Hubert commit
Browse filesFlat T5 77M. trained on 3 datasets 48k records. Vero poor results
- config.json +61 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
- trainer_state.json +464 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MBZUAI/LaMini-Flan-T5-77M",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 1024,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.20.1",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32100
|
| 61 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d43731255471a785ea9c72a039191b954a7c6c5b895cc8a2ad3f85344a1fbc8
|
| 3 |
+
size 615571145
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c997c08839e2b9e455c6b2d8726c9db386551f568af99d2462fd74b9ca73e8
|
| 3 |
+
size 307793733
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee38bad2f1acd6dcd8c0800ce6d24023bfbf77862af659027c32dd3f607b3383
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:222996cf72a7616ed87e81fbd9ff328d265f9b13e18de3364b4def1a53b8b352
|
| 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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"pad_token": "<pad>",
|
| 108 |
+
"sp_model_kwargs": {},
|
| 109 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,464 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.578947368421053,
|
| 5 |
+
"global_step": 8000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 0.0002962686567164179,
|
| 13 |
+
"loss": 1.5814,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"eval_loss": 0.0006077612633816898,
|
| 19 |
+
"eval_runtime": 128.8821,
|
| 20 |
+
"eval_samples_per_second": 75.48,
|
| 21 |
+
"eval_steps_per_second": 2.359,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.41,
|
| 26 |
+
"learning_rate": 0.00029004975124378106,
|
| 27 |
+
"loss": 0.0051,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.41,
|
| 32 |
+
"eval_loss": 0.0004873188154306263,
|
| 33 |
+
"eval_runtime": 129.1791,
|
| 34 |
+
"eval_samples_per_second": 75.306,
|
| 35 |
+
"eval_steps_per_second": 2.353,
|
| 36 |
+
"step": 500
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.62,
|
| 40 |
+
"learning_rate": 0.00028383084577114425,
|
| 41 |
+
"loss": 0.0033,
|
| 42 |
+
"step": 750
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.62,
|
| 46 |
+
"eval_loss": 0.0002883475972339511,
|
| 47 |
+
"eval_runtime": 128.9078,
|
| 48 |
+
"eval_samples_per_second": 75.465,
|
| 49 |
+
"eval_steps_per_second": 2.358,
|
| 50 |
+
"step": 750
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.82,
|
| 54 |
+
"learning_rate": 0.00027761194029850744,
|
| 55 |
+
"loss": 0.0026,
|
| 56 |
+
"step": 1000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.82,
|
| 60 |
+
"eval_loss": 0.00016567455895710737,
|
| 61 |
+
"eval_runtime": 128.8984,
|
| 62 |
+
"eval_samples_per_second": 75.47,
|
| 63 |
+
"eval_steps_per_second": 2.358,
|
| 64 |
+
"step": 1000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.03,
|
| 68 |
+
"learning_rate": 0.00027139303482587063,
|
| 69 |
+
"loss": 0.002,
|
| 70 |
+
"step": 1250
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.03,
|
| 74 |
+
"eval_loss": 0.0001291305961785838,
|
| 75 |
+
"eval_runtime": 128.8976,
|
| 76 |
+
"eval_samples_per_second": 75.471,
|
| 77 |
+
"eval_steps_per_second": 2.358,
|
| 78 |
+
"step": 1250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.23,
|
| 82 |
+
"learning_rate": 0.0002651741293532338,
|
| 83 |
+
"loss": 0.0016,
|
| 84 |
+
"step": 1500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.23,
|
| 88 |
+
"eval_loss": 0.00010879799810936674,
|
| 89 |
+
"eval_runtime": 128.8894,
|
| 90 |
+
"eval_samples_per_second": 75.476,
|
| 91 |
+
"eval_steps_per_second": 2.359,
|
| 92 |
+
"step": 1500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.44,
|
| 96 |
+
