Initial commit

README.md

@@ -1,3 +1,88 @@
 ---
-license: apache-2.0
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- it5/datasets
+metrics:
+- rouge
+model-index:
+- name: it5-efficient-small-el32-st_g2r-0.0003
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: it5/datasets st_g2r
+      type: it5/datasets
+      args: st_g2r
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 29.8455
 ---
+
+<!-- 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-st_g2r-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 st_g2r dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6892
+- Rouge1: 29.8455
+- Rouge2: 11.735
+- Rougel: 26.6048
+- Rougelsum: 26.8553
+- Gen Len: 14.6131
+
+## 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: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 3.2179        | 0.74  | 5000  | 2.7813          | 25.8006 | 9.3551  | 23.386  | 23.5287   | 13.5337 |
+| 2.9248        | 1.49  | 10000 | 2.6914          | 27.0409 | 10.0228 | 24.4581 | 24.6197   | 13.243  |
+| 2.6813        | 2.23  | 15000 | 2.6462          | 27.5333 | 10.3641 | 24.8696 | 25.0564   | 14.3052 |
+| 2.691         | 2.98  | 20000 | 2.6205          | 28.3681 | 10.8961 | 25.5144 | 25.722    | 14.5279 |
+| 2.5127        | 3.72  | 25000 | 2.6043          | 28.5979 | 11.0477 | 25.759  | 25.9605   | 14.0721 |
+| 2.3331        | 4.47  | 30000 | 2.6283          | 28.9106 | 11.3727 | 25.9338 | 26.1387   | 14.4519 |
+| 2.2034        | 5.21  | 35000 | 2.6400          | 29.099  | 11.2376 | 26.1221 | 26.3568   | 13.8715 |
+| 2.2137        | 5.96  | 40000 | 2.6340          | 29.2641 | 11.3565 | 26.2012 | 26.4214   | 14.5981 |
+| 2.1104        | 6.7   | 45000 | 2.6362          | 29.6204 | 11.6807 | 26.5976 | 26.8261   | 13.888  |
+| 2.003         | 7.45  | 50000 | 2.6541          | 29.5679 | 11.6334 | 26.5095 | 26.7418   | 14.2246 |
+| 1.8955        | 8.19  | 55000 | 2.6940          | 29.6748 | 11.5897 | 26.4862 | 26.7581   | 14.3902 |
+| 1.912         | 8.94  | 60000 | 2.6883          | 29.7285 | 11.6448 | 26.5368 | 26.7806   | 14.3574 |
+| 1.8581        | 9.68  | 65000 | 2.6874          | 29.7373 | 11.6532 | 26.4799 | 26.738    | 14.3821 |
+
+
+### 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": 10.0,
+    "eval_gen_len": 14.6131,
+    "eval_loss": 2.689188003540039,
+    "eval_rouge1": 29.8455,
+    "eval_rouge2": 11.735,
+    "eval_rougeL": 26.6048,
+    "eval_rougeLsum": 26.8553,
+    "eval_runtime": 552.946,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 18.085,
+    "eval_steps_per_second": 2.261,
+    "train_loss": 2.3931242498576544,
+    "train_runtime": 39455.2858,
+    "train_samples": 53701,
+    "train_samples_per_second": 13.611,
+    "train_steps_per_second": 1.701
+}

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": 10.0,
+    "eval_gen_len": 14.6131,
+    "eval_loss": 2.689188003540039,
+    "eval_rouge1": 29.8455,
+    "eval_rouge2": 11.735,
+    "eval_rougeL": 26.6048,
+    "eval_rougeLsum": 26.8553,
+    "eval_runtime": 552.946,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 18.085,
+    "eval_steps_per_second": 2.261
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e1d91c847c60760a7770676b10d29ebfd229411c9278ababc4ab0c8a663994
+size 569246164

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d916bfc53276a0962897350664f25cd6c84b7e043d2a264bf537efc8c0b174
+size 569387035

runs/Apr28_19-50-08_pg-gpu19/1651168255.0301058/events.out.tfevents.1651168255.pg-gpu19.30521.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dd64c9d3529fd827989904700e98107bc3ff7cd7844d0ddc15ac93221b6b56
+size 5139

runs/Apr28_19-50-08_pg-gpu19/events.out.tfevents.1651168254.pg-gpu19.30521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5e4985f2058f1d3bf0ef4161ab23b82d91f6352e02ea3858274aff47918339
+size 32267

runs/Apr28_19-50-08_pg-gpu19/events.out.tfevents.1651208265.pg-gpu19.30521.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21252d83eed2d6ca0239338d6dcdc8d3a1cd40938e65bb0d68af464a4587be9
+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:ef441e6cc8ae3611b93395f2a4cc7b146cb5f1259ba16d90be8c964d7a44e369
+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": 10.0,
+    "train_loss": 2.3931242498576544,
+    "train_runtime": 39455.2858,
+    "train_samples": 53701,
