Model save

last-checkpoint/config.json

@@ -1,56 +0,0 @@
-{
-  "_name_or_path": "oMateos2020/pegasus-newsroom-cnn_full-adafactor-bs6",
-  "activation_dropout": 0.1,
-  "activation_function": "relu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
-  "architectures": [
-    "PegasusForConditionalGeneration"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 16,
-  "decoder_start_token_id": 0,
-  "dropout": 0.0,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 16,
-  "eos_token_id": 1,
-  "extra_pos_embeddings": 1,
-  "forced_eos_token_id": 1,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "length_penalty": 0.8,
-  "max_length": 128,
-  "max_position_embeddings": 512,
-  "min_length": 32,
-  "model_type": "pegasus",
-  "normalize_before": true,
-  "normalize_embedding": false,
-  "num_beams": 2,
-  "num_hidden_layers": 16,
-  "pad_token_id": 0,
-  "scale_embedding": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.20.1",
-  "use_cache": true,
-  "vocab_size": 96103
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92fcb081a65a24f5203f68033129916e8f3de1f9ddb98648805bbc5104873aba
-size 5840398

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b3dce194dc738268dd2c1f5262d8d2f2ba2fe4941f8e5db5a86356c6e0edd8b
-size 2279605745

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87aaf30dcfcb440c49f986834c15f5d1924efd3c01470dc1364bf02404df01d7
-size 14503

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a8ca221068257890306847f8d3ee335b25a16ad3c8d4a625f911e0389b9d1b6f
-size 559

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0e1f0b1cc1d5e456531ad0948086aa7319d517038ef91e91e924651ec8a9048f
-size 623

last-checkpoint/special_tokens_map.json

@@ -1,110 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<mask_1>",
-    "<unk_2>",
-    "<unk_3>",
-    "<unk_4>",
-    "<unk_5>",
-    "<unk_6>",
-    "<unk_7>",
-    "<unk_8>",
-    "<unk_9>",
-    "<unk_10>",
-    "<unk_11>",
-    "<unk_12>",
-    "<unk_13>",
-    "<unk_14>",
-    "<unk_15>",
-    "<unk_16>",
-    "<unk_17>",
-    "<unk_18>",
-    "<unk_19>",
-    "<unk_20>",
-    "<unk_21>",
-    "<unk_22>",
-    "<unk_23>",
-    "<unk_24>",
-    "<unk_25>",
-    "<unk_26>",
-    "<unk_27>",
-    "<unk_28>",
-    "<unk_29>",
-    "<unk_30>",
-    "<unk_31>",
-    "<unk_32>",
-    "<unk_33>",
-    "<unk_34>",
-    "<unk_35>",
-    "<unk_36>",
-    "<unk_37>",
-    "<unk_38>",
-    "<unk_39>",
-    "<unk_40>",
-    "<unk_41>",
-    "<unk_42>",
-    "<unk_43>",
-    "<unk_44>",
-    "<unk_45>",
-    "<unk_46>",
-    "<unk_47>",
-    "<unk_48>",
-    "<unk_49>",
-    "<unk_50>",
-    "<unk_51>",
-    "<unk_52>",
-    "<unk_53>",
-    "<unk_54>",
-    "<unk_55>",
-    "<unk_56>",
-    "<unk_57>",
-    "<unk_58>",
-    "<unk_59>",
-    "<unk_60>",
-    "<unk_61>",
-    "<unk_62>",
-    "<unk_63>",
-    "<unk_64>",
-    "<unk_65>",
-    "<unk_66>",
-    "<unk_67>",
-    "<unk_68>",
-    "<unk_69>",
-    "<unk_70>",
-    "<unk_71>",
-    "<unk_72>",
-    "<unk_73>",
-    "<unk_74>",
-    "<unk_75>",
-    "<unk_76>",
-    "<unk_77>",
-    "<unk_78>",
-    "<unk_79>",
-    "<unk_80>",
-    "<unk_81>",
-    "<unk_82>",
-    "<unk_83>",
-    "<unk_84>",
-    "<unk_85>",
-    "<unk_86>",
-    "<unk_87>",
-    "<unk_88>",
-    "<unk_89>",
-    "<unk_90>",
-    "<unk_91>",
-    "<unk_92>",
-    "<unk_93>",
-    "<unk_94>",
-    "<unk_95>",
-    "<unk_96>",
-    "<unk_97>",
-    "<unk_98>",
-    "<unk_99>",
-    "<unk_100>",
-    "<unk_101>",
-    "<unk_102>"
-  ],
-  "eos_token": "</s>",
-  "mask_token": "<mask_2>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}

