Commit
•
ca79b4c
1
Parent(s):
d90455b
feat: Baseline Model
Browse files
- config.json +60 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +467 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 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": 6,
|
| 21 |
+
"num_heads": 8,
|
| 22 |
+
"num_layers": 6,
|
| 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": "4.30.2",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.30.2"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f84b3cc9fb8e9717544736645adf6cd4b86a75e35e579416077c9d1743ce9e41
|
| 3 |
+
size 484130565
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa51035225c92add97277af43f4abfa1b8e0fff2b471b95315e9d09dba25e46e
|
| 3 |
+
size 242071641
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff6959ed8d1291fd55400668e43aee7512eb604c51c6ffc6749f160bd1ff3d1
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daaedac35250ef1ced3437442c43e80298f6c3c1a8e743335e3ed835bcb73680
|
| 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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 512,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"tokenizer_class": "T5Tokenizer",
|
| 110 |
+
"unk_token": "<unk>"
|
| 111 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,467 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.653179190751445,
|
| 5 |
+
"global_step": 17000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.58,
|
| 12 |
+
"learning_rate": 1.15606936416185e-05,
|
| 13 |
+
"loss": 4.1602,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_gen_len": 15.5003,
|
| 19 |
+
"eval_loss": 2.8024423122406006,
|
| 20 |
+
"eval_rouge1": 0.2552,
|
| 21 |
+
"eval_rouge2": 0.1019,
|
| 22 |
+
"eval_rougeL": 0.2331,
|
| 23 |
+
"eval_rougeLsum": 0.2332,
|
| 24 |
+
"eval_runtime": 184.148,
|
| 25 |
+
"eval_samples_per_second": 18.778,
|
| 26 |
+
"eval_steps_per_second": 1.178,
|
| 27 |
+
"step": 865
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.16,
|
| 31 |
+
"learning_rate": 1.9835716458777003e-05,
|
| 32 |
+
"loss": 3.1173,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.73,
|
| 37 |
+
"learning_rate": 1.922725889869182e-05,
|
| 38 |
+
"loss": 2.9624,
|
| 39 |
+
"step": 1500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_gen_len": 15.8271,
|
| 44 |
+
"eval_loss": 2.6451988220214844,
|
| 45 |
+
"eval_rouge1": 0.2882,
|
| 46 |
+
"eval_rouge2": 0.1183,
|
| 47 |
+
"eval_rougeL": 0.2626,
|
| 48 |
+
"eval_rougeLsum": 0.2626,
|
| 49 |
+
"eval_runtime": 182.4271,
|
| 50 |
+
"eval_samples_per_second": 18.956,
|
| 51 |
+
"eval_steps_per_second": 1.19,
|
| 52 |
+
"step": 1730
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.31,
|
| 56 |
+
"learning_rate": 1.8618801338606633e-05,
|
| 57 |
+
"loss": 2.8766,
|
| 58 |
+
"step": 2000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.89,
|
| 62 |
+
"learning_rate": 1.801034377852145e-05,
|
| 63 |
+
"loss": 2.8206,
|
| 64 |
+
"step": 2500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.0,
|
| 68 |
+
"eval_gen_len": 16.2183,
|
| 69 |
+
"eval_loss": 2.5787582397460938,
|
| 70 |
+
"eval_rouge1": 0.2952,
