Upload 22 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+generated_predictions.txt filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,17 @@
+{
+    "eval_loss": 2.7799501419067383,
+    "eval_sacrebleu": 8.1449,
+    "eval_gen_len": 47.0545,
+    "eval_runtime": 1481.1488,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 0.769,
+    "epoch": 8.0,
+    "eval_samples": 2277,
+    "predict_loss": 2.773041248321533,
+    "predict_sacrebleu": 8.4276,
+    "predict_gen_len": 47.2727,
+    "predict_runtime": 154422.7036,
+    "predict_samples_per_second": 1.518,
+    "predict_steps_per_second": 0.759,
+    "predict_samples": 234392
+}

checkpoint-236688/config.json

@@ -0,0 +1,29 @@
+{
+  "_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,
+  "model_type": "t5",
+  "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": "4.11.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

checkpoint-236688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090882263d999594bab27f09c78c107c5d07fc6362a9b6838b92c6c42e74553f
+size 1980458179

checkpoint-236688/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9bcd2521c9e6080d5f97c0fa99c5ef00c22273b7bc74c87161e8237c829558
+size 990273369

checkpoint-236688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02471ae2a5bf632e5b42fde6317e60023d59cb6b345b90b8fa6fa3d7390f7ac9
+size 14657

checkpoint-236688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c54b41671c92a8abfbe0513c59f51e87fe5f9020cfec985e4e7ffd21e4e89c
+size 623

checkpoint-236688/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>"]}

checkpoint-236688/spiece.model

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

checkpoint-236688/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>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/rifat/.cache/huggingface/transformers/ff0ed476d41a6f336fa52bd906c6c8f0a8684fe67bec634b201ed2d24331c915.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "tokenizer_file": null, "name_or_path": "csebuetnlp/banglat5", "tokenizer_class": "T5Tokenizer"}

checkpoint-236688/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.5348,
+  "best_model_checkpoint": "outputs/checkpoint-29586",
+  "epoch": 8.0,
+  "global_step": 236688,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004469415766030179,
+      "loss": 3.6106,
+      "step": 29586
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 15.296,
+      "eval_loss": 2.7799501419067383,
+      "eval_runtime": 368.7401,
+      "eval_sacrebleu": 0.5348,
+      "eval_samples_per_second": 6.175,
+      "eval_steps_per_second": 3.089,
+      "step": 29586
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00038309277994544387,
+      "loss": 2.7653,
+      "step": 59172
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 14.7356,
+      "eval_loss": 2.742591619491577,
+      "eval_runtime": 368.9941,
+      "eval_sacrebleu": 0.4271,
+      "eval_samples_per_second": 6.171,
+      "eval_steps_per_second": 3.087,
+      "step": 59172
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0003192439832878699,
+      "loss": 2.7302,
+      "step": 88758
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 14.7444,
+      "eval_loss": 2.7364578247070312,
+      "eval_runtime": 357.3278,
+      "eval_sacrebleu": 0.4211,
+      "eval_samples_per_second": 6.372,
+      "eval_steps_per_second": 3.188,
+      "step": 88758
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002553951866302959,
+      "loss": 2.705,
+      "step": 118344
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 14.8669,
+      "eval_loss": 2.7070209980010986,
+      "eval_runtime": 365.3611,
+      "eval_sacrebleu": 0.4635,
+      "eval_samples_per_second": 6.232,
+      "eval_steps_per_second": 3.117,
+      "step": 118344
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00019154638997272193,
+      "loss": 2.6613,
+      "step": 147930
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 13.9183,
+      "eval_loss": 2.6642842292785645,
+      "eval_runtime": 363.1965,
+      "eval_sacrebleu": 0.3438,
+      "eval_samples_per_second": 6.269,
+      "eval_steps_per_second": 3.136,
+      "step": 147930
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00012769759331514796,
+      "loss": 2.6045,
+      "step": 177516
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 14.9087,
+      "eval_loss": 2.614426374435425,
+      "eval_runtime": 359.5255,
+      "eval_sacrebleu": 0.4651,
+      "eval_samples_per_second": 6.333,
+      "eval_steps_per_second": 3.168,
+      "step": 177516
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.384879665757398e-05,
+      "loss": 2.5271,
+      "step": 207102
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 14.6271,
+      "eval_loss": 2.5494837760925293,
+      "eval_runtime": 358.1093,
+      "eval_sacrebleu": 0.468,
+      "eval_samples_per_second": 6.358,
+      "eval_steps_per_second": 3.181,
+      "step": 207102
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0,
+      "loss": 2.4325,
+      "step": 236688
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 14.7071,
+      "eval_loss": 2.4964401721954346,
+      "eval_runtime": 362.2324,
+      "eval_sacrebleu": 0.484,
+      "eval_samples_per_second": 6.286,
+      "eval_steps_per_second": 3.144,
+      "step": 236688
+    }
+  ],
+  "max_steps": 236688,
+  "num_train_epochs": 8,
+  "total_flos": 3.211579566884874e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-236688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63fd50675c2ea4c0750ddab1d9445c41255e3a9d8b20cb8ac31eb23d682f50a
+size 2735

config.json

@@ -0,0 +1,29 @@
+{
+  "_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,
+  "model_type": "t5",
+  "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": "4.11.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_gen_len": 47.0545,
+    "eval_loss": 2.7799501419067383,
+    "eval_runtime": 1481.1488,
+    "eval_sacrebleu": 8.1449,
+    "eval_samples": 2277,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 0.769
+}

generated_predictions.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac2ba5767d25920a264dbdbfeca03065bffa054175091133e13083680344073
+size 124518156

