Model

README.md

@@ -1,3 +1,100 @@
 ---
+tags:
+- text2text-generation
+- definition-modeling
+metrics:
+- rouge, bleu, bert-f1
+model-index:
+- name: flan-t5-definition-en-base
+  results: []
+language:
+- en
+widget:
+- text: "He ate a sweet apple. What is the definition of apple?"
+  example_title: "Definition generation"
+- text: "The paper contains a number of original ideas about color perception. What is the definition of original?"
+  example_title: "Definition generation"
 license: cc-by-sa-4.0
+datasets:
+- marksverdhei/wordnet-definitions-en-2021
 ---
+
+# FLAN-T5-Definition Base
+
+This model is a version of [FLAN-T5 Base](https://huggingface.co/google/flan-t5-base) finetuned on a dataset of English definitions and usage examples.
+
+It generates definitions of English words in context.
+Its input is the usage example and the instruction question "What is the definiton of TARGET_WORD?"
+
+## Model description
+
+See details in the paper `Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis` (ACL'2023) by Mario Giulianelli, Iris Luden, Raquel Fernandez and Andrey Kutuzov.
+
+## Intended uses & limitations
+
+The model is intended for research purposes, as a source of contextualized dictionary-like lexical definitions.
+
+The fine-tuning datasets were limited to English.
+Although the original FLAN-T5 is a multilingual model, we did not thoroughly evaluate its ability to generate definitions in languages other than English. 
+
+Generated definitions can contain all sorts of biases and stereotypes, stemming from the underlying language model.
+
+## Training and evaluation data
+
+Three datasets were used to fine-tune the model:
+- *WordNet* ([Ishiwatari et al., NAACL 2019](https://aclanthology.org/N19-1350/)), also [available on HF](https://huggingface.co/datasets/marksverdhei/wordnet-definitions-en-2021)
+- *Oxford dictionary or CHA* ([Gadetsky et al., ACL 2018](https://aclanthology.org/P18-2043/))
+- English subset of *CodWoE* ([Mickus et al., SemEval 2022](https://aclanthology.org/2022.semeval-1.1/))
+
+FLAN-T5-Definition Base achieves the following results on the WordNet test set:
+- ROUGE-L: 23.19
+- BLEU: 8.80
+- BERT-F1: 87.49
+
+FLAN-T5-Definition Base achieves the following results on the Oxford dictionary test set:
+- ROUGE-L: 17.25
+- BLEU: 3.71
+- BERT-F1: 86.44
+
+
+## Training procedure
+FLAN-T5 Base was fine-tuned in a sequence-to-sequence mode on examples of contextualized dictionary definitions.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.5645        | 1.0   | 2740  | 2.2535          | 24.4437 | 6.4189 | 22.7949 | 22.7909   | 11.4969 |
+| 2.3501        | 2.0   | 5480  | 2.1642          | 25.6642 | 7.289  | 23.8689 | 23.8749   | 11.7150 |
+| 2.2516        | 3.0   | 8220  | 2.1116          | 26.4562 | 7.8955 | 24.6275 | 24.6376   | 11.7441 |
+| 2.1806        | 4.0   | 10960 | 2.0737          | 27.0392 | 8.2393 | 25.1555 | 25.1641   | 11.7930 |
+| 2.1233        | 5.0   | 13700 | 2.0460          | 27.2709 | 8.4244 | 25.3847 | 25.4003   | 11.9014 |
+| 2.0765        | 6.0   | 16440 | 2.0236          | 27.5456 | 8.6096 | 25.6321 | 25.6462   | 11.8113 |
+| 2.0371        | 7.0   | 19180 | 2.0047          | 27.7209 | 8.7277 | 25.7871 | 25.8084   | 11.6875 |
+| 2.0036        | 8.0   | 21920 | 1.9918          | 28.0431 | 8.9863 | 26.1072 | 26.1198   | 11.5487 |
+| 1.9752        | 9.0   | 24660 | 1.9788          | 28.1807 | 9.0219 | 26.1692 | 26.1886   | 11.7939 |
+| 1.9513        | 10.0  | 27400 | 1.9702          | 28.3204 | 9.1572 | 26.2955 | 26.3029   | 11.5936 |
+| 1.9309        | 11.0  | 30140 | 1.9640          | 28.4289 | 9.2845 | 26.4006 | 26.418    | 11.8371 |
+| 1.9144        | 12.0  | 32880 | 1.9571          | 28.4504 | 9.3406 | 26.4273 | 26.4384   | 11.6201 |
+| 1.9013        | 13.0  | 35620 | 1.9544          | 28.6319 | 9.3682 | 26.605  | 26.613    | 11.7067 |
+| 1.8914        | 14.0  | 38360 | 1.9512          | 28.6435 | 9.3976 | 26.5839 | 26.5918   | 11.7307 |
+| 1.8866        | 15.0  | 41100 | 1.9509          | 28.6111 | 9.3857 | 26.551  | 26.5648   | 11.7470 |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.11.0
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 15.0,
+    "eval_gen_len": 13.420898297811473,
+    "eval_loss": 1.9511938095092773,
+    "eval_rouge1": 28.6545,
+    "eval_rouge2": 9.4088,
+    "eval_rougeL": 26.5273,
+    "eval_rougeLsum": 26.5517,
+    "eval_runtime": 179.6643,
+    "eval_samples": 13982,
+    "eval_samples_per_second": 77.823,
+    "eval_steps_per_second": 1.219,
+    "train_loss": 2.069233327155566,
+    "train_runtime": 14173.3385,
+    "train_samples": 175332,
+    "train_samples_per_second": 185.558,
+    "train_steps_per_second": 2.9
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/fp/projects01/ec30/models/flan-t5-base/",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 15.0,
+    "eval_gen_len": 13.420898297811473,
+    "eval_loss": 1.9511938095092773,
+    "eval_rouge1": 28.6545,
+    "eval_rouge2": 9.4088,
+    "eval_rougeL": 26.5273,
+    "eval_rougeLsum": 26.5517,
+    "eval_runtime": 179.6643,
+    "eval_samples": 13982,
+    "eval_samples_per_second": 77.823,
+    "eval_steps_per_second": 1.219
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e65bae9aea15a2fbbc9fefd7576118c862d0627401681c2fece07045cf2754
+size 990406605

