sakunaj1996@gmail.com
commited on
Commit
•
15dfb3d
1
Parent(s):
0e84a06
Initial commit
Browse files- config.json +60 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer_config.json +113 -0
- trainer_state.json +639 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-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 |
+
"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 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.26.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
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": "4.26.0"
|
| 7 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf62a433f8a0b35905fdca4966b958503f230ea33aa33ed6df48272691e995e
|
| 3 |
+
size 1783380741
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2fb1e73f35e66575848d9ab6118aa05091908b7cf1bfd08f3c72bf1b3c63305
|
| 3 |
+
size 891702929
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e93157e390a8d678a1a7cdf1a647d6d6ee2a5508ea474f5088bb2408d76a7d25
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:858b9591988a6893ca1347369557958ff310d33a108608c92e8c9454bad29551
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4508e4b2bd059556ce46ca7eba30bc525614894a05b37d919d3e1a4b32ee1480
|
| 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 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
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": "t5-base",
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"special_tokens_map_file": null,
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5060370564460754,
|
| 3 |
+
"best_model_checkpoint": "t5_results/checkpoint-46875",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 46875,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 1.978752e-05,
|
| 13 |
+
"loss": 0.7612,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 1.9574613333333336e-05,
|
| 19 |
+
"loss": 0.67,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 1.9361280000000002e-05,
|
| 25 |
+
"loss": 0.6474,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 1.914794666666667e-05,
|
| 31 |
+
"loss": 0.6322,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 1.8934613333333335e-05,
|
| 37 |
+
"loss": 0.6293,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.32,
|
| 42 |
+
"learning_rate": 1.8721706666666667e-05,
|
| 43 |
+
"loss": 0.6208,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.37,
|
| 48 |
+
"learning_rate": 1.8508373333333333e-05,
|
| 49 |
+
"loss": 0.6115,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.43,
|
| 54 |
+
"learning_rate": 1.8295040000000003e-05,
|
| 55 |
+
"loss": 0.6073,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"learning_rate": 1.8081706666666666e-05,
|
| 61 |
+
"loss": 0.6049,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.53,
|
| 66 |
+
"learning_rate": 1.7868373333333336e-05,
|
| 67 |
+
"loss": 0.6014,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.59,
|
| 72 |
+
"learning_rate": 1.7655040000000002e-05,
|
| 73 |
+
"loss": 0.5932,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.64,
|
| 78 |
+
"learning_rate": 1.744170666666667e-05,
|
| 79 |
+
"loss": 0.5947,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.69,
|
| 84 |
+
"learning_rate": 1.7228373333333335e-05,
|
| 85 |
+
"loss": 0.5972,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.75,
|
| 90 |
+
"learning_rate": 1.701504e-05,
|
| 91 |
+
"loss": 0.5875,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 1.6801706666666668e-05,
|
| 97 |
+
"loss": 0.5896,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"learning_rate": 1.6588373333333335e-05,
|
| 103 |
+
"loss": 0.5832,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.91,
|
| 108 |
+
"learning_rate": 1.637546666666667e-05,
