Initial commit

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-qa-0.0003
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: it5/datasets qa
+      type: it5/datasets
+      args: qa
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 74.2234
 ---
+
+<!-- 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-qa-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 qa dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8225
+- Rouge1: 74.2234
+- Rouge2: 40.5909
+- Rougel: 74.1327
+- Rougelsum: 74.2081
+- Gen Len: 4.7055
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.1164        | 0.8   | 5000  | 0.8244          | 66.4678 | 35.3554 | 66.4543 | 66.4522   | 4.541   |
+| 0.9097        | 1.59  | 10000 | 0.7299          | 70.0574 | 37.5535 | 69.9512 | 70.0084   | 4.5548  |
+| 0.6637        | 2.39  | 15000 | 0.7314          | 72.0767 | 39.2263 | 72.0257 | 72.0473   | 4.703   |
+| 0.5015        | 3.19  | 20000 | 0.7147          | 73.0185 | 39.9998 | 72.9347 | 72.9576   | 4.75    |
+| 0.5101        | 3.99  | 25000 | 0.7055          | 73.7898 | 40.5481 | 73.7235 | 73.7901   | 4.8728  |
+| 0.3903        | 4.78  | 30000 | 0.7442          | 74.0845 | 39.9841 | 74.0172 | 74.0635   | 4.5938  |
+| 0.2993        | 5.58  | 35000 | 0.8184          | 73.8405 | 40.2569 | 73.7756 | 73.7972   | 4.7412  |
+| 0.2227        | 6.38  | 40000 | 0.8278          | 74.0159 | 40.6403 | 73.9412 | 73.9722   | 4.742   |
+
+
+### 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": 4.7055,
+    "eval_loss": 0.8224949240684509,
+    "eval_rouge1": 74.2234,
+    "eval_rouge2": 40.5909,
+    "eval_rougeL": 74.1327,
+    "eval_rougeLsum": 74.2081,
+    "eval_runtime": 110.8699,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 36.078,
+    "eval_steps_per_second": 4.51,
+    "train_loss": 0.639304427944139,
+    "train_runtime": 13849.1505,
+    "train_samples": 50159,
+    "train_samples_per_second": 25.353,
+    "train_steps_per_second": 3.169
+}

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": 4.7055,
+    "eval_loss": 0.8224949240684509,
+    "eval_rouge1": 74.2234,
+    "eval_rouge2": 40.5909,
+    "eval_rougeL": 74.1327,
+    "eval_rougeLsum": 74.2081,
+    "eval_runtime": 110.8699,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 36.078,
+    "eval_steps_per_second": 4.51
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e915ac57bb558ddb9377c6dd1f2994d71525b430eb0b4f5a25926c3a157bb09
+size 569246164

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e95dbad8bab6a16f778003f3569f028d7dbd9647dea4866231543eeaebb408
+size 569387035

runs/Apr26_12-34-52_pg-gpu27/1650969352.401718/events.out.tfevents.1650969352.pg-gpu27.29084.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bf12be4326a32ac3ee73b11225826813a84f6458ad8d178ae3cf70ed6bbe74
+size 5127

runs/Apr26_12-34-52_pg-gpu27/events.out.tfevents.1650969352.pg-gpu27.29084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3084b5f9113e39251cc00d5a2385ed5c019be51844eb874cfbe707a457f6a9dd
+size 22059

runs/Apr26_12-34-52_pg-gpu27/events.out.tfevents.1650983316.pg-gpu27.29084.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d481f04287119f49c15b2fd1a0021bcdddd851ed69235a8e65aeb6cf84d18cc
+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 sha256:2cbbcf69da0bb6912d11e103dcefa8680c366bb0e6cff3eaa0b5fadabd25ae89
+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": 0.639304427944139,
+    "train_runtime": 13849.1505,
+    "train_samples": 50159,
+    "train_samples_per_second": 25.353,
+    "train_steps_per_second": 3.169
+}