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_gen_len": 47.2727,
+    "predict_loss": 2.773041248321533,
+    "predict_runtime": 154422.7036,
+    "predict_sacrebleu": 8.4276,
+    "predict_samples": 234392,
+    "predict_samples_per_second": 1.518,
+    "predict_steps_per_second": 0.759
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247b9355f1787c3c32aea79d28cdb11c0bab1ed556b2a3201025deffed2d6872
+size 990273369

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>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/rifat/.cache/huggingface/transformers/ff0ed476d41a6f336fa52bd906c6c8f0a8684fe67bec634b201ed2d24331c915.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "tokenizer_file": null, "name_or_path": "csebuetnlp/banglat5", "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 2.7545470263067835,
+    "train_runtime": 376582.9978,
+    "train_samples": 946752,
+    "train_samples_per_second": 20.112,
+    "train_steps_per_second": 0.629
+}

trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 0.5348,
+  "best_model_checkpoint": "outputs/checkpoint-29586",
+  "epoch": 8.0,
+  "global_step": 236688,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004469415766030179,
+      "loss": 3.6106,
+      "step": 29586
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 15.296,
+      "eval_loss": 2.7799501419067383,
+      "eval_runtime": 368.7401,
+      "eval_sacrebleu": 0.5348,
+      "eval_samples_per_second": 6.175,
+      "eval_steps_per_second": 3.089,
+      "step": 29586
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00038309277994544387,
+      "loss": 2.7653,
+      "step": 59172
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 14.7356,
+      "eval_loss": 2.742591619491577,
+      "eval_runtime": 368.9941,
+      "eval_sacrebleu": 0.4271,
+      "eval_samples_per_second": 6.171,
+      "eval_steps_per_second": 3.087,
+      "step": 59172
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0003192439832878699,
+      "loss": 2.7302,
+      "step": 88758
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 14.7444,
+      "eval_loss": 2.7364578247070312,
+      "eval_runtime": 357.3278,
+      "eval_sacrebleu": 0.4211,
+      "eval_samples_per_second": 6.372,
+      "eval_steps_per_second": 3.188,
+      "step": 88758
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002553951866302959,
+      "loss": 2.705,
+      "step": 118344
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 14.8669,
+      "eval_loss": 2.7070209980010986,
+      "eval_runtime": 365.3611,
+      "eval_sacrebleu": 0.4635,
+      "eval_samples_per_second": 6.232,
+      "eval_steps_per_second": 3.117,
+      "step": 118344
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00019154638997272193,
+      "loss": 2.6613,
+      "step": 147930
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 13.9183,
+      "eval_loss": 2.6642842292785645,
+      "eval_runtime": 363.1965,
+      "eval_sacrebleu": 0.3438,
+      "eval_samples_per_second": 6.269,
+      "eval_steps_per_second": 3.136,
+      "step": 147930
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00012769759331514796,
+      "loss": 2.6045,
+      "step": 177516
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 14.9087,
+      "eval_loss": 2.614426374435425,
+      "eval_runtime": 359.5255,
+      "eval_sacrebleu": 0.4651,
+      "eval_samples_per_second": 6.333,
+      "eval_steps_per_second": 3.168,
+      "step": 177516
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.384879665757398e-05,
+      "loss": 2.5271,
+      "step": 207102
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 14.6271,
+      "eval_loss": 2.5494837760925293,
+      "eval_runtime": 358.1093,
+      "eval_sacrebleu": 0.468,
+      "eval_samples_per_second": 6.358,
+      "eval_steps_per_second": 3.181,
+      "step": 207102
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0,
+      "loss": 2.4325,
+      "step": 236688
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 14.7071,
+      "eval_loss": 2.4964401721954346,
+      "eval_runtime": 362.2324,
+      "eval_sacrebleu": 0.484,
+      "eval_samples_per_second": 6.286,
+      "eval_steps_per_second": 3.144,
+      "step": 236688
+    },
+    {
+      "epoch": 8.0,
+      "step": 236688,
+      "total_flos": 3.211579566884874e+18,
+      "train_loss": 2.7545470263067835,
+      "train_runtime": 376582.9978,
+      "train_samples_per_second": 20.112,
+      "train_steps_per_second": 0.629
+    }
+  ],
+  "max_steps": 236688,
+  "num_train_epochs": 8,
+  "total_flos": 3.211579566884874e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63fd50675c2ea4c0750ddab1d9445c41255e3a9d8b20cb8ac31eb23d682f50a
+size 2735