last-checkpoint/spiece.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
-size 1912529

last-checkpoint/tokenizer_config.json

@@ -1,118 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<mask_1>",
-    "<unk_2>",
-    "<unk_3>",
-    "<unk_4>",
-    "<unk_5>",
-    "<unk_6>",
-    "<unk_7>",
-    "<unk_8>",
-    "<unk_9>",
-    "<unk_10>",
-    "<unk_11>",
-    "<unk_12>",
-    "<unk_13>",
-    "<unk_14>",
-    "<unk_15>",
-    "<unk_16>",
-    "<unk_17>",
-    "<unk_18>",
-    "<unk_19>",
-    "<unk_20>",
-    "<unk_21>",
-    "<unk_22>",
-    "<unk_23>",
-    "<unk_24>",
-    "<unk_25>",
-    "<unk_26>",
-    "<unk_27>",
-    "<unk_28>",
-    "<unk_29>",
-    "<unk_30>",
-    "<unk_31>",
-    "<unk_32>",
-    "<unk_33>",
-    "<unk_34>",
-    "<unk_35>",
-    "<unk_36>",
-    "<unk_37>",
-    "<unk_38>",
-    "<unk_39>",
-    "<unk_40>",
-    "<unk_41>",
-    "<unk_42>",
-    "<unk_43>",
-    "<unk_44>",
-    "<unk_45>",
-    "<unk_46>",
-    "<unk_47>",
-    "<unk_48>",
-    "<unk_49>",
-    "<unk_50>",
-    "<unk_51>",
-    "<unk_52>",
-    "<unk_53>",
-    "<unk_54>",
-    "<unk_55>",
-    "<unk_56>",
-    "<unk_57>",
-    "<unk_58>",
-    "<unk_59>",
-    "<unk_60>",
-    "<unk_61>",
-    "<unk_62>",
-    "<unk_63>",
-    "<unk_64>",
-    "<unk_65>",
-    "<unk_66>",
-    "<unk_67>",
-    "<unk_68>",
-    "<unk_69>",
-    "<unk_70>",
-    "<unk_71>",
-    "<unk_72>",
-    "<unk_73>",
-    "<unk_74>",
-    "<unk_75>",
-    "<unk_76>",
-    "<unk_77>",
-    "<unk_78>",
-    "<unk_79>",
-    "<unk_80>",
-    "<unk_81>",
-    "<unk_82>",
-    "<unk_83>",
-    "<unk_84>",
-    "<unk_85>",
-    "<unk_86>",
-    "<unk_87>",
-    "<unk_88>",
-    "<unk_89>",
-    "<unk_90>",
-    "<unk_91>",
-    "<unk_92>",
-    "<unk_93>",
-    "<unk_94>",
-    "<unk_95>",
-    "<unk_96>",
-    "<unk_97>",
-    "<unk_98>",
-    "<unk_99>",
-    "<unk_100>",
-    "<unk_101>",
-    "<unk_102>"
-  ],
-  "eos_token": "</s>",
-  "full_tokenizer_file": null,
-  "mask_token": "<mask_2>",
-  "mask_token_sent": "<mask_1>",
-  "model_max_length": 512,
-  "name_or_path": "oMateos2020/pegasus-newsroom-cnn_full-adafactor-bs6",
-  "offset": 103,
-  "pad_token": "<pad>",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "tokenizer_class": "PegasusTokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,59 +0,0 @@
-{
-  "best_metric": 43.9038,
-  "best_model_checkpoint": "pegasus-newsroom-cnn_full-adafactor-bs6/checkpoint-560",
-  "epoch": 0.49931038325972776,
-  "global_step": 560,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.28e-05,
-      "loss": 3.0058,
-      "step": 100
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 2.56e-05,
-      "loss": 2.931,
-      "step": 200
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 3.84e-05,
-      "loss": 2.9422,
-      "step": 300
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 5.12e-05,
-      "loss": 2.9606,
-      "step": 400
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 6.4e-05,
-      "loss": 2.9656,
-      "step": 500
-    },
-    {
-      "epoch": 0.5,
-      "eval_gen_len": 69.515,
-      "eval_loss": 2.8840489387512207,
-      "eval_rouge1": 43.9038,
-      "eval_rouge2": 21.2396,
-      "eval_rougeL": 31.099,
-      "eval_rougeLsum": 40.8409,
-      "eval_runtime": 8242.0465,
-      "eval_samples_per_second": 1.622,
-      "eval_steps_per_second": 0.405,
-      "step": 560
-    }
-  ],
-  "max_steps": 1121,
-  "num_train_epochs": 1,
-  "total_flos": 2.070798218085335e+17,
-  "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:c74e3795b3c07d65c60dc9c1ac7384595751fa7d2fd4cd81dc4acde86aa7fbb1
-size 3567