trainer_state.json

@@ -0,0 +1,651 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 43890,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002965823650034176,
+      "loss": 3.7122,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00029316473000683526,
+      "loss": 1.7581,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002897470950102529,
+      "loss": 1.5341,
+      "step": 1500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00028632946001367054,
+      "loss": 1.4748,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002829118250170881,
+      "loss": 1.3464,
+      "step": 2500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002794941900205058,
+      "loss": 1.2892,
+      "step": 3000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002760765550239234,
+      "loss": 1.2375,
+      "step": 3500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00027265892002734105,
+      "loss": 1.2408,
+      "step": 4000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002692412850307587,
+      "loss": 1.1577,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002658236500341763,
+      "loss": 1.1164,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8,
+      "eval_gen_len": 4.541,
+      "eval_loss": 0.8244166970252991,
+      "eval_rouge1": 66.4678,
+      "eval_rouge2": 35.3554,
+      "eval_rougeL": 66.4543,
+      "eval_rougeLsum": 66.4522,
+      "eval_runtime": 109.1952,
+      "eval_samples_per_second": 36.632,
+      "eval_steps_per_second": 4.579,
+      "step": 5000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00026240601503759397,
+      "loss": 1.1345,
+      "step": 5500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002589883800410116,
+      "loss": 1.1116,
+      "step": 6000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00025557074504442925,
+      "loss": 1.0336,
+      "step": 6500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0002521531100478469,
+      "loss": 0.9108,
+      "step": 7000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002487354750512645,
+      "loss": 0.92,
+      "step": 7500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002453178400546821,
+      "loss": 0.9071,
+      "step": 8000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00024190020505809978,
+      "loss": 0.8936,
+      "step": 8500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002384825700615174,
+      "loss": 0.888,
+      "step": 9000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00023506493506493504,
+      "loss": 0.8847,
+      "step": 9500
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00023164730006835268,
+      "loss": 0.9097,
+      "step": 10000
+    },
+    {
+      "epoch": 1.59,
+      "eval_gen_len": 4.5548,
+      "eval_loss": 0.7299422025680542,
+      "eval_rouge1": 70.0574,
+      "eval_rouge2": 37.5535,
+      "eval_rougeL": 69.9512,
+      "eval_rougeLsum": 70.0084,
+      "eval_runtime": 106.5141,
+      "eval_samples_per_second": 37.554,
+      "eval_steps_per_second": 4.694,
+      "step": 10000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00022822966507177032,
+      "loss": 0.8895,
+      "step": 10500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00022481203007518796,
+      "loss": 0.8544,
+      "step": 11000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0002213943950786056,
+      "loss": 0.8807,
+      "step": 11500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00021797676008202322,
+      "loss": 0.8451,
+      "step": 12000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00021455912508544086,
+      "loss": 0.82,
+      "step": 12500
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00021114149008885847,
+      "loss": 0.6878,
+      "step": 13000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00020772385509227614,
+      "loss": 0.6759,
+      "step": 13500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00020430622009569378,
+      "loss": 0.6998,
+      "step": 14000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.0002008885850991114,
+      "loss": 0.6751,
+      "step": 14500
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.00019747095010252903,
+      "loss": 0.6637,
+      "step": 15000
+    },
+    {
+      "epoch": 2.39,
+      "eval_gen_len": 4.703,
+      "eval_loss": 0.7314157485961914,
+      "eval_rouge1": 72.0767,
+      "eval_rouge2": 39.2263,
+      "eval_rougeL": 72.0257,
+      "eval_rougeLsum": 72.0473,
+      "eval_runtime": 110.4087,
+      "eval_samples_per_second": 36.229,
+      "eval_steps_per_second": 4.529,
