add trained model

README.md

@@ -0,0 +1,59 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: summarization_mlsum
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# summarization_mlsum
+
+This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0190
+- Rouge1: 19.2854
+- Rouge2: 6.0392
+- Rougel: 16.4987
+- Rougelsum: 16.616
+- Gen Len: 32.7635
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.12.0.dev0
+- Pytorch 1.9.1+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,28 @@
+{
+    "epoch": 4.0,
+    "eval_gen_len": 32.7635,
+    "eval_loss": 2.0189740657806396,
+    "eval_rouge1": 19.2854,
+    "eval_rouge2": 6.0392,
+    "eval_rougeL": 16.4987,
+    "eval_rougeLsum": 16.616,
+    "eval_runtime": 647.9074,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 6.174,
+    "eval_steps_per_second": 1.029,
+    "predict_gen_len": 32.5268,
+    "predict_loss": 1.9996718168258667,
+    "predict_rouge1": 19.3739,
+    "predict_rouge2": 5.9753,
+    "predict_rougeL": 16.691,
+    "predict_rougeLsum": 16.7862,
+    "predict_runtime": 650.8156,
+    "predict_samples": 4000,
+    "predict_samples_per_second": 6.146,
+    "predict_steps_per_second": 1.025,
+    "train_loss": 2.132151625336569,
+    "train_runtime": 19550.5305,
+    "train_samples": 31997,
+    "train_samples_per_second": 6.547,
+    "train_steps_per_second": 1.091
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "gsarti/it5-base",
+  "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": "4.12.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32103
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_gen_len": 32.7635,
+    "eval_loss": 2.0189740657806396,
+    "eval_rouge1": 19.2854,
+    "eval_rouge2": 6.0392,
+    "eval_rougeL": 16.4987,
+    "eval_rougeLsum": 16.616,
+    "eval_runtime": 647.9074,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 6.174,
+    "eval_steps_per_second": 1.029
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 32.5268,
+    "predict_loss": 1.9996718168258667,
+    "predict_rouge1": 19.3739,
+    "predict_rouge2": 5.9753,
+    "predict_rougeL": 16.691,
+    "predict_rougeLsum": 16.7862,
+    "predict_runtime": 650.8156,
+    "predict_samples": 4000,
+    "predict_samples_per_second": 6.146,
+    "predict_steps_per_second": 1.025
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a2e861d40ecd3b41c78c6d58bb53271e4ee48a2db66998a4d975039b91eee4
+size 990284749

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>"]}

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>"], "special_tokens_map_file": null, "name_or_path": "gsarti/it5-base", "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 2.132151625336569,
+    "train_runtime": 19550.5305,
+    "train_samples": 31997,
+    "train_samples_per_second": 6.547,
+    "train_steps_per_second": 1.091
+}

trainer_state.json

@@ -0,0 +1,277 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 21332,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.882805175323458e-05,
+      "loss": 2.894,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.7656103506469155e-05,
+      "loss": 2.3094,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.648415525970373e-05,
+      "loss": 2.256,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.5312207012938315e-05,
+      "loss": 2.2547,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4140258766172885e-05,
+      "loss": 2.2201,
+      "step": 2500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.296831051940747e-05,
+      "loss": 2.1982,
+      "step": 3000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.1796362272642045e-05,
+      "loss": 2.2123,
+      "step": 3500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.0624414025876614e-05,
+      "loss": 2.178,
+      "step": 4000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.94524657791112e-05,
+      "loss": 2.1991,
+      "step": 4500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.8280517532345774e-05,
+      "loss": 2.1734,
+      "step": 5000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.710856928558035e-05,
+      "loss": 2.1487,
+      "step": 5500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.593662103881493e-05,
+      "loss": 2.1605,
+      "step": 6000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.476467279204951e-05,
+      "loss": 2.1316,
+      "step": 6500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.359272454528408e-05,
+      "loss": 2.1173,
+      "step": 7000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.242077629851866e-05,
+      "loss": 2.1218,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.124882805175324e-05,
+      "loss": 2.1017,
+      "step": 8000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 3.0076879804987813e-05,
+      "loss": 2.1083,
+      "step": 8500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8904931558222393e-05,
+      "loss": 2.1279,
+      "step": 9000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.7732983311456966e-05,
+      "loss": 2.1056,
+      "step": 9500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.6561035064691543e-05,
+      "loss": 2.1081,
+      "step": 10000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.5389086817926123e-05,
+      "loss": 2.1229,
+      "step": 10500
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.42171385711607e-05,
+      "loss": 2.1051,
+      "step": 11000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.3045190324395276e-05,
+      "loss": 2.0861,
+      "step": 11500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.1873242077629852e-05,
+      "loss": 2.0813,
+      "step": 12000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.070129383086443e-05,
+      "loss": 2.0704,
+      "step": 12500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.952934558409901e-05,
+      "loss": 2.0753,
+      "step": 13000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.8357397337333585e-05,
+      "loss": 2.0803,
+      "step": 13500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.718544909056816e-05,
+      "loss": 2.0947,
+      "step": 14000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.6013500843802738e-05,
+      "loss": 2.0526,
+      "step": 14500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.4841552597037315e-05,
+      "loss": 2.0683,
+      "step": 15000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.3669604350271891e-05,
+      "loss": 2.0641,
+      "step": 15500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.249765610350647e-05,
+      "loss": 2.0679,
+      "step": 16000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 1.1325707856741047e-05,
+      "loss": 2.0329,
+      "step": 16500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.0153759609975624e-05,
+      "loss": 2.0512,
+      "step": 17000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 8.9818113632102e-06,
+      "loss": 2.0731,
+      "step": 17500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.809863116444779e-06,
+      "loss": 2.0693,
+      "step": 18000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 6.637914869679355e-06,
+      "loss": 2.0459,
+      "step": 18500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.4659666229139326e-06,
+      "loss": 2.0371,
+      "step": 19000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 4.294018376148509e-06,
+      "loss": 2.0285,
+      "step": 19500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 3.122070129383087e-06,
+      "loss": 2.0494,
+      "step": 20000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.9501218826176638e-06,
+      "loss": 2.0385,
+      "step": 20500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 7.781736358522408e-07,
+      "loss": 2.0785,
+      "step": 21000
+    },
+    {
+      "epoch": 4.0,
+      "step": 21332,
+      "total_flos": 7.623777879473818e+16,
+      "train_loss": 2.132151625336569,
+      "train_runtime": 19550.5305,
+      "train_samples_per_second": 6.547,
+      "train_steps_per_second": 1.091
+    }
+  ],
+  "max_steps": 21332,
+  "num_train_epochs": 4,
+  "total_flos": 7.623777879473818e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beace91aac75f278e7cd5a31be3a2e2b092696778bc85a752abf34ab2d39a72c
+size 2927