Upload 10 files

all_results.json

@@ -0,0 +1,27 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 18.1764,
+    "eval_loss": 0.24472491443157196,
+    "eval_mem_cpu_alloc_delta": 3649620,
+    "eval_mem_cpu_peaked_delta": 2934075,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 243386880,
+    "eval_rouge1": 95.1451,
+    "eval_rouge2": 89.0807,
+    "eval_rougeL": 92.6003,
+    "eval_rougeLsum": 92.6314,
+    "eval_runtime": 206.2127,
+    "eval_samples": 822,
+    "eval_samples_per_second": 3.986,
+    "init_mem_cpu_alloc_delta": 345260,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 2951196672,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 921772,
+    "train_mem_cpu_peaked_delta": 134198942,
+    "train_mem_gpu_alloc_delta": 8854116864,
+    "train_mem_gpu_peaked_delta": 2456471552,
+    "train_runtime": 2038.0134,
+    "train_samples": 3177,
+    "train_samples_per_second": 1.17
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "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": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 18.1764,
+    "eval_loss": 0.24472491443157196,
+    "eval_mem_cpu_alloc_delta": 3649620,
+    "eval_mem_cpu_peaked_delta": 2934075,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 243386880,
+    "eval_rouge1": 95.1451,
+    "eval_rouge2": 89.0807,
+    "eval_rougeL": 92.6003,
+    "eval_rougeLsum": 92.6314,
+    "eval_runtime": 206.2127,
+    "eval_samples": 822,
+    "eval_samples_per_second": 3.986
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfba3f177d76935f7ccf7c390af3ad9b50f49c8a43e94c39c26cc620096ce8c
+size 2950916820

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

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, "name_or_path": "t5-large"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 345260,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 2951196672,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 921772,
+    "train_mem_cpu_peaked_delta": 134198942,
+    "train_mem_gpu_alloc_delta": 8854116864,
+    "train_mem_gpu_peaked_delta": 2456471552,
+    "train_runtime": 2038.0134,
+    "train_samples": 3177,
+    "train_samples_per_second": 1.17
+}

trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2385,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.9517819706498955e-05,
+      "loss": 0.3391,
+      "step": 500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.9035639412997907e-05,
+      "loss": 0.2391,
+      "step": 1000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8553459119496856e-05,
+      "loss": 0.1777,
+      "step": 1500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 8.071278825995808e-06,
+      "loss": 0.1349,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2385,
+      "total_flos": 2578738654660608.0,
+      "train_runtime": 2038.0134,
+      "train_samples_per_second": 1.17
+    }
+  ],
+  "max_steps": 2385,
+  "num_train_epochs": 3,
+  "total_flos": 2578738654660608.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5b057ba28b168845e8227f239314c43fdeb9e29f93ebe3a95e772717f700a1
+size 2351