Initial training
Browse files- README.md +67 -0
- config.json +61 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
- trainer_state.json +753 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: flan-t5-base-tldr-100k
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# flan-t5-base-tldr-100k
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.7323
|
| 20 |
+
- Rouge1: 17.0772
|
| 21 |
+
- Rouge2: 4.4204
|
| 22 |
+
- Rougel: 14.549
|
| 23 |
+
- Rougelsum: 15.0148
|
| 24 |
+
- Gen Len: 16.0925
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 5
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Gen Len | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:-------:|:---------------:|:-------:|:------:|:-------:|:---------:|
|
| 55 |
+
| 3.1467 | 1.0 | 11250 | 16.4911 | 2.9531 | 15.909 | 3.8156 | 13.4884 | 13.9568 |
|
| 56 |
+
| 3.0673 | 2.0 | 22500 | 16.4639 | 2.9318 | 16.4972 | 3.9757 | 13.9517 | 14.4336 |
|
| 57 |
+
| 2.9952 | 3.0 | 33750 | 16.2585 | 2.9245 | 16.5997 | 4.1068 | 14.0299 | 14.5147 |
|
| 58 |
+
| 2.9524 | 4.0 | 45000 | 2.7323 | 17.0772 | 4.4204 | 14.549 | 15.0148 | 16.0925 |
|
| 59 |
+
| 2.9223 | 5.0 | 56250 | 2.7328 | 17.1468 | 4.4384 | 14.5798| 15.0572 | 16.2163 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.27.4
|
| 65 |
+
- Pytorch 2.0.0+cu117
|
| 66 |
+
- Datasets 2.11.0
|
| 67 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.27.4",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.27.4"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fdb2b6814204eba2061434de01be223a89389bc75ce0ea1e319a63fc338114b
|
| 3 |
+
size 1980790149
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c82aa9b6a927124dccbe7ec64099f793171749f178ac34cb9b59ab65ec439a8
|
| 3 |
+
size 990408885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa3ce086a9504962536d377981c2367867a18f78b8eae2c0916a420701a4208b
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a018b9a26ea0c156eeb9c9950d8d16831fd8327c3fb8add9ccd3661e0ddb1219
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"pad_token": "<pad>",
|
| 108 |
+
"sp_model_kwargs": {},
|
| 109 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,753 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.732292890548706,
|
| 3 |
+
"best_model_checkpoint": "flan-t5-base-tldr-100k/checkpoint-45000",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 56250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.955555555555556e-05,
|
| 13 |
+
"loss": 3.2897,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.9111111111111114e-05,
|
| 19 |
+
"loss": 3.2632,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 4.866666666666667e-05,
|
| 25 |
+
"loss": 3.2601,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 4.8222222222222225e-05,
|
| 31 |
+
"loss": 3.2293,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 37 |
+
"loss": 3.2164,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 43 |
+
"loss": 3.1959,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"learning_rate": 4.6888888888888895e-05,
|
| 49 |
+
"loss": 3.1905,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 4.644444444444445e-05,
|
| 55 |
+
"loss": 3.233,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"learning_rate": 4.600000000000001e-05,
|
| 61 |
+
"loss": 3.1792,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"learning_rate": 4.555555555555556e-05,
|
| 67 |
+
"loss": 3.2026,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.49,
|
| 72 |
+
"learning_rate": 4.511111111111112e-05,
|
| 73 |
+
"loss": 3.1937,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.53,
|
| 78 |
+
"learning_rate": 4.466666666666667e-05,
|
| 79 |
+
"loss": 3.1751,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.58,
|
| 84 |
