Upload 12 files
Browse files- config.json +61 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +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 +937 -0
- trainer_state.json +1983 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.41.2",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
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": "4.41.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d894b0f561f44a64fed1b83cf0ff46c6a7c8b05ed35766ccc2a008b50186d819
|
| 3 |
+
size 891644712
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8a75e1ac5d82aa34f9e1835094e4e9af1f29231a75b9976be90590eb55a2b85
|
| 3 |
+
size 1783444794
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80855817725f2c98abb462ae824d11131cb32ad351603ae8cff14629b80c32cf
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69287d7a7c80dfa691bd549952560fda4424fc093a7baeab94528e81ec917b5
|
| 3 |
+
size 1064
|
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 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 1512,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1983 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3938915799371898e-07,
|
| 3 |
+
"best_model_checkpoint": "Models/t5-base-class-gen/checkpoint-11600",
|
| 4 |
+
"epoch": 4.868913857677903,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 13000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03745318352059925,
|
| 13 |
+
"grad_norm": 69268.25,
|
| 14 |
+
"learning_rate": 3.970037453183521e-05,
|
| 15 |
+
"loss": 0.5911,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03745318352059925,
|
| 20 |
+
"eval_loss": 0.11300157010555267,
|
| 21 |
+
"eval_runtime": 0.271,
|
| 22 |
+
"eval_samples_per_second": 110.716,
|
| 23 |
+
"eval_steps_per_second": 7.381,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0749063670411985,
|
| 28 |
+
"grad_norm": 40263.34765625,
|
| 29 |
+
"learning_rate": 3.9400749063670414e-05,
|
| 30 |
+
"loss": 0.1556,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0749063670411985,
|
| 35 |
+
"eval_loss": 0.044787291437387466,
|
| 36 |
+
"eval_runtime": 0.2726,
|
| 37 |
+
"eval_samples_per_second": 110.063,
|
| 38 |
+
"eval_steps_per_second": 7.338,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.11235955056179775,
|
| 43 |
+
"grad_norm": 54568.01171875,
|
| 44 |
+
"learning_rate": 3.910112359550562e-05,
|
| 45 |
+
"loss": 0.0855,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.11235955056179775,
|
| 50 |
+
"eval_loss": 0.028027888387441635,
|
| 51 |
+
"eval_runtime": 0.2713,
|
| 52 |
+
"eval_samples_per_second": 110.579,
|
| 53 |
+
"eval_steps_per_second": 7.372,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.149812734082397,
|
| 58 |
+
"grad_norm": 31384.4140625,
|
| 59 |
+
"learning_rate": 3.880149812734083e-05,
|
| 60 |
+
"loss": 0.0672,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.149812734082397,
|
| 65 |
+
"eval_loss": 0.02276856079697609,
|
| 66 |
+
"eval_runtime": 0.2731,
|
| 67 |
+
"eval_samples_per_second": 109.855,
|
| 68 |
+
"eval_steps_per_second": 7.324,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.18726591760299627,
|
| 73 |
+
"grad_norm": 47479.01953125,
|
| 74 |
+
"learning_rate": 3.850187265917604e-05,
|
| 75 |
+
"loss": 0.0427,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.18726591760299627,
|
| 80 |
+
"eval_loss": 0.01850857213139534,
|
| 81 |
+
"eval_runtime": 0.2701,
|
| 82 |
+
"eval_samples_per_second": 111.089,
|
| 83 |
+
"eval_steps_per_second": 7.406,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.2247191011235955,
|
| 88 |
+
"grad_norm": 39500.9140625,
|
| 89 |
+
"learning_rate": 3.820224719101124e-05,
|
| 90 |
+
"loss": 0.0385,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.2247191011235955,
|
| 95 |
+
"eval_loss": 0.00761110894382,
|
| 96 |
+
"eval_runtime": 0.2742,
|
| 97 |
+
"eval_samples_per_second": 109.412,
|
| 98 |
+
"eval_steps_per_second": 7.294,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.26217228464419473,
|
| 103 |
+
"grad_norm": 75871.453125,
|
| 104 |
+
"learning_rate": 3.790262172284645e-05,
|
| 105 |
+
"loss": 0.0356,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.26217228464419473,
|
| 110 |
+
"eval_loss": 0.007164248265326023,
|
| 111 |
+
"eval_runtime": 0.2703,
|
| 112 |
+
"eval_samples_per_second": 110.979,
|
| 113 |
+
"eval_steps_per_second": 7.399,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.299625468164794,
|
| 118 |
+
"grad_norm": 41190.5390625,
|
| 119 |
+
"learning_rate": 3.7602996254681646e-05,
|
| 120 |
+
"loss": 0.0268,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.299625468164794,
|
| 125 |
+
"eval_loss": 0.0059220679104328156,
|
| 126 |
+
"eval_runtime": 0.2696,
|
| 127 |
+
"eval_samples_per_second": 111.27,
|
| 128 |
+
"eval_steps_per_second": 7.418,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.33707865168539325,
|
| 133 |
+
"grad_norm": 6835.3095703125,
|
| 134 |
+
"learning_rate": 3.730337078651685e-05,
|
| 135 |
+
"loss": 0.0276,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.33707865168539325,
|
| 140 |
+
"eval_loss": 0.004661493003368378,
|
| 141 |
+
"eval_runtime": 0.2701,
|
| 142 |
+
"eval_samples_per_second": 111.086,
|
| 143 |
+
"eval_steps_per_second": 7.406,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.37453183520599254,
|
| 148 |
+
"grad_norm": 47556.41015625,
|
| 149 |
+
"learning_rate": 3.7003745318352064e-05,
|
| 150 |
+
"loss": 0.0234,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.37453183520599254,
|
| 155 |
+
"eval_loss": 0.005712361074984074,
|
| 156 |
+
"eval_runtime": 0.2702,
|
| 157 |
+
"eval_samples_per_second": 111.024,
|
| 158 |
+
"eval_steps_per_second": 7.402,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.41198501872659177,
|
| 163 |
+
"grad_norm": 20349.455078125,
|
| 164 |
+
"learning_rate": 3.670411985018727e-05,
|
| 165 |
+
"loss": 0.0288,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.41198501872659177,
|
| 170 |
+
"eval_loss": 0.0040772343054413795,
|
| 171 |
+
"eval_runtime": 0.2695,
|
| 172 |
+
"eval_samples_per_second": 111.298,
|
| 173 |
+
"eval_steps_per_second": 7.42,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.449438202247191,
|
| 178 |
+
"grad_norm": 37560.2734375,
|
| 179 |
+
"learning_rate": 3.6404494382022475e-05,
|
| 180 |
+
"loss": 0.0213,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.449438202247191,
|
| 185 |
+
"eval_loss": 0.003308301791548729,
|
| 186 |
+
"eval_runtime": 0.2703,
|
| 187 |
+
"eval_samples_per_second": 110.979,
|
| 188 |
+
"eval_steps_per_second": 7.399,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4868913857677903,
|
| 193 |
+
"grad_norm": 23133.609375,
|
| 194 |
+
"learning_rate": 3.610486891385768e-05,
|
| 195 |
+
"loss": 0.0194,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.4868913857677903,
|
| 200 |
+
"eval_loss": 0.003378539811819792,
|
| 201 |
+
"eval_runtime": 0.2712,
|
| 202 |
+
"eval_samples_per_second": 110.612,
|
| 203 |
+
"eval_steps_per_second": 7.374,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.5243445692883895,
|
| 208 |
+
"grad_norm": 8233.9853515625,
|
| 209 |
+
"learning_rate": 3.5805243445692885e-05,
|
| 210 |
+
"loss": 0.02,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.5243445692883895,
|
| 215 |
+
"eval_loss": 0.0034168362617492676,
|
| 216 |
+
"eval_runtime": 0.2693,
|
| 217 |
+
"eval_samples_per_second": 111.389,
|
| 218 |
+
"eval_steps_per_second": 7.426,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5617977528089888,
|
| 223 |
+
"grad_norm": 10800.7392578125,
|
| 224 |
+
"learning_rate": 3.550561797752809e-05,
|
| 225 |
+
"loss": 0.0201,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5617977528089888,
|
| 230 |
+
"eval_loss": 0.004822230897843838,
|
| 231 |
+
"eval_runtime": 0.2698,
|
| 232 |
+
"eval_samples_per_second": 111.205,
|
| 233 |
+
"eval_steps_per_second": 7.414,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.599250936329588,
