Commit
•
45a3dcc
1
Parent(s):
b69d139
Upload 9 files
Browse files- config.json +31 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- trainer_state.json +616 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/t5-v1_1-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 |
+
"num_decoder_layers": 12,
|
| 20 |
+
"num_heads": 12,
|
| 21 |
+
"num_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.24.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32128
|
| 31 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f38869a4d989d459c9ff2c75d7970fb52a225fe23ccf571135ab26003450be72
|
| 3 |
+
size 14439
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cda965c70e092420eebf8adc9132001af6cdc5ec85651d04891049853d2035f
|
| 3 |
+
size 623
|
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 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"name_or_path": "google/t5-v1_1-base",
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/b5fc947a416ea3cb079532cb3c2bbadeb7f800fc/special_tokens_map.json",
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 72.99270072992701,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.82,
|
| 12 |
+
"learning_rate": 4.875e-05,
|
| 13 |
+
"loss": 10.1798,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.82,
|
| 18 |
+
"eval_test_accuracy": 0.0,
|
| 19 |
+
"eval_test_loss": 3.4965455532073975,
|
| 20 |
+
"eval_test_runtime": 7.5045,
|
| 21 |
+
"eval_test_samples_per_second": 162.702,
|
| 22 |
+
"eval_test_steps_per_second": 2.665,
|
| 23 |
+
"step": 250
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.65,
|
| 27 |
+
"learning_rate": 4.75e-05,
|
| 28 |
+
"loss": 4.0133,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 3.65,
|
| 33 |
+
"eval_test_accuracy": 0.085995085995086,
|
| 34 |
+
"eval_test_loss": 2.1827144622802734,
|
| 35 |
+
"eval_test_runtime": 11.227,
|
| 36 |
+
"eval_test_samples_per_second": 108.755,
|
| 37 |
+
"eval_test_steps_per_second": 1.781,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 5.47,
|
| 42 |
+
"learning_rate": 4.6250000000000006e-05,
|
| 43 |
+
"loss": 2.1831,
|
| 44 |
+
"step": 750
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.47,
|
| 48 |
+
"eval_test_accuracy": 0.28992628992628994,
|
| 49 |
+
"eval_test_loss": 1.1154128313064575,
|
| 50 |
+
"eval_test_runtime": 4.9154,
|
| 51 |
+
"eval_test_samples_per_second": 248.402,
|
| 52 |
+
"eval_test_steps_per_second": 4.069,
|
| 53 |
+
"step": 750
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 7.3,
|
| 57 |
+
"learning_rate": 4.5e-05,
|
| 58 |
+
"loss": 1.178,
|
| 59 |
+
"step": 1000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 7.3,
|
| 63 |
+
"eval_test_accuracy": 0.4430794430794431,
|
| 64 |
+
"eval_test_loss": 0.7581946849822998,
|
| 65 |
+
"eval_test_runtime": 5.2157,
|
| 66 |
+
"eval_test_samples_per_second": 234.1,
|
| 67 |
+
"eval_test_steps_per_second": 3.835,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 9.12,
|
| 72 |
+
"learning_rate": 4.375e-05,
|
| 73 |
+
"loss": 0.8603,
|
| 74 |
+
"step": 1250
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 9.12,
|
| 78 |
+
"eval_test_accuracy": 0.506961506961507,
|
| 79 |
+
"eval_test_loss": 0.6857301592826843,
|
| 80 |
+
"eval_test_runtime": 4.1605,
|
| 81 |
+
"eval_test_samples_per_second": 293.474,
|
| 82 |
+
"eval_test_steps_per_second": 4.807,
|
| 83 |
+
"step": 1250
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 10.95,
|
| 87 |