"learning_rate": 0.000258955223880597,
|
| 97 |
+
"loss": 0.0014,
|
| 98 |
+
"step": 1750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.44,
|
| 102 |
+
"eval_loss": 0.00010257180110784248,
|
| 103 |
+
"eval_runtime": 129.1985,
|
| 104 |
+
"eval_samples_per_second": 75.295,
|
| 105 |
+
"eval_steps_per_second": 2.353,
|
| 106 |
+
"step": 1750
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.64,
|
| 110 |
+
"learning_rate": 0.0002527363184079602,
|
| 111 |
+
"loss": 0.0012,
|
| 112 |
+
"step": 2000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.64,
|
| 116 |
+
"eval_loss": 6.881527951918542e-05,
|
| 117 |
+
"eval_runtime": 129.1934,
|
| 118 |
+
"eval_samples_per_second": 75.298,
|
| 119 |
+
"eval_steps_per_second": 2.353,
|
| 120 |
+
"step": 2000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.85,
|
| 124 |
+
"learning_rate": 0.00024651741293532333,
|
| 125 |
+
"loss": 0.0016,
|
| 126 |
+
"step": 2250
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.85,
|
| 130 |
+
"eval_loss": 7.058009214233607e-05,
|
| 131 |
+
"eval_runtime": 128.8993,
|
| 132 |
+
"eval_samples_per_second": 75.47,
|
| 133 |
+
"eval_steps_per_second": 2.358,
|
| 134 |
+
"step": 2250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.06,
|
| 138 |
+
"learning_rate": 0.00024029850746268655,
|
| 139 |
+
"loss": 0.001,
|
| 140 |
+
"step": 2500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.06,
|
| 144 |
+
"eval_loss": 6.400555139407516e-05,
|
| 145 |
+
"eval_runtime": 128.8789,
|
| 146 |
+
"eval_samples_per_second": 75.482,
|
| 147 |
+
"eval_steps_per_second": 2.359,
|
| 148 |
+
"step": 2500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.26,
|
| 152 |
+
"learning_rate": 0.0002340796019900497,
|
| 153 |
+
"loss": 0.001,
|
| 154 |
+
"step": 2750
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.26,
|
| 158 |
+
"eval_loss": 6.463182216975838e-05,
|
| 159 |
+
"eval_runtime": 128.8854,
|
| 160 |
+
"eval_samples_per_second": 75.478,
|
| 161 |
+
"eval_steps_per_second": 2.359,
|
| 162 |
+
"step": 2750
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.47,
|
| 166 |
+
"learning_rate": 0.00022786069651741292,
|
| 167 |
+
"loss": 0.0012,
|
| 168 |
+
"step": 3000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.47,
|
| 172 |
+
"eval_loss": 0.0001349268713966012,
|
| 173 |
+
"eval_runtime": 128.8866,
|
| 174 |
+
"eval_samples_per_second": 75.477,
|
| 175 |
+
"eval_steps_per_second": 2.359,
|
| 176 |
+
"step": 3000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.67,
|
| 180 |
+
"learning_rate": 0.0002216417910447761,
|
| 181 |
+
"loss": 0.0009,
|
| 182 |
+
"step": 3250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.67,
|
| 186 |
+
"eval_loss": 6.4761312387418e-05,
|
| 187 |
+
"eval_runtime": 129.1959,
|
| 188 |
+
"eval_samples_per_second": 75.296,
|
| 189 |
+
"eval_steps_per_second": 2.353,
|
| 190 |
+
"step": 3250
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.88,
|
| 194 |
+
"learning_rate": 0.00021542288557213927,
|
| 195 |
+
"loss": 0.0009,
|
| 196 |
+
"step": 3500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.88,
|
| 200 |
+
"eval_loss": 5.111826249049045e-05,
|
| 201 |
+
"eval_runtime": 128.8809,
|
| 202 |
+
"eval_samples_per_second": 75.481,
|
| 203 |
+
"eval_steps_per_second": 2.359,
|
| 204 |
+
"step": 3500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.08,
|
| 208 |
+
"learning_rate": 0.00020920398009950246,
|
| 209 |
+
"loss": 0.0007,
|
| 210 |
+
"step": 3750
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.08,
|
| 214 |
+
"eval_loss": 6.521103205159307e-05,
|
| 215 |
+
"eval_runtime": 128.9,
|
| 216 |
+
"eval_samples_per_second": 75.469,
|
| 217 |
+
"eval_steps_per_second": 2.358,
|
| 218 |
+
"step": 3750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.29,