|
| 238 |
+
"grad_norm": 18013.958984375,
|
| 239 |
+
"learning_rate": 3.52059925093633e-05,
|
| 240 |
+
"loss": 0.0175,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.599250936329588,
|
| 245 |
+
"eval_loss": 0.0028443075716495514,
|
| 246 |
+
"eval_runtime": 0.2713,
|
| 247 |
+
"eval_samples_per_second": 110.566,
|
| 248 |
+
"eval_steps_per_second": 7.371,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.6367041198501873,
|
| 253 |
+
"grad_norm": 4363.4677734375,
|
| 254 |
+
"learning_rate": 3.490636704119851e-05,
|
| 255 |
+
"loss": 0.0157,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.6367041198501873,
|
| 260 |
+
"eval_loss": 0.003480424638837576,
|
| 261 |
+
"eval_runtime": 0.2687,
|
| 262 |
+
"eval_samples_per_second": 111.651,
|
| 263 |
+
"eval_steps_per_second": 7.443,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.6741573033707865,
|
| 268 |
+
"grad_norm": 20063.248046875,
|
| 269 |
+
"learning_rate": 3.4606741573033714e-05,
|
| 270 |
+
"loss": 0.0158,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.6741573033707865,
|
| 275 |
+
"eval_loss": 0.0031679689418524504,
|
| 276 |
+
"eval_runtime": 0.2697,
|
| 277 |
+
"eval_samples_per_second": 111.228,
|
| 278 |
+
"eval_steps_per_second": 7.415,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.7116104868913857,
|
| 283 |
+
"grad_norm": 41422.4765625,
|
| 284 |
+
"learning_rate": 3.430711610486892e-05,
|
| 285 |
+
"loss": 0.0171,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.7116104868913857,
|
| 290 |
+
"eval_loss": 0.0027744669932872057,
|
| 291 |
+
"eval_runtime": 0.2732,
|
| 292 |
+
"eval_samples_per_second": 109.799,
|
| 293 |
+
"eval_steps_per_second": 7.32,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.7490636704119851,
|
| 298 |
+
"grad_norm": 32689.869140625,
|
| 299 |
+
"learning_rate": 3.4007490636704125e-05,
|
| 300 |
+
"loss": 0.0157,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.7490636704119851,
|
| 305 |
+
"eval_loss": 0.006064592860639095,
|
| 306 |
+
"eval_runtime": 0.2699,
|
| 307 |
+
"eval_samples_per_second": 111.173,
|
| 308 |
+
"eval_steps_per_second": 7.412,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.7865168539325843,
|
| 313 |
+
"grad_norm": 8271.3828125,
|
| 314 |
+
"learning_rate": 3.370786516853933e-05,
|
| 315 |
+
"loss": 0.012,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.7865168539325843,
|
| 320 |
+
"eval_loss": 0.0077110580168664455,
|
| 321 |
+
"eval_runtime": 0.2699,
|
| 322 |
+
"eval_samples_per_second": 111.144,
|
| 323 |
+
"eval_steps_per_second": 7.41,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8239700374531835,
|
| 328 |
+
"grad_norm": 81113.7265625,
|
| 329 |
+
"learning_rate": 3.3408239700374535e-05,
|
| 330 |
+
"loss": 0.0119,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8239700374531835,
|
| 335 |
+
"eval_loss": 0.0007900427444837987,
|
| 336 |
+
"eval_runtime": 0.2804,
|
| 337 |
+
"eval_samples_per_second": 106.996,
|
| 338 |
+
"eval_steps_per_second": 7.133,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8614232209737828,
|
| 343 |
+
"grad_norm": 48094.25390625,
|
| 344 |
+
"learning_rate": 3.310861423220974e-05,
|
| 345 |
+
"loss": 0.0112,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8614232209737828,
|
| 350 |
+
"eval_loss": 0.0006070551462471485,
|
| 351 |
+
"eval_runtime": 0.2712,
|
| 352 |
+
"eval_samples_per_second": 110.615,
|
| 353 |
+
"eval_steps_per_second": 7.374,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.898876404494382,
|
| 358 |
+
"grad_norm": 13731.2001953125,
|
| 359 |
+
"learning_rate": 3.2808988764044946e-05,
|
| 360 |
+
"loss": 0.0168,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.898876404494382,
|
| 365 |
+
"eval_loss": 0.0011749672703444958,
|
| 366 |
+
"eval_runtime": 0.2697,
|
| 367 |
+
"eval_samples_per_second": 111.246,
|
| 368 |
+
"eval_steps_per_second": 7.416,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.9363295880149812,
|
| 373 |
+
"grad_norm": 13338.21484375,
|
| 374 |
+
"learning_rate": 3.250936329588015e-05,
|
| 375 |
+
"loss": 0.014,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.9363295880149812,
|
| 380 |
+
"eval_loss": 0.003979253116995096,
|
| 381 |
+
"eval_runtime": 0.2689,
|
| 382 |
+
"eval_samples_per_second": 111.55,
|
| 383 |
+
"eval_steps_per_second": 7.437,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.9737827715355806,
|
| 388 |
+
"grad_norm": 9933.720703125,
|
| 389 |
+
"learning_rate": 3.220973782771536e-05,
|
| 390 |
+
"loss": 0.0153,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.9737827715355806,
|
| 395 |
+
"eval_loss": 0.0011219431180506945,
|
| 396 |
+
"eval_runtime": 0.2694,
|
| 397 |
+
"eval_samples_per_second": 111.371,
|
| 398 |
+
"eval_steps_per_second": 7.425,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.0112359550561798,
|
| 403 |
+
"grad_norm": 13659.6982421875,
|
| 404 |
+
"learning_rate": 3.191011235955056e-05,
|
| 405 |
+
"loss": 0.0107,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.0112359550561798,
|
| 410 |
+
"eval_loss": 0.0038317707367241383,
|
| 411 |
+
"eval_runtime": 0.2722,
|
| 412 |
+
"eval_samples_per_second": 110.194,
|
| 413 |
+
"eval_steps_per_second": 7.346,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.048689138576779,
|
| 418 |
+
"grad_norm": 9676.2880859375,
|
| 419 |
+
"learning_rate": 3.1610486891385774e-05,
|
| 420 |
+
"loss": 0.0129,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.048689138576779,
|
| 425 |
+
"eval_loss": 0.0013198582455515862,
|
| 426 |
+
"eval_runtime": 0.269,
|
| 427 |
+
"eval_samples_per_second": 111.536,
|
| 428 |
+
"eval_steps_per_second": 7.436,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.0861423220973783,
|
| 433 |
+
"grad_norm": 4065.046142578125,
|
| 434 |
+
"learning_rate": 3.131086142322098e-05,
|
| 435 |
+
"loss": 0.0114,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0861423220973783,
|
| 440 |
+
"eval_loss": 0.0012054108083248138,
|
| 441 |
+
"eval_runtime": 0.27,
|
| 442 |
+
"eval_samples_per_second": 111.106,
|
| 443 |
+
"eval_steps_per_second": 7.407,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.1235955056179776,
|
| 448 |
+
"grad_norm": 2907.2998046875,
|
| 449 |
+
"learning_rate": 3.1011235955056185e-05,
|
| 450 |
+
"loss": 0.0094,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.1235955056179776,
|
| 455 |
+
"eval_loss": 0.001887617981992662,
|
| 456 |
+
"eval_runtime": 0.2702,
|
| 457 |
+
"eval_samples_per_second": 111.034,
|
| 458 |
+
"eval_steps_per_second": 7.402,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.1610486891385767,
|
| 463 |
+
"grad_norm": 8905.38671875,
|
| 464 |
+
"learning_rate": 3.071161048689139e-05,
|
| 465 |
+
"loss": 0.0116,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.1610486891385767,
|
| 470 |
+
"eval_loss": 0.0023780567571520805,
|
| 471 |
+
"eval_runtime": 0.2704,
|
| 472 |
+
"eval_samples_per_second": 110.96,
|
| 473 |
+
"eval_steps_per_second": 7.397,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.198501872659176,
|
| 478 |
+
"grad_norm": 35338.76953125,
|
| 479 |
+
"learning_rate": 3.0411985018726593e-05,
|
| 480 |
+
"loss": 0.014,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.198501872659176,
|
| 485 |
+
"eval_loss": 0.0016208798624575138,
|
| 486 |
+
"eval_runtime": 0.2702,
|
| 487 |
+
"eval_samples_per_second": 111.03,
|
| 488 |
+
"eval_steps_per_second": 7.402,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.2359550561797752,
|
| 493 |
+
"grad_norm": 1403.9569091796875,
|
| 494 |
+
"learning_rate": 3.0112359550561798e-05,
|
| 495 |
+
"loss": 0.0103,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.2359550561797752,
|
| 500 |
+
"eval_loss": 0.0008052433258853853,
|
| 501 |
+
"eval_runtime": 0.2843,
|
| 502 |
+
"eval_samples_per_second": 105.529,
|
| 503 |
+
"eval_steps_per_second": 7.035,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.2734082397003745,
