Initial commmit

README.md

@@ -1,3 +1,83 @@
 ---
-license: apache-2.0
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- it5/datasets
+metrics:
+- rouge
+model-index:
+- name: it5-efficient-small-el32-qg-0.0003
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: it5/datasets qg
+      type: it5/datasets
+      args: qg
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 40.5452
 ---
+
+<!-- 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. -->
+
+# it5-efficient-small-el32-qg-0.0003
+
+This model is a fine-tuned version of [stefan-it/it5-efficient-small-el32](https://huggingface.co/stefan-it/it5-efficient-small-el32) on the it5/datasets qg dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8460
+- Rouge1: 40.5452
+- Rouge2: 21.7821
+- Rougel: 37.9644
+- Rougelsum: 37.9407
+- Gen Len: 14.059
+
+## 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: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.3227        | 0.78  | 5000  | 2.0119          | 35.4228 | 16.8454 | 33.0039 | 33.0042   | 13.4213 |
+| 2.0517        | 1.56  | 10000 | 1.9002          | 36.7771 | 18.1217 | 34.4954 | 34.4605   | 12.7787 |
+| 1.8388        | 2.35  | 15000 | 1.8676          | 38.3396 | 19.4592 | 35.8451 | 35.8358   | 13.2803 |
+| 1.6942        | 3.13  | 20000 | 1.8758          | 39.0889 | 20.3841 | 36.655  | 36.6291   | 13.0213 |
+| 1.7123        | 3.91  | 25000 | 1.8253          | 39.6282 | 20.9321 | 37.1541 | 37.1195   | 13.1837 |
+| 1.5719        | 4.69  | 30000 | 1.8311          | 39.7541 | 21.1663 | 37.3503 | 37.3096   | 13.3723 |
+| 1.4763        | 5.47  | 35000 | 1.8474          | 39.8798 | 21.3044 | 37.4297 | 37.4135   | 13.2783 |
+| 1.3963        | 6.25  | 40000 | 1.8533          | 40.1839 | 21.4959 | 37.5371 | 37.5414   | 13.4713 |
+
+
+### Framework versions
+
+- Transformers 4.15.0
+- Pytorch 1.10.0+cu102
+- Datasets 1.17.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 7.0,
+    "eval_gen_len": 14.059,
+    "eval_loss": 1.8460021018981934,
+    "eval_rouge1": 40.5452,
+    "eval_rouge2": 21.7821,
+    "eval_rougeL": 37.9644,
+    "eval_rougeLsum": 37.9407,
+    "eval_runtime": 116.4742,
+    "eval_samples": 3000,
+    "eval_samples_per_second": 25.757,
+    "eval_steps_per_second": 3.22,
+    "train_loss": 1.7918549016882,
+    "train_runtime": 13775.2907,
+    "train_samples": 51159,
+    "train_samples_per_second": 25.997,
+    "train_steps_per_second": 3.25
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 6,
+  "num_heads": 8,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 7.0,
+    "eval_gen_len": 14.059,
+    "eval_loss": 1.8460021018981934,
+    "eval_rouge1": 40.5452,
+    "eval_rouge2": 21.7821,
+    "eval_rougeL": 37.9644,
+    "eval_rougeLsum": 37.9407,
+    "eval_runtime": 116.4742,
+    "eval_samples": 3000,
+    "eval_samples_per_second": 25.757,
+    "eval_steps_per_second": 3.22
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a0d79302924998f7960b4871ab8efc1b703fd7ff0ae1012e6a208c62247b61
+size 569246164

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28faf5fd43b2c586e2a67158b6d5248841d9faafea93dfe02742c5191c2143c2
+size 569387035

runs/Apr26_13-05-50_pg-gpu34/1650971209.8765502/events.out.tfevents.1650971209.pg-gpu34.16405.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07671b828afb84fc6d64a01eda7ceece9e386708562f276f253b30e143bb6abe
+size 5127

runs/Apr26_13-05-50_pg-gpu34/events.out.tfevents.1650971209.pg-gpu34.16405.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae22815369d8fea3aff4004552e66fafdb9b3096b1e71e4ce9a1f3dadc65fd87
+size 22379

runs/Apr26_13-05-50_pg-gpu34/events.out.tfevents.1650985106.pg-gpu34.16405.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb473412f58c767a22de089d729682e380e5c1a4d2fc857ccf3363ef3135f5c
+size 575