+    "train_samples_per_second": 13.611,
+    "train_steps_per_second": 1.701
+}

trainer_state.json

@@ -0,0 +1,998 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 67130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000297765529569492,
+      "loss": 4.2198,
+      "step": 500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00029553105913898405,
+      "loss": 3.702,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00029329658870847603,
+      "loss": 3.5122,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029106211827796807,
+      "loss": 3.4147,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002888276478474601,
+      "loss": 3.3907,
+      "step": 2500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002865931774169522,
+      "loss": 3.3163,
+      "step": 3000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002843587069864442,
+      "loss": 3.253,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002821242365559362,
+      "loss": 3.248,
+      "step": 4000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00027988976612542825,
+      "loss": 3.2532,
+      "step": 4500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002776552956949203,
+      "loss": 3.2179,
+      "step": 5000
+    },
+    {
+      "epoch": 0.74,
+      "eval_gen_len": 13.5337,
+      "eval_loss": 2.7812678813934326,
+      "eval_rouge1": 25.8006,
+      "eval_rouge2": 9.3551,
+      "eval_rougeL": 23.386,
+      "eval_rougeLsum": 23.5287,
+      "eval_runtime": 531.59,
+      "eval_samples_per_second": 18.811,
+      "eval_steps_per_second": 2.351,
+      "step": 5000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002754208252644123,
+      "loss": 3.1697,
+      "step": 5500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002731863548339043,
+      "loss": 3.1744,
+      "step": 6000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00027095188440339634,
+      "loss": 3.1526,
+      "step": 6500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002687174139728884,
+      "loss": 3.0155,
+      "step": 7000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0002664829435423804,
+      "loss": 2.9585,
+      "step": 7500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00026424847311187245,
+      "loss": 2.9227,
+      "step": 8000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0002620140026813645,
+      "loss": 2.9469,
+      "step": 8500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00025977953225085653,
+      "loss": 2.9259,
+      "step": 9000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00025754506182034857,
+      "loss": 2.9517,
+      "step": 9500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002553105913898406,
+      "loss": 2.9248,
+      "step": 10000
+    },
+    {
+      "epoch": 1.49,
+      "eval_gen_len": 13.243,
+      "eval_loss": 2.691446542739868,
+      "eval_rouge1": 27.0409,
+      "eval_rouge2": 10.0228,
+      "eval_rougeL": 24.4581,
+      "eval_rougeLsum": 24.6197,
+      "eval_runtime": 528.3278,
+      "eval_samples_per_second": 18.928,
+      "eval_steps_per_second": 2.366,
+      "step": 10000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002530761209593326,
+      "loss": 2.9173,
+      "step": 10500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002508416505288246,
+      "loss": 2.923,
+      "step": 11000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00024860718009831666,
+      "loss": 2.9318,
+      "step": 11500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002463727096678087,
+      "loss": 2.901,
+      "step": 12000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00024413823923730073,
+      "loss": 2.8678,
+      "step": 12500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00024190376880679277,
+      "loss": 2.8576,
+      "step": 13000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0002396692983762848,
+      "loss": 2.8734,
+      "step": 13500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00023743482794577684,
+      "loss": 2.6712,
+      "step": 14000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00023520035751526885,
+      "loss": 2.6779,
+      "step": 14500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.0002329658870847609,