|
| 508 |
+
"grad_norm": 2095.459716796875,
|
| 509 |
+
"learning_rate": 2.9812734082397007e-05,
|
| 510 |
+
"loss": 0.0109,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.2734082397003745,
|
| 515 |
+
"eval_loss": 0.0006734432536177337,
|
| 516 |
+
"eval_runtime": 0.2718,
|
| 517 |
+
"eval_samples_per_second": 110.379,
|
| 518 |
+
"eval_steps_per_second": 7.359,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.3108614232209739,
|
| 523 |
+
"grad_norm": 39442.0703125,
|
| 524 |
+
"learning_rate": 2.9513108614232212e-05,
|
| 525 |
+
"loss": 0.0121,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3108614232209739,
|
| 530 |
+
"eval_loss": 0.0014634514227509499,
|
| 531 |
+
"eval_runtime": 0.2902,
|
| 532 |
+
"eval_samples_per_second": 103.377,
|
| 533 |
+
"eval_steps_per_second": 6.892,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.348314606741573,
|
| 538 |
+
"grad_norm": 4135.88671875,
|
| 539 |
+
"learning_rate": 2.9213483146067417e-05,
|
| 540 |
+
"loss": 0.0089,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.348314606741573,
|
| 545 |
+
"eval_loss": 0.001179067650809884,
|
| 546 |
+
"eval_runtime": 0.2756,
|
| 547 |
+
"eval_samples_per_second": 108.856,
|
| 548 |
+
"eval_steps_per_second": 7.257,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.3857677902621723,
|
| 553 |
+
"grad_norm": 8729.4716796875,
|
| 554 |
+
"learning_rate": 2.8913857677902623e-05,
|
| 555 |
+
"loss": 0.0101,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.3857677902621723,
|
| 560 |
+
"eval_loss": 0.0001626112061785534,
|
| 561 |
+
"eval_runtime": 0.27,
|
| 562 |
+
"eval_samples_per_second": 111.124,
|
| 563 |
+
"eval_steps_per_second": 7.408,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.4232209737827715,
|
| 568 |
+
"grad_norm": 56410.66015625,
|
| 569 |
+
"learning_rate": 2.8614232209737828e-05,
|
| 570 |
+
"loss": 0.0114,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.4232209737827715,
|
| 575 |
+
"eval_loss": 9.747984586283565e-05,
|
| 576 |
+
"eval_runtime": 0.2718,
|
| 577 |
+
"eval_samples_per_second": 110.357,
|
| 578 |
+
"eval_steps_per_second": 7.357,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.4606741573033708,
|
| 583 |
+
"grad_norm": 35145.53125,
|
| 584 |
+
"learning_rate": 2.8314606741573034e-05,
|
| 585 |
+
"loss": 0.0105,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.4606741573033708,
|
| 590 |
+
"eval_loss": 0.00023929693270474672,
|
| 591 |
+
"eval_runtime": 0.2713,
|
| 592 |
+
"eval_samples_per_second": 110.563,
|
| 593 |
+
"eval_steps_per_second": 7.371,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.4981273408239701,
|
| 598 |
+
"grad_norm": 626.2529907226562,
|
| 599 |
+
"learning_rate": 2.8014981273408242e-05,
|
| 600 |
+
"loss": 0.0093,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.4981273408239701,
|
| 605 |
+
"eval_loss": 0.00014960776024963707,
|
| 606 |
+
"eval_runtime": 0.2703,
|
| 607 |
+
"eval_samples_per_second": 110.999,
|
| 608 |
+
"eval_steps_per_second": 7.4,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.5355805243445693,
|
| 613 |
+
"grad_norm": 6510.17578125,
|
| 614 |
+
"learning_rate": 2.7715355805243448e-05,
|
| 615 |
+
"loss": 0.0093,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.5355805243445693,
|
| 620 |
+
"eval_loss": 0.00028584664687514305,
|
| 621 |
+
"eval_runtime": 0.2706,
|
| 622 |
+
"eval_samples_per_second": 110.846,
|
| 623 |
+
"eval_steps_per_second": 7.39,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.5730337078651684,
|
| 628 |
+
"grad_norm": 576.2495727539062,
|
| 629 |
+
"learning_rate": 2.7415730337078653e-05,
|
| 630 |
+
"loss": 0.0089,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.5730337078651684,
|
| 635 |
+
"eval_loss": 0.0004513164167292416,
|
| 636 |
+
"eval_runtime": 0.271,
|
| 637 |
+
"eval_samples_per_second": 110.71,
|
| 638 |
+
"eval_steps_per_second": 7.381,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.6104868913857677,
|
| 643 |
+
"grad_norm": 36006.58984375,
|
| 644 |
+
"learning_rate": 2.711610486891386e-05,
|
| 645 |
+
"loss": 0.0106,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.6104868913857677,
|
| 650 |
+
"eval_loss": 0.002157117472961545,
|
| 651 |
+
"eval_runtime": 0.2707,
|
| 652 |
+
"eval_samples_per_second": 110.83,
|
| 653 |
+
"eval_steps_per_second": 7.389,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.647940074906367,
|
| 658 |
+
"grad_norm": 8769.625,
|
| 659 |
+
"learning_rate": 2.6816479400749064e-05,
|
| 660 |
+
"loss": 0.0115,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.647940074906367,
|
| 665 |
+
"eval_loss": 0.0011888875160366297,
|
| 666 |
+
"eval_runtime": 0.2704,
|
| 667 |
+
"eval_samples_per_second": 110.955,
|
| 668 |
+
"eval_steps_per_second": 7.397,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.6853932584269664,
|
| 673 |
+
"grad_norm": 4818.69091796875,
|
| 674 |
+
"learning_rate": 2.651685393258427e-05,
|
| 675 |
+
"loss": 0.0094,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.6853932584269664,
|
| 680 |
+
"eval_loss": 0.0001289191859541461,
|
| 681 |
+
"eval_runtime": 0.2704,
|
| 682 |
+
"eval_samples_per_second": 110.931,
|
| 683 |
+
"eval_steps_per_second": 7.395,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.7228464419475655,
|
| 688 |
+
"grad_norm": 31683.6875,
|
| 689 |
+
"learning_rate": 2.6217228464419478e-05,
|
| 690 |
+
"loss": 0.0101,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.7228464419475655,
|
| 695 |
+
"eval_loss": 0.00011979354167124256,
|
| 696 |
+
"eval_runtime": 0.2694,
|
| 697 |
+
"eval_samples_per_second": 111.374,
|
| 698 |
+
"eval_steps_per_second": 7.425,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.7602996254681647,
|
| 703 |
+
"grad_norm": 7775.08984375,
|
| 704 |
+
"learning_rate": 2.5917602996254683e-05,
|
| 705 |
+
"loss": 0.0123,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.7602996254681647,
|
| 710 |
+
"eval_loss": 0.00030495377723127604,
|
| 711 |
+
"eval_runtime": 0.2695,
|
| 712 |
+
"eval_samples_per_second": 111.3,
|
| 713 |
+
"eval_steps_per_second": 7.42,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.797752808988764,
|
| 718 |
+
"grad_norm": 101875.0234375,
|
| 719 |
+
"learning_rate": 2.561797752808989e-05,
|
| 720 |
+
"loss": 0.0114,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.797752808988764,
|
| 725 |
+
"eval_loss": 0.00019709841581061482,
|
| 726 |
+
"eval_runtime": 0.2754,
|
| 727 |
+
"eval_samples_per_second": 108.946,
|
| 728 |
+
"eval_steps_per_second": 7.263,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.8352059925093633,
|
| 733 |
+
"grad_norm": 92537.5703125,
|
| 734 |
+
"learning_rate": 2.5318352059925094e-05,
|
| 735 |
+
"loss": 0.0093,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.8352059925093633,
|
| 740 |
+
"eval_loss": 0.00014086294686421752,
|
| 741 |
+
"eval_runtime": 0.2698,
|
| 742 |
+
"eval_samples_per_second": 111.203,
|
| 743 |
+
"eval_steps_per_second": 7.414,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.8726591760299627,
|
| 748 |
+
"grad_norm": 4901.89892578125,
|
| 749 |
+
"learning_rate": 2.50187265917603e-05,
|
| 750 |
+
"loss": 0.0103,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.8726591760299627,
|
| 755 |
+
"eval_loss": 0.00010910825221799314,
|
| 756 |
+
"eval_runtime": 0.2701,
|
| 757 |
+
"eval_samples_per_second": 111.059,
|
| 758 |
+
"eval_steps_per_second": 7.404,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.9101123595505618,
|
| 763 |
+
"grad_norm": 13060.30078125,
|
| 764 |
+
"learning_rate": 2.4719101123595505e-05,
|
| 765 |
+
"loss": 0.0099,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.9101123595505618,
|
| 770 |
+
"eval_loss": 3.3620919566601515e-05,
|
| 771 |
+
"eval_runtime": 0.272,
|
| 772 |
+
"eval_samples_per_second": 110.304,
|
| 773 |
+
"eval_steps_per_second": 7.354,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.947565543071161,