+      "step": 15000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00019405331510594667,
+      "loss": 0.6698,
+      "step": 15500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0001906356801093643,
+      "loss": 0.672,
+      "step": 16000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00018721804511278195,
+      "loss": 0.6431,
+      "step": 16500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.00018380041011619957,
+      "loss": 0.6653,
+      "step": 17000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.0001803827751196172,
+      "loss": 0.6824,
+      "step": 17500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.00017696514012303485,
+      "loss": 0.6668,
+      "step": 18000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.00017354750512645246,
+      "loss": 0.6318,
+      "step": 18500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.0001701298701298701,
+      "loss": 0.5934,
+      "step": 19000
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.00016671223513328777,
+      "loss": 0.5086,
+      "step": 19500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.00016329460013670539,
+      "loss": 0.5015,
+      "step": 20000
+    },
+    {
+      "epoch": 3.19,
+      "eval_gen_len": 4.75,
+      "eval_loss": 0.7147404551506042,
+      "eval_rouge1": 73.0185,
+      "eval_rouge2": 39.9998,
+      "eval_rougeL": 72.9347,
+      "eval_rougeLsum": 72.9576,
+      "eval_runtime": 106.9579,
+      "eval_samples_per_second": 37.398,
+      "eval_steps_per_second": 4.675,
+      "step": 20000
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00015987696514012303,
+      "loss": 0.4909,
+      "step": 20500
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 0.00015645933014354064,
+      "loss": 0.5114,
+      "step": 21000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.00015304169514695828,
+      "loss": 0.5314,
+      "step": 21500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 0.00014962406015037592,
+      "loss": 0.5089,
+      "step": 22000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.00014620642515379356,
+      "loss": 0.5133,
+      "step": 22500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.0001427887901572112,
+      "loss": 0.5057,
+      "step": 23000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.00013937115516062882,
+      "loss": 0.5181,
+      "step": 23500
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.00013595352016404648,
+      "loss": 0.4826,
+      "step": 24000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.0001325358851674641,
+      "loss": 0.497,
+      "step": 24500
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.00012911825017088174,
+      "loss": 0.5101,
+      "step": 25000
+    },
+    {
+      "epoch": 3.99,
+      "eval_gen_len": 4.8728,
+      "eval_loss": 0.7054756283760071,
+      "eval_rouge1": 73.7898,
+      "eval_rouge2": 40.5481,
+      "eval_rougeL": 73.7235,
+      "eval_rougeLsum": 73.7901,
+      "eval_runtime": 110.0456,
+      "eval_samples_per_second": 36.349,
+      "eval_steps_per_second": 4.544,
+      "step": 25000
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 0.00012570061517429938,
+      "loss": 0.3961,
+      "step": 25500
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00012228298017771702,
+      "loss": 0.3725,
+      "step": 26000
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00011886534518113465,
+      "loss": 0.3698,
+      "step": 26500
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.00011544771018455227,
+      "loss": 0.3946,
+      "step": 27000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 0.00011203007518796991,
+      "loss": 0.4009,
+      "step": 27500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.00010861244019138756,
+      "loss": 0.391,
+      "step": 28000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00010519480519480518,
+      "loss": 0.3787,
+      "step": 28500
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 0.00010177717019822282,
+      "loss": 0.3736,
+      "step": 29000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 9.835953520164045e-05,
+      "loss": 0.3842,
+      "step": 29500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 9.494190020505809e-05,
+      "loss": 0.3903,
+      "step": 30000
+    },
+    {
+      "epoch": 4.78,
+      "eval_gen_len": 4.5938,
+      "eval_loss": 0.7442232370376587,
+      "eval_rouge1": 74.0845,
+      "eval_rouge2": 39.9841,
+      "eval_rougeL": 74.0172,
+      "eval_rougeLsum": 74.0635,
+      "eval_runtime": 110.762,
