": 50268,
-  "<INPUT_START>": 50267,
-  "<INSTR_END>": 50261,
-  "<INSTR_START>": 50259,
-  "<NEXT_INGR>": 50263,
-  "<NEXT_INPUT>": 50269,
-  "<NEXT_INSTR>": 50260,
-  "<RECIPE_END>": 50266,
-  "<RECIPE_START>": 50265,
-  "<TITLE_END>": 50258,
-  "<TITLE_START>": 50257,
-  "[PAD]": 50270
-}

last-checkpoint/config.json

@@ -1,39 +0,0 @@
-{
-  "_name_or_path": "gpt2",
-  "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": "4.25.1",
-  "use_cache": true,
-  "vocab_size": 50271
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:adb5bf4ad301083d7056c3342aa6355ba10c67f1a489430c1dfe8b222b3ad110
-size 995691205

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f9d0fef853655f36a46edf17d7072ed1ec12ca5a03f1708f8878d39625ff3f22
-size 510441021

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7ce6048f0ccd628e6039c296d311a3909e9686636b73b5e7d15653969b00d162
-size 14575

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63e0fc7286366870137cf1410b315d98773c81e4579384816fe036707f4642f5
-size 557

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8a8a62866478c29307a99c7d85ab43da4c465b895ec1d05c20c8d22df2fb2fa2
-size 627

last-checkpoint/special_tokens_map.json

@@ -1,21 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<TITLE_START>",
-    "<TITLE_END>",
-    "<INSTR_START>",
-    "<NEXT_INSTR>",
-    "<INSTR_END>",
-    "<INGR_START>",
-    "<NEXT_INGR>",
-    "<INGR_END>",
-    "<RECIPE_START>",
-    "<RECIPE_END>",
-    "<INPUT_START>",
-    "<INPUT_END>",
-    "<NEXT_INPUT>"
-  ],
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "[PAD]",
-  "unk_token": "<|endoftext|>"
-}

last-checkpoint/tokenizer_config.json

@@ -1,34 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 1024,
-  "name_or_path": "mbien/recipenlg",
-  "pad_token": null,
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--mbien--recipenlg/snapshots/b690df9e40f6bf58c7cf8d96e1a91e101134167b/special_tokens_map.json",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

last-checkpoint/trainer_state.json

@@ -1,40 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.007910328515943267,
-  "global_step": 2000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0,
-      "learning_rate": 4.994181305762486e-05,
-      "loss": 6.9984,
-      "step": 500
-    },
-    {
-      "epoch": 0.0,
-      "learning_rate": 4.984285567263314e-05,
-      "loss": 2.1323,
-      "step": 1000
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 4.974389828764141e-05,
-      "loss": 2.057,
-      "step": 1500
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 4.9644940902649685e-05,
-      "loss": 2.0162,
-      "step": 2000
-    }
-  ],
-  "max_steps": 252834,
-  "num_train_epochs": 1,
-  "total_flos": 3560981713920000.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94b449301e8cb309a196c4db9621e76c288e3d1a370651e3066e055684c85ada
-size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d0fef853655f36a46edf17d7072ed1ec12ca5a03f1708f8878d39625ff3f22
+oid sha256:1bc52b054bfbf5a19da7f55649703c44877eae1ea3500ac519cba05cb730207c
 size 510441021