initial commit

all_results.json

@@ -0,0 +1,34 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 19.915,
+    "eval_gen_len": 30.3861,
+    "eval_loss": 0.966217577457428,
+    "eval_mem_cpu_alloc_delta": 11444096,
+    "eval_mem_cpu_peaked_delta": 8708480,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 2886867968,
+    "eval_runtime": 295.2332,
+    "eval_samples": 2753,
+    "eval_samples_per_second": 9.325,
+    "init_mem_cpu_alloc_delta": 2594509,
+    "init_mem_cpu_peaked_delta": 18258,
+    "init_mem_gpu_alloc_delta": 891614208,
+    "init_mem_gpu_peaked_delta": 0,
+    "test_bleu": 37.7751,
+    "test_gen_len": 30.2921,
+    "test_loss": 1.4876766204833984,
+    "test_mem_cpu_alloc_delta": 9661817,
+    "test_mem_cpu_peaked_delta": 7654041,
+    "test_mem_gpu_alloc_delta": 0,
+    "test_mem_gpu_peaked_delta": 2771026944,
+    "test_runtime": 220.938,
+    "test_samples": 2345,
+    "test_samples_per_second": 10.614,
+    "train_mem_cpu_alloc_delta": 708883,
+    "train_mem_cpu_peaked_delta": 101010629,
+    "train_mem_gpu_alloc_delta": 2696306176,
+    "train_mem_gpu_peaked_delta": 5983077888,
+    "train_runtime": 3574.4512,
+    "train_samples": 28883,
+    "train_samples_per_second": 5.053
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 19.915,
+    "eval_gen_len": 30.3861,
+    "eval_loss": 0.966217577457428,
+    "eval_mem_cpu_alloc_delta": 11444096,
+    "eval_mem_cpu_peaked_delta": 8708480,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 2886867968,
+    "eval_runtime": 295.2332,
+    "eval_samples": 2753,
+    "eval_samples_per_second": 9.325
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452bd43b476c36a66947c618890244bf8c996ca6288cc191e662031db072055d
+size 891737400

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:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

test_results.json

@@ -0,0 +1,12 @@
+{
+    "test_bleu": 37.7751,
+    "test_gen_len": 30.2921,
+    "test_loss": 1.4876766204833984,
+    "test_mem_cpu_alloc_delta": 9661817,
+    "test_mem_cpu_peaked_delta": 7654041,
+    "test_mem_gpu_alloc_delta": 0,
+    "test_mem_gpu_peaked_delta": 2771026944,
+    "test_runtime": 220.938,
+    "test_samples": 2345,
+    "test_samples_per_second": 10.614
+}

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": null, "name_or_path": "t5-base"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "init_mem_cpu_alloc_delta": 2594509,
+    "init_mem_cpu_peaked_delta": 18258,
+    "init_mem_gpu_alloc_delta": 891614208,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 708883,
+    "train_mem_cpu_peaked_delta": 101010629,
+    "train_mem_gpu_alloc_delta": 2696306176,
+    "train_mem_gpu_peaked_delta": 5983077888,
+    "train_runtime": 3574.4512,
+    "train_samples": 28883,
+    "train_samples_per_second": 5.053
+}

trainer_state.json

@@ -0,0 +1,239 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 18060,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.8615725359911405e-05,
+      "loss": 2.0329,
+      "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.7231450719822815e-05,
+      "loss": 1.8194,
+      "step": 1000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.5847176079734225e-05,
+      "loss": 1.7417,
+      "step": 1500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.446290143964563e-05,
+      "loss": 1.6496,
+      "step": 2000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.307862679955704e-05,
+      "loss": 1.5903,
+      "step": 2500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.169435215946844e-05,
+      "loss": 1.548,
+      "step": 3000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.0310077519379843e-05,
+      "loss": 1.5246,
+      "step": 3500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.892580287929125e-05,
+      "loss": 1.4658,
+      "step": 4000
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 3.754152823920266e-05,
+      "loss": 1.4364,
+      "step": 4500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.6157253599114066e-05,
+      "loss": 1.4202,
+      "step": 5000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 3.477297895902547e-05,
+      "loss": 1.3989,
+      "step": 5500
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.338870431893688e-05,
+      "loss": 1.3573,
+      "step": 6000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.200442967884829e-05,
+      "loss": 1.3409,
+      "step": 6500
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 3.062015503875969e-05,
+      "loss": 1.3303,
+      "step": 7000
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 2.92358803986711e-05,
+      "loss": 1.3021,
+      "step": 7500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.7851605758582504e-05,
+      "loss": 1.2974,
+      "step": 8000
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 2.646733111849391e-05,
+      "loss": 1.2693,
+      "step": 8500
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 2.5083056478405313e-05,
+      "loss": 1.2679,
+      "step": 9000
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.3698781838316723e-05,
+      "loss": 1.2332,
+      "step": 9500
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 2.231450719822813e-05,
+      "loss": 1.2372,
+      "step": 10000
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 1.2371,
+      "step": 10500
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 1.9545957918050942e-05,
+      "loss": 1.2229,
+      "step": 11000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 1.816168327796235e-05,
+      "loss": 1.1959,
+      "step": 11500
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 1.6777408637873755e-05,
+      "loss": 1.2178,
+      "step": 12000
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.539313399778516e-05,
+      "loss": 1.1638,
+      "step": 12500
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 1.4008859357696569e-05,
+      "loss": 1.193,
+      "step": 13000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 1.2624584717607974e-05,
+      "loss": 1.1522,
+      "step": 13500
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 1.1240310077519382e-05,
+      "loss": 1.1695,
+      "step": 14000
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 9.856035437430786e-06,
+      "loss": 1.1662,
+      "step": 14500
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 8.471760797342193e-06,
+      "loss": 1.1395,
+      "step": 15000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 7.087486157253599e-06,
+      "loss": 1.1739,
+      "step": 15500
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 5.703211517165006e-06,
+      "loss": 1.1426,
+      "step": 16000
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 4.318936877076412e-06,
+      "loss": 1.1466,
+      "step": 16500
+    },
+    {
+      "epoch": 9.41,
+      "learning_rate": 2.9346622369878186e-06,
+      "loss": 1.1441,
+      "step": 17000
+    },
+    {
+      "epoch": 9.69,
+      "learning_rate": 1.550387596899225e-06,
+      "loss": 1.1268,
+      "step": 17500
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 1.6611295681063123e-07,
+      "loss": 1.1508,
+      "step": 18000
+    },
+    {
+      "epoch": 10.0,
+      "step": 18060,
+      "total_flos": 4.259198586198989e+16,
+      "train_runtime": 3574.4512,
+      "train_samples_per_second": 5.053
+    }
+  ],
+  "max_steps": 18060,
+  "num_train_epochs": 10,
+  "total_flos": 4.259198586198989e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d965380af71e92c7ff587509266d5a4de9e61c817f7936f367c4ae5d6e1640d5
+size 2351