|
| 71 |
+
"eval_rouge2": 0.1218,
|
| 72 |
+
"eval_rougeL": 0.2684,
|
| 73 |
+
"eval_rougeLsum": 0.2685,
|
| 74 |
+
"eval_runtime": 182.2993,
|
| 75 |
+
"eval_samples_per_second": 18.969,
|
| 76 |
+
"eval_steps_per_second": 1.19,
|
| 77 |
+
"step": 2595
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.47,
|
| 81 |
+
"learning_rate": 1.7401886218436267e-05,
|
| 82 |
+
"loss": 2.7764,
|
| 83 |
+
"step": 3000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.0,
|
| 87 |
+
"eval_gen_len": 16.3418,
|
| 88 |
+
"eval_loss": 2.5332629680633545,
|
| 89 |
+
"eval_rouge1": 0.3029,
|
| 90 |
+
"eval_rouge2": 0.1258,
|
| 91 |
+
"eval_rougeL": 0.2755,
|
| 92 |
+
"eval_rougeLsum": 0.2754,
|
| 93 |
+
"eval_runtime": 181.4496,
|
| 94 |
+
"eval_samples_per_second": 19.058,
|
| 95 |
+
"eval_steps_per_second": 1.196,
|
| 96 |
+
"step": 3460
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 4.05,
|
| 100 |
+
"learning_rate": 1.679342865835108e-05,
|
| 101 |
+
"loss": 2.7414,
|
| 102 |
+
"step": 3500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.62,
|
| 106 |
+
"learning_rate": 1.6184971098265897e-05,
|
| 107 |
+
"loss": 2.6997,
|
| 108 |
+
"step": 4000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.0,
|
| 112 |
+
"eval_gen_len": 16.4101,
|
| 113 |
+
"eval_loss": 2.504000186920166,
|
| 114 |
+
"eval_rouge1": 0.3046,
|
| 115 |
+
"eval_rouge2": 0.1273,
|
| 116 |
+
"eval_rougeL": 0.2773,
|
| 117 |
+
"eval_rougeLsum": 0.2771,
|
| 118 |
+
"eval_runtime": 181.6751,
|
| 119 |
+
"eval_samples_per_second": 19.034,
|
| 120 |
+
"eval_steps_per_second": 1.194,
|
| 121 |
+
"step": 4325
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 5.2,
|
| 125 |
+
"learning_rate": 1.5576513538180714e-05,
|
| 126 |
+
"loss": 2.6795,
|
| 127 |
+
"step": 4500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 5.78,
|
| 131 |
+
"learning_rate": 1.4968055978095528e-05,
|
| 132 |
+
"loss": 2.6647,
|
| 133 |
+
"step": 5000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 6.0,
|
| 137 |
+
"eval_gen_len": 16.354,
|
| 138 |
+
"eval_loss": 2.4734175205230713,
|
| 139 |
+
"eval_rouge1": 0.3069,
|
| 140 |
+
"eval_rouge2": 0.1298,
|
| 141 |
+
"eval_rougeL": 0.2802,
|
| 142 |
+
"eval_rougeLsum": 0.2801,
|
| 143 |
+
"eval_runtime": 181.0262,
|
| 144 |
+
"eval_samples_per_second": 19.102,
|
| 145 |
+
"eval_steps_per_second": 1.199,
|
| 146 |
+
"step": 5190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.36,
|
| 150 |
+
"learning_rate": 1.4359598418010346e-05,
|
| 151 |
+
"loss": 2.6287,
|
| 152 |
+
"step": 5500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.94,
|
| 156 |
+
"learning_rate": 1.375114085792516e-05,
|
| 157 |
+
"loss": 2.6196,
|
| 158 |
+
"step": 6000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 7.0,
|
| 162 |
+
"eval_gen_len": 16.526,
|
| 163 |
+
"eval_loss": 2.4547228813171387,
|
| 164 |
+
"eval_rouge1": 0.3077,
|
| 165 |
+
"eval_rouge2": 0.131,
|
| 166 |
+
"eval_rougeL": 0.2804,
|
| 167 |
+
"eval_rougeLsum": 0.2804,
|
| 168 |
+
"eval_runtime": 182.5951,
|
| 169 |
+
"eval_samples_per_second": 18.938,
|
| 170 |
+
"eval_steps_per_second": 1.188,