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 sha256:2dffd01fc009b7e92d98eddff8853983e271b41302ed0d363000e8581df12000
+size 817200

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96c5805470ff7e8022bb180014da85e36574097e631c206f91b95d8bb676d3e
+size 569947488

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": "stefan-it/it5-efficient-small-el32", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 1.7918549016882,
+    "train_runtime": 13775.2907,
+    "train_samples": 51159,
+    "train_samples_per_second": 25.997,
+    "train_steps_per_second": 3.25
+}

trainer_state.json

@@ -0,0 +1,663 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 44765,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00029664916787668934,
+      "loss": 3.2895,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002932983357533787,
+      "loss": 2.7517,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00028994750363006813,
+      "loss": 2.6498,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002865966715067575,
+      "loss": 2.5331,
+      "step": 2000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00028324583938344687,
+      "loss": 2.4775,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00027989500726013623,
+      "loss": 2.4187,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00027654417513682566,
+      "loss": 2.402,
+      "step": 3500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000273193343013515,
+      "loss": 2.3717,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002698425108902044,
+      "loss": 2.3738,
+      "step": 4500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00026649167876689376,
+      "loss": 2.3227,
+      "step": 5000
+    },
+    {
+      "epoch": 0.78,
+      "eval_gen_len": 13.4213,
+      "eval_loss": 2.011871576309204,
+      "eval_rouge1": 35.4228,
+      "eval_rouge2": 16.8454,
+      "eval_rougeL": 33.0039,
+      "eval_rougeLsum": 33.0042,
+      "eval_runtime": 109.3685,
+      "eval_samples_per_second": 27.43,
+      "eval_steps_per_second": 3.429,
+      "step": 5000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002631408466435831,
+      "loss": 2.2981,
+      "step": 5500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00025979001452027255,
+      "loss": 2.2863,
+      "step": 6000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002564391823969619,
+      "loss": 2.2597,
+      "step": 6500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00025308835027365123,
+      "loss": 2.0983,
+      "step": 7000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00024973751815034065,
+      "loss": 2.0933,
+      "step": 7500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00024638668602703,
+      "loss": 2.1024,
+      "step": 8000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002430358539037194,
+      "loss": 2.0818,
+      "step": 8500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00023968502178040878,
+      "loss": 2.0917,
+      "step": 9000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00023633418965709815,
+      "loss": 2.0658,
+      "step": 9500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00023298335753378752,
+      "loss": 2.0517,
+      "step": 10000
+    },
+    {
+      "epoch": 1.56,
+      "eval_gen_len": 12.7787,
+      "eval_loss": 1.900165319442749,
+      "eval_rouge1": 36.7771,
+      "eval_rouge2": 18.1217,
+      "eval_rougeL": 34.4954,
+      "eval_rougeLsum": 34.4605,
+      "eval_runtime": 106.6009,
+      "eval_samples_per_second": 28.142,
+      "eval_steps_per_second": 3.518,
+      "step": 10000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002296325254104769,
+      "loss": 2.0494,
+      "step": 10500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00022628169328716628,
+      "loss": 2.0672,
+      "step": 11000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00022293086116385567,
+      "loss": 2.0591,
+      "step": 11500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00021958002904054504,
+      "loss": 2.0515,
+      "step": 12000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00021622919691723444,
+      "loss": 2.0628,
+      "step": 12500
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0002128783647939238,
+      "loss": 1.959,
+      "step": 13000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00020952753267061317,
+      "loss": 1.8223,
+      "step": 13500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00020617670054730257,
+      "loss": 1.8548,
+      "step": 14000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00020282586842399193,
+      "loss": 1.8462,
+      "step": 14500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.00019947503630068133,
+      "loss": 1.8388,
+      "step": 15000
+    },
+    {
+      "epoch": 2.35,
+      "eval_gen_len": 13.2803,