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3dce194dc738268dd2c1f5262d8d2f2ba2fe4941f8e5db5a86356c6e0edd8b
+oid sha256:4042f04d7c8ddfdfa52e5cddd47f1a6e3fa58520dbe86f5cc5ca0071c42e8eb3
 size 2279605745

trainer_state.json

@@ -1,120 +1,117 @@
 {
-  "best_metric": 39.4265,
-  "best_model_checkpoint": "pegasus-newsroom-cnn_full-adafactor-bs6/checkpoint-598",
-  "epoch": 0.49986416734582995,
-  "global_step": 1495,
+  "best_metric": 43.9897,
+  "best_model_checkpoint": "pegasus-newsroom-cnn_full-adafactor-bs6/checkpoint-1120",
+  "epoch": 0.9995123922038479,
+  "global_step": 1121,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "learning_rate": 7.839464882943145e-05,
-      "loss": 3.2894,
-      "step": 299
+      "epoch": 0.09,
+      "learning_rate": 1.28e-05,
+      "loss": 3.0058,
+      "step": 100
     },
     {
-      "epoch": 0.1,
-      "eval_gen_len": 64.6904,
-      "eval_loss": 2.9463675022125244,
-      "eval_rouge1": 39.4079,
-      "eval_rouge2": 18.3064,
-      "eval_rougeL": 28.093,
-      "eval_rougeLsum": 36.5182,
-      "eval_runtime": 1204.537,
-      "eval_samples_per_second": 2.075,
-      "eval_steps_per_second": 0.346,
-      "step": 299
+      "epoch": 0.18,
+      "learning_rate": 2.56e-05,
+      "loss": 2.931,
+      "step": 200
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00015812709030100337,
-      "loss": 3.0427,
-      "step": 598
+      "epoch": 0.27,
+      "learning_rate": 3.84e-05,
+      "loss": 2.9422,
+      "step": 300
     },
     {
-      "epoch": 0.2,
-      "eval_gen_len": 60.5696,
-      "eval_loss": 2.93066143989563,
-      "eval_rouge1": 39.4265,
-      "eval_rouge2": 18.2924,
-      "eval_rougeL": 28.247,
-      "eval_rougeLsum": 36.6382,
-      "eval_runtime": 1153.059,
-      "eval_samples_per_second": 2.168,
-      "eval_steps_per_second": 0.362,
-      "step": 598
+      "epoch": 0.36,
+      "learning_rate": 5.12e-05,
+      "loss": 2.9606,
+      "step": 400
     },
     {
-      "epoch": 0.3,
-      "learning_rate": 0.00014086956521739132,
-      "loss": 3.1017,
-      "step": 897
+      "epoch": 0.45,
+      "learning_rate": 6.4e-05,
+      "loss": 2.9656,
+      "step": 500
     },
     {
-      "epoch": 0.3,
-      "eval_gen_len": 58.5172,
-      "eval_loss": 2.9890542030334473,
-      "eval_rouge1": 39.0977,
-      "eval_rouge2": 17.9198,
-      "eval_rougeL": 27.9078,
-      "eval_rougeLsum": 36.2363,
-      "eval_runtime": 1087.3782,
-      "eval_samples_per_second": 2.299,
-      "eval_steps_per_second": 0.383,
-      "step": 897
+      "epoch": 0.5,
+      "eval_gen_len": 69.515,
+      "eval_loss": 2.8840489387512207,
+      "eval_rouge1": 43.9038,
+      "eval_rouge2": 21.2396,
+      "eval_rougeL": 31.099,
+      "eval_rougeLsum": 40.8409,
+      "eval_runtime": 8242.0465,