|
| 109 |
+
"loss": 0.5866,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.96,
|
| 114 |
+
"learning_rate": 1.616256e-05,
|
| 115 |
+
"loss": 0.5815,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0,
|
| 120 |
+
"eval_gen_len": 17.2391,
|
| 121 |
+
"eval_loss": 0.5298414826393127,
|
| 122 |
+
"eval_rouge1": 72.5682,
|
| 123 |
+
"eval_rouge2": 63.0274,
|
| 124 |
+
"eval_rougeL": 71.9035,
|
| 125 |
+
"eval_rougeLsum": 71.9355,
|
| 126 |
+
"eval_runtime": 1951.2025,
|
| 127 |
+
"eval_samples_per_second": 51.25,
|
| 128 |
+
"eval_steps_per_second": 3.203,
|
| 129 |
+
"step": 9375
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.01,
|
| 133 |
+
"learning_rate": 1.5949226666666667e-05,
|
| 134 |
+
"loss": 0.5847,
|
| 135 |
+
"step": 9500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.07,
|
| 139 |
+
"learning_rate": 1.5735893333333334e-05,
|
| 140 |
+
"loss": 0.5753,
|
| 141 |
+
"step": 10000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.12,
|
| 145 |
+
"learning_rate": 1.5522560000000003e-05,
|
| 146 |
+
"loss": 0.5704,
|
| 147 |
+
"step": 10500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.17,
|
| 151 |
+
"learning_rate": 1.5309226666666666e-05,
|
| 152 |
+
"loss": 0.5757,
|
| 153 |
+
"step": 11000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.23,
|
| 157 |
+
"learning_rate": 1.5095893333333333e-05,
|
| 158 |
+
"loss": 0.571,
|
| 159 |
+
"step": 11500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.28,
|
| 163 |
+
"learning_rate": 1.4882560000000001e-05,
|
| 164 |
+
"loss": 0.5684,
|
| 165 |
+
"step": 12000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.33,
|
| 169 |
+
"learning_rate": 1.4669226666666667e-05,
|
| 170 |
+
"loss": 0.5713,
|
| 171 |
+
"step": 12500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.39,
|
| 175 |
+
"learning_rate": 1.4455893333333336e-05,
|
| 176 |
+
"loss": 0.5652,
|
| 177 |
+
"step": 13000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 1.4242986666666667e-05,
|
| 182 |
+
"loss": 0.5671,
|
| 183 |
+
"step": 13500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.49,
|
| 187 |
+
"learning_rate": 1.4029653333333335e-05,
|
| 188 |
+
"loss": 0.5646,
|
| 189 |
+
"step": 14000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.55,
|
| 193 |
+
"learning_rate": 1.3817173333333333e-05,
|
| 194 |
+
"loss": 0.564,
|
| 195 |
+
"step": 14500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6,
|
| 199 |
+
"learning_rate": 1.3603840000000001e-05,
|
| 200 |
+
"loss": 0.5628,
|
| 201 |
+
"step": 15000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.65,
|
| 205 |
+
"learning_rate": 1.3390506666666668e-05,
|
| 206 |
+
"loss": 0.5638,
|
| 207 |
+
"step": 15500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.71,
|
| 211 |
+
"learning_rate": 1.3177173333333336e-05,
|
| 212 |
+
"loss": 0.5631,
|
| 213 |
+
"step": 16000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.76,
|
| 217 |
+
"learning_rate": 1.296384e-05,
|
| 218 |
+
"loss": 0.5641,
|
| 219 |
+
"step": 16500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.81,
|
| 223 |
+
"learning_rate": 1.2750933333333335e-05,
|
| 224 |
+
"loss": 0.5659,
|
| 225 |
+
"step": 17000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.87,
|
| 229 |
+
"learning_rate": 1.25376e-05,
|
| 230 |
+
"loss": 0.5625,
|
| 231 |
+
"step": 17500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.92,
|
| 235 |
+
"learning_rate": 1.2324266666666666e-05,
|
| 236 |
+
"loss": 0.5637,
|
| 237 |
+
"step": 18000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.97,
|
| 241 |
+
"learning_rate": 1.2110933333333335e-05,
|
| 242 |
+
"loss": 0.5626,
|
| 243 |
+
"step": 18500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.0,