|
| 171 |
+
"step": 6055
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.51,
|
| 175 |
+
"learning_rate": 1.3142683297839978e-05,
|
| 176 |
+
"loss": 2.5916,
|
| 177 |
+
"step": 6500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.0,
|
| 181 |
+
"eval_gen_len": 16.4419,
|
| 182 |
+
"eval_loss": 2.435168504714966,
|
| 183 |
+
"eval_rouge1": 0.3107,
|
| 184 |
+
"eval_rouge2": 0.1332,
|
| 185 |
+
"eval_rougeL": 0.2833,
|
| 186 |
+
"eval_rougeLsum": 0.2834,
|
| 187 |
+
"eval_runtime": 181.1692,
|
| 188 |
+
"eval_samples_per_second": 19.087,
|
| 189 |
+
"eval_steps_per_second": 1.198,
|
| 190 |
+
"step": 6920
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 8.09,
|
| 194 |
+
"learning_rate": 1.2534225737754793e-05,
|
| 195 |
+
"loss": 2.5986,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 8.67,
|
| 200 |
+
"learning_rate": 1.1925768177669607e-05,
|
| 201 |
+
"loss": 2.5716,
|
| 202 |
+
"step": 7500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 9.0,
|
| 206 |
+
"eval_gen_len": 16.4023,
|
| 207 |
+
"eval_loss": 2.4196717739105225,
|
| 208 |
+
"eval_rouge1": 0.3092,
|
| 209 |
+
"eval_rouge2": 0.132,
|
| 210 |
+
"eval_rougeL": 0.2819,
|
| 211 |
+
"eval_rougeLsum": 0.2817,
|
| 212 |
+
"eval_runtime": 181.3331,
|
| 213 |
+
"eval_samples_per_second": 19.07,
|
| 214 |
+
"eval_steps_per_second": 1.197,
|
| 215 |
+
"step": 7785
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 9.25,
|
| 219 |
+
"learning_rate": 1.1317310617584426e-05,
|
| 220 |
+
"loss": 2.5347,
|
| 221 |
+
"step": 8000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 9.83,
|
| 225 |
+
"learning_rate": 1.070885305749924e-05,
|
| 226 |
+
"loss": 2.548,
|
| 227 |
+
"step": 8500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 10.0,
|
| 231 |
+
"eval_gen_len": 16.3256,
|
| 232 |
+
"eval_loss": 2.4123945236206055,
|
| 233 |
+
"eval_rouge1": 0.3094,
|
| 234 |
+
"eval_rouge2": 0.1329,
|
| 235 |
+
"eval_rougeL": 0.2822,
|
| 236 |
+
"eval_rougeLsum": 0.2823,
|
| 237 |
+
"eval_runtime": 181.1565,
|
| 238 |
+
"eval_samples_per_second": 19.088,
|
| 239 |
+
"eval_steps_per_second": 1.198,
|
| 240 |
+
"step": 8650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 10.4,
|
| 244 |
+
"learning_rate": 1.0100395497414058e-05,
|
| 245 |
+
"loss": 2.5237,
|
| 246 |
+
"step": 9000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 10.98,
|
| 250 |
+
"learning_rate": 9.491937937328873e-06,
|
| 251 |
+
"loss": 2.5352,
|
| 252 |
+
"step": 9500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 11.0,
|
| 256 |
+
"eval_gen_len": 16.3774,
|
| 257 |
+
"eval_loss": 2.402285575866699,
|
| 258 |
+
"eval_rouge1": 0.3096,
|
| 259 |
+
"eval_rouge2": 0.1323,
|
| 260 |
+
"eval_rougeL": 0.2821,
|
| 261 |
+
"eval_rougeLsum": 0.282,
|
| 262 |
+
"eval_runtime": 181.4776,
|
| 263 |
+
"eval_samples_per_second": 19.055,
|
| 264 |
+
"eval_steps_per_second": 1.196,
|
| 265 |
+
"step": 9515
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 11.56,
|
| 269 |
+
"learning_rate": 8.883480377243688e-06,
|
| 270 |
+
"loss": 2.5087,
|
| 271 |
+