+
"learning_rate": 4.422222222222222e-05,
|
| 85 |
+
"loss": 3.173,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"learning_rate": 4.377777777777778e-05,
|
| 91 |
+
"loss": 3.1968,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.67,
|
| 96 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 97 |
+
"loss": 3.1666,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.71,
|
| 102 |
+
"learning_rate": 4.2888888888888886e-05,
|
| 103 |
+
"loss": 3.1855,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.76,
|
| 108 |
+
"learning_rate": 4.2444444444444445e-05,
|
| 109 |
+
"loss": 3.1626,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.8,
|
| 114 |
+
"learning_rate": 4.2e-05,
|
| 115 |
+
"loss": 3.1699,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.84,
|
| 120 |
+
"learning_rate": 4.155555555555556e-05,
|
| 121 |
+
"loss": 3.1657,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.89,
|
| 126 |
+
"learning_rate": 4.111111111111111e-05,
|
| 127 |
+
"loss": 3.1547,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.93,
|
| 132 |
+
"learning_rate": 4.066666666666667e-05,
|
| 133 |
+
"loss": 3.1496,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.98,
|
| 138 |
+
"learning_rate": 4.022222222222222e-05,
|
| 139 |
+
"loss": 3.1467,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.0,
|
| 144 |
+
"eval_gen_len": 16.4911,
|
| 145 |
+
"eval_loss": 2.953094482421875,
|
| 146 |
+
"eval_rouge1": 15.909,
|
| 147 |
+
"eval_rouge2": 3.8156,
|
| 148 |
+
"eval_rougeL": 13.4884,
|
| 149 |
+
"eval_rougeLsum": 13.9568,
|
| 150 |
+
"eval_runtime": 1704.954,
|
| 151 |
+
"eval_samples_per_second": 5.865,
|
| 152 |
+
"eval_steps_per_second": 0.733,
|
| 153 |
+
"step": 11250
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.02,
|
| 157 |
+
"learning_rate": 3.977777777777778e-05,
|
| 158 |
+
"loss": 3.0983,
|
| 159 |
+
"step": 11500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.07,
|
| 163 |
+
"learning_rate": 3.933333333333333e-05,
|
| 164 |
+
"loss": 3.0641,
|
| 165 |
+
"step": 12000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.11,
|
| 169 |
+
"learning_rate": 3.888888888888889e-05,
|
| 170 |
+
"loss": 3.0471,
|
| 171 |
+
"step": 12500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.16,
|
| 175 |
+
"learning_rate": 3.844444444444444e-05,
|
| 176 |
+
"loss": 3.0583,
|
| 177 |
+
"step": 13000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.2,
|
| 181 |
+
"learning_rate": 3.8e-05,
|
| 182 |
+
"loss": 3.069,
|
| 183 |
+
"step": 13500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.24,
|
| 187 |
+
"learning_rate": 3.7555555555555554e-05,
|
| 188 |
+
"loss": 3.0642,
|
| 189 |
+
"step": 14000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.29,
|
| 193 |
+
"learning_rate": 3.7111111111111113e-05,
|
| 194 |
+
"loss": 3.0729,
|
| 195 |
+
"step": 14500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.33,
|
| 199 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 200 |
+
"loss": 3.0753,
|
| 201 |
+
"step": 15000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.38,
|
| 205 |
+
"learning_rate": 3.6222222222222225e-05,
|
| 206 |
+
"loss": 3.0415,
|
| 207 |
+
"step": 15500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.42,
|
| 211 |
+
"learning_rate": 3.577777777777778e-05,
|
| 212 |
+
"loss": 3.0632,
|
| 213 |
+
"step": 16000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.47,
|
| 217 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 218 |
+
"loss": 3.0757,
|
| 219 |
+
"step": 16500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.51,
|
| 223 |
+
"learning_rate": 3.4888888888888895e-05,
|
| 224 |
+
"loss": 3.0589,
|
| 225 |
+
"step": 17000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.56,