+
"learning_rate": 4.25e-05,
|
| 88 |
+
"loss": 0.7179,
|
| 89 |
+
"step": 1500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 10.95,
|
| 93 |
+
"eval_test_accuracy": 0.5356265356265356,
|
| 94 |
+
"eval_test_loss": 0.629558801651001,
|
| 95 |
+
"eval_test_runtime": 4.1543,
|
| 96 |
+
"eval_test_samples_per_second": 293.909,
|
| 97 |
+
"eval_test_steps_per_second": 4.814,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 12.77,
|
| 102 |
+
"learning_rate": 4.125e-05,
|
| 103 |
+
"loss": 0.6347,
|
| 104 |
+
"step": 1750
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 12.77,
|
| 108 |
+
"eval_test_accuracy": 0.556920556920557,
|
| 109 |
+
"eval_test_loss": 0.6828880310058594,
|
| 110 |
+
"eval_test_runtime": 4.1527,
|
| 111 |
+
"eval_test_samples_per_second": 294.026,
|
| 112 |
+
"eval_test_steps_per_second": 4.816,
|
| 113 |
+
"step": 1750
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 14.6,
|
| 117 |
+
"learning_rate": 4e-05,
|
| 118 |
+
"loss": 0.5714,
|
| 119 |
+
"step": 2000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 14.6,
|
| 123 |
+
"eval_test_accuracy": 0.5683865683865684,
|
| 124 |
+
"eval_test_loss": 0.6402557492256165,
|
| 125 |
+
"eval_test_runtime": 4.1126,
|
| 126 |
+
"eval_test_samples_per_second": 296.89,
|
| 127 |
+
"eval_test_steps_per_second": 4.863,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 16.42,
|
| 132 |
+
"learning_rate": 3.875e-05,
|
| 133 |
+
"loss": 0.535,
|
| 134 |
+
"step": 2250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 16.42,
|
| 138 |
+
"eval_test_accuracy": 0.5823095823095823,
|
| 139 |
+
"eval_test_loss": 0.6427932381629944,
|
| 140 |
+
"eval_test_runtime": 4.1425,
|
| 141 |
+
"eval_test_samples_per_second": 294.751,
|
| 142 |
+
"eval_test_steps_per_second": 4.828,
|
| 143 |
+
"step": 2250
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 18.25,
|
| 147 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 148 |
+
"loss": 0.4864,
|
| 149 |
+
"step": 2500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 18.25,
|
| 153 |
+
"eval_test_accuracy": 0.5749385749385749,
|
| 154 |
+
"eval_test_loss": 0.6692995429039001,
|
| 155 |
+
"eval_test_runtime": 4.1218,
|
| 156 |
+
"eval_test_samples_per_second": 296.233,
|
| 157 |
+
"eval_test_steps_per_second": 4.852,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 20.07,
|
| 162 |
+
"learning_rate": 3.625e-05,
|
| 163 |
+
"loss": 0.4523,
|
| 164 |
+
"step": 2750
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 20.07,
|
| 168 |
+
"eval_test_accuracy": 0.588042588042588,
|
| 169 |
+
"eval_test_loss": 0.6854296326637268,
|
| 170 |
+
"eval_test_runtime": 4.1256,
|
| 171 |
+
"eval_test_samples_per_second": 295.954,
|
| 172 |
+
"eval_test_steps_per_second": 4.848,
|
| 173 |
+
"step": 2750
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 21.9,
|
| 177 |
+
"learning_rate": 3.5e-05,
|
| 178 |
+
"loss": 0.4267,
|
| 179 |
+
"step": 3000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 21.9,
|
| 183 |
+
"eval_test_accuracy": 0.5847665847665847,
|
| 184 |
+
"eval_test_loss": 0.6832742691040039,
|
| 185 |
+
"eval_test_runtime": 4.114,
|
| 186 |
+
"eval_test_samples_per_second": 296.79,
|
| 187 |
+
"eval_test_steps_per_second": 4.861,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 23.72,
|
| 192 |
+
"learning_rate": 3.375000000000001e-05,
|
| 193 |
+
"loss": 0.4017,
|
| 194 |
+
"step": 3250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 23.72,