"step": 10000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 12.0,
|
| 275 |
+
"eval_gen_len": 16.4592,
|
| 276 |
+
"eval_loss": 2.39676570892334,
|
| 277 |
+
"eval_rouge1": 0.3107,
|
| 278 |
+
"eval_rouge2": 0.1326,
|
| 279 |
+
"eval_rougeL": 0.2831,
|
| 280 |
+
"eval_rougeLsum": 0.2832,
|
| 281 |
+
"eval_runtime": 182.2228,
|
| 282 |
+
"eval_samples_per_second": 18.977,
|
| 283 |
+
"eval_steps_per_second": 1.191,
|
| 284 |
+
"step": 10380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 12.14,
|
| 288 |
+
"learning_rate": 8.275022817158503e-06,
|
| 289 |
+
"loss": 2.514,
|
| 290 |
+
"step": 10500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 12.72,
|
| 294 |
+
"learning_rate": 7.66656525707332e-06,
|
| 295 |
+
"loss": 2.4865,
|
| 296 |
+
"step": 11000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 13.0,
|
| 300 |
+
"eval_gen_len": 16.4586,
|
| 301 |
+
"eval_loss": 2.38985013961792,
|
| 302 |
+
"eval_rouge1": 0.3117,
|
| 303 |
+
"eval_rouge2": 0.1339,
|
| 304 |
+
"eval_rougeL": 0.2841,
|
| 305 |
+
"eval_rougeLsum": 0.2842,
|
| 306 |
+
"eval_runtime": 181.3381,
|
| 307 |
+
"eval_samples_per_second": 19.069,
|
| 308 |
+
"eval_steps_per_second": 1.197,
|
| 309 |
+
"step": 11245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 13.29,
|
| 313 |
+
"learning_rate": 7.058107696988135e-06,
|
| 314 |
+
"loss": 2.4861,
|
| 315 |
+
"step": 11500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 13.87,
|
| 319 |
+
"learning_rate": 6.449650136902952e-06,
|
| 320 |
+
"loss": 2.5081,
|
| 321 |
+
"step": 12000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 14.0,
|
| 325 |
+
"eval_gen_len": 16.4072,
|
| 326 |
+
"eval_loss": 2.3885083198547363,
|
| 327 |
+
"eval_rouge1": 0.3124,
|
| 328 |
+
"eval_rouge2": 0.1337,
|
| 329 |
+
"eval_rougeL": 0.2845,
|
| 330 |
+
"eval_rougeLsum": 0.2845,
|
| 331 |
+
"eval_runtime": 181.2166,
|
| 332 |
+
"eval_samples_per_second": 19.082,
|
| 333 |
+
"eval_steps_per_second": 1.197,
|
| 334 |
+
"step": 12110
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 14.45,
|
| 338 |
+
"learning_rate": 5.841192576817768e-06,
|
| 339 |
+
"loss": 2.4748,
|
| 340 |
+
"step": 12500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 15.0,
|
| 344 |
+
"eval_gen_len": 16.4572,
|
| 345 |
+
"eval_loss": 2.3791513442993164,
|
| 346 |
+
"eval_rouge1": 0.3131,
|
| 347 |
+
"eval_rouge2": 0.134,
|
| 348 |
+
"eval_rougeL": 0.285,
|
| 349 |
+
"eval_rougeLsum": 0.2849,
|
| 350 |
+
"eval_runtime": 181.192,
|
| 351 |
+
"eval_samples_per_second": 19.085,
|
| 352 |
+
"eval_steps_per_second": 1.198,
|
| 353 |
+
"step": 12975
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 15.03,
|
| 357 |
+
"learning_rate": 5.232735016732583e-06,
|
| 358 |
+
"loss": 2.4641,
|
| 359 |
+
"step": 13000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 15.61,
|
| 363 |
+
"learning_rate": 4.6242774566473994e-06,
|
| 364 |
+
"loss": 2.469,
|
| 365 |
+
"step": 13500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 16.0,
|
| 369 |
+
"eval_gen_len": 16.3907,
|
| 370 |
+
"eval_loss": 2.3784728050231934,
|
| 371 |
+
"eval_rouge1": 0.3119,
|
| 372 |
+
