Upload folder using huggingface_hub
Browse files- added_tokens.json +40 -0
- config.json +31 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +326 -0
- trainer_state.json +2148 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "kaizen9/phi-1_5_HQ_6000_200k_FP",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"QPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
+
"gradient_checkpointing_step": 7,
|
| 11 |
+
"hidden_act": "gelu_new",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 2048,
|
| 17 |
+
"model_type": "phi",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"num_key_value_heads": 32,
|
| 21 |
+
"partial_rotary_factor": 0.5,
|
| 22 |
+
"qk_layernorm": false,
|
| 23 |
+
"resid_pdrop": 0.0,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.47.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 51200
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.47.0"
|
| 4 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bc8d8eb723656398edb6c5ae97d719ce4048f2ab639dbe3427aadbf168a158b
|
| 3 |
+
size 2837479464
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb408dd46d97d56b7b0b68b2a835ed2e21cd62606f5fff0cc650fb0f5c8fa4ff
|
| 3 |
+
size 2051182202
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65efacbf532f891d581bc44560cc4a191acde3008f06b38c6379dd43be56af76
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba868f182320f3198afac742a233ba97edc4cc4bffda1245f222b2a7526abbd6
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2b68abd6c86aa925023746562610bf7f4e284153048eb68a42712f88e800e8
|
| 3 |
+
size 1000
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"clean_up_tokenization_spaces": true,
|
| 319 |
+
"eos_token": "<|endoftext|>",
|
| 320 |
+
"extra_special_tokens": {},
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"padding_side": "right",
|
| 323 |
+
"return_token_type_ids": false,
|
| 324 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 325 |
+
"unk_token": "<|endoftext|>"
|
| 326 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.08483363182203789,
|
| 5 |
+
"eval_steps": 300,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0002827787727401263,
|
| 13 |
+
"grad_norm": 0.80859375,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 2.7268,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005655575454802526,
|
| 20 |
+
"grad_norm": 0.7890625,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 2.718,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.000848336318220379,
|
| 27 |
+
"grad_norm": 0.77734375,
|
| 28 |
+
"learning_rate": 7.5e-06,
|
| 29 |
+
"loss": 2.6908,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0011311150909605052,
|
| 34 |
+
"grad_norm": 0.796875,
|
| 35 |
+
"learning_rate": 1e-05,
|
| 36 |
+
"loss": 2.8856,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0014138938637006315,
|
| 41 |
+
"grad_norm": 0.78125,
|
| 42 |
+
"learning_rate": 1.25e-05,
|
| 43 |
+
"loss": 2.7944,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.001696672636440758,
|
| 48 |
+
"grad_norm": 0.76171875,
|
| 49 |
+
"learning_rate": 1.5e-05,
|
| 50 |
+
"loss": 2.8203,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.001979451409180884,
|
| 55 |
+
"grad_norm": 0.76953125,
|
| 56 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 57 |
+
"loss": 2.6714,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0022622301819210104,
|
| 62 |
+
"grad_norm": 0.8203125,
|
| 63 |
+
"learning_rate": 2e-05,
|
| 64 |
+
"loss": 2.6746,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0025450089546611367,
|
| 69 |
+
"grad_norm": 0.74609375,
|
| 70 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 71 |
+
"loss": 2.7972,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.002827787727401263,
|
| 76 |
+
"grad_norm": 0.8046875,
|
| 77 |
+
"learning_rate": 2.5e-05,
|
| 78 |
+
"loss": 2.8224,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.003110566500141389,
|
| 83 |
+
"grad_norm": 0.80078125,
|
| 84 |
+
"learning_rate": 2.75e-05,
|
| 85 |
+
