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-de",
+  "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 sha256:41b955eb73a50769838355f94b86c453a727e9fb762c254b2ecf350888819869
+size 1114399802

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da462add580b9c8d92c46b6b13bf8df317e0ba8e80febc108d1b5ba05b8c96a4
+size 557202652

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911833b2519a88004e219c69c68a9eba78315e4be1c627434fae31d3a84a8ec5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59017f169c4590b3158649ca54aef88bb1e63c790107132aaaebef5ab22acfb0
+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-de",
+  "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": 1.0013060569763184,
+  "best_model_checkpoint": "bygpt5_quatags_con/base/de/checkpoint-126928",
+  "epoch": 8.0,
+  "global_step": 126928,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.948822752188864e-05,
+      "loss": 1.2085,
+      "step": 15866
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0804483890533447,
+      "eval_runtime": 375.4034,
+      "eval_samples_per_second": 75.133,
+      "eval_steps_per_second": 9.393,
+      "step": 15866
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.7044371705883534e-05,
+      "loss": 1.0806,
+      "step": 31732
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0416626930236816,
+      "eval_runtime": 375.8397,
+      "eval_samples_per_second": 75.045,
+      "eval_steps_per_second": 9.382,
+      "step": 31732
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.2828209599601426e-05,
+      "loss": 1.0431,
+      "step": 47598
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0254769325256348,
+      "eval_runtime": 375.5399,
+      "eval_samples_per_second": 75.105,
+      "eval_steps_per_second": 9.389,
+      "step": 47598
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.7278145783201285e-05,
+      "loss": 1.0179,
+      "step": 63464
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0140334367752075,
+      "eval_runtime": 374.8271,
+      "eval_samples_per_second": 75.248,
+      "eval_steps_per_second": 9.407,
+      "step": 63464
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.0971286481716286e-05,
+      "loss": 0.9988,
+      "step": 79330
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0083739757537842,
+      "eval_runtime": 374.1706,
+      "eval_samples_per_second": 75.38,
+      "eval_steps_per_second": 9.424,
+      "step": 79330
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.4563430958668448e-05,
+      "loss": 0.984,
+      "step": 95196
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.0033071041107178,
+      "eval_runtime": 373.5069,
+      "eval_samples_per_second": 75.514,
+      "eval_steps_per_second": 9.44,
+      "step": 95196
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 8.720880257396538e-06,
+      "loss": 0.9729,
+      "step": 111062
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.0022804737091064,
+      "eval_runtime": 373.5585,
+      "eval_samples_per_second": 75.504,
+      "eval_steps_per_second": 9.439,
+      "step": 111062
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.05115394728147e-06,
+      "loss": 0.9651,
+      "step": 126928
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0013060569763184,
+      "eval_runtime": 373.9662,
+      "eval_samples_per_second": 75.421,
+      "eval_steps_per_second": 9.429,
+      "step": 126928
+    }
+  ],
+  "max_steps": 158660,
+  "num_train_epochs": 10,
+  "total_flos": 3.61085560823808e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c701d8d37026c0b6aa0ae80670837138a8011e87ab3b034d41a1e8870bb7c2d
+size 3768