'instruction'
Browse files- config.json +31 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +103 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +108 -0
- trainer_state.json +618 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "VietAI/vit5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": false,
|
| 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 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.30.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 36096
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45d931fba99c218d711fb10875cf1391e1d530b1473b6c8d5511e14e541dd449
|
| 3 |
+
size 1807760133
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:546c17891fd693b6a7806460deeb5dae57f3e4571d8673306243685c5d9f883d
|
| 3 |
+
size 903892625
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa402679ff7c808d1df7eb5944a4125d8cfd7b874b70b59ec9ed9c684ec28d7
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf928355da597edad3b10c86cba6df7361b9e35e5e45cc85d1ee1a4d4fa92559
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
],
|
| 100 |
+
"eos_token": "</s>",
|
| 101 |
+
"pad_token": "<pad>",
|
| 102 |
+
"unk_token": "<unk>"
|
| 103 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
|
| 3 |
+
size 820370
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
],
|
| 100 |
+
"clean_up_tokenization_spaces": true,
|
| 101 |
+
"eos_token": "</s>",
|
| 102 |
+
"extra_ids": 96,
|
| 103 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 104 |
+
"pad_token": "<pad>",
|
| 105 |
+
"sp_model_kwargs": {},
|
| 106 |
+
"tokenizer_class": "T5Tokenizer",
|
| 107 |
+
"unk_token": "<unk>"
|
| 108 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,618 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.974948758824869,
|
| 5 |
+
"global_step": 10950,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.23,
|
| 12 |
+
"learning_rate": 4.553734061930783e-05,
|
| 13 |
+
"loss": 4.5455,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"eval_loss": 0.06012005731463432,
|
| 19 |
+
"eval_runtime": 125.7302,
|
| 20 |
+
"eval_samples_per_second": 19.86,
|
| 21 |
+
"eval_steps_per_second": 1.249,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.46,
|
| 26 |
+
"learning_rate": 9.107468123861566e-05,
|
| 27 |
+
"loss": 0.0471,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.46,
|
| 32 |
+
"eval_loss": 0.05808735638856888,
|
| 33 |
+
"eval_runtime": 125.3179,
|
| 34 |
+
"eval_samples_per_second": 19.925,
|
| 35 |
+
"eval_steps_per_second": 1.253,
|
| 36 |
+
"step": 500
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.68,
|
| 40 |
+
"learning_rate": 9.807120237981e-05,
|
| 41 |
+
"loss": 0.0443,
|
| 42 |
+
"step": 750
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.68,
|
| 46 |
+
"eval_loss": 0.05481741577386856,
|
| 47 |
+
"eval_runtime": 125.3239,
|
| 48 |
+
"eval_samples_per_second": 19.924,
|
| 49 |
+
"eval_steps_per_second": 1.253,
|
| 50 |
+
"step": 750
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.91,
|
| 54 |
+
"learning_rate": 9.567220036464831e-05,
|
| 55 |
+
"loss": 0.0428,
|
| 56 |
+
"step": 1000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.91,
|
| 60 |
+
"eval_loss": 0.05039665102958679,
|
| 61 |
+
"eval_runtime": 125.3169,
|
| 62 |
+
"eval_samples_per_second": 19.925,
|
| 63 |
+
"eval_steps_per_second": 1.253,
|
| 64 |
+