|
| 198 |
+
"eval_test_accuracy": 0.5864045864045864,
|
| 199 |
+
"eval_test_loss": 0.7026733756065369,
|
| 200 |
+
"eval_test_runtime": 4.162,
|
| 201 |
+
"eval_test_samples_per_second": 293.366,
|
| 202 |
+
"eval_test_steps_per_second": 4.805,
|
| 203 |
+
"step": 3250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 25.55,
|
| 207 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 208 |
+
"loss": 0.3737,
|
| 209 |
+
"step": 3500
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 25.55,
|
| 213 |
+
"eval_test_accuracy": 0.5823095823095823,
|
| 214 |
+
"eval_test_loss": 0.7358095645904541,
|
| 215 |
+
"eval_test_runtime": 4.1139,
|
| 216 |
+
"eval_test_samples_per_second": 296.797,
|
| 217 |
+
"eval_test_steps_per_second": 4.862,
|
| 218 |
+
"step": 3500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 27.37,
|
| 222 |
+
"learning_rate": 3.125e-05,
|
| 223 |
+
"loss": 0.3567,
|
| 224 |
+
"step": 3750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 27.37,
|
| 228 |
+
"eval_test_accuracy": 0.583947583947584,
|
| 229 |
+
"eval_test_loss": 0.7573221921920776,
|
| 230 |
+
"eval_test_runtime": 4.1462,
|
| 231 |
+
"eval_test_samples_per_second": 294.489,
|
| 232 |
+
"eval_test_steps_per_second": 4.824,
|
| 233 |
+
"step": 3750
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 29.2,
|
| 237 |
+
"learning_rate": 3e-05,
|
| 238 |
+
"loss": 0.3329,
|
| 239 |
+
"step": 4000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 29.2,
|
| 243 |
+
"eval_test_accuracy": 0.5831285831285832,
|
| 244 |
+
"eval_test_loss": 0.7671645283699036,
|
| 245 |
+
"eval_test_runtime": 4.1876,
|
| 246 |
+
"eval_test_samples_per_second": 291.577,
|
| 247 |
+
"eval_test_steps_per_second": 4.776,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 31.02,
|
| 252 |
+
"learning_rate": 2.8749999999999997e-05,
|
| 253 |
+
"loss": 0.3178,
|
| 254 |
+
"step": 4250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 31.02,
|
| 258 |
+
"eval_test_accuracy": 0.5937755937755937,
|
| 259 |
+
"eval_test_loss": 0.8280954360961914,
|
| 260 |
+
"eval_test_runtime": 4.1401,
|
| 261 |
+
"eval_test_samples_per_second": 294.919,
|
| 262 |
+
"eval_test_steps_per_second": 4.831,
|
| 263 |
+
"step": 4250
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 32.85,
|
| 267 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 268 |
+
"loss": 0.3031,
|
| 269 |
+
"step": 4500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 32.85,
|
| 273 |
+
"eval_test_accuracy": 0.5954135954135954,
|
| 274 |
+
"eval_test_loss": 0.8298905491828918,
|
| 275 |
+
"eval_test_runtime": 4.1172,
|
| 276 |
+
"eval_test_samples_per_second": 296.557,
|
| 277 |
+
"eval_test_steps_per_second": 4.858,
|
| 278 |
+
"step": 4500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 34.67,
|
| 282 |
+
"learning_rate": 2.625e-05,
|
| 283 |
+
"loss": 0.2942,
|
| 284 |
+
"step": 4750
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 34.67,
|
| 288 |
+
"eval_test_accuracy": 0.592956592956593,
|
| 289 |
+
"eval_test_loss": 0.8406508564949036,
|
| 290 |
+
"eval_test_runtime": 4.1428,
|
| 291 |
+
"eval_test_samples_per_second": 294.726,
|
| 292 |
+
"eval_test_steps_per_second": 4.828,
|
| 293 |
+
"step": 4750
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 36.5,
|
| 297 |
+
"learning_rate": 2.5e-05,
|
| 298 |
+
"loss": 0.2794,
|
| 299 |
+
"step": 5000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 36.5,