|
| 247 |
+
"eval_gen_len": 17.2327,
|
| 248 |
+
"eval_loss": 0.5176606774330139,
|
| 249 |
+
"eval_rouge1": 72.7237,
|
| 250 |
+
"eval_rouge2": 63.3082,
|
| 251 |
+
"eval_rougeL": 72.0632,
|
| 252 |
+
"eval_rougeLsum": 72.0935,
|
| 253 |
+
"eval_runtime": 1949.9946,
|
| 254 |
+
"eval_samples_per_second": 51.282,
|
| 255 |
+
"eval_steps_per_second": 3.205,
|
| 256 |
+
"step": 18750
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.03,
|
| 260 |
+
"learning_rate": 1.1897600000000001e-05,
|
| 261 |
+
"loss": 0.5541,
|
| 262 |
+
"step": 19000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.08,
|
| 266 |
+
"learning_rate": 1.1684266666666668e-05,
|
| 267 |
+
"loss": 0.557,
|
| 268 |
+
"step": 19500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.13,
|
| 272 |
+
"learning_rate": 1.1470933333333334e-05,
|
| 273 |
+
"loss": 0.5559,
|
| 274 |
+
"step": 20000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.19,
|
| 278 |
+
"learning_rate": 1.1257600000000002e-05,
|
| 279 |
+
"loss": 0.5577,
|
| 280 |
+
"step": 20500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.24,
|
| 284 |
+
"learning_rate": 1.1044266666666667e-05,
|
| 285 |
+
"loss": 0.5506,
|
| 286 |
+
"step": 21000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.29,
|
| 290 |
+
"learning_rate": 1.0830933333333333e-05,
|
| 291 |
+
"loss": 0.5517,
|
| 292 |
+
"step": 21500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.35,
|
| 296 |
+
"learning_rate": 1.0617600000000001e-05,
|
| 297 |
+
"loss": 0.551,
|
| 298 |
+
"step": 22000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.4,
|
| 302 |
+
"learning_rate": 1.0404266666666666e-05,
|
| 303 |
+
"loss": 0.5507,
|
| 304 |
+
"step": 22500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.45,
|
| 308 |
+
"learning_rate": 1.0191360000000001e-05,
|
| 309 |
+
"loss": 0.5501,
|
| 310 |
+
"step": 23000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.51,
|
| 314 |
+
"learning_rate": 9.978026666666667e-06,
|
| 315 |
+
"loss": 0.552,
|
| 316 |
+
"step": 23500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.56,
|
| 320 |
+
"learning_rate": 9.764693333333334e-06,
|
| 321 |
+
"loss": 0.5511,
|
| 322 |
+
"step": 24000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.61,
|
| 326 |
+
"learning_rate": 9.55136e-06,
|
| 327 |
+
"loss": 0.5479,
|
| 328 |
+
"step": 24500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.67,
|
| 332 |
+
"learning_rate": 9.338453333333333e-06,
|
| 333 |
+
"loss": 0.5522,
|
| 334 |
+
"step": 25000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.72,
|
| 338 |
+
"learning_rate": 9.12512e-06,
|
| 339 |
+
"loss": 0.5511,
|
| 340 |
+
"step": 25500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.77,
|
| 344 |
+
"learning_rate": 8.912213333333335e-06,
|
| 345 |
+
"loss": 0.5502,
|
| 346 |
+
"step": 26000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.83,
|
| 350 |
+
"learning_rate": 8.698880000000001e-06,
|
| 351 |
+
"loss": 0.548,
|
| 352 |
+
"step": 26500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.88,
|
| 356 |
+
"learning_rate": 8.485546666666667e-06,
|
| 357 |
+
"loss": 0.5513,
|
| 358 |
+
"step": 27000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.93,
|
| 362 |
+
"learning_rate": 8.272213333333334e-06,
|
| 363 |
+
"loss": 0.5484,
|
| 364 |
+
"step": 27500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.99,
|
| 368 |
+
"learning_rate": 8.05888e-06,
|
| 369 |
+
"loss": 0.547,
|
| 370 |
+
"step": 28000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.0,
|
| 374 |
+
"eval_gen_len": 17.2248,
|
| 375 |
+
"eval_loss": 0.5098650455474854,
|
| 376 |
+
"eval_rouge1": 72.8028,
|
| 377 |
+
"eval_rouge2": 63.4587,
|
| 378 |
+
"eval_rougeL": 72.1437,
|