"step": 1000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.14,
|
| 68 |
+
"learning_rate": 9.327319834948663e-05,
|
| 69 |
+
"loss": 0.0329,
|
| 70 |
+
"step": 1250
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.14,
|
| 74 |
+
"eval_loss": 0.05058171600103378,
|
| 75 |
+
"eval_runtime": 125.3095,
|
| 76 |
+
"eval_samples_per_second": 19.927,
|
| 77 |
+
"eval_steps_per_second": 1.253,
|
| 78 |
+
"step": 1250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.37,
|
| 82 |
+
"learning_rate": 9.087419633432492e-05,
|
| 83 |
+
"loss": 0.0299,
|
| 84 |
+
"step": 1500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.37,
|
| 88 |
+
"eval_loss": 0.04842585325241089,
|
| 89 |
+
"eval_runtime": 125.3053,
|
| 90 |
+
"eval_samples_per_second": 19.927,
|
| 91 |
+
"eval_steps_per_second": 1.253,
|
| 92 |
+
"step": 1500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.59,
|
| 96 |
+
"learning_rate": 8.847519431916324e-05,
|
| 97 |
+
"loss": 0.0295,
|
| 98 |
+
"step": 1750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.59,
|
| 102 |
+
"eval_loss": 0.049905285239219666,
|
| 103 |
+
"eval_runtime": 125.3158,
|
| 104 |
+
"eval_samples_per_second": 19.926,
|
| 105 |
+
"eval_steps_per_second": 1.253,
|
| 106 |
+
"step": 1750
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.82,
|
| 110 |
+
"learning_rate": 8.607619230400153e-05,
|
| 111 |
+
"loss": 0.0304,
|
| 112 |
+
"step": 2000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.82,
|
| 116 |
+
"eval_loss": 0.047520652413368225,
|
| 117 |
+
"eval_runtime": 125.3111,
|
| 118 |
+
"eval_samples_per_second": 19.926,
|
| 119 |
+
"eval_steps_per_second": 1.253,
|
| 120 |
+
"step": 2000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.05,
|
| 124 |
+
"learning_rate": 8.367719028883985e-05,
|
| 125 |
+
"loss": 0.0277,
|
| 126 |
+
"step": 2250
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.05,
|
| 130 |
+
"eval_loss": 0.04981054365634918,
|
| 131 |
+
"eval_runtime": 125.3207,
|
| 132 |
+
"eval_samples_per_second": 19.925,
|
| 133 |
+
"eval_steps_per_second": 1.253,
|
| 134 |
+
"step": 2250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.28,
|
| 138 |
+
"learning_rate": 8.127818827367816e-05,
|
| 139 |
+
"loss": 0.0186,
|
| 140 |
+
"step": 2500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.28,
|
| 144 |
+
"eval_loss": 0.04637761414051056,
|
| 145 |
+
"eval_runtime": 125.3226,
|
| 146 |
+
"eval_samples_per_second": 19.925,
|
| 147 |
+
"eval_steps_per_second": 1.253,
|
| 148 |
+
"step": 2500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.51,
|
| 152 |
+
"learning_rate": 7.887918625851645e-05,
|
| 153 |
+
"loss": 0.0199,
|
| 154 |
+
"step": 2750
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.51,
|
| 158 |
+
"eval_loss": 0.04944201186299324,
|
| 159 |
+
"eval_runtime": 125.3132,
|
| 160 |
+
"eval_samples_per_second": 19.926,
|
| 161 |
+
"eval_steps_per_second": 1.253,
|
| 162 |
+
"step": 2750
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.73,
|
| 166 |
+
"learning_rate": 7.648018424335477e-05,
|
| 167 |
+
"loss": 0.0205,
|
| 168 |
+
"step": 3000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.73,
|
| 172 |
+
"eval_loss": 0.045388150960206985,
|
| 173 |
+
"eval_runtime": 125.3269,
|
| 174 |
+
"eval_samples_per_second": 19.924,
|
| 175 |
+
"eval_steps_per_second": 1.253,
|
| 176 |
+