|
| 229 |
+
"learning_rate": 3.444444444444445e-05,
|
| 230 |
+
"loss": 3.0586,
|
| 231 |
+
"step": 17500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.6,
|
| 235 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 236 |
+
"loss": 3.0582,
|
| 237 |
+
"step": 18000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.64,
|
| 241 |
+
"learning_rate": 3.355555555555556e-05,
|
| 242 |
+
"loss": 3.0657,
|
| 243 |
+
"step": 18500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.69,
|
| 247 |
+
"learning_rate": 3.311111111111112e-05,
|
| 248 |
+
"loss": 3.0653,
|
| 249 |
+
"step": 19000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.73,
|
| 253 |
+
"learning_rate": 3.266666666666667e-05,
|
| 254 |
+
"loss": 3.0513,
|
| 255 |
+
"step": 19500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.78,
|
| 259 |
+
"learning_rate": 3.222222222222223e-05,
|
| 260 |
+
"loss": 3.082,
|
| 261 |
+
"step": 20000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.82,
|
| 265 |
+
"learning_rate": 3.177777777777778e-05,
|
| 266 |
+
"loss": 3.0785,
|
| 267 |
+
"step": 20500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.87,
|
| 271 |
+
"learning_rate": 3.1333333333333334e-05,
|
| 272 |
+
"loss": 3.0654,
|
| 273 |
+
"step": 21000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.91,
|
| 277 |
+
"learning_rate": 3.088888888888889e-05,
|
| 278 |
+
"loss": 3.0531,
|
| 279 |
+
"step": 21500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.96,
|
| 283 |
+
"learning_rate": 3.044444444444445e-05,
|
| 284 |
+
"loss": 3.0518,
|
| 285 |
+
"step": 22000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.0,
|
| 289 |
+
"learning_rate": 3e-05,
|
| 290 |
+
"loss": 3.0673,
|
| 291 |
+
"step": 22500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.0,
|
| 295 |
+
"eval_gen_len": 16.4639,
|
| 296 |
+
"eval_loss": 2.93178129196167,
|
| 297 |
+
"eval_rouge1": 16.4972,
|
| 298 |
+
"eval_rouge2": 3.9757,
|
| 299 |
+
"eval_rougeL": 13.9517,
|
| 300 |
+
"eval_rougeLsum": 14.4336,
|
| 301 |
+
"eval_runtime": 1398.1721,
|
| 302 |
+
"eval_samples_per_second": 7.152,
|
| 303 |
+
"eval_steps_per_second": 0.894,
|
| 304 |
+
"step": 22500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.04,
|
| 308 |
+
"learning_rate": 2.955555555555556e-05,
|
| 309 |
+
"loss": 2.9751,
|
| 310 |
+
"step": 23000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.09,
|
| 314 |
+
"learning_rate": 2.9111111111111112e-05,
|
| 315 |
+
"loss": 2.9883,
|
| 316 |
+
"step": 23500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.13,
|
| 320 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 321 |
+
"loss": 2.9911,
|
| 322 |
+
"step": 24000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.18,
|
| 326 |
+
"learning_rate": 2.8222222222222223e-05,
|
| 327 |
+
"loss": 2.9796,
|
| 328 |
+
"step": 24500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.22,
|
| 332 |
+
"learning_rate": 2.777777777777778e-05,
|
| 333 |
+
"loss": 2.9767,
|
| 334 |
+
"step": 25000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.27,
|
| 338 |
+
"learning_rate": 2.733333333333333e-05,
|
| 339 |
+
"loss": 2.9795,
|
| 340 |
+
"step": 25500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.31,
|
| 344 |
+
"learning_rate": 2.688888888888889e-05,
|
| 345 |
+
"loss": 2.9654,
|
| 346 |
+
"step": 26000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.36,
|
| 350 |
+
"learning_rate": 2.6444444444444443e-05,
|
| 351 |
+
"loss": 2.9904,
|
| 352 |
+
"step": 26500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.4,
|
| 356 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 357 |
+
"loss": 2.9785,
|
| 358 |
+
"step": 27000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.44,
|