|
| 222 |
+
"learning_rate": 0.00020298507462686565,
|
| 223 |
+
"loss": 0.0007,
|
| 224 |
+
"step": 4000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.29,
|
| 228 |
+
"eval_loss": 4.892368451692164e-05,
|
| 229 |
+
"eval_runtime": 128.8971,
|
| 230 |
+
"eval_samples_per_second": 75.471,
|
| 231 |
+
"eval_steps_per_second": 2.358,
|
| 232 |
+
"step": 4000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.5,
|
| 236 |
+
"learning_rate": 0.00019676616915422884,
|
| 237 |
+
"loss": 0.0006,
|
| 238 |
+
"step": 4250
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.5,
|
| 242 |
+
"eval_loss": 4.084123429493047e-05,
|
| 243 |
+
"eval_runtime": 69.0191,
|
| 244 |
+
"eval_samples_per_second": 140.947,
|
| 245 |
+
"eval_steps_per_second": 4.405,
|
| 246 |
+
"step": 4250
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.7,
|
| 250 |
+
"learning_rate": 0.00019054726368159203,
|
| 251 |
+
"loss": 0.0006,
|
| 252 |
+
"step": 4500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.7,
|
| 256 |
+
"eval_loss": 6.229727296158671e-05,
|
| 257 |
+
"eval_runtime": 83.9466,
|
| 258 |
+
"eval_samples_per_second": 115.883,
|
| 259 |
+
"eval_steps_per_second": 3.621,
|
| 260 |
+
"step": 4500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.91,
|
| 264 |
+
"learning_rate": 0.00018432835820895522,
|
| 265 |
+
"loss": 0.0008,
|
| 266 |
+
"step": 4750
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.91,
|
| 270 |
+
"eval_loss": 4.437619645614177e-05,
|
| 271 |
+
"eval_runtime": 129.1502,
|
| 272 |
+
"eval_samples_per_second": 75.323,
|
| 273 |
+
"eval_steps_per_second": 2.354,
|
| 274 |
+
"step": 4750
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.11,
|
| 278 |
+
"learning_rate": 0.00017810945273631838,
|
| 279 |
+
"loss": 0.0008,
|
| 280 |
+
"step": 5000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.11,
|
| 284 |
+
"eval_loss": 4.2610481614246964e-05,
|
| 285 |
+
"eval_runtime": 128.7805,
|
| 286 |
+
"eval_samples_per_second": 75.539,
|
| 287 |
+
"eval_steps_per_second": 2.361,
|
| 288 |
+
"step": 5000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.32,
|
| 292 |
+
"learning_rate": 0.00017189054726368157,
|
| 293 |
+
"loss": 0.0005,
|
| 294 |
+
"step": 5250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.32,
|
| 298 |
+
"eval_loss": 7.266196189448237e-05,
|
| 299 |
+
"eval_runtime": 128.7609,
|
| 300 |
+
"eval_samples_per_second": 75.551,
|
| 301 |
+
"eval_steps_per_second": 2.361,
|
| 302 |
+
"step": 5250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.52,
|
| 306 |
+
"learning_rate": 0.00016567164179104478,
|
| 307 |
+
"loss": 0.0006,
|
| 308 |
+
"step": 5500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.52,
|
| 312 |
+
"eval_loss": 3.264641054556705e-05,
|
| 313 |
+
"eval_runtime": 128.7913,
|
| 314 |
+
"eval_samples_per_second": 75.533,
|
| 315 |
+
"eval_steps_per_second": 2.36,
|
| 316 |
+
"step": 5500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.73,
|
| 320 |
+
"learning_rate": 0.00015945273631840794,
|
| 321 |
+
"loss": 0.0005,
|
| 322 |
+
"step": 5750
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.73,
|
| 326 |
+
"eval_loss": 2.6435563995619304e-05,
|
| 327 |
+
"eval_runtime": 128.7891,
|
| 328 |
+
"eval_samples_per_second": 75.534,
|
| 329 |
+
"eval_steps_per_second": 2.36,
|
| 330 |
+
"step": 5750
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.93,
|
| 334 |
+
"learning_rate": 0.00015323383084577113,
|
| 335 |
+
"loss": 0.0006,
|
| 336 |
+
"step": 6000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.93,
|
| 340 |
+
"eval_loss": 4.4951906602364033e-05,
|
| 341 |
+
"eval_runtime": 129.1622,
|
| 342 |
+
"eval_samples_per_second": 75.316,
|
| 343 |
+
"eval_steps_per_second": 2.354,
|
| 344 |
+