+      "loss": 2.6813,
+      "step": 15000
+    },
+    {
+      "epoch": 2.23,
+      "eval_gen_len": 14.3052,
+      "eval_loss": 2.6461832523345947,
+      "eval_rouge1": 27.5333,
+      "eval_rouge2": 10.3641,
+      "eval_rougeL": 24.8696,
+      "eval_rougeLsum": 25.0564,
+      "eval_runtime": 527.1253,
+      "eval_samples_per_second": 18.971,
+      "eval_steps_per_second": 2.371,
+      "step": 15000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00023073141665425293,
+      "loss": 2.6964,
+      "step": 15500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00022849694622374496,
+      "loss": 2.6816,
+      "step": 16000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.000226262475793237,
+      "loss": 2.669,
+      "step": 16500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.000224028005362729,
+      "loss": 2.6871,
+      "step": 17000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.00022179353493222105,
+      "loss": 2.6783,
+      "step": 17500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.00021955906450171308,
+      "loss": 2.7131,
+      "step": 18000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00021732459407120512,
+      "loss": 2.7029,
+      "step": 18500
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00021509012364069713,
+      "loss": 2.7081,
+      "step": 19000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.00021285565321018917,
+      "loss": 2.6989,
+      "step": 19500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0002106211827796812,
+      "loss": 2.691,
+      "step": 20000
+    },
+    {
+      "epoch": 2.98,
+      "eval_gen_len": 14.5279,
+      "eval_loss": 2.6205477714538574,
+      "eval_rouge1": 28.3681,
+      "eval_rouge2": 10.8961,
+      "eval_rougeL": 25.5144,
+      "eval_rougeLsum": 25.722,
+      "eval_runtime": 530.0749,
+      "eval_samples_per_second": 18.865,
+      "eval_steps_per_second": 2.358,
+      "step": 20000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.00020838671234917324,
+      "loss": 2.5377,
+      "step": 20500
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.00020615224191866528,
+      "loss": 2.4832,
+      "step": 21000
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.0002039177714881573,
+      "loss": 2.4958,
+      "step": 21500
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.00020168330105764932,
+      "loss": 2.4949,
+      "step": 22000
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 0.00019944883062714136,
+      "loss": 2.4796,
+      "step": 22500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.0001972143601966334,
+      "loss": 2.5323,
+      "step": 23000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0001949798897661254,
+      "loss": 2.515,
+      "step": 23500
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.00019274541933561744,
+      "loss": 2.5291,
+      "step": 24000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.00019051094890510948,
+      "loss": 2.5206,
+      "step": 24500
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.00018827647847460152,
+      "loss": 2.5127,
+      "step": 25000
+    },
+    {
+      "epoch": 3.72,
+      "eval_gen_len": 14.0721,
+      "eval_loss": 2.6042990684509277,
+      "eval_rouge1": 28.5979,
+      "eval_rouge2": 11.0477,
+      "eval_rougeL": 25.759,
+      "eval_rougeLsum": 25.9605,
+      "eval_runtime": 523.9369,
+      "eval_samples_per_second": 19.086,
+      "eval_steps_per_second": 2.386,
+      "step": 25000
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00018604200804409355,
+      "loss": 2.5203,
+      "step": 25500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.00018380753761358556,
+      "loss": 2.5064,
+      "step": 26000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.0001815730671830776,
+      "loss": 2.4892,
+      "step": 26500
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.00017933859675256964,
+      "loss": 2.4728,
+      "step": 27000
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 0.00017710412632206167,
+      "loss": 2.319,
+      "step": 27500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.00017486965589155368,
+      "loss": 2.3135,
+      "step": 28000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.00017263518546104572,