"loss": 2.7473,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.003393345272881516,
|
| 90 |
+
"grad_norm": 0.83203125,
|
| 91 |
+
"learning_rate": 3e-05,
|
| 92 |
+
"loss": 2.7134,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.003676124045621642,
|
| 97 |
+
"grad_norm": 0.81640625,
|
| 98 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 99 |
+
"loss": 2.7946,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.003958902818361768,
|
| 104 |
+
"grad_norm": 0.73828125,
|
| 105 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 106 |
+
"loss": 2.8185,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.004241681591101895,
|
| 111 |
+
"grad_norm": 0.76171875,
|
| 112 |
+
"learning_rate": 3.75e-05,
|
| 113 |
+
"loss": 2.7015,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004524460363842021,
|
| 118 |
+
"grad_norm": 0.73828125,
|
| 119 |
+
"learning_rate": 4e-05,
|
| 120 |
+
"loss": 2.7398,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004807239136582147,
|
| 125 |
+
"grad_norm": 0.74609375,
|
| 126 |
+
"learning_rate": 4.25e-05,
|
| 127 |
+
"loss": 2.6954,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.005090017909322273,
|
| 132 |
+
"grad_norm": 0.79296875,
|
| 133 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 134 |
+
"loss": 2.7737,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0053727966820624,
|
| 139 |
+
"grad_norm": 0.78515625,
|
| 140 |
+
"learning_rate": 4.75e-05,
|
| 141 |
+
"loss": 2.7532,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005655575454802526,
|
| 146 |
+
"grad_norm": 0.7734375,
|
| 147 |
+
"learning_rate": 5e-05,
|
| 148 |
+
"loss": 2.7254,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005938354227542652,
|
| 153 |
+
"grad_norm": 0.7890625,
|
| 154 |
+
"learning_rate": 5.25e-05,
|
| 155 |
+
"loss": 2.8117,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.006221133000282778,
|
| 160 |
+
"grad_norm": 0.76171875,
|
| 161 |
+
"learning_rate": 5.5e-05,
|
| 162 |
+
"loss": 2.7023,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0065039117730229055,
|
| 167 |
+
"grad_norm": 0.796875,
|
| 168 |
+
"learning_rate": 5.75e-05,
|
| 169 |
+
"loss": 2.7226,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.006786690545763032,
|
| 174 |
+
"grad_norm": 0.75,
|
| 175 |
+
"learning_rate": 6e-05,
|
| 176 |
+
"loss": 2.7699,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.007069469318503158,
|
| 181 |
+
"grad_norm": 0.75390625,
|
| 182 |
+
"learning_rate": 6.25e-05,
|
| 183 |
+
"loss": 2.8024,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.007352248091243284,
|
| 188 |
+
"grad_norm": 0.69921875,
|
| 189 |
+
"learning_rate": 6.500000000000001e-05,
|
| 190 |
+
"loss": 2.8438,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0076350268639834105,
|
| 195 |
+
"grad_norm": 0.69921875,
|
| 196 |
+
"learning_rate": 6.75e-05,
|
| 197 |
+
"loss": 2.7921,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007917805636723537,
|
| 202 |
+
"grad_norm": 0.69140625,
|
| 203 |
+
"learning_rate": 7.000000000000001e-05,
|
| 204 |
+
"loss": 2.6334,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.008200584409463663,
|
| 209 |
+
"grad_norm": 0.7421875,
|
| 210 |
+
"learning_rate": 7.25e-05,
|
| 211 |
+
"loss": 2.7756,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.00848336318220379,
|
| 216 |
+
"grad_norm": 0.7421875,
|
| 217 |
+
"learning_rate": 7.5e-05,
|
| 218 |
+
"loss": 2.7423,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008766141954943915,
|
| 223 |
+
"grad_norm": 0.65234375,
|
| 224 |
+
"learning_rate": 7.75e-05,
|
| 225 |
+
"loss": 2.8511,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.009048920727684042,
|
| 230 |
+
"grad_norm": 0.625,
|
| 231 |
+
"learning_rate": 8e-05,
|
| 232 |
+
"loss": 2.7675,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.009331699500424168,
|
| 237 |
+
"grad_norm": 0.65234375,
|
| 238 |
+
"learning_rate": 8.25e-05,
|
| 239 |
+
"loss": 2.7701,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.009614478273164294,