| 362 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 363 |
+
"loss": 2.9856,
|
| 364 |
+
"step": 27500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.49,
|
| 368 |
+
"learning_rate": 2.5111111111111113e-05,
|
| 369 |
+
"loss": 3.007,
|
| 370 |
+
"step": 28000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.53,
|
| 374 |
+
"learning_rate": 2.466666666666667e-05,
|
| 375 |
+
"loss": 2.9819,
|
| 376 |
+
"step": 28500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.58,
|
| 380 |
+
"learning_rate": 2.4222222222222224e-05,
|
| 381 |
+
"loss": 3.0003,
|
| 382 |
+
"step": 29000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.62,
|
| 386 |
+
"learning_rate": 2.377777777777778e-05,
|
| 387 |
+
"loss": 2.981,
|
| 388 |
+
"step": 29500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.67,
|
| 392 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 393 |
+
"loss": 2.9926,
|
| 394 |
+
"step": 30000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.71,
|
| 398 |
+
"learning_rate": 2.288888888888889e-05,
|
| 399 |
+
"loss": 2.9901,
|
| 400 |
+
"step": 30500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.76,
|
| 404 |
+
"learning_rate": 2.2444444444444447e-05,
|
| 405 |
+
"loss": 2.9893,
|
| 406 |
+
"step": 31000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.8,
|
| 410 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 411 |
+
"loss": 2.9668,
|
| 412 |
+
"step": 31500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.84,
|
| 416 |
+
"learning_rate": 2.1555555555555555e-05,
|
| 417 |
+
"loss": 2.9903,
|
| 418 |
+
"step": 32000
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.89,
|
| 422 |
+
"learning_rate": 2.111111111111111e-05,
|
| 423 |
+
"loss": 2.9687,
|
| 424 |
+
"step": 32500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.93,
|
| 428 |
+
"learning_rate": 2.0666666666666666e-05,
|
| 429 |
+
"loss": 2.9839,
|
| 430 |
+
"step": 33000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.98,
|
| 434 |
+
"learning_rate": 2.0222222222222222e-05,
|
| 435 |
+
"loss": 2.9952,
|
| 436 |
+
"step": 33500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 3.0,
|
| 440 |
+
"eval_gen_len": 16.2585,
|
| 441 |
+
"eval_loss": 2.924546003341675,
|
| 442 |
+
"eval_rouge1": 16.5997,
|
| 443 |
+
"eval_rouge2": 4.1068,
|
| 444 |
+
"eval_rougeL": 14.0299,
|
| 445 |
+
"eval_rougeLsum": 14.5147,
|
| 446 |
+
"eval_runtime": 945.9838,
|
| 447 |
+
"eval_samples_per_second": 10.571,
|
| 448 |
+
"eval_steps_per_second": 1.321,
|
| 449 |
+
"step": 33750
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.02,
|
| 453 |
+
"learning_rate": 1.9777777777777778e-05,
|
| 454 |
+
"loss": 2.9548,
|
| 455 |
+
"step": 34000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.07,
|
| 459 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 460 |
+
"loss": 2.9566,
|
| 461 |
+
"step": 34500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.11,
|
| 465 |
+
"learning_rate": 1.888888888888889e-05,
|
| 466 |
+
"loss": 2.953,
|
| 467 |
+
"step": 35000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.16,
|
| 471 |
+
"learning_rate": 1.8444444444444445e-05,
|
| 472 |
+
"loss": 2.9514,
|
| 473 |
+
"step": 35500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.2,
|
| 477 |
+
"learning_rate": 1.8e-05,
|
| 478 |
+
"loss": 2.9362,
|
| 479 |
+
"step": 36000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.24,
|
| 483 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 484 |
+
"loss": 2.9482,
|
| 485 |
+
"step": 36500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.29,
|
| 489 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 490 |
+
"loss": 2.9441,
|
| 491 |
+
"step": 37000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.33,
|
