Model save

last-checkpoint/config.json

@@ -1,60 +0,0 @@
-{
-  "_name_or_path": "t5-small",
-  "architectures": [
-    "T5ForConditionalGeneration"
-  ],
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 512,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "relu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": false,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "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: "
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
-  "use_cache": true,
-  "vocab_size": 32128
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d2e62c4053b12130f3c15a8374771d8badc383fb218eea178a53e3db0b4e7c00
-size 839109

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:edea7e76f138b5a937076945663ef9be5be34e8a1ad1531b591d608674a1d656
-size 242071641

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e720383a081028ce4daca98249eb4eb040bf48648a0545b31209dc8f6dbde5af
-size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
-size 627

last-checkpoint/special_tokens_map.json

@@ -1,107 +0,0 @@
-{
-  "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>"
-  ],
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}

last-checkpoint/tokenizer_config.json

@@ -1,111 +0,0 @@
-{
-  "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>"
-  ],
-  "eos_token": "</s>",
-  "extra_ids": 100,
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "T5Tokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,192 +0,0 @@
-{
-  "best_metric": 1.8752236366271973,
-  "best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/t5-small-e-snli-generation-label_and_explanation-selected-b64/checkpoint-6000",
-  "epoch": 1.8639328984156571,
-  "global_step": 16000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.0004659832246039143,
-      "loss": 1.6638,
-      "step": 2000
-    },
-    {
-      "epoch": 0.23,
-      "eval_accuracy": 0.7882544198333672,
-      "eval_bertscore_f1": 0.9274053666630888,
-      "eval_bleu": 0.3730230029620418,
-      "eval_f1": 0.7869310553570436,
-      "eval_loss": 2.0038630962371826,
-      "eval_rouge1": 0.5705349256664797,
-      "eval_rouge2": 0.36005675419970606,
-      "eval_rougeL": 0.5174575845618529,
-      "eval_rougeLsum": 0.519191892876955,
-      "eval_runtime": 132.0522,
-      "eval_samples_per_second": 74.531,
-      "eval_steps_per_second": 1.166,
-      "step": 2000
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.0009319664492078286,
-      "loss": 1.2998,
-      "step": 4000
-    },
-    {
-      "epoch": 0.47,
-      "eval_accuracy": 0.8282869335500914,
-      "eval_bertscore_f1": 0.9302830712518128,
-      "eval_bleu": 0.38537751631933276,
-      "eval_f1": 0.8292574332070184,
-      "eval_loss": 1.9378293752670288,
-      "eval_rouge1": 0.5860810235891796,
-      "eval_rouge2": 0.37476551181712653,
-      "eval_rougeL": 0.5309995593771393,
-      "eval_rougeLsum": 0.5329380545888618,
-      "eval_runtime": 122.8565,
-      "eval_samples_per_second": 80.11,
-      "eval_steps_per_second": 1.253,
-      "step": 4000
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.0009790552803256977,
-      "loss": 1.2351,
-      "step": 6000
-    },
-    {
-      "epoch": 0.7,
-      "eval_accuracy": 0.8431213168055274,
-      "eval_bertscore_f1": 0.9320737935498197,
-      "eval_bleu": 0.3954191513500076,
-      "eval_f1": 0.8436887448101525,
-      "eval_loss": 1.8752236366271973,
-      "eval_rouge1": 0.5950780098064086,
-      "eval_rouge2": 0.387995341938732,
-      "eval_rougeL": 0.5410511557431861,
-      "eval_rougeLsum": 0.5429767615233919,
-      "eval_runtime": 128.496,
-      "eval_samples_per_second": 76.594,
-      "eval_steps_per_second": 1.198,
-      "step": 6000
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.0009545298474518076,
