Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,27 @@
+{
+  "</quatrain>": 386,
+  "<alexandrine>": 408,
+  "<amphibrach>": 407,
+  "<anapaest>": 404,
+  "<dactyl>": 405,
+  "<iambus>": 402,
+  "<other>": 406,
+  "<quatrain>": 385,
+  "<trochee>": 403,
+  "[AAAA]": 400,
+  "[AAAB]": 398,
+  "[AABA]": 396,
+  "[AABB]": 397,
+  "[AABC]": 388,
+  "[ABAA]": 401,
+  "[ABAB]": 392,
+  "[ABAC]": 389,
+  "[ABBA]": 391,
+  "[ABBB]": 395,
+  "[ABBC]": 394,
+  "[ABCA]": 399,
+  "[ABCB]": 393,
+  "[ABCC]": 390,
+  "[ABCD]": 387,
+  "[PAD]": 384
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "nllg/bygpt5-base-en",
+  "architectures": [
+    "ByGPT5LMHeadModel"
+  ],
+  "d_ff": 3968,
+  "d_kv": 64,
+  "d_model": 1536,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_decoder": true,
+  "is_encoder_decoder": false,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "bygpt5",
+  "num_decoder_layers": 6,
+  "num_heads": 12,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "use_cache": true,
+  "vocab_size": 409
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fee1a0393b1668c2277023a3470c48160b7fc6e1a39a4048d94f639f8a90f1
+size 1114399802

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c761c9979c3e1f8a61b9fcbc3527815e5ade14117cafbdea5b8eae9590cd28d
+size 557202652

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde537eca4e28a5012d8a5479ed7849781b43eca2a7c2edd78948fbc589c3e9f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c57136c72db7ad1e70b3e9242e71ce00988a2625cef6c8e0f1f776a2962d94
+size 1064

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "[ABCD]",
+    "[AABC]",
+    "[ABAC]",
+    "[ABCC]",
+    "[ABBA]",
+    "[ABAB]",
+    "[ABCB]",
+    "[ABBC]",
+    "[ABBB]",
+    "[AABA]",
+    "[AABB]",
+    "[AAAB]",
+    "[ABCA]",
+    "[AAAA]",
+    "[ABAA]",
+    "<iambus>",
+    "<trochee>",
+    "<anapaest>",
+    "<dactyl>",
+    "<other>",
+    "<amphibrach>",
+    "<alexandrine>"
+  ],
+  "bos_token": "<quatrain>",
+  "eos_token": "</quatrain>",
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,160 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>",
+    "<extra_id_100>",
+    "<extra_id_101>",
+    "<extra_id_102>",
+    "<extra_id_103>",
+    "<extra_id_104>",
+    "<extra_id_105>",
+    "<extra_id_106>",
+    "<extra_id_107>",
+    "<extra_id_108>",
+    "<extra_id_109>",
+    "<extra_id_110>",
+    "<extra_id_111>",
+    "<extra_id_112>",
+    "<extra_id_113>",
+    "<extra_id_114>",
+    "<extra_id_115>",
+    "<extra_id_116>",
+    "<extra_id_117>",
+    "<extra_id_118>",
+    "<extra_id_119>",
+    "<extra_id_120>",
+    "<extra_id_121>",
+    "<extra_id_122>",
+    "<extra_id_123>",
+    "<extra_id_124>"
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "extra_ids": 125,
+  "name_or_path": "nllg/bygpt5-base-en",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "/home/jbelouadi/.cache/huggingface/transformers/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109",
+  "tokenizer_class": "ByGPT5Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": 1.0824099779129028,
+  "best_model_checkpoint": "bygpt5_quatags_con/base/en/checkpoint-90840",
+  "epoch": 8.0,
+  "global_step": 90840,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.948826997701317e-05,
+      "loss": 1.2611,
+      "step": 11355
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1518595218658447,
+      "eval_runtime": 242.6001,
+      "eval_samples_per_second": 83.207,
+      "eval_steps_per_second": 10.404,
+      "step": 11355
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.704445954688097e-05,
+      "loss": 1.1532,
+      "step": 22710
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1212660074234009,
+      "eval_runtime": 241.8691,
+      "eval_samples_per_second": 83.458,
+      "eval_steps_per_second": 10.435,
+      "step": 22710
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.282832230852865e-05,
+      "loss": 1.1187,
+      "step": 34065
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1034783124923706,
+      "eval_runtime": 243.698,
+      "eval_samples_per_second": 82.832,
+      "eval_steps_per_second": 10.357,
+      "step": 34065
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.7278263072276784e-05,
+      "loss": 1.0945,
+      "step": 45420
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0929205417633057,
+      "eval_runtime": 242.4754,
+      "eval_samples_per_second": 83.25,
+      "eval_steps_per_second": 10.409,
+      "step": 45420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.0971391293814688e-05,
+      "loss": 1.0758,
+      "step": 56775
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.086612343788147,
+      "eval_runtime": 243.5145,
+      "eval_samples_per_second": 82.894,
+      "eval_steps_per_second": 10.365,
+      "step": 56775
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.4563511746431305e-05,
+      "loss": 1.0611,
+      "step": 68130
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.084080696105957,
+      "eval_runtime": 242.803,
+      "eval_samples_per_second": 83.137,
+      "eval_steps_per_second": 10.395,
+      "step": 68130
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 8.72093225141226e-06,
+      "loss": 1.0501,
+      "step": 79485
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.082816243171692,
+      "eval_runtime": 242.3815,
+      "eval_samples_per_second": 83.282,
+      "eval_steps_per_second": 10.413,
+      "step": 79485
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.051179274451455e-06,
+      "loss": 1.0422,
+      "step": 90840
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0824099779129028,
+      "eval_runtime": 242.3799,
+      "eval_samples_per_second": 83.282,
+      "eval_steps_per_second": 10.413,
+      "step": 90840
+    }
+  ],
+  "max_steps": 113550,
+  "num_train_epochs": 10,
+  "total_flos": 2.506903706824704e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8a6409635e84bd31cb6440581e5a20386383d663b338041d9c643387291b98
+size 3768