|
| 778 |
+
"grad_norm": 168.86660766601562,
|
| 779 |
+
"learning_rate": 2.4419475655430717e-05,
|
| 780 |
+
"loss": 0.0099,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.947565543071161,
|
| 785 |
+
"eval_loss": 0.00021029771596658975,
|
| 786 |
+
"eval_runtime": 0.2705,
|
| 787 |
+
"eval_samples_per_second": 110.885,
|
| 788 |
+
"eval_steps_per_second": 7.392,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.9850187265917603,
|
| 793 |
+
"grad_norm": 14831.890625,
|
| 794 |
+
"learning_rate": 2.411985018726592e-05,
|
| 795 |
+
"loss": 0.009,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.9850187265917603,
|
| 800 |
+
"eval_loss": 1.2607515600393526e-05,
|
| 801 |
+
"eval_runtime": 0.2708,
|
| 802 |
+
"eval_samples_per_second": 110.79,
|
| 803 |
+
"eval_steps_per_second": 7.386,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.0224719101123596,
|
| 808 |
+
"grad_norm": 24069.68359375,
|
| 809 |
+
"learning_rate": 2.3820224719101125e-05,
|
| 810 |
+
"loss": 0.007,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.0224719101123596,
|
| 815 |
+
"eval_loss": 0.00012969045201316476,
|
| 816 |
+
"eval_runtime": 0.2727,
|
| 817 |
+
"eval_samples_per_second": 110.006,
|
| 818 |
+
"eval_steps_per_second": 7.334,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.059925093632959,
|
| 823 |
+
"grad_norm": 6022.14599609375,
|
| 824 |
+
"learning_rate": 2.352059925093633e-05,
|
| 825 |
+
"loss": 0.0099,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.059925093632959,
|
| 830 |
+
"eval_loss": 1.658714609220624e-05,
|
| 831 |
+
"eval_runtime": 0.2735,
|
| 832 |
+
"eval_samples_per_second": 109.696,
|
| 833 |
+
"eval_steps_per_second": 7.313,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.097378277153558,
|
| 838 |
+
"grad_norm": 14537.3671875,
|
| 839 |
+
"learning_rate": 2.3220973782771535e-05,
|
| 840 |
+
"loss": 0.0069,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.097378277153558,
|
| 845 |
+
"eval_loss": 9.241083171218634e-05,
|
| 846 |
+
"eval_runtime": 0.2711,
|
| 847 |
+
"eval_samples_per_second": 110.646,
|
| 848 |
+
"eval_steps_per_second": 7.376,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.134831460674157,
|
| 853 |
+
"grad_norm": 3323.2705078125,
|
| 854 |
+
"learning_rate": 2.292134831460674e-05,
|
| 855 |
+
"loss": 0.008,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.134831460674157,
|
| 860 |
+
"eval_loss": 0.001304484554566443,
|
| 861 |
+
"eval_runtime": 0.2724,
|
| 862 |
+
"eval_samples_per_second": 110.15,
|
| 863 |
+
"eval_steps_per_second": 7.343,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.1722846441947565,
|
| 868 |
+
"grad_norm": 30671.177734375,
|
| 869 |
+
"learning_rate": 2.2621722846441953e-05,
|
| 870 |
+
"loss": 0.0084,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.1722846441947565,
|
| 875 |
+
"eval_loss": 0.00012851983774453402,
|
| 876 |
+
"eval_runtime": 0.2707,
|
| 877 |
+
"eval_samples_per_second": 110.817,
|
| 878 |
+
"eval_steps_per_second": 7.388,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.209737827715356,
|
| 883 |
+
"grad_norm": 21532.076171875,
|
| 884 |
+
"learning_rate": 2.2322097378277158e-05,
|
| 885 |
+
"loss": 0.0097,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.209737827715356,
|
| 890 |
+
"eval_loss": 0.0001036034373100847,
|
| 891 |
+
"eval_runtime": 0.2707,
|
| 892 |
+
"eval_samples_per_second": 110.829,
|
| 893 |
+
"eval_steps_per_second": 7.389,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.247191011235955,
|
| 898 |
+
"grad_norm": 12783.5244140625,
|
| 899 |
+
"learning_rate": 2.202247191011236e-05,
|
| 900 |
+
"loss": 0.0092,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.247191011235955,
|
| 905 |
+
"eval_loss": 0.0001524754916317761,
|
| 906 |
+
"eval_runtime": 0.2696,
|
| 907 |
+
"eval_samples_per_second": 111.263,
|
| 908 |
+
"eval_steps_per_second": 7.418,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.284644194756554,
|
| 913 |
+
"grad_norm": 12.399551391601562,
|
| 914 |
+
"learning_rate": 2.1722846441947566e-05,
|
| 915 |
+
"loss": 0.008,
|
| 916 |
+
"step": 6100
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 2.284644194756554,
|
| 920 |
+
"eval_loss": 6.522914918605238e-05,
|
| 921 |
+
"eval_runtime": 0.2688,
|
| 922 |
+
"eval_samples_per_second": 111.598,
|
| 923 |
+
"eval_steps_per_second": 7.44,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.3220973782771535,
|
| 928 |
+
"grad_norm": 1171.171630859375,
|
| 929 |
+
"learning_rate": 2.142322097378277e-05,
|
| 930 |
+
"loss": 0.0083,
|
| 931 |
+
"step": 6200
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.3220973782771535,
|
| 935 |
+
"eval_loss": 2.3407532353303395e-05,
|
| 936 |
+
"eval_runtime": 0.2711,
|
| 937 |
+
"eval_samples_per_second": 110.676,
|
| 938 |
+
"eval_steps_per_second": 7.378,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.359550561797753,
|
| 943 |
+
"grad_norm": 14939.6650390625,
|
| 944 |
+
"learning_rate": 2.1123595505617976e-05,
|
| 945 |
+
"loss": 0.0084,
|
| 946 |
+
"step": 6300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.359550561797753,
|
| 950 |
+
"eval_loss": 7.250668204505928e-06,
|
| 951 |
+
"eval_runtime": 0.2736,
|
| 952 |
+
"eval_samples_per_second": 109.63,
|
| 953 |
+
"eval_steps_per_second": 7.309,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.397003745318352,
|
| 958 |
+
"grad_norm": 31581.005859375,
|
| 959 |
+
"learning_rate": 2.082397003745319e-05,
|
| 960 |
+
"loss": 0.0093,
|
| 961 |
+
"step": 6400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.397003745318352,
|
| 965 |
+
"eval_loss": 0.00011670963431242853,
|
| 966 |
+
"eval_runtime": 0.2702,
|
| 967 |
+
"eval_samples_per_second": 111.025,
|
| 968 |
+
"eval_steps_per_second": 7.402,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.4344569288389515,
|
| 973 |
+
"grad_norm": 1787.995849609375,
|
| 974 |
+
"learning_rate": 2.0524344569288394e-05,
|
| 975 |
+
"loss": 0.0095,
|
| 976 |
+
"step": 6500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.4344569288389515,
|
| 980 |
+
"eval_loss": 0.0032277393620461226,
|
| 981 |
+
"eval_runtime": 0.2705,
|
| 982 |
+
"eval_samples_per_second": 110.89,
|
| 983 |
+
"eval_steps_per_second": 7.393,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.4719101123595504,
|
| 988 |
+
"grad_norm": 8077.27978515625,
|
| 989 |
+
"learning_rate": 2.02247191011236e-05,
|
| 990 |
+
"loss": 0.0087,
|
| 991 |
+
"step": 6600
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.4719101123595504,
|
| 995 |
+
"eval_loss": 7.2363211074844e-05,
|
| 996 |
+
"eval_runtime": 0.2711,
|
| 997 |
+
"eval_samples_per_second": 110.656,
|
| 998 |
+
"eval_steps_per_second": 7.377,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.5093632958801497,
|
| 1003 |
+
"grad_norm": 47643.1484375,
|
| 1004 |
+
"learning_rate": 1.99250936329588e-05,
|
| 1005 |
+
"loss": 0.008,
|
| 1006 |
+
"step": 6700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.5093632958801497,
|
| 1010 |
+
"eval_loss": 0.0006091619143262506,
|
| 1011 |
+
"eval_runtime": 0.2716,
|
| 1012 |
+
"eval_samples_per_second": 110.449,
|
| 1013 |
+
"eval_steps_per_second": 7.363,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.546816479400749,
|
| 1018 |
+
"grad_norm": 23858.97265625,
|
| 1019 |
+
"learning_rate": 1.9625468164794007e-05,
|
| 1020 |
+
"loss": 0.0089,
|
| 1021 |
+
"step": 6800
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.546816479400749,
|
| 1025 |
+
"eval_loss": 0.00017142061551567167,
|
| 1026 |
+
"eval_runtime": 0.2735,
|
| 1027 |
+
"eval_samples_per_second": 109.688,
|
| 1028 |
+
"eval_steps_per_second": 7.313,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.5842696629213484,
|
| 1033 |
+
"grad_norm": 49.6945915222168,
|
| 1034 |
+
"learning_rate": 1.9325842696629215e-05,
|
| 1035 |
+
"loss": 0.0079,
|
| 1036 |
+
"step": 6900