+      "eval_loss": 1.8676202297210693,
+      "eval_rouge1": 38.3396,
+      "eval_rouge2": 19.4592,
+      "eval_rougeL": 35.8451,
+      "eval_rougeLsum": 35.8358,
+      "eval_runtime": 111.5416,
+      "eval_samples_per_second": 26.896,
+      "eval_steps_per_second": 3.362,
+      "step": 15000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0001961242041773707,
+      "loss": 1.8675,
+      "step": 15500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.0001927733720540601,
+      "loss": 1.8656,
+      "step": 16000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.00018942253993074946,
+      "loss": 1.8836,
+      "step": 16500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.00018607170780743885,
+      "loss": 1.8646,
+      "step": 17000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.00018272087568412822,
+      "loss": 1.8718,
+      "step": 17500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.0001793700435608176,
+      "loss": 1.8641,
+      "step": 18000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00017601921143750698,
+      "loss": 1.8633,
+      "step": 18500
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.00017266837931419635,
+      "loss": 1.8435,
+      "step": 19000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.00016931754719088575,
+      "loss": 1.7436,
+      "step": 19500
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.0001659667150675751,
+      "loss": 1.6942,
+      "step": 20000
+    },
+    {
+      "epoch": 3.13,
+      "eval_gen_len": 13.0213,
+      "eval_loss": 1.8757922649383545,
+      "eval_rouge1": 39.0889,
+      "eval_rouge2": 20.3841,
+      "eval_rougeL": 36.655,
+      "eval_rougeLsum": 36.6291,
+      "eval_runtime": 103.7035,
+      "eval_samples_per_second": 28.929,
+      "eval_steps_per_second": 3.616,
+      "step": 20000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00016261588294426446,
+      "loss": 1.691,
+      "step": 20500
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.00015926505082095385,
+      "loss": 1.6786,
+      "step": 21000
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.00015591421869764322,
+      "loss": 1.7014,
+      "step": 21500
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.0001525633865743326,
+      "loss": 1.72,
+      "step": 22000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.000149212554451022,
+      "loss": 1.7038,
+      "step": 22500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00014586172232771135,
+      "loss": 1.7212,
+      "step": 23000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00014251089020440074,
+      "loss": 1.6839,
+      "step": 23500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0001391600580810901,
+      "loss": 1.6908,
+      "step": 24000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.0001358092259577795,
+      "loss": 1.6973,
+      "step": 24500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.00013245839383446887,
+      "loss": 1.7123,
+      "step": 25000
+    },
+    {
+      "epoch": 3.91,
+      "eval_gen_len": 13.1837,
+      "eval_loss": 1.8253004550933838,
+      "eval_rouge1": 39.6282,
+      "eval_rouge2": 20.9321,
+      "eval_rougeL": 37.1541,
+      "eval_rougeLsum": 37.1195,
+      "eval_runtime": 103.6467,
+      "eval_samples_per_second": 28.944,
+      "eval_steps_per_second": 3.618,
+      "step": 25000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.00012910756171115827,
+      "loss": 1.7076,
+      "step": 25500
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 0.00012575672958784764,
+      "loss": 1.5729,
+      "step": 26000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.00012240589746453703,
+      "loss": 1.5568,
+      "step": 26500
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.0001190550653412264,
+      "loss": 1.5458,
+      "step": 27000
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00011570423321791578,
+      "loss": 1.5678,
+      "step": 27500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.00011235340109460516,
+      "loss": 1.5979,
+      "step": 28000
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.00010900256897129453,
+      "loss": 1.5604,
+      "step": 28500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 0.00010565173684798391,
+      "loss": 1.5539,
+      "step": 29000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.00010230090472467328,
+      "loss": 1.5681,
+      "step": 29500
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 9.895007260136266e-05,
+      "loss": 1.5719,
+      "step": 30000
+    },
+    {
+      "epoch": 4.69,
+      "eval_gen_len": 13.3723,
+      "eval_loss": 1.8311357498168945,
+      "eval_rouge1": 39.7541,
+      "eval_rouge2": 21.1663,
+      "eval_rougeL": 37.3503,
+      "eval_rougeLsum": 37.3096,