+      "eval_samples_per_second": 1.622,
+      "eval_steps_per_second": 0.405,
+      "step": 560
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.00012100334448160536,
-      "loss": 3.2891,
-      "step": 1196
+      "epoch": 0.53,
+      "learning_rate": 5.369404186795491e-05,
+      "loss": 2.9878,
+      "step": 600
     },
     {
-      "epoch": 0.4,
-      "eval_gen_len": 45.0232,
-      "eval_loss": 3.57556414604187,
-      "eval_rouge1": 29.5555,
-      "eval_rouge2": 11.7552,
-      "eval_rougeL": 22.4675,
-      "eval_rougeLsum": 27.2432,
-      "eval_runtime": 981.4008,
-      "eval_samples_per_second": 2.547,
-      "eval_steps_per_second": 0.425,
-      "step": 1196
+      "epoch": 0.62,
+      "learning_rate": 4.338808373590982e-05,
+      "loss": 3.0051,
+      "step": 700
     },
     {
-      "epoch": 0.5,
-      "learning_rate": 0.00011110367892976589,
-      "loss": 637.0317,
-      "step": 1495
+      "epoch": 0.71,
+      "learning_rate": 3.308212560386473e-05,
+      "loss": 3.0096,
+      "step": 800
     },
     {
-      "epoch": 0.5,
-      "eval_gen_len": 1.0,
-      "eval_loss": NaN,
-      "eval_rouge1": 0.0,
-      "eval_rouge2": 0.0,
-      "eval_rougeL": 0.0,
-      "eval_rougeLsum": 0.0,
-      "eval_runtime": 1564.693,
-      "eval_samples_per_second": 1.598,
-      "eval_steps_per_second": 0.267,
-      "step": 1495
+      "epoch": 0.8,
+      "learning_rate": 2.2776167471819646e-05,
+      "loss": 3.0016,
+      "step": 900
     },
     {
-      "epoch": 0.5,
-      "step": 1495,
-      "total_flos": 2.0734783091992166e+17,
-      "train_loss": 129.9509090768055,
-      "train_runtime": 31793.2991,
-      "train_samples_per_second": 9.031,
-      "train_steps_per_second": 0.094
+      "epoch": 0.89,
+      "learning_rate": 1.2470209339774557e-05,
+      "loss": 3.0071,
+      "step": 1000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.1642512077294685e-06,
+      "loss": 2.9976,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 72.362,
+      "eval_loss": 2.8759312629699707,
+      "eval_rouge1": 43.9897,
+      "eval_rouge2": 21.287,
+      "eval_rougeL": 31.1064,
+      "eval_rougeLsum": 40.9035,
+      "eval_runtime": 8420.7089,
+      "eval_samples_per_second": 1.588,
+      "eval_steps_per_second": 0.397,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0,
+      "step": 1121,
+      "total_flos": 4.145227793147167e+17,
+      "train_loss": 2.983753987022216,
+      "train_runtime": 51642.0714,
+      "train_samples_per_second": 5.56,
+      "train_steps_per_second": 0.022
     }
   ],
-  "max_steps": 2990,
+  "max_steps": 1121,
   "num_train_epochs": 1,
-  "total_flos": 2.0734783091992166e+17,
+  "total_flos": 4.145227793147167e+17,
   "trial_name": null,
   "trial_params": null
 }