-      "loss": 1.1948,
-      "step": 8000
-    },
-    {
-      "epoch": 0.93,
-      "eval_accuracy": 0.853586669376143,
-      "eval_bertscore_f1": 0.9332542442325847,
-      "eval_bleu": 0.4005757380852503,
-      "eval_f1": 0.8529062465495825,
-      "eval_loss": 1.9346258640289307,
-      "eval_rouge1": 0.6018073936798602,
-      "eval_rouge2": 0.39307647629207804,
-      "eval_rougeL": 0.5451341858386651,
-      "eval_rougeLsum": 0.5471925151539236,
-      "eval_runtime": 124.1433,
-      "eval_samples_per_second": 79.279,
-      "eval_steps_per_second": 1.241,
-      "step": 8000
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 0.0009300044145779173,
-      "loss": 1.1537,
-      "step": 10000
-    },
-    {
-      "epoch": 1.16,
-      "eval_accuracy": 0.8653728916886811,
-      "eval_bertscore_f1": 0.9331838286242768,
-      "eval_bleu": 0.40960288490504165,
-      "eval_f1": 0.8646878910419536,
-      "eval_loss": 1.88812255859375,
-      "eval_rouge1": 0.6070431684612829,
-      "eval_rouge2": 0.40225937264181405,
-      "eval_rougeL": 0.5483146296815378,
-      "eval_rougeLsum": 0.5505540288475277,
-      "eval_runtime": 124.2229,
-      "eval_samples_per_second": 79.229,
-      "eval_steps_per_second": 1.24,
-      "step": 10000
-    },
-    {
-      "epoch": 1.4,
-      "learning_rate": 0.0009054789817040271,
-      "loss": 1.1298,
-      "step": 12000
-    },
-    {
-      "epoch": 1.4,
-      "eval_accuracy": 0.8690306848201585,
-      "eval_bertscore_f1": 0.9337236821784695,
-      "eval_bleu": 0.4093407550709913,
-      "eval_f1": 0.8684526023202777,
-      "eval_loss": 1.9264899492263794,
-      "eval_rouge1": 0.6052909335108297,
-      "eval_rouge2": 0.3988120323032148,
-      "eval_rougeL": 0.5507358395779893,
-      "eval_rougeLsum": 0.5525962718036264,
-      "eval_runtime": 124.4402,
-      "eval_samples_per_second": 79.09,
-      "eval_steps_per_second": 1.238,
-      "step": 12000
-    },
-    {
-      "epoch": 1.63,
-      "learning_rate": 0.0008809535488301369,
-      "loss": 1.1219,
-      "step": 14000
-    },
-    {
-      "epoch": 1.63,
-      "eval_accuracy": 0.8712660028449503,
-      "eval_bertscore_f1": 0.933247425254102,
-      "eval_bleu": 0.4042307480916517,
-      "eval_f1": 0.8714448369951496,
-      "eval_loss": 1.9016553163528442,
-      "eval_rouge1": 0.6029172997635328,
-      "eval_rouge2": 0.3941212931043536,
-      "eval_rougeL": 0.5470042844879892,
-      "eval_rougeLsum": 0.5488824169286723,
-      "eval_runtime": 125.6867,
-      "eval_samples_per_second": 78.306,
-      "eval_steps_per_second": 1.225,
-      "step": 14000
-    },
-    {
-      "epoch": 1.86,
-      "learning_rate": 0.0008564281159562467,
-      "loss": 1.1088,
-      "step": 16000
-    },
-    {
-      "epoch": 1.86,
-      "eval_accuracy": 0.8732981101402154,
-      "eval_bertscore_f1": 0.9355657943088188,
-      "eval_bleu": 0.4223746159966924,
-      "eval_f1": 0.8729633394714756,
-      "eval_loss": 1.9257447719573975,
-      "eval_rouge1": 0.6144211309547953,
-      "eval_rouge2": 0.40963176352893027,
-      "eval_rougeL": 0.5592204703479691,
-      "eval_rougeLsum": 0.5610705650496804,
-      "eval_runtime": 122.6208,
-      "eval_samples_per_second": 80.264,
-      "eval_steps_per_second": 1.256,
-      "step": 16000
-    }
-  ],
-  "max_steps": 85840,
-  "num_train_epochs": 10,
-  "total_flos": 1.5969080133353472e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d26d77783a5be2f09e74ce5ec88c9772e03222d1dd997806a339afe33fbf979d
-size 3963

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edea7e76f138b5a937076945663ef9be5be34e8a1ad1531b591d608674a1d656
+oid sha256:620a22917828d7d9e1692adaaca61f727beb88eda118006eaf406bf2a28c9aed
 size 242071641