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "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>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "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>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "/fp/projects01/ec30/models/flan-t5-base/",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "train_loss": 2.069233327155566,
+    "train_runtime": 14173.3385,
+    "train_samples": 175332,
+    "train_samples_per_second": 185.558,
+    "train_steps_per_second": 2.9
+}

trainer_state.json

@@ -0,0 +1,310 @@
+{
+  "best_metric": 28.6435,
+  "best_model_checkpoint": "base_ox-wn_cod_15ep/checkpoint-38360",
+  "epoch": 15.0,
+  "global_step": 41100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 2.5645,
+      "step": 2740
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 11.496853096838793,
+      "eval_loss": 2.2535109519958496,
+      "eval_rouge1": 24.4437,
+      "eval_rouge2": 6.4189,
+      "eval_rougeL": 22.7949,
+      "eval_rougeLsum": 22.7909,
+      "eval_runtime": 92.2279,
+      "eval_samples_per_second": 151.603,
+      "eval_steps_per_second": 2.375,
+      "step": 2740
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 2.3501,
+      "step": 5480
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 11.71499070233157,
+      "eval_loss": 2.1641664505004883,
+      "eval_rouge1": 25.6642,
+      "eval_rouge2": 7.289,
+      "eval_rougeL": 23.8689,
+      "eval_rougeLsum": 23.8749,
+      "eval_runtime": 92.3758,
+      "eval_samples_per_second": 151.36,
+      "eval_steps_per_second": 2.371,
+      "step": 5480
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4e-05,
+      "loss": 2.2516,
+      "step": 8220
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 11.744099556572737,
+      "eval_loss": 2.1115779876708984,
+      "eval_rouge1": 26.4562,
+      "eval_rouge2": 7.8955,
+      "eval_rougeL": 24.6275,
+      "eval_rougeLsum": 24.6376,
+      "eval_runtime": 91.9643,
+      "eval_samples_per_second": 152.037,
+      "eval_steps_per_second": 2.381,
+      "step": 8220
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 2.1806,
+      "step": 10960
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 11.793019596624232,
+      "eval_loss": 2.073715925216675,
+      "eval_rouge1": 27.0392,
+      "eval_rouge2": 8.2393,
+      "eval_rougeL": 25.1555,
+      "eval_rougeLsum": 25.1641,
+      "eval_runtime": 92.1881,
+      "eval_samples_per_second": 151.668,
+      "eval_steps_per_second": 2.376,
+      "step": 10960
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.1233,
+      "step": 13700
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 11.901444714633099,
+      "eval_loss": 2.0459506511688232,
+      "eval_rouge1": 27.2709,
+      "eval_rouge2": 8.4244,
+      "eval_rougeL": 25.3847,
+      "eval_rougeLsum": 25.4003,
+      "eval_runtime": 92.1849,
+      "eval_samples_per_second": 151.674,
+      "eval_steps_per_second": 2.376,
+      "step": 13700
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3e-05,
+      "loss": 2.0765,
+      "step": 16440
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 11.811257330853955,
+      "eval_loss": 2.0235939025878906,
+      "eval_rouge1": 27.5456,
+      "eval_rouge2": 8.6096,
+      "eval_rougeL": 25.6321,
+      "eval_rougeLsum": 25.6462,
+      "eval_runtime": 92.2077,
+      "eval_samples_per_second": 151.636,
+      "eval_steps_per_second": 2.375,
+      "step": 16440
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 2.0371,
+      "step": 19180
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 11.687455299671006,
+      "eval_loss": 2.004668951034546,
+      "eval_rouge1": 27.7209,
+      "eval_rouge2": 8.7277,
+      "eval_rougeL": 25.7871,
+      "eval_rougeLsum": 25.8084,
+      "eval_runtime": 92.3796,
+      "eval_samples_per_second": 151.354,
+      "eval_steps_per_second": 2.371,
+      "step": 19180
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 2.0036,
+      "step": 21920
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 11.548705478472321,
