Upload 10 files

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.999259442113058,
+    "train_n_objs": -1,
+    "train_runtime": 14680.3381,
+    "train_samples_per_second": 0.172,
+    "val_gen_len": 17.7,
+    "val_loss": 3.5691,
+    "val_n_objs": -1,
+    "val_rouge1": 20.6577,
+    "val_rouge2": 8.3409,
+    "val_rougeL": 18.2211,
+    "val_rougeLsum": 18.2354,
+    "val_runtime": 317.0503,
+    "val_samples_per_second": 3.192
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "csebuetnlp/banglat5",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "t5",
+  "num_beams": 4,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b16a9ad940dbb0c17d76d736eaa6c06a34544c1c3207852b4040dd6e2709952
+size 2387071

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f85cce38f2212db83165ca4e72584f6e674895bb2e11eda35ec8814a2dd30fcf
+size 990445401

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960ce06ba97f6c687221308534486715a034d4434506c66425afd34539e68c7b
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
+size 1111492

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "model_max_length": 512, "special_tokens_map_file": "/home/rifat/.cache/huggingface/transformers/ff0ed476d41a6f336fa52bd906c6c8f0a8684fe67bec634b201ed2d24331c915.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "tokenizer_file": null, "name_or_path": "csebuetnlp/banglat5"}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.880770180202418,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003949642063687978,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 25.19717788696289,
+      "step": 1
+    },
+    {
+      "epoch": 0.9992594421130585,
+      "eval_gen_len": 16.6,
+      "eval_loss": 13.611336708068848,
+      "eval_rouge1": 9.8775,
+      "eval_rouge2": 2.958,
+      "eval_rougeL": 8.7847,
+      "eval_rougeLsum": 8.871,
+      "eval_runtime": 220.704,
+      "eval_samples_per_second": 4.585,
+      "step": 253
+    },
+    {
+      "epoch": 1.9755615897309307,
+      "learning_rate": 4.176954732510288e-05,
+      "loss": 13.314938470691382,
+      "step": 500
+    },
+    {
+      "epoch": 1.9992594421130585,
+      "eval_gen_len": 13.0,
+      "eval_loss": 7.852785110473633,
+      "eval_rouge1": 10.5151,
+      "eval_rouge2": 3.2488,
+      "eval_rougeL": 9.5196,
+      "eval_rougeLsum": 9.5659,
+      "eval_runtime": 203.1626,
+      "eval_samples_per_second": 4.981,
+      "step": 506
+    },
+    {
+      "epoch": 2.9992594421130585,
+      "eval_gen_len": 5.3,
+      "eval_loss": 5.0542707443237305,
+      "eval_rouge1": 3.3057,
+      "eval_rouge2": 1.0908,
+      "eval_rougeL": 2.9248,
+      "eval_rougeLsum": 2.906,
+      "eval_runtime": 191.681,
+      "eval_samples_per_second": 5.28,
+      "step": 759
+    },
+    {
+      "epoch": 3.951863737348803,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 6.2216669921875,
+      "step": 1000
+    },
+    {
+      "epoch": 3.9992594421130585,
+      "eval_gen_len": 14.8,
+      "eval_loss": 4.541400909423828,
+      "eval_rouge1": 15.0004,
+      "eval_rouge2": 5.7011,
+      "eval_rougeL": 13.2283,
+      "eval_rougeLsum": 13.2086,
+      "eval_runtime": 197.5356,
+      "eval_samples_per_second": 5.123,
+      "step": 1012
+    },
+    {
+      "epoch": 4.9992594421130585,
+      "eval_gen_len": 16.3,
+      "eval_loss": 4.135443687438965,
+      "eval_rouge1": 17.3311,
+      "eval_rouge2": 6.3922,
+      "eval_rougeL": 15.3676,
+      "eval_rougeLsum": 15.3563,
+      "eval_runtime": 200.4736,
+      "eval_samples_per_second": 5.048,
+      "step": 1265
+    },
+    {
+      "epoch": 5.928165884966675,
+      "learning_rate": 2.1193415637860082e-05,
+      "loss": 4.99077294921875,
+      "step": 1500
+    },
+    {
+      "epoch": 5.9992594421130585,
+      "eval_gen_len": 17.1,
+      "eval_loss": 3.8587934970855713,
+      "eval_rouge1": 18.2338,
+      "eval_rouge2": 6.8747,
+      "eval_rougeL": 16.1719,
+      "eval_rougeLsum": 16.1563,
+      "eval_runtime": 201.2411,
+      "eval_samples_per_second": 5.029,
+      "step": 1518
+    },
+    {
+      "epoch": 6.9992594421130585,
+      "eval_gen_len": 17.4,
+      "eval_loss": 3.6997532844543457,
+      "eval_rouge1": 19.4383,
+      "eval_rouge2": 7.6786,
+      "eval_rougeL": 17.1778,
+      "eval_rougeLsum": 17.1963,
+      "eval_runtime": 200.0236,
+      "eval_samples_per_second": 5.059,
+      "step": 1771
+    },
+    {
+      "epoch": 7.904468032584547,
+      "learning_rate": 1.0905349794238684e-05,
+      "loss": 4.552568359375,
+      "step": 2000
+    },
+    {
+      "epoch": 7.9992594421130585,
+      "eval_gen_len": 17.6,
+      "eval_loss": 3.6233103275299072,
+      "eval_rouge1": 20.0385,
+      "eval_rouge2": 7.9683,
+      "eval_rougeL": 17.6542,
+      "eval_rougeLsum": 17.6752,
+      "eval_runtime": 201.3719,
+      "eval_samples_per_second": 5.026,
+      "step": 2024
+    },
+    {
+      "epoch": 8.999259442113058,
+      "eval_gen_len": 17.7,
+      "eval_loss": 3.5823326110839844,
+      "eval_rouge1": 20.504,
+      "eval_rouge2": 8.2176,
+      "eval_rougeL": 18.0877,
+      "eval_rougeLsum": 18.082,
+      "eval_runtime": 199.3661,
+      "eval_samples_per_second": 5.076,
+      "step": 2277
+    },
+    {
+      "epoch": 9.880770180202418,
+      "learning_rate": 6.17283950617284e-07,
+      "loss": 4.4207666015625,
+      "step": 2500
+    }
+  ],
+  "max_steps": 2530,
+  "num_train_epochs": 10,
+  "total_flos": 63945902037307392,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd43c94f0073cd8c30718ef3c146747ce8a884526f9d26e50cf090be900481a1
+size 2095