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 2.5842696629213484,
|
| 1040 |
+
"eval_loss": 3.809615009231493e-05,
|
| 1041 |
+
"eval_runtime": 0.2699,
|
| 1042 |
+
"eval_samples_per_second": 111.159,
|
| 1043 |
+
"eval_steps_per_second": 7.411,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.6217228464419478,
|
| 1048 |
+
"grad_norm": 294.8653564453125,
|
| 1049 |
+
"learning_rate": 1.902621722846442e-05,
|
| 1050 |
+
"loss": 0.008,
|
| 1051 |
+
"step": 7000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 2.6217228464419478,
|
| 1055 |
+
"eval_loss": 5.702438556909328e-06,
|
| 1056 |
+
"eval_runtime": 0.273,
|
| 1057 |
+
"eval_samples_per_second": 109.906,
|
| 1058 |
+
"eval_steps_per_second": 7.327,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.6591760299625467,
|
| 1063 |
+
"grad_norm": 929.7149658203125,
|
| 1064 |
+
"learning_rate": 1.8726591760299626e-05,
|
| 1065 |
+
"loss": 0.0097,
|
| 1066 |
+
"step": 7100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.6591760299625467,
|
| 1070 |
+
"eval_loss": 3.306344524389715e-06,
|
| 1071 |
+
"eval_runtime": 0.2695,
|
| 1072 |
+
"eval_samples_per_second": 111.315,
|
| 1073 |
+
"eval_steps_per_second": 7.421,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.696629213483146,
|
| 1078 |
+
"grad_norm": 28578.640625,
|
| 1079 |
+
"learning_rate": 1.8426966292134835e-05,
|
| 1080 |
+
"loss": 0.0093,
|
| 1081 |
+
"step": 7200
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.696629213483146,
|
| 1085 |
+
"eval_loss": 7.41585245123133e-05,
|
| 1086 |
+
"eval_runtime": 0.2718,
|
| 1087 |
+
"eval_samples_per_second": 110.387,
|
| 1088 |
+
"eval_steps_per_second": 7.359,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.7340823970037453,
|
| 1093 |
+
"grad_norm": 18150.853515625,
|
| 1094 |
+
"learning_rate": 1.812734082397004e-05,
|
| 1095 |
+
"loss": 0.009,
|
| 1096 |
+
"step": 7300
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.7340823970037453,
|
| 1100 |
+
"eval_loss": 0.00015120919852051884,
|
| 1101 |
+
"eval_runtime": 0.2704,
|
| 1102 |
+
"eval_samples_per_second": 110.966,
|
| 1103 |
+
"eval_steps_per_second": 7.398,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.7715355805243447,
|
| 1108 |
+
"grad_norm": 17.830102920532227,
|
| 1109 |
+
"learning_rate": 1.7827715355805242e-05,
|
| 1110 |
+
"loss": 0.0077,
|
| 1111 |
+
"step": 7400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.7715355805243447,
|
| 1115 |
+
"eval_loss": 0.000870275020133704,
|
| 1116 |
+
"eval_runtime": 0.2752,
|
| 1117 |
+
"eval_samples_per_second": 109.007,
|
| 1118 |
+
"eval_steps_per_second": 7.267,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.808988764044944,
|
| 1123 |
+
"grad_norm": 16.789941787719727,
|
| 1124 |
+
"learning_rate": 1.752808988764045e-05,
|
| 1125 |
+
"loss": 0.0088,
|
| 1126 |
+
"step": 7500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.808988764044944,
|
| 1130 |
+
"eval_loss": 6.32848750683479e-05,
|
| 1131 |
+
"eval_runtime": 0.2693,
|
| 1132 |
+
"eval_samples_per_second": 111.418,
|
| 1133 |
+
"eval_steps_per_second": 7.428,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.846441947565543,
|
| 1138 |
+
"grad_norm": 17693.96875,
|
| 1139 |
+
"learning_rate": 1.7228464419475657e-05,
|
| 1140 |
+
"loss": 0.0093,
|
| 1141 |
+
"step": 7600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.846441947565543,
|
| 1145 |
+
"eval_loss": 3.997669409727678e-05,
|
| 1146 |
+
"eval_runtime": 0.2694,
|
| 1147 |
+
"eval_samples_per_second": 111.364,
|
| 1148 |
+
"eval_steps_per_second": 7.424,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.8838951310861423,
|
| 1153 |
+
"grad_norm": 56.93388366699219,
|
| 1154 |
+
"learning_rate": 1.6928838951310862e-05,
|
| 1155 |
+
"loss": 0.0071,
|
| 1156 |
+
"step": 7700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 2.8838951310861423,
|
| 1160 |
+
"eval_loss": 4.744604211737169e-06,
|
| 1161 |
+
"eval_runtime": 0.2702,
|
| 1162 |
+
"eval_samples_per_second": 111.018,
|
| 1163 |
+
"eval_steps_per_second": 7.401,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.9213483146067416,
|
| 1168 |
+
"grad_norm": 7.296459674835205,
|
| 1169 |
+
"learning_rate": 1.662921348314607e-05,
|
| 1170 |
+
"loss": 0.0094,
|
| 1171 |
+
"step": 7800
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.9213483146067416,
|
| 1175 |
+
"eval_loss": 3.2065245250123553e-06,
|
| 1176 |
+
"eval_runtime": 0.2713,
|
| 1177 |
+
"eval_samples_per_second": 110.58,
|
| 1178 |
+
"eval_steps_per_second": 7.372,
|
| 1179 |
+
"step": 7800
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.958801498127341,
|
| 1183 |
+
"grad_norm": 3018.1708984375,
|
| 1184 |
+
"learning_rate": 1.6329588014981276e-05,
|
| 1185 |
+
"loss": 0.0093,
|
| 1186 |
+
"step": 7900
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.958801498127341,
|
| 1190 |
+
"eval_loss": 1.5507857824559323e-06,
|
| 1191 |
+
"eval_runtime": 0.2707,
|
| 1192 |
+
"eval_samples_per_second": 110.815,
|
| 1193 |
+
"eval_steps_per_second": 7.388,
|
| 1194 |
+
"step": 7900
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.9962546816479403,
|
| 1198 |
+
"grad_norm": 1547.920166015625,
|
| 1199 |
+
"learning_rate": 1.602996254681648e-05,
|
| 1200 |
+
"loss": 0.0103,
|
| 1201 |
+
"step": 8000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.9962546816479403,
|
| 1205 |
+
"eval_loss": 2.826002173605957e-06,
|
| 1206 |
+
"eval_runtime": 0.2719,
|
| 1207 |
+
"eval_samples_per_second": 110.33,
|
| 1208 |
+
"eval_steps_per_second": 7.355,
|
| 1209 |
+
"step": 8000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.033707865168539,
|
| 1213 |
+
"grad_norm": 688.6261596679688,
|
| 1214 |
+
"learning_rate": 1.5730337078651687e-05,
|
| 1215 |
+
"loss": 0.009,
|
| 1216 |
+
"step": 8100
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.033707865168539,
|
| 1220 |
+
"eval_loss": 5.406631771620596e-06,
|
| 1221 |
+
"eval_runtime": 0.2693,
|
| 1222 |
+
"eval_samples_per_second": 111.416,
|
| 1223 |
+
"eval_steps_per_second": 7.428,
|
| 1224 |
+
"step": 8100
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.0711610486891385,
|
| 1228 |
+
"grad_norm": 64.58126831054688,
|
| 1229 |
+
"learning_rate": 1.5430711610486892e-05,
|
| 1230 |
+
"loss": 0.0074,
|
| 1231 |
+
"step": 8200
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.0711610486891385,
|
| 1235 |
+
"eval_loss": 5.987918029859429e-06,
|
| 1236 |
+
"eval_runtime": 0.2706,
|
| 1237 |
+
"eval_samples_per_second": 110.848,
|
| 1238 |
+
"eval_steps_per_second": 7.39,
|
| 1239 |
+
"step": 8200
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.108614232209738,
|
| 1243 |
+
"grad_norm": 27061.69921875,
|
| 1244 |
+
"learning_rate": 1.5131086142322098e-05,
|
| 1245 |
+
"loss": 0.0057,
|
| 1246 |
+
"step": 8300
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 3.108614232209738,
|
| 1250 |
+
"eval_loss": 9.855740245257039e-06,
|
| 1251 |
+
"eval_runtime": 0.2693,
|
| 1252 |
+
"eval_samples_per_second": 111.4,
|
| 1253 |
+
"eval_steps_per_second": 7.427,
|
| 1254 |
+
"step": 8300
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 3.146067415730337,
|
| 1258 |
+
"grad_norm": 111.40906524658203,
|
| 1259 |
+
"learning_rate": 1.4831460674157305e-05,
|
| 1260 |
+
"loss": 0.0059,
|
| 1261 |
+
"step": 8400
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 3.146067415730337,
|
| 1265 |
+
"eval_loss": 2.333690645173192e-06,
|
| 1266 |
+
"eval_runtime": 0.2709,
|
| 1267 |
+
"eval_samples_per_second": 110.749,
|
| 1268 |
+
"eval_steps_per_second": 7.383,
|
| 1269 |
+
"step": 8400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.1835205992509366,
|
| 1273 |
+
"grad_norm": 40.62784957885742,
|
| 1274 |
+
"learning_rate": 1.453183520599251e-05,
|
| 1275 |
+
"loss": 0.0083,
|
| 1276 |
+
"step": 8500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.1835205992509366,
|
| 1280 |
+
"eval_loss": 1.2001773029624019e-05,
|
| 1281 |
+