| 379 |
+
"eval_rougeLsum": 72.1738,
|
| 380 |
+
"eval_runtime": 1955.4373,
|
| 381 |
+
"eval_samples_per_second": 51.139,
|
| 382 |
+
"eval_steps_per_second": 3.196,
|
| 383 |
+
"step": 28125
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.04,
|
| 387 |
+
"learning_rate": 7.845546666666667e-06,
|
| 388 |
+
"loss": 0.5466,
|
| 389 |
+
"step": 28500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.09,
|
| 393 |
+
"learning_rate": 7.632640000000002e-06,
|
| 394 |
+
"loss": 0.5464,
|
| 395 |
+
"step": 29000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.15,
|
| 399 |
+
"learning_rate": 7.419306666666667e-06,
|
| 400 |
+
"loss": 0.5484,
|
| 401 |
+
"step": 29500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.2,
|
| 405 |
+
"learning_rate": 7.2059733333333336e-06,
|
| 406 |
+
"loss": 0.5421,
|
| 407 |
+
"step": 30000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.25,
|
| 411 |
+
"learning_rate": 6.992640000000001e-06,
|
| 412 |
+
"loss": 0.5425,
|
| 413 |
+
"step": 30500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.31,
|
| 417 |
+
"learning_rate": 6.779306666666667e-06,
|
| 418 |
+
"loss": 0.5446,
|
| 419 |
+
"step": 31000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.36,
|
| 423 |
+
"learning_rate": 6.565973333333335e-06,
|
| 424 |
+
"loss": 0.5407,
|
| 425 |
+
"step": 31500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.41,
|
| 429 |
+
"learning_rate": 6.352640000000001e-06,
|
| 430 |
+
"loss": 0.546,
|
| 431 |
+
"step": 32000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.47,
|
| 435 |
+
"learning_rate": 6.139306666666667e-06,
|
| 436 |
+
"loss": 0.5415,
|
| 437 |
+
"step": 32500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.52,
|
| 441 |
+
"learning_rate": 5.925973333333334e-06,
|
| 442 |
+
"loss": 0.5456,
|
| 443 |
+
"step": 33000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.57,
|
| 447 |
+
"learning_rate": 5.71264e-06,
|
| 448 |
+
"loss": 0.5435,
|
| 449 |
+
"step": 33500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.63,
|
| 453 |
+
"learning_rate": 5.4997333333333335e-06,
|
| 454 |
+
"loss": 0.5424,
|
| 455 |
+
"step": 34000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.68,
|
| 459 |
+
"learning_rate": 5.2868266666666665e-06,
|
| 460 |
+
"loss": 0.5439,
|
| 461 |
+
"step": 34500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.73,
|
| 465 |
+
"learning_rate": 5.073493333333334e-06,
|
| 466 |
+
"loss": 0.5402,
|
| 467 |
+
"step": 35000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.79,
|
| 471 |
+
"learning_rate": 4.86016e-06,
|
| 472 |
+
"loss": 0.5396,
|
| 473 |
+
"step": 35500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.84,
|
| 477 |
+
"learning_rate": 4.6468266666666675e-06,
|
| 478 |
+
"loss": 0.5362,
|
| 479 |
+
"step": 36000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.89,
|
| 483 |
+
"learning_rate": 4.4339200000000006e-06,
|
| 484 |
+
"loss": 0.5459,
|
| 485 |
+
"step": 36500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.95,
|
| 489 |
+
"learning_rate": 4.220586666666667e-06,
|
| 490 |
+
"loss": 0.5419,
|
| 491 |
+
"step": 37000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.0,
|
| 495 |
+
"learning_rate": 4.0072533333333335e-06,
|
| 496 |
+
"loss": 0.5432,
|
| 497 |
+
"step": 37500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.0,
|
| 501 |
+
"eval_gen_len": 17.2265,
|
| 502 |
+
"eval_loss": 0.5071600079536438,
|
| 503 |
+
"eval_rouge1": 72.831,
|
| 504 |
+
"eval_rouge2": 63.5122,
|
| 505 |
+
"eval_rougeL": 72.1737,
|
| 506 |
+
"eval_rougeLsum": 72.2038,
|
| 507 |
+
"eval_runtime": 1947.9767,
|
| 508 |
+
"eval_samples_per_second": 51.335,
|
| 509 |
+
"eval_steps_per_second": 3.208,
|
| 510 |
+