+      "eval_samples_per_second": 36.113,
+      "eval_steps_per_second": 4.514,
+      "step": 30000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 9.152426520847573e-05,
+      "loss": 0.3945,
+      "step": 30500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 8.810663021189336e-05,
+      "loss": 0.4128,
+      "step": 31000
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 8.468899521531099e-05,
+      "loss": 0.363,
+      "step": 31500
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 8.127136021872864e-05,
+      "loss": 0.3144,
+      "step": 32000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 7.785372522214627e-05,
+      "loss": 0.3106,
+      "step": 32500
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 7.44360902255639e-05,
+      "loss": 0.2982,
+      "step": 33000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 7.101845522898154e-05,
+      "loss": 0.3016,
+      "step": 33500
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 6.760082023239918e-05,
+      "loss": 0.3095,
+      "step": 34000
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 6.41831852358168e-05,
+      "loss": 0.2863,
+      "step": 34500
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 6.076555023923445e-05,
+      "loss": 0.2993,
+      "step": 35000
+    },
+    {
+      "epoch": 5.58,
+      "eval_gen_len": 4.7412,
+      "eval_loss": 0.8183711171150208,
+      "eval_rouge1": 73.8405,
+      "eval_rouge2": 40.2569,
+      "eval_rougeL": 73.7756,
+      "eval_rougeLsum": 73.7972,
+      "eval_runtime": 109.7934,
+      "eval_samples_per_second": 36.432,
+      "eval_steps_per_second": 4.554,
+      "step": 35000
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 5.734791524265208e-05,
+      "loss": 0.2975,
+      "step": 35500
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 5.393028024606972e-05,
+      "loss": 0.3014,
+      "step": 36000
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 5.051264524948735e-05,
+      "loss": 0.2996,
+      "step": 36500
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 4.7095010252904986e-05,
+      "loss": 0.3068,
+      "step": 37000
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 4.367737525632262e-05,
+      "loss": 0.2993,
+      "step": 37500
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 4.025974025974026e-05,
+      "loss": 0.2447,
+      "step": 38000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 3.684210526315789e-05,
+      "loss": 0.2379,
+      "step": 38500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 3.342447026657553e-05,
+      "loss": 0.2447,
+      "step": 39000
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 3.0006835269993163e-05,
+      "loss": 0.2452,
+      "step": 39500
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 2.65892002734108e-05,
+      "loss": 0.2227,
+      "step": 40000
+    },
+    {
+      "epoch": 6.38,
+      "eval_gen_len": 4.742,
+      "eval_loss": 0.8277584910392761,
+      "eval_rouge1": 74.0159,
+      "eval_rouge2": 40.6403,
+      "eval_rougeL": 73.9412,
+      "eval_rougeLsum": 73.9722,
+      "eval_runtime": 108.0867,
+      "eval_samples_per_second": 37.007,
+      "eval_steps_per_second": 4.626,
+      "step": 40000
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 2.3171565276828434e-05,
+      "loss": 0.2331,
+      "step": 40500
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 1.9753930280246068e-05,
+      "loss": 0.2374,
+      "step": 41000
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 1.6336295283663705e-05,
+      "loss": 0.2462,
+      "step": 41500
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 1.2918660287081339e-05,
+      "loss": 0.24,
+      "step": 42000
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 9.501025290498975e-06,
+      "loss": 0.2217,
+      "step": 42500
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 6.083390293916609e-06,
+      "loss": 0.2283,
+      "step": 43000
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 2.6657552973342446e-06,
+      "loss": 0.2345,
+      "step": 43500
+    },
+    {
+      "epoch": 7.0,
+      "step": 43890,
+      "total_flos": 8.113234147780608e+16,
+      "train_loss": 0.639304427944139,
+      "train_runtime": 13849.1505,
+      "train_samples_per_second": 25.353,
+      "train_steps_per_second": 3.169
+    }
+  ],
+  "max_steps": 43890,
+  "num_train_epochs": 7,
+  "total_flos": 8.113234147780608e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c2f097975531c8e6b1a18a860ae8bb85d0ad0373722e5b0d61e4b27dbedb65
+size 3183