"step": 3000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.96,
|
| 180 |
+
"learning_rate": 7.408118222819308e-05,
|
| 181 |
+
"loss": 0.0202,
|
| 182 |
+
"step": 3250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.96,
|
| 186 |
+
"eval_loss": 0.04644118994474411,
|
| 187 |
+
"eval_runtime": 125.317,
|
| 188 |
+
"eval_samples_per_second": 19.925,
|
| 189 |
+
"eval_steps_per_second": 1.253,
|
| 190 |
+
"step": 3250
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.19,
|
| 194 |
+
"learning_rate": 7.168218021303138e-05,
|
| 195 |
+
"loss": 0.015,
|
| 196 |
+
"step": 3500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.19,
|
| 200 |
+
"eval_loss": 0.0492834635078907,
|
| 201 |
+
"eval_runtime": 125.3122,
|
| 202 |
+
"eval_samples_per_second": 19.926,
|
| 203 |
+
"eval_steps_per_second": 1.253,
|
| 204 |
+
"step": 3500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.42,
|
| 208 |
+
"learning_rate": 6.928317819786969e-05,
|
| 209 |
+
"loss": 0.0136,
|
| 210 |
+
"step": 3750
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.42,
|
| 214 |
+
"eval_loss": 0.050950221717357635,
|
| 215 |
+
"eval_runtime": 125.3101,
|
| 216 |
+
"eval_samples_per_second": 19.927,
|
| 217 |
+
"eval_steps_per_second": 1.253,
|
| 218 |
+
"step": 3750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.64,
|
| 222 |
+
"learning_rate": 6.6884176182708e-05,
|
| 223 |
+
"loss": 0.0139,
|
| 224 |
+
"step": 4000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.64,
|
| 228 |
+
"eval_loss": 0.0521300733089447,
|
| 229 |
+
"eval_runtime": 125.3091,
|
| 230 |
+
"eval_samples_per_second": 19.927,
|
| 231 |
+
"eval_steps_per_second": 1.253,
|
| 232 |
+
"step": 4000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.87,
|
| 236 |
+
"learning_rate": 6.44851741675463e-05,
|
| 237 |
+
"loss": 0.0149,
|
| 238 |
+
"step": 4250
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.87,
|
| 242 |
+
"eval_loss": 0.049005962908267975,
|
| 243 |
+
"eval_runtime": 125.2924,
|
| 244 |
+
"eval_samples_per_second": 19.929,
|
| 245 |
+
"eval_steps_per_second": 1.253,
|
| 246 |
+
"step": 4250
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.1,
|
| 250 |
+
"learning_rate": 6.208617215238462e-05,
|
| 251 |
+
"loss": 0.012,
|
| 252 |
+
"step": 4500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.1,
|
| 256 |
+
"eval_loss": 0.05201614275574684,
|
| 257 |
+
"eval_runtime": 125.3236,
|
| 258 |
+
"eval_samples_per_second": 19.924,
|
| 259 |
+
"eval_steps_per_second": 1.253,
|
| 260 |
+
"step": 4500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.33,
|
| 264 |
+
"learning_rate": 5.968717013722291e-05,
|
| 265 |
+
"loss": 0.0094,
|
| 266 |
+
"step": 4750
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.33,
|
| 270 |
+
"eval_loss": 0.052882954478263855,
|
| 271 |
+
"eval_runtime": 125.3182,
|
| 272 |
+
"eval_samples_per_second": 19.925,
|
| 273 |
+
"eval_steps_per_second": 1.253,
|
| 274 |
+
"step": 4750
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.55,
|
| 278 |
+
"learning_rate": 5.7288168122061226e-05,
|
| 279 |
+
"loss": 0.0104,
|
| 280 |
+
"step": 5000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.55,
|
| 284 |
+
"eval_loss": 0.05443257838487625,
|
| 285 |
+
"eval_runtime": 125.308,
|
| 286 |
+
"eval_samples_per_second": 19.927,
|
| 287 |
+
"eval_steps_per_second": 1.253,
|
| 288 |
+