"eval_runtime": 0.2696,
|
| 1282 |
+
"eval_samples_per_second": 111.271,
|
| 1283 |
+
"eval_steps_per_second": 7.418,
|
| 1284 |
+
"step": 8500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.2209737827715355,
|
| 1288 |
+
"grad_norm": 964.7347412109375,
|
| 1289 |
+
"learning_rate": 1.4232209737827715e-05,
|
| 1290 |
+
"loss": 0.0072,
|
| 1291 |
+
"step": 8600
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.2209737827715355,
|
| 1295 |
+
"eval_loss": 2.515283449611161e-05,
|
| 1296 |
+
"eval_runtime": 0.2704,
|
| 1297 |
+
"eval_samples_per_second": 110.931,
|
| 1298 |
+
"eval_steps_per_second": 7.395,
|
| 1299 |
+
"step": 8600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.258426966292135,
|
| 1303 |
+
"grad_norm": 20970.783203125,
|
| 1304 |
+
"learning_rate": 1.3932584269662923e-05,
|
| 1305 |
+
"loss": 0.0077,
|
| 1306 |
+
"step": 8700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 3.258426966292135,
|
| 1310 |
+
"eval_loss": 1.2501574019552208e-05,
|
| 1311 |
+
"eval_runtime": 0.2702,
|
| 1312 |
+
"eval_samples_per_second": 111.039,
|
| 1313 |
+
"eval_steps_per_second": 7.403,
|
| 1314 |
+
"step": 8700
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.295880149812734,
|
| 1318 |
+
"grad_norm": 22375.5546875,
|
| 1319 |
+
"learning_rate": 1.3632958801498128e-05,
|
| 1320 |
+
"loss": 0.0077,
|
| 1321 |
+
"step": 8800
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.295880149812734,
|
| 1325 |
+
"eval_loss": 0.00010068963456433266,
|
| 1326 |
+
"eval_runtime": 0.2687,
|
| 1327 |
+
"eval_samples_per_second": 111.63,
|
| 1328 |
+
"eval_steps_per_second": 7.442,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.3333333333333335,
|
| 1333 |
+
"grad_norm": 17.80713653564453,
|
| 1334 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 1335 |
+
"loss": 0.0087,
|
| 1336 |
+
"step": 8900
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.3333333333333335,
|
| 1340 |
+
"eval_loss": 4.862140485784039e-06,
|
| 1341 |
+
"eval_runtime": 0.2711,
|
| 1342 |
+
"eval_samples_per_second": 110.641,
|
| 1343 |
+
"eval_steps_per_second": 7.376,
|
| 1344 |
+
"step": 8900
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 3.370786516853933,
|
| 1348 |
+
"grad_norm": 311.2126770019531,
|
| 1349 |
+
"learning_rate": 1.303370786516854e-05,
|
| 1350 |
+
"loss": 0.0065,
|
| 1351 |
+
"step": 9000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.370786516853933,
|
| 1355 |
+
"eval_loss": 1.9432780391070992e-05,
|
| 1356 |
+
"eval_runtime": 0.2685,
|
| 1357 |
+
"eval_samples_per_second": 111.729,
|
| 1358 |
+
"eval_steps_per_second": 7.449,
|
| 1359 |
+
"step": 9000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.4082397003745317,
|
| 1363 |
+
"grad_norm": 74.10047912597656,
|
| 1364 |
+
"learning_rate": 1.2734082397003746e-05,
|
| 1365 |
+
"loss": 0.0085,
|
| 1366 |
+
"step": 9100
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 3.4082397003745317,
|
| 1370 |
+
"eval_loss": 1.4302119097919785e-06,
|
| 1371 |
+
"eval_runtime": 0.2727,
|
| 1372 |
+
"eval_samples_per_second": 110.01,
|
| 1373 |
+
"eval_steps_per_second": 7.334,
|
| 1374 |
+
"step": 9100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.445692883895131,
|
| 1378 |
+
"grad_norm": 156.77000427246094,
|
| 1379 |
+
"learning_rate": 1.2434456928838951e-05,
|
| 1380 |
+
"loss": 0.0075,
|
| 1381 |
+
"step": 9200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.445692883895131,
|
| 1385 |
+
"eval_loss": 3.0803469144302653e-06,
|
| 1386 |
+
"eval_runtime": 0.2691,
|
| 1387 |
+
"eval_samples_per_second": 111.479,
|
| 1388 |
+
"eval_steps_per_second": 7.432,
|
| 1389 |
+
"step": 9200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.4831460674157304,
|
| 1393 |
+
"grad_norm": 537.3113403320312,
|
| 1394 |
+
"learning_rate": 1.213483146067416e-05,
|
| 1395 |
+
"loss": 0.0062,
|
| 1396 |
+
"step": 9300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.4831460674157304,
|
| 1400 |
+
"eval_loss": 7.492248550988734e-05,
|
| 1401 |
+
"eval_runtime": 0.2694,
|
| 1402 |
+
"eval_samples_per_second": 111.353,
|
| 1403 |
+
"eval_steps_per_second": 7.424,
|
| 1404 |
+
"step": 9300
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 3.5205992509363297,
|
| 1408 |
+
"grad_norm": 31979.20703125,
|
| 1409 |
+
"learning_rate": 1.1835205992509364e-05,
|
| 1410 |
+
"loss": 0.0078,
|
| 1411 |
+
"step": 9400
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 3.5205992509363297,
|
| 1415 |
+
"eval_loss": 6.174228474264964e-05,
|
| 1416 |
+
"eval_runtime": 0.2699,
|
| 1417 |
+
"eval_samples_per_second": 111.165,
|
| 1418 |
+
"eval_steps_per_second": 7.411,
|
| 1419 |
+
"step": 9400
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.558052434456929,
|
| 1423 |
+
"grad_norm": 17425.19921875,
|
| 1424 |
+
"learning_rate": 1.1535580524344569e-05,
|
| 1425 |
+
"loss": 0.0096,
|
| 1426 |
+
"step": 9500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 3.558052434456929,
|
| 1430 |
+
"eval_loss": 0.00016342249000445008,
|
| 1431 |
+
"eval_runtime": 0.2705,
|
| 1432 |
+
"eval_samples_per_second": 110.905,
|
| 1433 |
+
"eval_steps_per_second": 7.394,
|
| 1434 |
+
"step": 9500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 3.595505617977528,
|
| 1438 |
+
"grad_norm": 47.60939407348633,
|
| 1439 |
+
"learning_rate": 1.1235955056179778e-05,
|
| 1440 |
+
"loss": 0.0049,
|
| 1441 |
+
"step": 9600
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 3.595505617977528,
|
| 1445 |
+
"eval_loss": 8.28147130960133e-06,
|
| 1446 |
+
"eval_runtime": 0.2779,
|
| 1447 |
+
"eval_samples_per_second": 107.94,
|
| 1448 |
+
"eval_steps_per_second": 7.196,
|
| 1449 |
+
"step": 9600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 3.6329588014981273,
|
| 1453 |
+
"grad_norm": 3124.997314453125,
|
| 1454 |
+
"learning_rate": 1.0936329588014981e-05,
|
| 1455 |
+
"loss": 0.0096,
|
| 1456 |
+
"step": 9700
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 3.6329588014981273,
|
| 1460 |
+
"eval_loss": 2.2524438918480882e-06,
|
| 1461 |
+
"eval_runtime": 0.2702,
|
| 1462 |
+
"eval_samples_per_second": 111.015,
|
| 1463 |
+
"eval_steps_per_second": 7.401,
|
| 1464 |
+
"step": 9700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 3.6704119850187267,
|
| 1468 |
+
"grad_norm": 22.917911529541016,
|
| 1469 |
+
"learning_rate": 1.0636704119850187e-05,
|
| 1470 |
+
"loss": 0.0098,
|
| 1471 |
+
"step": 9800
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 3.6704119850187267,
|
| 1475 |
+
"eval_loss": 2.805942585837329e-06,
|
| 1476 |
+
"eval_runtime": 0.2717,
|
| 1477 |
+
"eval_samples_per_second": 110.402,
|
| 1478 |
+
"eval_steps_per_second": 7.36,
|
| 1479 |
+
"step": 9800
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.7078651685393256,
|
| 1483 |
+
"grad_norm": 46.66259002685547,
|
| 1484 |
+
"learning_rate": 1.0337078651685396e-05,
|
| 1485 |
+
"loss": 0.0091,
|
| 1486 |
+
"step": 9900
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 3.7078651685393256,
|
| 1490 |
+
"eval_loss": 1.3199253771745134e-05,
|
| 1491 |
+
"eval_runtime": 0.2717,
|
| 1492 |
+
"eval_samples_per_second": 110.403,
|
| 1493 |
+
"eval_steps_per_second": 7.36,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.7453183520599254,
|
| 1498 |
+
"grad_norm": 9.422457695007324,
|
| 1499 |
+
"learning_rate": 1.0037453183520601e-05,
|
| 1500 |
+
"loss": 0.0076,
|
| 1501 |
+
"step": 10000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.7453183520599254,
|
| 1505 |
+
"eval_loss": 2.4877342639229028e-06,
|
| 1506 |
+
"eval_runtime": 0.2712,
|
| 1507 |
+
"eval_samples_per_second": 110.604,
|
| 1508 |
+
"eval_steps_per_second": 7.374,
|
| 1509 |
+
"step": 10000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 3.7827715355805243,
|
| 1513 |
+
"grad_norm": 354.9677734375,
|
| 1514 |
+
"learning_rate": 9.737827715355806e-06,
|
| 1515 |
+
"loss": 0.0089,
|
| 1516 |
+
"step": 10100
