add trained model

README.md

@@ -0,0 +1,59 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: summarization_ilpost
+  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_ilpost
+
+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: 1.6020
+- Rouge1: 33.7802
+- Rouge2: 16.2953
+- Rougel: 27.4797
+- Rougelsum: 30.2273
+- Gen Len: 45.3175
+
+## 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": 45.3175,
+    "eval_loss": 1.6020476818084717,
+    "eval_rouge1": 33.7802,
+    "eval_rouge2": 16.2953,
+    "eval_rougeL": 27.4797,
+    "eval_rougeLsum": 30.2273,
+    "eval_runtime": 846.7357,
+    "eval_samples": 4400,
+    "eval_samples_per_second": 5.196,
+    "eval_steps_per_second": 0.867,
+    "predict_gen_len": 45.3175,
+    "predict_loss": 1.6020476818084717,
+    "predict_rouge1": 33.7802,
+    "predict_rouge2": 16.2953,
+    "predict_rougeL": 27.4797,
+    "predict_rougeLsum": 30.2273,
+    "predict_runtime": 846.3322,
+    "predict_samples": 4400,
+    "predict_samples_per_second": 5.199,
+    "predict_steps_per_second": 0.867,
+    "train_loss": 1.7515089764228484,
+    "train_runtime": 22215.4472,
+    "train_samples": 35201,
+    "train_samples_per_second": 6.338,
+    "train_steps_per_second": 1.056
+}

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": 45.3175,
+    "eval_loss": 1.6020476818084717,
+    "eval_rouge1": 33.7802,
+    "eval_rouge2": 16.2953,
+    "eval_rougeL": 27.4797,
+    "eval_rougeLsum": 30.2273,
+    "eval_runtime": 846.7357,
+    "eval_samples": 4400,
+    "eval_samples_per_second": 5.196,
+    "eval_steps_per_second": 0.867
+}

events.out.tfevents.1633958968.meterreader.12204.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692f06dfb7174fd08433bbceea1556673796c9a8970d572ec81ee10deb7eeaad
+size 40

events.out.tfevents.1633959348.meterreader.15458.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd701874c548df74fd7c3643b0541d80e49923c16e7550352f30d63e0aa865e2
+size 40

events.out.tfevents.1633959595.meterreader.18291.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1bc19cc7015498a20e94a9d49f58ed4a5dcbfd621f7abc46d20da7978bea82
+size 40

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 45.3175,
+    "predict_loss": 1.6020476818084717,
+    "predict_rouge1": 33.7802,
+    "predict_rouge2": 16.2953,
+    "predict_rougeL": 27.4797,
+    "predict_rougeLsum": 30.2273,
+    "predict_runtime": 846.3322,
+    "predict_samples": 4400,
+    "predict_samples_per_second": 5.199,
+    "predict_steps_per_second": 0.867
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1f4b03272b95a0ada86122f4518bc36359445ed9cee83f4986201bc2a12fb0
+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": 1.7515089764228484,
+    "train_runtime": 22215.4472,
+    "train_samples": 35201,
+    "train_samples_per_second": 6.338,
+    "train_steps_per_second": 1.056
+}

trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 23468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.893471961820351e-05,
+      "loss": 2.3053,
+      "step": 500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7869439236407024e-05,
+      "loss": 1.9792,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.680415885461054e-05,
+      "loss": 1.9158,
+      "step": 1500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.5738878472814045e-05,
+      "loss": 1.8901,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.467359809101756e-05,
+      "loss": 1.8747,
+      "step": 2500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.3608317709221067e-05,
+      "loss": 1.8479,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.254303732742458e-05,
+      "loss": 1.8417,
+      "step": 3500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.1477756945628095e-05,
+      "loss": 1.8416,
+      "step": 4000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.04124765638316e-05,
+      "loss": 1.8413,
+      "step": 4500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.934719618203511e-05,
+      "loss": 1.8118,
+      "step": 5000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.828191580023863e-05,
+      "loss": 1.789,
+      "step": 5500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.721663541844214e-05,
+      "loss": 1.7796,
+      "step": 6000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.6151355036645645e-05,
+      "loss": 1.7649,
+      "step": 6500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.508607465484916e-05,
+      "loss": 1.7664,
+      "step": 7000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.4020794273052666e-05,
+      "loss": 1.7606,
+      "step": 7500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.295551389125618e-05,
+      "loss": 1.7345,
+      "step": 8000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.1890233509459694e-05,
+      "loss": 1.713,
+      "step": 8500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.08249531276632e-05,
+      "loss": 1.7604,
+      "step": 9000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.9759672745866712e-05,
+      "loss": 1.7539,
+      "step": 9500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.8694392364070227e-05,
+      "loss": 1.744,
+      "step": 10000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.7629111982273737e-05,
+      "loss": 1.7442,
+      "step": 10500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.6563831600477245e-05,
+      "loss": 1.7275,
+      "step": 11000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.5498551218680762e-05,
+      "loss": 1.702,
+      "step": 11500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 2.443327083688427e-05,
+      "loss": 1.714,
+      "step": 12000
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.336799045508778e-05,
+      "loss": 1.6891,
+      "step": 12500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.230271007329129e-05,
+      "loss": 1.7327,
+      "step": 13000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.1237429691494805e-05,
+      "loss": 1.7197,
+      "step": 13500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.0172149309698312e-05,
+      "loss": 1.6997,
+      "step": 14000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.9106868927901826e-05,
+      "loss": 1.6961,
+      "step": 14500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.8041588546105337e-05,
+      "loss": 1.6966,
+      "step": 15000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.6976308164308848e-05,
+      "loss": 1.6905,
+      "step": 15500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.591102778251236e-05,
+      "loss": 1.6984,
+      "step": 16000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.484574740071587e-05,
+      "loss": 1.673,
+      "step": 16500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.378046701891938e-05,
+      "loss": 1.6719,
+      "step": 17000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.2715186637122892e-05,
+      "loss": 1.6932,
+      "step": 17500
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.1649906255326403e-05,
+      "loss": 1.679,
+      "step": 18000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 1.0584625873529914e-05,
+      "loss": 1.6691,
+      "step": 18500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 9.519345491733426e-06,
+      "loss": 1.6633,
+      "step": 19000
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 8.454065109936937e-06,
+      "loss": 1.6607,
+      "step": 19500
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 7.3887847281404465e-06,
+      "loss": 1.6757,
+      "step": 20000
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 6.323504346343959e-06,
+      "loss": 1.6765,
+      "step": 20500
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 5.25822396454747e-06,
+      "loss": 1.6758,
+      "step": 21000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 4.19294358275098e-06,
+      "loss": 1.6745,
+      "step": 21500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 3.1276632009544914e-06,
+      "loss": 1.665,
+      "step": 22000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.0623828191580025e-06,
+      "loss": 1.6721,
+      "step": 22500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 9.971024373615137e-07,
+      "loss": 1.6684,
+      "step": 23000
+    },
+    {
+      "epoch": 4.0,
+      "step": 23468,
+      "total_flos": 9.246597801402931e+16,
+      "train_loss": 1.7515089764228484,
+      "train_runtime": 22215.4472,
+      "train_samples_per_second": 6.338,
+      "train_steps_per_second": 1.056
+    }
+  ],
+  "max_steps": 23468,
+  "num_train_epochs": 4,
+  "total_flos": 9.246597801402931e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b07921dc23952cdabd1155124792d6dd8022b7239be353b88b9a2bd7737a74
+size 2927