"step": 5000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.78,
|
| 292 |
+
"learning_rate": 5.488916610689954e-05,
|
| 293 |
+
"loss": 0.0095,
|
| 294 |
+
"step": 5250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.78,
|
| 298 |
+
"eval_loss": 0.0512896366417408,
|
| 299 |
+
"eval_runtime": 125.3186,
|
| 300 |
+
"eval_samples_per_second": 19.925,
|
| 301 |
+
"eval_steps_per_second": 1.253,
|
| 302 |
+
"step": 5250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.01,
|
| 306 |
+
"learning_rate": 5.249016409173784e-05,
|
| 307 |
+
"loss": 0.0099,
|
| 308 |
+
"step": 5500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.01,
|
| 312 |
+
"eval_loss": 0.05250149220228195,
|
| 313 |
+
"eval_runtime": 125.3202,
|
| 314 |
+
"eval_samples_per_second": 19.925,
|
| 315 |
+
"eval_steps_per_second": 1.253,
|
| 316 |
+
"step": 5500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 5.24,
|
| 320 |
+
"learning_rate": 5.009116207657615e-05,
|
| 321 |
+
"loss": 0.0067,
|
| 322 |
+
"step": 5750
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 5.24,
|
| 326 |
+
"eval_loss": 0.05294517055153847,
|
| 327 |
+
"eval_runtime": 125.3036,
|
| 328 |
+
"eval_samples_per_second": 19.928,
|
| 329 |
+
"eval_steps_per_second": 1.253,
|
| 330 |
+
"step": 5750
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.47,
|
| 334 |
+
"learning_rate": 4.769216006141446e-05,
|
| 335 |
+
"loss": 0.0064,
|
| 336 |
+
"step": 6000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.47,
|
| 340 |
+
"eval_loss": 0.05718787759542465,
|
| 341 |
+
"eval_runtime": 125.3174,
|
| 342 |
+
"eval_samples_per_second": 19.925,
|
| 343 |
+
"eval_steps_per_second": 1.253,
|
| 344 |
+
"step": 6000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.69,
|
| 348 |
+
"learning_rate": 4.5293158046252756e-05,
|
| 349 |
+
"loss": 0.0062,
|
| 350 |
+
"step": 6250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.69,
|
| 354 |
+
"eval_loss": 0.0588238462805748,
|
| 355 |
+
"eval_runtime": 125.32,
|
| 356 |
+
"eval_samples_per_second": 19.925,
|
| 357 |
+
"eval_steps_per_second": 1.253,
|
| 358 |
+
"step": 6250
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.92,
|
| 362 |
+
"learning_rate": 4.289415603109107e-05,
|
| 363 |
+
"loss": 0.0066,
|
| 364 |
+
"step": 6500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 5.92,
|
| 368 |
+
"eval_loss": 0.055590804666280746,
|
| 369 |
+
"eval_runtime": 125.32,
|
| 370 |
+
"eval_samples_per_second": 19.925,
|
| 371 |
+
"eval_steps_per_second": 1.253,
|
| 372 |
+
"step": 6500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.15,
|
| 376 |
+
"learning_rate": 4.0495154015929375e-05,
|
| 377 |
+
"loss": 0.0049,
|
| 378 |
+
"step": 6750
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 6.15,
|
| 382 |
+
"eval_loss": 0.060405001044273376,
|
| 383 |
+
"eval_runtime": 125.3175,
|
| 384 |
+
"eval_samples_per_second": 19.925,
|
| 385 |
+
"eval_steps_per_second": 1.253,
|
| 386 |
+
"step": 6750
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 6.38,
|
| 390 |
+
"learning_rate": 3.809615200076768e-05,
|
| 391 |
+
"loss": 0.0044,
|
| 392 |
+
"step": 7000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.38,
|
| 396 |
+
"eval_loss": 0.0592646524310112,
|
| 397 |
+
"eval_runtime": 125.3136,
|
| 398 |
+
"eval_samples_per_second": 19.926,
|
| 399 |
+
"eval_steps_per_second": 1.253,
|
| 400 |
+