| 495 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 496 |
+
"loss": 2.9366,
|
| 497 |
+
"step": 37500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 3.38,
|
| 501 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 502 |
+
"loss": 2.9558,
|
| 503 |
+
"step": 38000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.42,
|
| 507 |
+
"learning_rate": 1.577777777777778e-05,
|
| 508 |
+
"loss": 2.959,
|
| 509 |
+
"step": 38500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 3.47,
|
| 513 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 514 |
+
"loss": 2.9634,
|
| 515 |
+
"step": 39000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.51,
|
| 519 |
+
"learning_rate": 1.4888888888888888e-05,
|
| 520 |
+
"loss": 2.9464,
|
| 521 |
+
"step": 39500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.56,
|
| 525 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 526 |
+
"loss": 2.9669,
|
| 527 |
+
"step": 40000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.6,
|
| 531 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 532 |
+
"loss": 2.9404,
|
| 533 |
+
"step": 40500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 3.64,
|
| 537 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 538 |
+
"loss": 2.9686,
|
| 539 |
+
"step": 41000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 3.69,
|
| 543 |
+
"learning_rate": 1.3111111111111113e-05,
|
| 544 |
+
"loss": 2.9384,
|
| 545 |
+
"step": 41500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.73,
|
| 549 |
+
"learning_rate": 1.2666666666666668e-05,
|
| 550 |
+
"loss": 2.9304,
|
| 551 |
+
"step": 42000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 3.78,
|
| 555 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 556 |
+
"loss": 2.9474,
|
| 557 |
+
"step": 42500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 3.82,
|
| 561 |
+
"learning_rate": 1.1777777777777778e-05,
|
| 562 |
+
"loss": 2.9455,
|
| 563 |
+
"step": 43000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.87,
|
| 567 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 568 |
+
"loss": 2.9456,
|
| 569 |
+
"step": 43500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.91,
|
| 573 |
+
"learning_rate": 1.088888888888889e-05,
|
| 574 |
+
"loss": 2.9359,
|
| 575 |
+
"step": 44000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.96,
|
| 579 |
+
"learning_rate": 1.0444444444444445e-05,
|
| 580 |
+
"loss": 2.9445,
|
| 581 |
+
"step": 44500
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.0,
|
| 585 |
+
"learning_rate": 1e-05,
|
| 586 |
+
"loss": 2.9524,
|
| 587 |
+
"step": 45000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 4.0,
|
| 591 |
+
"eval_gen_len": 16.0925,
|
| 592 |
+
"eval_loss": 2.732292890548706,
|
| 593 |
+
"eval_rouge1": 17.0772,
|
| 594 |
+
"eval_rouge2": 4.4204,
|
| 595 |
+
"eval_rougeL": 14.549,
|
| 596 |
+
"eval_rougeLsum": 15.0148,
|
| 597 |
+
"eval_runtime": 957.2679,
|
| 598 |
+
"eval_samples_per_second": 10.446,
|
| 599 |
+
"eval_steps_per_second": 1.306,
|
| 600 |
+
"step": 45000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.04,
|
| 604 |
+
"learning_rate": 9.555555555555556e-06,
|
| 605 |
+
"loss": 2.8978,
|
| 606 |
+
"step": 45500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 4.09,
|
| 610 |
+
"learning_rate": 9.111111111111112e-06,
|
| 611 |
+
"loss": 2.8935,
|
| 612 |
+
"step": 46000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.13,
|
| 616 |
+
"learning_rate": 8.666666666666668e-06,
|
| 617 |
+
"loss": 2.9088,
|
| 618 |
+
"step": 46500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.18,
|
| 622 |
+
"learning_rate": 8.222222222222223e-06,
|
| 623 |
+
"loss": 2.9148,
|
| 624 |
+
"step": 47000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.22,