|
| 303 |
+
"eval_test_accuracy": 0.6003276003276004,
|
| 304 |
+
"eval_test_loss": 0.8442530035972595,
|
| 305 |
+
"eval_test_runtime": 4.3235,
|
| 306 |
+
"eval_test_samples_per_second": 282.409,
|
| 307 |
+
"eval_test_steps_per_second": 4.626,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 38.32,
|
| 312 |
+
"learning_rate": 2.375e-05,
|
| 313 |
+
"loss": 0.2733,
|
| 314 |
+
"step": 5250
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 38.32,
|
| 318 |
+
"eval_test_accuracy": 0.6052416052416052,
|
| 319 |
+
"eval_test_loss": 0.8638033270835876,
|
| 320 |
+
"eval_test_runtime": 4.1266,
|
| 321 |
+
"eval_test_samples_per_second": 295.887,
|
| 322 |
+
"eval_test_steps_per_second": 4.847,
|
| 323 |
+
"step": 5250
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 40.15,
|
| 327 |
+
"learning_rate": 2.25e-05,
|
| 328 |
+
"loss": 0.2631,
|
| 329 |
+
"step": 5500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 40.15,
|
| 333 |
+
"eval_test_accuracy": 0.5888615888615889,
|
| 334 |
+
"eval_test_loss": 0.890779435634613,
|
| 335 |
+
"eval_test_runtime": 4.1284,
|
| 336 |
+
"eval_test_samples_per_second": 295.759,
|
| 337 |
+
"eval_test_steps_per_second": 4.845,
|
| 338 |
+
"step": 5500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 41.97,
|
| 342 |
+
"learning_rate": 2.125e-05,
|
| 343 |
+
"loss": 0.2574,
|
| 344 |
+
"step": 5750
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 41.97,
|
| 348 |
+
"eval_test_accuracy": 0.588042588042588,
|
| 349 |
+
"eval_test_loss": 0.9194920063018799,
|
| 350 |
+
"eval_test_runtime": 4.2329,
|
| 351 |
+
"eval_test_samples_per_second": 288.451,
|
| 352 |
+
"eval_test_steps_per_second": 4.725,
|
| 353 |
+
"step": 5750
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 43.8,
|
| 357 |
+
"learning_rate": 2e-05,
|
| 358 |
+
"loss": 0.2445,
|
| 359 |
+
"step": 6000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 43.8,
|
| 363 |
+
"eval_test_accuracy": 0.5913185913185913,
|
| 364 |
+
"eval_test_loss": 0.9236257672309875,
|
| 365 |
+
"eval_test_runtime": 4.1684,
|
| 366 |
+
"eval_test_samples_per_second": 292.916,
|
| 367 |
+
"eval_test_steps_per_second": 4.798,
|
| 368 |
+
"step": 6000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 45.62,
|
| 372 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 373 |
+
"loss": 0.2417,
|
| 374 |
+
"step": 6250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 45.62,
|
| 378 |
+
"eval_test_accuracy": 0.5913185913185913,
|
| 379 |
+
"eval_test_loss": 0.9303093552589417,
|
| 380 |
+
"eval_test_runtime": 4.1896,
|
| 381 |
+
"eval_test_samples_per_second": 291.435,
|
| 382 |
+
"eval_test_steps_per_second": 4.774,
|
| 383 |
+
"step": 6250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 47.45,
|
| 387 |
+
"learning_rate": 1.75e-05,
|
| 388 |
+
"loss": 0.2316,
|
| 389 |
+
"step": 6500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 47.45,
|
| 393 |
+
"eval_test_accuracy": 0.6060606060606061,
|
| 394 |
+
"eval_test_loss": 0.9456475377082825,
|
| 395 |
+
"eval_test_runtime": 4.1609,
|
| 396 |
+
"eval_test_samples_per_second": 293.446,
|
| 397 |
+
"eval_test_steps_per_second": 4.807,
|
| 398 |
+
"step": 6500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 49.27,
|
| 402 |
+
"learning_rate": 1.6250000000000002e-05,
|
| 403 |
+
"loss": 0.227,
|
| 404 |
+
"step": 6750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 49.27,
|