"step": 7000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 6.6,
|
| 404 |
+
"learning_rate": 3.569714998560599e-05,
|
| 405 |
+
"loss": 0.0042,
|
| 406 |
+
"step": 7250
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 6.6,
|
| 410 |
+
"eval_loss": 0.059081513434648514,
|
| 411 |
+
"eval_runtime": 125.2994,
|
| 412 |
+
"eval_samples_per_second": 19.928,
|
| 413 |
+
"eval_steps_per_second": 1.253,
|
| 414 |
+
"step": 7250
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 6.83,
|
| 418 |
+
"learning_rate": 3.32981479704443e-05,
|
| 419 |
+
"loss": 0.0048,
|
| 420 |
+
"step": 7500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 6.83,
|
| 424 |
+
"eval_loss": 0.06123210862278938,
|
| 425 |
+
"eval_runtime": 125.3056,
|
| 426 |
+
"eval_samples_per_second": 19.927,
|
| 427 |
+
"eval_steps_per_second": 1.253,
|
| 428 |
+
"step": 7500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.06,
|
| 432 |
+
"learning_rate": 3.0899145955282606e-05,
|
| 433 |
+
"loss": 0.004,
|
| 434 |
+
"step": 7750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 7.06,
|
| 438 |
+
"eval_loss": 0.060906291007995605,
|
| 439 |
+
"eval_runtime": 125.3113,
|
| 440 |
+
"eval_samples_per_second": 19.926,
|
| 441 |
+
"eval_steps_per_second": 1.253,
|
| 442 |
+
"step": 7750
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 7.29,
|
| 446 |
+
"learning_rate": 2.850014394012091e-05,
|
| 447 |
+
"loss": 0.003,
|
| 448 |
+
"step": 8000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 7.29,
|
| 452 |
+
"eval_loss": 0.06742047518491745,
|
| 453 |
+
"eval_runtime": 125.3117,
|
| 454 |
+
"eval_samples_per_second": 19.926,
|
| 455 |
+
"eval_steps_per_second": 1.253,
|
| 456 |
+
"step": 8000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 7.52,
|
| 460 |
+
"learning_rate": 2.6101141924959215e-05,
|
| 461 |
+
"loss": 0.003,
|
| 462 |
+
"step": 8250
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 7.52,
|
| 466 |
+
"eval_loss": 0.0640687569975853,
|
| 467 |
+
"eval_runtime": 125.31,
|
| 468 |
+
"eval_samples_per_second": 19.927,
|
| 469 |
+
"eval_steps_per_second": 1.253,
|
| 470 |
+
"step": 8250
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 7.74,
|
| 474 |
+
"learning_rate": 2.3702139909797524e-05,
|
| 475 |
+
"loss": 0.0027,
|
| 476 |
+
"step": 8500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 7.74,
|
| 480 |
+
"eval_loss": 0.06774434447288513,
|
| 481 |
+
"eval_runtime": 125.316,
|
| 482 |
+
"eval_samples_per_second": 19.926,
|
| 483 |
+
"eval_steps_per_second": 1.253,
|
| 484 |
+
"step": 8500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 7.97,
|
| 488 |
+
"learning_rate": 2.1303137894635834e-05,
|
| 489 |
+
"loss": 0.0028,
|
| 490 |
+
"step": 8750
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 7.97,
|
| 494 |
+
"eval_loss": 0.06737840920686722,
|
| 495 |
+
"eval_runtime": 125.323,
|
| 496 |
+
"eval_samples_per_second": 19.925,
|
| 497 |
+
"eval_steps_per_second": 1.253,
|
| 498 |
+
"step": 8750
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 8.2,
|
| 502 |
+
"learning_rate": 1.890413587947414e-05,
|
| 503 |
+
"loss": 0.0021,
|
| 504 |
+
"step": 9000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 8.2,
|
| 508 |
+
"eval_loss": 0.06941425800323486,
|
| 509 |
+
"eval_runtime": 125.3147,
|
| 510 |
+
"eval_samples_per_second": 19.926,
|
| 511 |
+
"eval_steps_per_second": 1.253,
|