+      "loss": 2.339,
+      "step": 28500
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.00017040071503053776,
+      "loss": 2.3818,
+      "step": 29000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 0.0001681662446000298,
+      "loss": 2.3551,
+      "step": 29500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.00016593177416952183,
+      "loss": 2.3331,
+      "step": 30000
+    },
+    {
+      "epoch": 4.47,
+      "eval_gen_len": 14.4519,
+      "eval_loss": 2.6282742023468018,
+      "eval_rouge1": 28.9106,
+      "eval_rouge2": 11.3727,
+      "eval_rougeL": 25.9338,
+      "eval_rougeLsum": 26.1387,
+      "eval_runtime": 544.5243,
+      "eval_samples_per_second": 18.365,
+      "eval_steps_per_second": 2.296,
+      "step": 30000
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.00016369730373901384,
+      "loss": 2.3632,
+      "step": 30500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 0.00016146283330850588,
+      "loss": 2.3592,
+      "step": 31000
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 0.00015922836287799791,
+      "loss": 2.3468,
+      "step": 31500
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 0.00015699389244748995,
+      "loss": 2.361,
+      "step": 32000
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 0.00015475942201698196,
+      "loss": 2.3444,
+      "step": 32500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.000152524951586474,
+      "loss": 2.3435,
+      "step": 33000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.00015029048115596604,
+      "loss": 2.3755,
+      "step": 33500
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.00014805601072545804,
+      "loss": 2.2407,
+      "step": 34000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 0.00014582154029495008,
+      "loss": 2.2036,
+      "step": 34500
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.00014358706986444212,
+      "loss": 2.2034,
+      "step": 35000
+    },
+    {
+      "epoch": 5.21,
+      "eval_gen_len": 13.8715,
+      "eval_loss": 2.6400413513183594,
+      "eval_rouge1": 29.099,
+      "eval_rouge2": 11.2376,
+      "eval_rougeL": 26.1221,
+      "eval_rougeLsum": 26.3568,
+      "eval_runtime": 529.9312,
+      "eval_samples_per_second": 18.87,
+      "eval_steps_per_second": 2.359,
+      "step": 35000
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.00014135259943393416,
+      "loss": 2.1988,
+      "step": 35500
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.0001391181290034262,
+      "loss": 2.2228,
+      "step": 36000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 0.0001368836585729182,
+      "loss": 2.2078,
+      "step": 36500
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 0.00013464918814241024,
+      "loss": 2.2399,
+      "step": 37000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 0.00013241471771190228,
+      "loss": 2.2287,
+      "step": 37500
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 0.0001301802472813943,
+      "loss": 2.2174,
+      "step": 38000
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 0.00012794577685088632,
+      "loss": 2.2216,
+      "step": 38500
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 0.00012571130642037836,
+      "loss": 2.2196,
+      "step": 39000
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 0.00012347683598987037,
+      "loss": 2.2432,
+      "step": 39500
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00012124236555936242,
+      "loss": 2.2137,
+      "step": 40000
+    },
+    {
+      "epoch": 5.96,
+      "eval_gen_len": 14.5981,
+      "eval_loss": 2.634021759033203,
+      "eval_rouge1": 29.2641,
+      "eval_rouge2": 11.3565,
+      "eval_rougeL": 26.2012,
+      "eval_rougeLsum": 26.4214,
+      "eval_runtime": 532.2281,
+      "eval_samples_per_second": 18.789,
+      "eval_steps_per_second": 2.349,
+      "step": 40000
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.00011900789512885446,
+      "loss": 2.1445,
+      "step": 40500
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.00011677342469834648,
+      "loss": 2.0664,
+      "step": 41000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.00011453895426783852,
+      "loss": 2.094,