+      "eval_runtime": 106.3723,
+      "eval_samples_per_second": 28.203,
+      "eval_steps_per_second": 3.525,
+      "step": 30000
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 9.559924047805204e-05,
+      "loss": 1.5787,
+      "step": 30500
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 9.224840835474142e-05,
+      "loss": 1.5805,
+      "step": 31000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 8.889757623143079e-05,
+      "loss": 1.5646,
+      "step": 31500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.554674410812017e-05,
+      "loss": 1.5593,
+      "step": 32000
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 8.219591198480955e-05,
+      "loss": 1.4606,
+      "step": 32500
+    },
+    {
+      "epoch": 5.16,
+      "learning_rate": 7.884507986149893e-05,
+      "loss": 1.4393,
+      "step": 33000
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 7.549424773818831e-05,
+      "loss": 1.4826,
+      "step": 33500
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 7.21434156148777e-05,
+      "loss": 1.4668,
+      "step": 34000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 6.879258349156706e-05,
+      "loss": 1.4599,
+      "step": 34500
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 6.544175136825644e-05,
+      "loss": 1.4763,
+      "step": 35000
+    },
+    {
+      "epoch": 5.47,
+      "eval_gen_len": 13.2783,
+      "eval_loss": 1.8474199771881104,
+      "eval_rouge1": 39.8798,
+      "eval_rouge2": 21.3044,
+      "eval_rougeL": 37.4297,
+      "eval_rougeLsum": 37.4135,
+      "eval_runtime": 104.818,
+      "eval_samples_per_second": 28.621,
+      "eval_steps_per_second": 3.578,
+      "step": 35000
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 6.209091924494583e-05,
+      "loss": 1.4651,
+      "step": 35500
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 5.87400871216352e-05,
+      "loss": 1.475,
+      "step": 36000
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 5.538925499832458e-05,
+      "loss": 1.4734,
+      "step": 36500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 5.203842287501396e-05,
+      "loss": 1.4487,
+      "step": 37000
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 4.868759075170333e-05,
+      "loss": 1.4408,
+      "step": 37500
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 4.533675862839271e-05,
+      "loss": 1.4643,
+      "step": 38000
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 4.198592650508209e-05,
+      "loss": 1.4441,
+      "step": 38500
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 3.863509438177147e-05,
+      "loss": 1.3854,
+      "step": 39000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 3.528426225846085e-05,
+      "loss": 1.3919,
+      "step": 39500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 3.193343013515022e-05,
+      "loss": 1.3963,
+      "step": 40000
+    },
+    {
+      "epoch": 6.25,
+      "eval_gen_len": 13.4713,
+      "eval_loss": 1.8532978296279907,
+      "eval_rouge1": 40.1839,
+      "eval_rouge2": 21.4959,
+      "eval_rougeL": 37.5371,
+      "eval_rougeLsum": 37.5414,
+      "eval_runtime": 113.6133,
+      "eval_samples_per_second": 26.405,
+      "eval_steps_per_second": 3.301,
+      "step": 40000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 2.8582598011839604e-05,
+      "loss": 1.379,
+      "step": 40500
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 2.5231765888528982e-05,
+      "loss": 1.3968,
+      "step": 41000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 2.188093376521836e-05,
+      "loss": 1.3814,
+      "step": 41500
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 1.8530101641907737e-05,
+      "loss": 1.3891,
+      "step": 42000
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 1.5179269518597117e-05,
+      "loss": 1.3787,
+      "step": 42500
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 1.1828437395286495e-05,
+      "loss": 1.386,
+      "step": 43000
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 8.477605271975873e-06,
+      "loss": 1.3927,
+      "step": 43500
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 5.126773148665251e-06,
+      "loss": 1.368,
+      "step": 44000
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 1.7759410253546295e-06,
+      "loss": 1.375,
+      "step": 44500
+    },
+    {
+      "epoch": 7.0,
+      "step": 44765,
+      "total_flos": 7.978118776281907e+16,
+      "train_loss": 1.7918549016882,
+      "train_runtime": 13775.2907,
+      "train_samples_per_second": 25.997,
+      "train_steps_per_second": 3.25
+    }
+  ],
+  "max_steps": 44765,
+  "num_train_epochs": 7,
+  "total_flos": 7.978118776281907e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a646a42a43e6a11c8a7a3ca672b0cf8e999346bdec9924c88ff6088473efb0a0
+size 3183