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 3.7827715355805243,
|
| 1520 |
+
"eval_loss": 7.319365522562293e-07,
|
| 1521 |
+
"eval_runtime": 0.2715,
|
| 1522 |
+
"eval_samples_per_second": 110.494,
|
| 1523 |
+
"eval_steps_per_second": 7.366,
|
| 1524 |
+
"step": 10100
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 3.8202247191011236,
|
| 1528 |
+
"grad_norm": 967.5068359375,
|
| 1529 |
+
"learning_rate": 9.438202247191012e-06,
|
| 1530 |
+
"loss": 0.0074,
|
| 1531 |
+
"step": 10200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 3.8202247191011236,
|
| 1535 |
+
"eval_loss": 1.387107386108255e-05,
|
| 1536 |
+
"eval_runtime": 0.2802,
|
| 1537 |
+
"eval_samples_per_second": 107.063,
|
| 1538 |
+
"eval_steps_per_second": 7.138,
|
| 1539 |
+
"step": 10200
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.857677902621723,
|
| 1543 |
+
"grad_norm": 24458.201171875,
|
| 1544 |
+
"learning_rate": 9.138576779026219e-06,
|
| 1545 |
+
"loss": 0.0084,
|
| 1546 |
+
"step": 10300
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 3.857677902621723,
|
| 1550 |
+
"eval_loss": 1.0614428902044892e-05,
|
| 1551 |
+
"eval_runtime": 0.2693,
|
| 1552 |
+
"eval_samples_per_second": 111.408,
|
| 1553 |
+
"eval_steps_per_second": 7.427,
|
| 1554 |
+
"step": 10300
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 3.895131086142322,
|
| 1558 |
+
"grad_norm": 32194.888671875,
|
| 1559 |
+
"learning_rate": 8.838951310861424e-06,
|
| 1560 |
+
"loss": 0.0104,
|
| 1561 |
+
"step": 10400
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 3.895131086142322,
|
| 1565 |
+
"eval_loss": 2.7534890705283033e-06,
|
| 1566 |
+
"eval_runtime": 0.2706,
|
| 1567 |
+
"eval_samples_per_second": 110.869,
|
| 1568 |
+
"eval_steps_per_second": 7.391,
|
| 1569 |
+
"step": 10400
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 3.932584269662921,
|
| 1573 |
+
"grad_norm": 18117.740234375,
|
| 1574 |
+
"learning_rate": 8.53932584269663e-06,
|
| 1575 |
+
"loss": 0.0058,
|
| 1576 |
+
"step": 10500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 3.932584269662921,
|
| 1580 |
+
"eval_loss": 2.031719077422167e-06,
|
| 1581 |
+
"eval_runtime": 0.2713,
|
| 1582 |
+
"eval_samples_per_second": 110.592,
|
| 1583 |
+
"eval_steps_per_second": 7.373,
|
| 1584 |
+
"step": 10500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 3.9700374531835205,
|
| 1588 |
+
"grad_norm": 14929.3486328125,
|
| 1589 |
+
"learning_rate": 8.239700374531837e-06,
|
| 1590 |
+
"loss": 0.0081,
|
| 1591 |
+
"step": 10600
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 3.9700374531835205,
|
| 1595 |
+
"eval_loss": 1.8773675947159063e-06,
|
| 1596 |
+
"eval_runtime": 0.2688,
|
| 1597 |
+
"eval_samples_per_second": 111.598,
|
| 1598 |
+
"eval_steps_per_second": 7.44,
|
| 1599 |
+
"step": 10600
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.007490636704119,
|
| 1603 |
+
"grad_norm": 1356.1688232421875,
|
| 1604 |
+
"learning_rate": 7.940074906367042e-06,
|
| 1605 |
+
"loss": 0.0058,
|
| 1606 |
+
"step": 10700
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 4.007490636704119,
|
| 1610 |
+
"eval_loss": 2.515456287710549e-07,
|
| 1611 |
+
"eval_runtime": 0.2743,
|
| 1612 |
+
"eval_samples_per_second": 109.363,
|
| 1613 |
+
"eval_steps_per_second": 7.291,
|
| 1614 |
+
"step": 10700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 4.044943820224719,
|
| 1618 |
+
"grad_norm": 4.012579917907715,
|
| 1619 |
+
"learning_rate": 7.640449438202247e-06,
|
| 1620 |
+
"loss": 0.0073,
|
| 1621 |
+
"step": 10800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 4.044943820224719,
|
| 1625 |
+
"eval_loss": 3.1969119618224795e-07,
|
| 1626 |
+
"eval_runtime": 0.2694,
|
| 1627 |
+
"eval_samples_per_second": 111.353,
|
| 1628 |
+
"eval_steps_per_second": 7.424,
|
| 1629 |
+
"step": 10800
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 4.082397003745318,
|
| 1633 |
+
"grad_norm": 22902.978515625,
|
| 1634 |
+
"learning_rate": 7.340823970037454e-06,
|
| 1635 |
+
"loss": 0.0077,
|
| 1636 |
+
"step": 10900
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 4.082397003745318,
|
| 1640 |
+
"eval_loss": 7.97858433543297e-07,
|
| 1641 |
+
"eval_runtime": 0.2701,
|
| 1642 |
+
"eval_samples_per_second": 111.07,
|
| 1643 |
+
"eval_steps_per_second": 7.405,
|
| 1644 |
+
"step": 10900
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.119850187265918,
|
| 1648 |
+
"grad_norm": 19.242652893066406,
|
| 1649 |
+
"learning_rate": 7.04119850187266e-06,
|
| 1650 |
+
"loss": 0.006,
|
| 1651 |
+
"step": 11000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 4.119850187265918,
|
| 1655 |
+
"eval_loss": 3.754879571715719e-07,
|
| 1656 |
+
"eval_runtime": 0.2696,
|
| 1657 |
+
"eval_samples_per_second": 111.279,
|
| 1658 |
+
"eval_steps_per_second": 7.419,
|
| 1659 |
+
"step": 11000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 4.157303370786517,
|
| 1663 |
+
"grad_norm": 594.0513916015625,
|
| 1664 |
+
"learning_rate": 6.741573033707865e-06,
|
| 1665 |
+
"loss": 0.0076,
|
| 1666 |
+
"step": 11100
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 4.157303370786517,
|
| 1670 |
+
"eval_loss": 1.5144707958825165e-06,
|
| 1671 |
+
"eval_runtime": 0.2689,
|
| 1672 |
+
"eval_samples_per_second": 111.549,
|
| 1673 |
+
"eval_steps_per_second": 7.437,
|
| 1674 |
+
"step": 11100
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 4.194756554307116,
|
| 1678 |
+
"grad_norm": 40.14280319213867,
|
| 1679 |
+
"learning_rate": 6.4419475655430715e-06,
|
| 1680 |
+
"loss": 0.0072,
|
| 1681 |
+
"step": 11200
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 4.194756554307116,
|
| 1685 |
+
"eval_loss": 4.6455261326627806e-07,
|
| 1686 |
+
"eval_runtime": 0.2709,
|
| 1687 |
+
"eval_samples_per_second": 110.757,
|
| 1688 |
+
"eval_steps_per_second": 7.384,
|
| 1689 |
+
"step": 11200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.2322097378277155,
|
| 1693 |
+
"grad_norm": 11464.6328125,
|
| 1694 |
+
"learning_rate": 6.142322097378277e-06,
|
| 1695 |
+
"loss": 0.0066,
|
| 1696 |
+
"step": 11300
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 4.2322097378277155,
|
| 1700 |
+
"eval_loss": 2.016280546968119e-07,
|
| 1701 |
+
"eval_runtime": 0.2784,
|
| 1702 |
+
"eval_samples_per_second": 107.752,
|
| 1703 |
+
"eval_steps_per_second": 7.183,
|
| 1704 |
+
"step": 11300
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 4.269662921348314,
|
| 1708 |
+
"grad_norm": 25621.724609375,
|
| 1709 |
+
"learning_rate": 5.842696629213483e-06,
|
| 1710 |
+
"loss": 0.0076,
|
| 1711 |
+
"step": 11400
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 4.269662921348314,
|
| 1715 |
+
"eval_loss": 2.0839000569594646e-07,
|
| 1716 |
+
"eval_runtime": 0.2707,
|
| 1717 |
+
"eval_samples_per_second": 110.843,
|
| 1718 |
+
"eval_steps_per_second": 7.39,
|
| 1719 |
+
"step": 11400
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 4.307116104868914,
|
| 1723 |
+
"grad_norm": 18361.001953125,
|
| 1724 |
+
"learning_rate": 5.54307116104869e-06,
|
| 1725 |
+
"loss": 0.0063,
|
| 1726 |
+
"step": 11500
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 4.307116104868914,
|
| 1730 |
+
"eval_loss": 3.3212629091394774e-07,
|
| 1731 |
+
"eval_runtime": 0.2696,
|
| 1732 |
+
"eval_samples_per_second": 111.296,
|
| 1733 |
+
"eval_steps_per_second": 7.42,
|
| 1734 |
+
"step": 11500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 4.344569288389513,
|
| 1738 |
+
"grad_norm": 68192.8984375,
|
| 1739 |
+
"learning_rate": 5.243445692883895e-06,
|
| 1740 |
+
"loss": 0.0078,
|
| 1741 |
+
"step": 11600
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 4.344569288389513,
|
| 1745 |
+
"eval_loss": 1.3938915799371898e-07,
|
| 1746 |
+
"eval_runtime": 0.2711,
|
| 1747 |
+
"eval_samples_per_second": 110.662,
|
| 1748 |
+
"eval_steps_per_second": 7.377,
|
| 1749 |
+
"step": 11600
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 4.382022471910112,