+      "step": 41500
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.00011230448383733054,
+      "loss": 2.1048,
+      "step": 42000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00011007001340682258,
+      "loss": 2.1001,
+      "step": 42500
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 0.0001078355429763146,
+      "loss": 2.1141,
+      "step": 43000
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 0.00010560107254580664,
+      "loss": 2.0866,
+      "step": 43500
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.00010336660211529866,
+      "loss": 2.0916,
+      "step": 44000
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 0.0001011321316847907,
+      "loss": 2.1056,
+      "step": 44500
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 9.889766125428273e-05,
+      "loss": 2.1104,
+      "step": 45000
+    },
+    {
+      "epoch": 6.7,
+      "eval_gen_len": 13.888,
+      "eval_loss": 2.6362199783325195,
+      "eval_rouge1": 29.6204,
+      "eval_rouge2": 11.6807,
+      "eval_rougeL": 26.5976,
+      "eval_rougeLsum": 26.8261,
+      "eval_runtime": 537.398,
+      "eval_samples_per_second": 18.608,
+      "eval_steps_per_second": 2.326,
+      "step": 45000
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 9.666319082377476e-05,
+      "loss": 2.1206,
+      "step": 45500
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 9.44287203932668e-05,
+      "loss": 2.1124,
+      "step": 46000
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 9.219424996275882e-05,
+      "loss": 2.1211,
+      "step": 46500
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 8.995977953225085e-05,
+      "loss": 2.1063,
+      "step": 47000
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 8.772530910174288e-05,
+      "loss": 1.9698,
+      "step": 47500
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 8.549083867123491e-05,
+      "loss": 1.9693,
+      "step": 48000
+    },
+    {
+      "epoch": 7.22,
+      "learning_rate": 8.325636824072694e-05,
+      "loss": 2.0098,
+      "step": 48500
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 8.102189781021897e-05,
+      "loss": 1.9976,
+      "step": 49000
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 7.8787427379711e-05,
+      "loss": 2.0059,
+      "step": 49500
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 7.655295694920303e-05,
+      "loss": 2.003,
+      "step": 50000
+    },
+    {
+      "epoch": 7.45,
+      "eval_gen_len": 14.2246,
+      "eval_loss": 2.6541028022766113,
+      "eval_rouge1": 29.5679,
+      "eval_rouge2": 11.6334,
+      "eval_rougeL": 26.5095,
+      "eval_rougeLsum": 26.7418,
+      "eval_runtime": 534.455,
+      "eval_samples_per_second": 18.711,
+      "eval_steps_per_second": 2.339,
+      "step": 50000
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 7.431848651869506e-05,
+      "loss": 1.9752,
+      "step": 50500
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 7.20840160881871e-05,
+      "loss": 2.0409,
+      "step": 51000
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 6.984954565767912e-05,
+      "loss": 2.0181,
+      "step": 51500
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 6.761507522717115e-05,
+      "loss": 1.9967,
+      "step": 52000
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 6.538060479666319e-05,
+      "loss": 1.9883,
+      "step": 52500
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 6.314613436615521e-05,
+      "loss": 2.0096,
+      "step": 53000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 6.091166393564725e-05,
+      "loss": 2.0075,
+      "step": 53500
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 5.867719350513928e-05,
+      "loss": 1.9409,
+      "step": 54000
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 5.6442723074631304e-05,
+      "loss": 1.9271,
+      "step": 54500
+    },
+    {
+      "epoch": 8.19,
+      "learning_rate": 5.4208252644123334e-05,
+      "loss": 1.8955,
+      "step": 55000
+    },
+    {
+      "epoch": 8.19,
+      "eval_gen_len": 14.3902,
+      "eval_loss": 2.694044828414917,
+      "eval_rouge1": 29.6748,
+      "eval_rouge2": 11.5897,
+      "eval_rougeL": 26.4862,
+      "eval_rougeLsum": 26.7581,