"eval_rouge2": 0.1333,
|
| 373 |
+
"eval_rougeL": 0.2841,
|
| 374 |
+
"eval_rougeLsum": 0.284,
|
| 375 |
+
"eval_runtime": 180.9918,
|
| 376 |
+
"eval_samples_per_second": 19.106,
|
| 377 |
+
"eval_steps_per_second": 1.199,
|
| 378 |
+
"step": 13840
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 16.18,
|
| 382 |
+
"learning_rate": 4.0158198965622155e-06,
|
| 383 |
+
"loss": 2.4771,
|
| 384 |
+
"step": 14000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 16.76,
|
| 388 |
+
"learning_rate": 3.4073623364770307e-06,
|
| 389 |
+
"loss": 2.4587,
|
| 390 |
+
"step": 14500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 17.0,
|
| 394 |
+
"eval_gen_len": 16.4488,
|
| 395 |
+
"eval_loss": 2.3765616416931152,
|
| 396 |
+
"eval_rouge1": 0.3115,
|
| 397 |
+
"eval_rouge2": 0.1334,
|
| 398 |
+
"eval_rougeL": 0.2835,
|
| 399 |
+
"eval_rougeLsum": 0.2834,
|
| 400 |
+
"eval_runtime": 181.9602,
|
| 401 |
+
"eval_samples_per_second": 19.004,
|
| 402 |
+
"eval_steps_per_second": 1.193,
|
| 403 |
+
"step": 14705
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 17.34,
|
| 407 |
+
"learning_rate": 2.798904776391847e-06,
|
| 408 |
+
"loss": 2.4679,
|
| 409 |
+
"step": 15000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 17.92,
|
| 413 |
+
"learning_rate": 2.1904472163066628e-06,
|
| 414 |
+
"loss": 2.4428,
|
| 415 |
+
"step": 15500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 18.0,
|
| 419 |
+
"eval_gen_len": 16.4141,
|
| 420 |
+
"eval_loss": 2.375408411026001,
|
| 421 |
+
"eval_rouge1": 0.3137,
|
| 422 |
+
"eval_rouge2": 0.1346,
|
| 423 |
+
"eval_rougeL": 0.2854,
|
| 424 |
+
"eval_rougeLsum": 0.2854,
|
| 425 |
+
"eval_runtime": 181.1095,
|
| 426 |
+
"eval_samples_per_second": 19.093,
|
| 427 |
+
"eval_steps_per_second": 1.198,
|
| 428 |
+
"step": 15570
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 18.5,
|
| 432 |
+
"learning_rate": 1.5819896562214788e-06,
|
| 433 |
+
"loss": 2.4548,
|
| 434 |
+
"step": 16000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 19.0,
|
| 438 |
+
"eval_gen_len": 16.4451,
|
| 439 |
+
"eval_loss": 2.3725531101226807,
|
| 440 |
+
"eval_rouge1": 0.3129,
|
| 441 |
+
"eval_rouge2": 0.1341,
|
| 442 |
+
"eval_rougeL": 0.2849,
|
| 443 |
+
"eval_rougeLsum": 0.285,
|
| 444 |
+
"eval_runtime": 180.98,
|
| 445 |
+
"eval_samples_per_second": 19.107,
|
| 446 |
+
"eval_steps_per_second": 1.199,
|
| 447 |
+
"step": 16435
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 19.08,
|
| 451 |
+
"learning_rate": 9.735320961362946e-07,
|
| 452 |
+
"loss": 2.4426,
|
| 453 |
+
"step": 16500
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 19.65,
|
| 457 |
+
"learning_rate": 3.650745360511105e-07,
|
| 458 |
+
"loss": 2.4389,
|
| 459 |
+
"step": 17000
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"max_steps": 17300,
|
| 463 |
+
"num_train_epochs": 20,
|
| 464 |
+
"total_flos": 6.944051276532941e+16,
|
| 465 |
+
"trial_name": null,
|
| 466 |
+
"trial_params": null
|
| 467 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:037777afe7f6a0e02734b8f27ee76168428c6a68b7c2296930ac277edcf3ea7b
|
| 3 |
+
size 4091
|