+      "eval_loss": 1.9917967319488525,
+      "eval_rouge1": 28.0431,
+      "eval_rouge2": 8.9863,
+      "eval_rougeL": 26.1072,
+      "eval_rougeLsum": 26.1198,
+      "eval_runtime": 92.2225,
+      "eval_samples_per_second": 151.612,
+      "eval_steps_per_second": 2.375,
+      "step": 21920
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2e-05,
+      "loss": 1.9752,
+      "step": 24660
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 11.793949363467314,
+      "eval_loss": 1.978798747062683,
+      "eval_rouge1": 28.1807,
+      "eval_rouge2": 9.0219,
+      "eval_rougeL": 26.1692,
+      "eval_rougeLsum": 26.1886,
+      "eval_runtime": 92.3313,
+      "eval_samples_per_second": 151.433,
+      "eval_steps_per_second": 2.372,
+      "step": 24660
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.9513,
+      "step": 27400
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 11.593620369045917,
+      "eval_loss": 1.9701664447784424,
+      "eval_rouge1": 28.3204,
+      "eval_rouge2": 9.1572,
+      "eval_rougeL": 26.2955,
+      "eval_rougeLsum": 26.3029,
+      "eval_runtime": 92.353,
+      "eval_samples_per_second": 151.397,
+      "eval_steps_per_second": 2.371,
+      "step": 27400
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.9309,
+      "step": 30140
+    },
+    {
+      "epoch": 11.0,
+      "eval_gen_len": 11.837076240881133,
+      "eval_loss": 1.9640249013900757,
+      "eval_rouge1": 28.4289,
+      "eval_rouge2": 9.2845,
+      "eval_rougeL": 26.4006,
+      "eval_rougeLsum": 26.418,
+      "eval_runtime": 92.2786,
+      "eval_samples_per_second": 151.519,
+      "eval_steps_per_second": 2.373,
+      "step": 30140
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1e-05,
+      "loss": 1.9144,
+      "step": 32880
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 11.620082963810614,
+      "eval_loss": 1.9570931196212769,
+      "eval_rouge1": 28.4504,
+      "eval_rouge2": 9.3406,
+      "eval_rougeL": 26.4273,
+      "eval_rougeLsum": 26.4384,
+      "eval_runtime": 143.3751,
+      "eval_samples_per_second": 97.52,
+      "eval_steps_per_second": 1.527,
+      "step": 32880
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.9013,
+      "step": 35620
+    },
+    {
+      "epoch": 13.0,
+      "eval_gen_len": 11.706694321270204,
+      "eval_loss": 1.954399824142456,
+      "eval_rouge1": 28.6319,
+      "eval_rouge2": 9.3682,
+      "eval_rougeL": 26.605,
+      "eval_rougeLsum": 26.613,
+      "eval_runtime": 92.2917,
+      "eval_samples_per_second": 151.498,
+      "eval_steps_per_second": 2.373,
+      "step": 35620
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.8914,
+      "step": 38360
+    },
+    {
+      "epoch": 14.0,
+      "eval_gen_len": 11.730653697611215,
+      "eval_loss": 1.9511938095092773,
+      "eval_rouge1": 28.6435,
+      "eval_rouge2": 9.3976,
+      "eval_rougeL": 26.5839,
+      "eval_rougeLsum": 26.5918,
+      "eval_runtime": 92.0528,
+      "eval_samples_per_second": 151.891,
+      "eval_steps_per_second": 2.379,
+      "step": 38360
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0,
+      "loss": 1.8866,
+      "step": 41100
+    },
+    {
+      "epoch": 15.0,
+      "eval_gen_len": 11.74696037762838,
+      "eval_loss": 1.9508894681930542,
+      "eval_rouge1": 28.6111,
+      "eval_rouge2": 9.3857,
+      "eval_rougeL": 26.551,
+      "eval_rougeLsum": 26.5648,
+      "eval_runtime": 91.9698,
+      "eval_samples_per_second": 152.028,
+      "eval_steps_per_second": 2.381,
+      "step": 41100
+    },
+    {
+      "epoch": 15.0,
+      "step": 41100,
+      "total_flos": 4.436322961707786e+17,
+      "train_loss": 2.069233327155566,
+      "train_runtime": 14173.3385,
+      "train_samples_per_second": 185.558,
+      "train_steps_per_second": 2.9
+    }
+  ],
+  "max_steps": 41100,
+  "num_train_epochs": 15,
+  "total_flos": 4.436322961707786e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296329d1d5b8669d15a9afaf3f0ba0f6dc6c566249f51a2f5714bab6a5fedb03
+size 3503