"step": 37500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 4.05,
|
| 514 |
+
"learning_rate": 3.7939200000000003e-06,
|
| 515 |
+
"loss": 0.5406,
|
| 516 |
+
"step": 38000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.11,
|
| 520 |
+
"learning_rate": 3.5810133333333334e-06,
|
| 521 |
+
"loss": 0.5414,
|
| 522 |
+
"step": 38500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 4.16,
|
| 526 |
+
"learning_rate": 3.368106666666667e-06,
|
| 527 |
+
"loss": 0.539,
|
| 528 |
+
"step": 39000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.21,
|
| 532 |
+
"learning_rate": 3.1547733333333337e-06,
|
| 533 |
+
"loss": 0.5391,
|
| 534 |
+
"step": 39500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 4.27,
|
| 538 |
+
"learning_rate": 2.9414400000000006e-06,
|
| 539 |
+
"loss": 0.5385,
|
| 540 |
+
"step": 40000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 4.32,
|
| 544 |
+
"learning_rate": 2.7281066666666666e-06,
|
| 545 |
+
"loss": 0.5391,
|
| 546 |
+
"step": 40500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 4.37,
|
| 550 |
+
"learning_rate": 2.5147733333333335e-06,
|
| 551 |
+
"loss": 0.5372,
|
| 552 |
+
"step": 41000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 4.43,
|
| 556 |
+
"learning_rate": 2.30144e-06,
|
| 557 |
+
"loss": 0.5375,
|
| 558 |
+
"step": 41500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.48,
|
| 562 |
+
"learning_rate": 2.0885333333333334e-06,
|
| 563 |
+
"loss": 0.5364,
|
| 564 |
+
"step": 42000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.53,
|
| 568 |
+
"learning_rate": 1.8752e-06,
|
| 569 |
+
"loss": 0.5343,
|
| 570 |
+
"step": 42500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.59,
|
| 574 |
+
"learning_rate": 1.661866666666667e-06,
|
| 575 |
+
"loss": 0.5386,
|
| 576 |
+
"step": 43000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.64,
|
| 580 |
+
"learning_rate": 1.4485333333333334e-06,
|
| 581 |
+
"loss": 0.5362,
|
| 582 |
+
"step": 43500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.69,
|
| 586 |
+
"learning_rate": 1.2352e-06,
|
| 587 |
+
"loss": 0.5385,
|
| 588 |
+
"step": 44000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.75,
|
| 592 |
+
"learning_rate": 1.0218666666666667e-06,
|
| 593 |
+
"loss": 0.5411,
|
| 594 |
+
"step": 44500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.8,
|
| 598 |
+
"learning_rate": 8.085333333333334e-07,
|
| 599 |
+
"loss": 0.537,
|
| 600 |
+
"step": 45000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.85,
|
| 604 |
+
"learning_rate": 5.952e-07,
|
| 605 |
+
"loss": 0.5378,
|
| 606 |
+
"step": 45500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 4.91,
|
| 610 |
+
"learning_rate": 3.818666666666667e-07,
|
| 611 |
+
"loss": 0.5407,
|
| 612 |
+
"step": 46000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.96,
|
| 616 |
+
"learning_rate": 1.6896000000000003e-07,
|
| 617 |
+
"loss": 0.54,
|
| 618 |
+
"step": 46500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.0,
|
| 622 |
+
"eval_gen_len": 17.2227,
|
| 623 |
+
"eval_loss": 0.5060370564460754,
|
| 624 |
+
"eval_rouge1": 72.8556,
|
| 625 |
+
"eval_rouge2": 63.5466,
|
| 626 |
+
"eval_rougeL": 72.1975,
|
| 627 |
+
"eval_rougeLsum": 72.228,
|
| 628 |
+
"eval_runtime": 1951.1899,
|
| 629 |
+
"eval_samples_per_second": 51.251,
|
| 630 |
+
"eval_steps_per_second": 3.203,
|
| 631 |
+
"step": 46875
|
| 632 |
+
}
|
| 633 |
+
],
|
| 634 |
+
"max_steps": 46875,
|
| 635 |
+
"num_train_epochs": 5,
|
| 636 |
+
"total_flos": 3.315684370415616e+17,
|
| 637 |
+
"trial_name": null,
|
| 638 |
+
"trial_params": null
|
| 639 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c74f14789b573292fcf6296a4a4c7a81cc003f1bd7d7c73f5bd5953f396be26
|
| 3 |
+
size 3579
|