| 408 |
+
"eval_test_accuracy": 0.5978705978705978,
|
| 409 |
+
"eval_test_loss": 0.9745798110961914,
|
| 410 |
+
"eval_test_runtime": 4.1394,
|
| 411 |
+
"eval_test_samples_per_second": 294.971,
|
| 412 |
+
"eval_test_steps_per_second": 4.832,
|
| 413 |
+
"step": 6750
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 51.09,
|
| 417 |
+
"learning_rate": 1.5e-05,
|
| 418 |
+
"loss": 0.2241,
|
| 419 |
+
"step": 7000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 51.09,
|
| 423 |
+
"eval_test_accuracy": 0.6052416052416052,
|
| 424 |
+
"eval_test_loss": 0.938654899597168,
|
| 425 |
+
"eval_test_runtime": 4.1652,
|
| 426 |
+
"eval_test_samples_per_second": 293.143,
|
| 427 |
+
"eval_test_steps_per_second": 4.802,
|
| 428 |
+
"step": 7000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 52.92,
|
| 432 |
+
"learning_rate": 1.3750000000000002e-05,
|
| 433 |
+
"loss": 0.2174,
|
| 434 |
+
"step": 7250
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 52.92,
|
| 438 |
+
"eval_test_accuracy": 0.5986895986895987,
|
| 439 |
+
"eval_test_loss": 0.9762380719184875,
|
| 440 |
+
"eval_test_runtime": 4.2021,
|
| 441 |
+
"eval_test_samples_per_second": 290.57,
|
| 442 |
+
"eval_test_steps_per_second": 4.76,
|
| 443 |
+
"step": 7250
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 54.74,
|
| 447 |
+
"learning_rate": 1.25e-05,
|
| 448 |
+
"loss": 0.212,
|
| 449 |
+
"step": 7500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 54.74,
|
| 453 |
+
"eval_test_accuracy": 0.601965601965602,
|
| 454 |
+
"eval_test_loss": 0.9834132194519043,
|
| 455 |
+
"eval_test_runtime": 4.1906,
|
| 456 |
+
"eval_test_samples_per_second": 291.369,
|
| 457 |
+
"eval_test_steps_per_second": 4.773,
|
| 458 |
+
"step": 7500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 56.57,
|
| 462 |
+
"learning_rate": 1.125e-05,
|
| 463 |
+
"loss": 0.206,
|
| 464 |
+
"step": 7750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 56.57,
|
| 468 |
+
"eval_test_accuracy": 0.5995085995085995,
|
| 469 |
+
"eval_test_loss": 0.9860948920249939,
|
| 470 |
+
"eval_test_runtime": 4.1715,
|
| 471 |
+
"eval_test_samples_per_second": 292.702,
|
| 472 |
+
"eval_test_steps_per_second": 4.794,
|
| 473 |
+
"step": 7750
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 58.39,
|
| 477 |
+
"learning_rate": 1e-05,
|
| 478 |
+
"loss": 0.2057,
|
| 479 |
+
"step": 8000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 58.39,
|
| 483 |
+
"eval_test_accuracy": 0.5962325962325963,
|
| 484 |
+
"eval_test_loss": 1.0094884634017944,
|
| 485 |
+
"eval_test_runtime": 4.2216,
|
| 486 |
+
"eval_test_samples_per_second": 289.23,
|
| 487 |
+
"eval_test_steps_per_second": 4.738,
|
| 488 |
+
"step": 8000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 60.22,
|
| 492 |
+
"learning_rate": 8.75e-06,
|
| 493 |
+
"loss": 0.2023,
|
| 494 |
+
"step": 8250
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 60.22,
|
| 498 |
+
"eval_test_accuracy": 0.597051597051597,
|
| 499 |
+
"eval_test_loss": 1.000124216079712,
|
| 500 |
+
"eval_test_runtime": 4.1702,
|
| 501 |
+
"eval_test_samples_per_second": 292.793,
|
| 502 |
+
"eval_test_steps_per_second": 4.796,
|
| 503 |
+
"step": 8250
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 62.04,
|
| 507 |
+
"learning_rate": 7.5e-06,
|
| 508 |
+
"loss": 0.1994,
|
| 509 |
+
"step": 8500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 62.04,
|
| 513 |
+