"step": 6000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.14,
|
| 348 |
+
"learning_rate": 0.00014701492537313432,
|
| 349 |
+
"loss": 0.0005,
|
| 350 |
+
"step": 6250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.14,
|
| 354 |
+
"eval_loss": 3.5103537811664864e-05,
|
| 355 |
+
"eval_runtime": 128.7717,
|
| 356 |
+
"eval_samples_per_second": 75.545,
|
| 357 |
+
"eval_steps_per_second": 2.361,
|
| 358 |
+
"step": 6250
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.35,
|
| 362 |
+
"learning_rate": 0.00014079601990049748,
|
| 363 |
+
"loss": 0.0004,
|
| 364 |
+
"step": 6500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 5.35,
|
| 368 |
+
"eval_loss": 3.251100133638829e-05,
|
| 369 |
+
"eval_runtime": 128.8099,
|
| 370 |
+
"eval_samples_per_second": 75.522,
|
| 371 |
+
"eval_steps_per_second": 2.36,
|
| 372 |
+
"step": 6500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.55,
|
| 376 |
+
"learning_rate": 0.0001345771144278607,
|
| 377 |
+
"loss": 0.0004,
|
| 378 |
+
"step": 6750
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.55,
|
| 382 |
+
"eval_loss": 3.5094544728053734e-05,
|
| 383 |
+
"eval_runtime": 128.8083,
|
| 384 |
+
"eval_samples_per_second": 75.523,
|
| 385 |
+
"eval_steps_per_second": 2.36,
|
| 386 |
+
"step": 6750
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.76,
|
| 390 |
+
"learning_rate": 0.00012835820895522386,
|
| 391 |
+
"loss": 0.0005,
|
| 392 |
+
"step": 7000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.76,
|
| 396 |
+
"eval_loss": 3.747216032934375e-05,
|
| 397 |
+
"eval_runtime": 128.7944,
|
| 398 |
+
"eval_samples_per_second": 75.531,
|
| 399 |
+
"eval_steps_per_second": 2.36,
|
| 400 |
+
"step": 7000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 5.96,
|
| 404 |
+
"learning_rate": 0.00012213930348258705,
|
| 405 |
+
"loss": 0.0004,
|
| 406 |
+
"step": 7250
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 5.96,
|
| 410 |
+
"eval_loss": 2.8431584723875858e-05,
|
| 411 |
+
"eval_runtime": 129.1362,
|
| 412 |
+
"eval_samples_per_second": 75.331,
|
| 413 |
+
"eval_steps_per_second": 2.354,
|
| 414 |
+
"step": 7250
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 6.17,
|
| 418 |
+
"learning_rate": 0.00011592039800995025,
|
| 419 |
+
"loss": 0.0003,
|
| 420 |
+
"step": 7500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 6.17,
|
| 424 |
+
"eval_loss": 2.733626024564728e-05,
|
| 425 |
+
"eval_runtime": 128.9297,
|
| 426 |
+
"eval_samples_per_second": 75.452,
|
| 427 |
+
"eval_steps_per_second": 2.358,
|
| 428 |
+
"step": 7500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 6.37,
|
| 432 |
+
"learning_rate": 0.00010970149253731342,
|
| 433 |
+
"loss": 0.0004,
|
| 434 |
+
"step": 7750
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.37,
|
| 438 |
+
"eval_loss": 2.5848928999039344e-05,
|
| 439 |
+
"eval_runtime": 128.8142,
|
| 440 |
+
"eval_samples_per_second": 75.52,
|
| 441 |
+
"eval_steps_per_second": 2.36,
|
| 442 |
+
"step": 7750
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 6.58,
|
| 446 |
+
"learning_rate": 0.0001034825870646766,
|
| 447 |
+
"loss": 0.0003,
|
| 448 |
+
"step": 8000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.58,
|
| 452 |
+
"eval_loss": 3.0041233912925236e-05,
|
| 453 |
+
"eval_runtime": 128.8146,
|
| 454 |
+
"eval_samples_per_second": 75.519,
|
| 455 |
+
"eval_steps_per_second": 2.36,
|
| 456 |
+
"step": 8000
|
| 457 |
+
}
|
| 458 |
+
],
|
| 459 |
+
"max_steps": 12160,
|
| 460 |
+
"num_train_epochs": 10,
|
| 461 |
+
"total_flos": 4.757334967871078e+16,
|
| 462 |
+
"trial_name": null,
|
| 463 |
+
"trial_params": null
|
| 464 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb202b48ecacc52660cacad3e74762f4ec298a01587361604c97e604f113ed18
|
| 3 |
+
size 3311
|