|
| 244 |
+
"grad_norm": 0.609375,
|
| 245 |
+
"learning_rate": 8.5e-05,
|
| 246 |
+
"loss": 2.855,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.00989725704590442,
|
| 251 |
+
"grad_norm": 0.6328125,
|
| 252 |
+
"learning_rate": 8.75e-05,
|
| 253 |
+
"loss": 2.8302,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.010180035818644547,
|
| 258 |
+
"grad_norm": 0.59375,
|
| 259 |
+
"learning_rate": 8.999999999999999e-05,
|
| 260 |
+
"loss": 2.8412,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.010462814591384673,
|
| 265 |
+
"grad_norm": 0.609375,
|
| 266 |
+
"learning_rate": 9.25e-05,
|
| 267 |
+
"loss": 2.8331,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0107455933641248,
|
| 272 |
+
"grad_norm": 0.61328125,
|
| 273 |
+
"learning_rate": 9.5e-05,
|
| 274 |
+
"loss": 2.7374,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.011028372136864925,
|
| 279 |
+
"grad_norm": 0.57421875,
|
| 280 |
+
"learning_rate": 9.750000000000001e-05,
|
| 281 |
+
"loss": 2.7886,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.011311150909605052,
|
| 286 |
+
"grad_norm": 0.5859375,
|
| 287 |
+
"learning_rate": 0.0001,
|
| 288 |
+
"loss": 2.7014,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.011593929682345178,
|
| 293 |
+
"grad_norm": 0.609375,
|
| 294 |
+
"learning_rate": 0.0001025,
|
| 295 |
+
"loss": 2.7952,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.011876708455085304,
|
| 300 |
+
"grad_norm": 0.53515625,
|
| 301 |
+
"learning_rate": 0.000105,
|
| 302 |
+
"loss": 2.7336,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.01215948722782543,
|
| 307 |
+
"grad_norm": 0.56640625,
|
| 308 |
+
"learning_rate": 0.0001075,
|
| 309 |
+
"loss": 2.7843,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.012442266000565557,
|
| 314 |
+
"grad_norm": 0.5625,
|
| 315 |
+
"learning_rate": 0.00011,
|
| 316 |
+
"loss": 2.6144,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.012725044773305685,
|
| 321 |
+
"grad_norm": 0.5078125,
|
| 322 |
+
"learning_rate": 0.00011250000000000001,
|
| 323 |
+
"loss": 2.7719,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.013007823546045811,
|
| 328 |
+
"grad_norm": 0.54296875,
|
| 329 |
+
"learning_rate": 0.000115,
|
| 330 |
+
"loss": 2.7298,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.013290602318785937,
|
| 335 |
+
"grad_norm": 0.51953125,
|
| 336 |
+
"learning_rate": 0.0001175,
|
| 337 |
+
"loss": 2.8204,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.013573381091526063,
|
| 342 |
+
"grad_norm": 0.51953125,
|
| 343 |
+
"learning_rate": 0.00012,
|
| 344 |
+
"loss": 2.793,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01385615986426619,
|
| 349 |
+
"grad_norm": 0.51171875,
|
| 350 |
+
"learning_rate": 0.0001225,
|
| 351 |
+
"loss": 2.7587,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.014138938637006316,
|
| 356 |
+
"grad_norm": 0.47265625,
|
| 357 |
+
"learning_rate": 0.000125,
|
| 358 |
+
"loss": 2.6685,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.014421717409746442,
|
| 363 |
+
"grad_norm": 0.46875,
|
| 364 |
+
"learning_rate": 0.0001275,
|
| 365 |
+
"loss": 2.7757,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.014704496182486568,
|
| 370 |
+
"grad_norm": 0.44921875,
|
| 371 |
+
"learning_rate": 0.00013000000000000002,
|
| 372 |
+
"loss": 2.7917,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.014987274955226695,
|
| 377 |
+
"grad_norm": 0.4765625,
|
| 378 |
+
"learning_rate": 0.00013250000000000002,
|
| 379 |
+
"loss": 2.7146,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.015270053727966821,
|
| 384 |
+
"grad_norm": 0.470703125,
|
| 385 |
+
"learning_rate": 0.000135,
|
| 386 |
+
"loss": 2.775,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.015552832500706947,
|
| 391 |
+
"grad_norm": 0.435546875,
|
| 392 |
+
"learning_rate": 0.0001375,
|
| 393 |
+
"loss": 2.7716,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.015835611273447073,
|
| 398 |
+