|
| 1753 |
+
"grad_norm": 62.034523010253906,
|
| 1754 |
+
"learning_rate": 4.943820224719101e-06,
|
| 1755 |
+
"loss": 0.0069,
|
| 1756 |
+
"step": 11700
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 4.382022471910112,
|
| 1760 |
+
"eval_loss": 1.2977771746136568e-07,
|
| 1761 |
+
"eval_runtime": 0.271,
|
| 1762 |
+
"eval_samples_per_second": 110.697,
|
| 1763 |
+
"eval_steps_per_second": 7.38,
|
| 1764 |
+
"step": 11700
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 4.419475655430712,
|
| 1768 |
+
"grad_norm": 27752.787109375,
|
| 1769 |
+
"learning_rate": 4.644194756554308e-06,
|
| 1770 |
+
"loss": 0.0081,
|
| 1771 |
+
"step": 11800
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 4.419475655430712,
|
| 1775 |
+
"eval_loss": 1.483793425904878e-07,
|
| 1776 |
+
"eval_runtime": 0.2751,
|
| 1777 |
+
"eval_samples_per_second": 109.043,
|
| 1778 |
+
"eval_steps_per_second": 7.27,
|
| 1779 |
+
"step": 11800
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 4.456928838951311,
|
| 1783 |
+
"grad_norm": 24.9007511138916,
|
| 1784 |
+
"learning_rate": 4.3445692883895135e-06,
|
| 1785 |
+
"loss": 0.0078,
|
| 1786 |
+
"step": 11900
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 4.456928838951311,
|
| 1790 |
+
"eval_loss": 5.084881422590115e-07,
|
| 1791 |
+
"eval_runtime": 0.2713,
|
| 1792 |
+
"eval_samples_per_second": 110.57,
|
| 1793 |
+
"eval_steps_per_second": 7.371,
|
| 1794 |
+
"step": 11900
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 4.49438202247191,
|
| 1798 |
+
"grad_norm": 7.775390148162842,
|
| 1799 |
+
"learning_rate": 4.04494382022472e-06,
|
| 1800 |
+
"loss": 0.0076,
|
| 1801 |
+
"step": 12000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 4.49438202247191,
|
| 1805 |
+
"eval_loss": 9.027158967001014e-07,
|
| 1806 |
+
"eval_runtime": 0.2721,
|
| 1807 |
+
"eval_samples_per_second": 110.24,
|
| 1808 |
+
"eval_steps_per_second": 7.349,
|
| 1809 |
+
"step": 12000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 4.531835205992509,
|
| 1813 |
+
"grad_norm": 3265.2392578125,
|
| 1814 |
+
"learning_rate": 3.7453183520599255e-06,
|
| 1815 |
+
"loss": 0.0061,
|
| 1816 |
+
"step": 12100
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 4.531835205992509,
|
| 1820 |
+
"eval_loss": 1.5819171039765934e-06,
|
| 1821 |
+
"eval_runtime": 0.2698,
|
| 1822 |
+
"eval_samples_per_second": 111.177,
|
| 1823 |
+
"eval_steps_per_second": 7.412,
|
| 1824 |
+
"step": 12100
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 4.569288389513108,
|
| 1828 |
+
"grad_norm": 12992.0361328125,
|
| 1829 |
+
"learning_rate": 3.4456928838951313e-06,
|
| 1830 |
+
"loss": 0.0079,
|
| 1831 |
+
"step": 12200
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 4.569288389513108,
|
| 1835 |
+
"eval_loss": 7.184162882367673e-07,
|
| 1836 |
+
"eval_runtime": 0.2716,
|
| 1837 |
+
"eval_samples_per_second": 110.468,
|
| 1838 |
+
"eval_steps_per_second": 7.365,
|
| 1839 |
+
"step": 12200
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 4.606741573033708,
|
| 1843 |
+
"grad_norm": 94.70529174804688,
|
| 1844 |
+
"learning_rate": 3.146067415730337e-06,
|
| 1845 |
+
"loss": 0.006,
|
| 1846 |
+
"step": 12300
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 4.606741573033708,
|
| 1850 |
+
"eval_loss": 1.6477933968417346e-06,
|
| 1851 |
+
"eval_runtime": 0.2698,
|
| 1852 |
+
"eval_samples_per_second": 111.208,
|
| 1853 |
+
"eval_steps_per_second": 7.414,
|
| 1854 |
+
"step": 12300
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 4.644194756554307,
|
| 1858 |
+
"grad_norm": 24.974130630493164,
|
| 1859 |
+
"learning_rate": 2.846441947565543e-06,
|
| 1860 |
+
"loss": 0.0061,
|
| 1861 |
+
"step": 12400
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 4.644194756554307,
|
| 1865 |
+
"eval_loss": 6.807524073337845e-07,
|
| 1866 |
+
"eval_runtime": 0.2704,
|
| 1867 |
+
"eval_samples_per_second": 110.947,
|
| 1868 |
+
"eval_steps_per_second": 7.396,
|
| 1869 |
+
"step": 12400
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 4.681647940074907,
|
| 1873 |
+
"grad_norm": 4.709781169891357,
|
| 1874 |
+
"learning_rate": 2.5468164794007496e-06,
|
| 1875 |
+
"loss": 0.0075,
|
| 1876 |
+
"step": 12500
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 4.681647940074907,
|
| 1880 |
+
"eval_loss": 3.077086603298085e-07,
|
| 1881 |
+
"eval_runtime": 0.2692,
|
| 1882 |
+
"eval_samples_per_second": 111.445,
|
| 1883 |
+
"eval_steps_per_second": 7.43,
|
| 1884 |
+
"step": 12500
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 4.719101123595506,
|
| 1888 |
+
"grad_norm": 61.4736442565918,
|
| 1889 |
+
"learning_rate": 2.2471910112359554e-06,
|
| 1890 |
+
"loss": 0.0054,
|
| 1891 |
+
"step": 12600
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 4.719101123595506,
|
| 1895 |
+
"eval_loss": 2.621384282974759e-07,
|
| 1896 |
+
"eval_runtime": 0.2704,
|
| 1897 |
+
"eval_samples_per_second": 110.964,
|
| 1898 |
+
"eval_steps_per_second": 7.398,
|
| 1899 |
+
"step": 12600
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 4.7565543071161045,
|
| 1903 |
+
"grad_norm": 279.9930114746094,
|
| 1904 |
+
"learning_rate": 1.947565543071161e-06,
|
| 1905 |
+
"loss": 0.0072,
|
| 1906 |
+
"step": 12700
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 4.7565543071161045,
|
| 1910 |
+
"eval_loss": 3.2119106663230923e-07,
|
| 1911 |
+
"eval_runtime": 0.2696,
|
| 1912 |
+
"eval_samples_per_second": 111.29,
|
| 1913 |
+
"eval_steps_per_second": 7.419,
|
| 1914 |
+
"step": 12700
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 4.794007490636704,
|
| 1918 |
+
"grad_norm": 1.977974772453308,
|
| 1919 |
+
"learning_rate": 1.647940074906367e-06,
|
| 1920 |
+
"loss": 0.0066,
|
| 1921 |
+
"step": 12800
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 4.794007490636704,
|
| 1925 |
+
"eval_loss": 2.8463981038839847e-07,
|
| 1926 |
+
"eval_runtime": 0.2718,
|
| 1927 |
+
"eval_samples_per_second": 110.378,
|
| 1928 |
+
"eval_steps_per_second": 7.359,
|
| 1929 |
+
"step": 12800
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 4.831460674157303,
|
| 1933 |
+
"grad_norm": 6.965720176696777,
|
| 1934 |
+
"learning_rate": 1.348314606741573e-06,
|
| 1935 |
+
"loss": 0.0076,
|
| 1936 |
+
"step": 12900
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 4.831460674157303,
|
| 1940 |
+
"eval_loss": 5.141406518305303e-07,
|
| 1941 |
+
"eval_runtime": 0.27,
|
| 1942 |
+
"eval_samples_per_second": 111.115,
|
| 1943 |
+
"eval_steps_per_second": 7.408,
|
| 1944 |
+
"step": 12900
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 4.868913857677903,
|
| 1948 |
+
"grad_norm": 68.03124237060547,
|
| 1949 |
+
"learning_rate": 1.0486891385767792e-06,
|
| 1950 |
+
"loss": 0.0076,
|
| 1951 |
+
"step": 13000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 4.868913857677903,
|
| 1955 |
+
"eval_loss": 5.566216145780345e-07,
|
| 1956 |
+
"eval_runtime": 0.2753,
|
| 1957 |
+
"eval_samples_per_second": 108.964,
|
| 1958 |
+
"eval_steps_per_second": 7.264,
|
| 1959 |
+
"step": 13000
|
| 1960 |
+
}
|
| 1961 |
+
],
|
| 1962 |
+
"logging_steps": 100,
|
| 1963 |
+
"max_steps": 13350,
|
| 1964 |
+
"num_input_tokens_seen": 0,
|
| 1965 |
+
"num_train_epochs": 5,
|
| 1966 |
+
"save_steps": 200,
|
| 1967 |
+
"stateful_callbacks": {
|
| 1968 |
+
"TrainerControl": {
|
| 1969 |
+
"args": {
|
| 1970 |
+
"should_epoch_stop": false,
|
| 1971 |
+
"should_evaluate": false,
|
| 1972 |
+
"should_log": false,
|
| 1973 |
+
"should_save": true,
|
| 1974 |
+
"should_training_stop": false
|
| 1975 |
+
},
|
| 1976 |
+
"attributes": {}
|
| 1977 |
+
}
|
| 1978 |
+
},
|
| 1979 |
+
"total_flos": 1.242248406331392e+16,
|
| 1980 |
+
"train_batch_size": 16,
|
| 1981 |
+
"trial_name": null,
|
| 1982 |
+
"trial_params": null
|
| 1983 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b42bdfe1ad153c0f1cccfd4f6c3b6d499f36fbf8b23d55b56a38d055875f54b
|
| 3 |
+
size 5240
|