"eval_test_accuracy": 0.5995085995085995,
|
| 514 |
+
"eval_test_loss": 1.0179657936096191,
|
| 515 |
+
"eval_test_runtime": 4.1982,
|
| 516 |
+
"eval_test_samples_per_second": 290.842,
|
| 517 |
+
"eval_test_steps_per_second": 4.764,
|
| 518 |
+
"step": 8500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 63.87,
|
| 522 |
+
"learning_rate": 6.25e-06,
|
| 523 |
+
"loss": 0.1967,
|
| 524 |
+
"step": 8750
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 63.87,
|
| 528 |
+
"eval_test_accuracy": 0.6044226044226044,
|
| 529 |
+
"eval_test_loss": 1.0143113136291504,
|
| 530 |
+
"eval_test_runtime": 4.1544,
|
| 531 |
+
"eval_test_samples_per_second": 293.907,
|
| 532 |
+
"eval_test_steps_per_second": 4.814,
|
| 533 |
+
"step": 8750
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 65.69,
|
| 537 |
+
"learning_rate": 5e-06,
|
| 538 |
+
"loss": 0.1915,
|
| 539 |
+
"step": 9000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 65.69,
|
| 543 |
+
"eval_test_accuracy": 0.6011466011466011,
|
| 544 |
+
"eval_test_loss": 1.0377224683761597,
|
| 545 |
+
"eval_test_runtime": 4.1791,
|
| 546 |
+
"eval_test_samples_per_second": 292.165,
|
| 547 |
+
"eval_test_steps_per_second": 4.786,
|
| 548 |
+
"step": 9000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 67.52,
|
| 552 |
+
"learning_rate": 3.75e-06,
|
| 553 |
+
"loss": 0.1934,
|
| 554 |
+
"step": 9250
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 67.52,
|
| 558 |
+
"eval_test_accuracy": 0.601965601965602,
|
| 559 |
+
"eval_test_loss": 1.02960205078125,
|
| 560 |
+
"eval_test_runtime": 4.2049,
|
| 561 |
+
"eval_test_samples_per_second": 290.372,
|
| 562 |
+
"eval_test_steps_per_second": 4.756,
|
| 563 |
+
"step": 9250
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 69.34,
|
| 567 |
+
"learning_rate": 2.5e-06,
|
| 568 |
+
"loss": 0.1932,
|
| 569 |
+
"step": 9500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 69.34,
|
| 573 |
+
"eval_test_accuracy": 0.601965601965602,
|
| 574 |
+
"eval_test_loss": 1.0294890403747559,
|
| 575 |
+
"eval_test_runtime": 4.1796,
|
| 576 |
+
"eval_test_samples_per_second": 292.135,
|
| 577 |
+
"eval_test_steps_per_second": 4.785,
|
| 578 |
+
"step": 9500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 71.17,
|
| 582 |
+
"learning_rate": 1.25e-06,
|
| 583 |
+
"loss": 0.1898,
|
| 584 |
+
"step": 9750
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 71.17,
|
| 588 |
+
"eval_test_accuracy": 0.6011466011466011,
|
| 589 |
+
"eval_test_loss": 1.0313055515289307,
|
| 590 |
+
"eval_test_runtime": 4.1318,
|
| 591 |
+
"eval_test_samples_per_second": 295.51,
|
| 592 |
+
"eval_test_steps_per_second": 4.84,
|
| 593 |
+
"step": 9750
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 72.99,
|
| 597 |
+
"learning_rate": 0.0,
|
| 598 |
+
"loss": 0.1916,
|
| 599 |
+
"step": 10000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 72.99,
|
| 603 |
+
"eval_test_accuracy": 0.6011466011466011,
|
| 604 |
+
"eval_test_loss": 1.0304898023605347,
|
| 605 |
+
"eval_test_runtime": 4.1756,
|
| 606 |
+
"eval_test_samples_per_second": 292.415,
|
| 607 |
+
"eval_test_steps_per_second": 4.79,
|
| 608 |
+
"step": 10000
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"max_steps": 10000,
|
| 612 |
+
"num_train_epochs": 73,
|
| 613 |
+
"total_flos": 0.0,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c62aaba8695c13f291e545c190ae44fcfa71e16f73188bf67b452fbc13213ec
|
| 3 |
+
size 3567
|