|
| 628 |
+
"learning_rate": 7.777777777777777e-06,
|
| 629 |
+
"loss": 2.9336,
|
| 630 |
+
"step": 47500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 4.27,
|
| 634 |
+
"learning_rate": 7.333333333333334e-06,
|
| 635 |
+
"loss": 2.9111,
|
| 636 |
+
"step": 48000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 4.31,
|
| 640 |
+
"learning_rate": 6.888888888888889e-06,
|
| 641 |
+
"loss": 2.934,
|
| 642 |
+
"step": 48500
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.36,
|
| 646 |
+
"learning_rate": 6.4444444444444445e-06,
|
| 647 |
+
"loss": 2.9219,
|
| 648 |
+
"step": 49000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 4.4,
|
| 652 |
+
"learning_rate": 6e-06,
|
| 653 |
+
"loss": 2.914,
|
| 654 |
+
"step": 49500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.44,
|
| 658 |
+
"learning_rate": 5.555555555555556e-06,
|
| 659 |
+
"loss": 2.9088,
|
| 660 |
+
"step": 50000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.49,
|
| 664 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 665 |
+
"loss": 2.93,
|
| 666 |
+
"step": 50500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.53,
|
| 670 |
+
"learning_rate": 4.666666666666667e-06,
|
| 671 |
+
"loss": 2.9101,
|
| 672 |
+
"step": 51000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.58,
|
| 676 |
+
"learning_rate": 4.222222222222223e-06,
|
| 677 |
+
"loss": 2.9189,
|
| 678 |
+
"step": 51500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 4.62,
|
| 682 |
+
"learning_rate": 3.777777777777778e-06,
|
| 683 |
+
"loss": 2.9197,
|
| 684 |
+
"step": 52000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.67,
|
| 688 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 689 |
+
"loss": 2.9263,
|
| 690 |
+
"step": 52500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 4.71,
|
| 694 |
+
"learning_rate": 2.888888888888889e-06,
|
| 695 |
+
"loss": 2.925,
|
| 696 |
+
"step": 53000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 4.76,
|
| 700 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 701 |
+
"loss": 2.9124,
|
| 702 |
+
"step": 53500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.8,
|
| 706 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 707 |
+
"loss": 2.8981,
|
| 708 |
+
"step": 54000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 4.84,
|
| 712 |
+
"learning_rate": 1.5555555555555556e-06,
|
| 713 |
+
"loss": 2.9145,
|
| 714 |
+
"step": 54500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.89,
|
| 718 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 719 |
+
"loss": 2.9135,
|
| 720 |
+
"step": 55000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 4.93,
|
| 724 |
+
"learning_rate": 6.666666666666667e-07,
|
| 725 |
+
"loss": 2.9066,
|
| 726 |
+
"step": 55500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.98,
|
| 730 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 731 |
+
"loss": 2.9223,
|
| 732 |
+
"step": 56000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 5.0,
|
| 736 |
+
"eval_gen_len": 16.2163,
|
| 737 |
+
"eval_loss": 2.732771158218384,
|
| 738 |
+
"eval_rouge1": 17.1468,
|
| 739 |
+
"eval_rouge2": 4.4384,
|
| 740 |
+
"eval_rougeL": 14.5798,
|
| 741 |
+
"eval_rougeLsum": 15.0572,
|
| 742 |
+
"eval_runtime": 1011.7448,
|
| 743 |
+
"eval_samples_per_second": 9.884,
|
| 744 |
+
"eval_steps_per_second": 1.235,
|
| 745 |
+
"step": 56250
|
| 746 |
+
}
|
| 747 |
+
],
|
| 748 |
+
"max_steps": 56250,
|
| 749 |
+
"num_train_epochs": 5,
|
| 750 |
+
"total_flos": 3.081408086016e+17,
|
| 751 |
+
"trial_name": null,
|
| 752 |
+
"trial_params": null
|
| 753 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a35832c4a9ab3abfb6dc0e4a1b83adfb1fc2be17a65a663ad2fd8b9f10ba17ea
|
| 3 |
+
size 3707
|