| 512 |
+
"step": 9000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.43,
|
| 516 |
+
"learning_rate": 1.6505133864312446e-05,
|
| 517 |
+
"loss": 0.0018,
|
| 518 |
+
"step": 9250
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.43,
|
| 522 |
+
"eval_loss": 0.07149343937635422,
|
| 523 |
+
"eval_runtime": 125.3155,
|
| 524 |
+
"eval_samples_per_second": 19.926,
|
| 525 |
+
"eval_steps_per_second": 1.253,
|
| 526 |
+
"step": 9250
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 8.65,
|
| 530 |
+
"learning_rate": 1.4106131849150753e-05,
|
| 531 |
+
"loss": 0.0021,
|
| 532 |
+
"step": 9500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 8.65,
|
| 536 |
+
"eval_loss": 0.06807977706193924,
|
| 537 |
+
"eval_runtime": 125.3164,
|
| 538 |
+
"eval_samples_per_second": 19.926,
|
| 539 |
+
"eval_steps_per_second": 1.253,
|
| 540 |
+
"step": 9500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 8.88,
|
| 544 |
+
"learning_rate": 1.1707129833989061e-05,
|
| 545 |
+
"loss": 0.0017,
|
| 546 |
+
"step": 9750
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 8.88,
|
| 550 |
+
"eval_loss": 0.07044515013694763,
|
| 551 |
+
"eval_runtime": 125.3307,
|
| 552 |
+
"eval_samples_per_second": 19.923,
|
| 553 |
+
"eval_steps_per_second": 1.253,
|
| 554 |
+
"step": 9750
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 9.11,
|
| 558 |
+
"learning_rate": 9.308127818827369e-06,
|
| 559 |
+
"loss": 0.0014,
|
| 560 |
+
"step": 10000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 9.11,
|
| 564 |
+
"eval_loss": 0.07252407819032669,
|
| 565 |
+
"eval_runtime": 125.329,
|
| 566 |
+
"eval_samples_per_second": 19.924,
|
| 567 |
+
"eval_steps_per_second": 1.253,
|
| 568 |
+
"step": 10000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 9.34,
|
| 572 |
+
"learning_rate": 6.909125803665675e-06,
|
| 573 |
+
"loss": 0.0012,
|
| 574 |
+
"step": 10250
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 9.34,
|
| 578 |
+
"eval_loss": 0.07298342883586884,
|
| 579 |
+
"eval_runtime": 125.3163,
|
| 580 |
+
"eval_samples_per_second": 19.926,
|
| 581 |
+
"eval_steps_per_second": 1.253,
|
| 582 |
+
"step": 10250
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 9.57,
|
| 586 |
+
"learning_rate": 4.510123788503983e-06,
|
| 587 |
+
"loss": 0.0012,
|
| 588 |
+
"step": 10500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 9.57,
|
| 592 |
+
"eval_loss": 0.07320970296859741,
|
| 593 |
+
"eval_runtime": 125.318,
|
| 594 |
+
"eval_samples_per_second": 19.925,
|
| 595 |
+
"eval_steps_per_second": 1.253,
|
| 596 |
+
"step": 10500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 9.79,
|
| 600 |
+
"learning_rate": 2.11112177334229e-06,
|
| 601 |
+
"loss": 0.0013,
|
| 602 |
+
"step": 10750
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 9.79,
|
| 606 |
+
"eval_loss": 0.07287949323654175,
|
| 607 |
+
"eval_runtime": 125.3257,
|
| 608 |
+
"eval_samples_per_second": 19.924,
|
| 609 |
+
"eval_steps_per_second": 1.253,
|
| 610 |
+
"step": 10750
|
| 611 |
+
}
|
| 612 |
+
],
|
| 613 |
+
"max_steps": 10970,
|
| 614 |
+
"num_train_epochs": 10,
|
| 615 |
+
"total_flos": 2.0454829414889472e+17,
|
| 616 |
+
"trial_name": null,
|
| 617 |
+
"trial_params": null
|
| 618 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ab448b7200df8a6ea7c01858ce1acb157a82a9450e57880108f11850920715
|
| 3 |
+
size 4027
|