+      "eval_runtime": 535.4767,
+      "eval_samples_per_second": 18.675,
+      "eval_steps_per_second": 2.334,
+      "step": 55000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 5.1973782213615364e-05,
+      "loss": 1.9114,
+      "step": 55500
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 4.9739311783107394e-05,
+      "loss": 1.9337,
+      "step": 56000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 4.7504841352599425e-05,
+      "loss": 1.9088,
+      "step": 56500
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 4.5270370922091455e-05,
+      "loss": 1.9104,
+      "step": 57000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 4.303590049158349e-05,
+      "loss": 1.9167,
+      "step": 57500
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 4.080143006107552e-05,
+      "loss": 1.9146,
+      "step": 58000
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 3.856695963056755e-05,
+      "loss": 1.8965,
+      "step": 58500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 3.633248920005958e-05,
+      "loss": 1.9186,
+      "step": 59000
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 3.409801876955161e-05,
+      "loss": 1.9153,
+      "step": 59500
+    },
+    {
+      "epoch": 8.94,
+      "learning_rate": 3.186354833904364e-05,
+      "loss": 1.912,
+      "step": 60000
+    },
+    {
+      "epoch": 8.94,
+      "eval_gen_len": 14.3574,
+      "eval_loss": 2.6882503032684326,
+      "eval_rouge1": 29.7285,
+      "eval_rouge2": 11.6448,
+      "eval_rougeL": 26.5368,
+      "eval_rougeLsum": 26.7806,
+      "eval_runtime": 531.6791,
+      "eval_samples_per_second": 18.808,
+      "eval_steps_per_second": 2.351,
+      "step": 60000
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 2.9629077908535672e-05,
+      "loss": 1.9182,
+      "step": 60500
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 2.7394607478027705e-05,
+      "loss": 1.8865,
+      "step": 61000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 2.5160137047519735e-05,
+      "loss": 1.8585,
+      "step": 61500
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 2.2925666617011765e-05,
+      "loss": 1.8478,
+      "step": 62000
+    },
+    {
+      "epoch": 9.31,
+      "learning_rate": 2.0691196186503795e-05,
+      "loss": 1.8604,
+      "step": 62500
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 1.845672575599583e-05,
+      "loss": 1.8599,
+      "step": 63000
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 1.622225532548786e-05,
+      "loss": 1.8661,
+      "step": 63500
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 1.3987784894979889e-05,
+      "loss": 1.8651,
+      "step": 64000
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 1.1753314464471919e-05,
+      "loss": 1.8657,
+      "step": 64500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 9.518844033963949e-06,
+      "loss": 1.8581,
+      "step": 65000
+    },
+    {
+      "epoch": 9.68,
+      "eval_gen_len": 14.3821,
+      "eval_loss": 2.687427282333374,
+      "eval_rouge1": 29.7373,
+      "eval_rouge2": 11.6532,
+      "eval_rougeL": 26.4799,
+      "eval_rougeLsum": 26.738,
+      "eval_runtime": 539.441,
+      "eval_samples_per_second": 18.538,
+      "eval_steps_per_second": 2.317,
+      "step": 65000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 7.284373603455981e-06,
+      "loss": 1.8359,
+      "step": 65500
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 5.04990317294801e-06,
+      "loss": 1.8372,
+      "step": 66000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 2.815432742440042e-06,
+      "loss": 1.8536,
+      "step": 66500
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 5.809623119320721e-07,
+      "loss": 1.8537,
+      "step": 67000
+    },
+    {
+      "epoch": 10.0,
+      "step": 67130,
+      "total_flos": 2.0718221980336128e+17,
+      "train_loss": 2.3931242498576544,
+      "train_runtime": 39455.2858,
+      "train_samples_per_second": 13.611,
+      "train_steps_per_second": 1.701
+    }
+  ],
+  "max_steps": 67130,
+  "num_train_epochs": 10,
+  "total_flos": 2.0718221980336128e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bad04f98de5b180ebc52c011310864903b4e631ee46b546b2f949926b7b5502
+size 3183