"grad_norm": 0.390625,
|
| 399 |
+
"learning_rate": 0.00014000000000000001,
|
| 400 |
+
"loss": 2.7673,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.0161183900461872,
|
| 405 |
+
"grad_norm": 0.40625,
|
| 406 |
+
"learning_rate": 0.0001425,
|
| 407 |
+
"loss": 2.7578,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.016401168818927326,
|
| 412 |
+
"grad_norm": 0.40234375,
|
| 413 |
+
"learning_rate": 0.000145,
|
| 414 |
+
"loss": 2.7354,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.016683947591667452,
|
| 419 |
+
"grad_norm": 0.37109375,
|
| 420 |
+
"learning_rate": 0.0001475,
|
| 421 |
+
"loss": 2.8292,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01696672636440758,
|
| 426 |
+
"grad_norm": 0.39453125,
|
| 427 |
+
"learning_rate": 0.00015,
|
| 428 |
+
"loss": 2.7623,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.017249505137147705,
|
| 433 |
+
"grad_norm": 0.353515625,
|
| 434 |
+
"learning_rate": 0.0001525,
|
| 435 |
+
"loss": 2.7563,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.01753228390988783,
|
| 440 |
+
"grad_norm": 0.361328125,
|
| 441 |
+
"learning_rate": 0.000155,
|
| 442 |
+
"loss": 2.7535,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.017815062682627957,
|
| 447 |
+
"grad_norm": 0.3671875,
|
| 448 |
+
"learning_rate": 0.0001575,
|
| 449 |
+
"loss": 2.7041,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.018097841455368083,
|
| 454 |
+
"grad_norm": 0.34375,
|
| 455 |
+
"learning_rate": 0.00016,
|
| 456 |
+
"loss": 2.7757,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.01838062022810821,
|
| 461 |
+
"grad_norm": 0.353515625,
|
| 462 |
+
"learning_rate": 0.00016250000000000002,
|
| 463 |
+
"loss": 2.8202,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.018663399000848336,
|
| 468 |
+
"grad_norm": 0.345703125,
|
| 469 |
+
"learning_rate": 0.000165,
|
| 470 |
+
"loss": 2.7248,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.018946177773588462,
|
| 475 |
+
"grad_norm": 0.341796875,
|
| 476 |
+
"learning_rate": 0.0001675,
|
| 477 |
+
"loss": 2.7991,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.01922895654632859,
|
| 482 |
+
"grad_norm": 0.33984375,
|
| 483 |
+
"learning_rate": 0.00017,
|
| 484 |
+
"loss": 2.7269,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.019511735319068715,
|
| 489 |
+
"grad_norm": 0.3359375,
|
| 490 |
+
"learning_rate": 0.0001725,
|
| 491 |
+
"loss": 2.7502,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.01979451409180884,
|
| 496 |
+
"grad_norm": 0.34375,
|
| 497 |
+
"learning_rate": 0.000175,
|
| 498 |
+
"loss": 2.7022,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.020077292864548967,
|
| 503 |
+
"grad_norm": 0.3203125,
|
| 504 |
+
"learning_rate": 0.0001775,
|
| 505 |
+
"loss": 2.7533,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.020360071637289093,
|
| 510 |
+
"grad_norm": 0.326171875,
|
| 511 |
+
"learning_rate": 0.00017999999999999998,
|
| 512 |
+
"loss": 2.8295,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.02064285041002922,
|
| 517 |
+
"grad_norm": 0.322265625,
|
| 518 |
+
"learning_rate": 0.0001825,
|
| 519 |
+
"loss": 2.8412,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.020925629182769346,
|
| 524 |
+
"grad_norm": 0.328125,
|
| 525 |
+
"learning_rate": 0.000185,
|
| 526 |
+
"loss": 2.8365,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.021208407955509472,
|
| 531 |
+
"grad_norm": 0.32421875,
|
| 532 |
+
"learning_rate": 0.0001875,
|
| 533 |
+
"loss": 2.7001,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.0214911867282496,
|
| 538 |
+
"grad_norm": 0.353515625,
|
| 539 |
+
"learning_rate": 0.00019,
|
| 540 |
+
"loss": 2.7443,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.021773965500989725,
|
| 545 |
+
"grad_norm": 0.326171875,
|
| 546 |
+
"learning_rate": 0.00019250000000000002,
|
| 547 |
+
"loss": 2.7344,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.02205674427372985,
|
| 552 |
+
"grad_norm": 0.326171875,
|
| 553 |
+
"learning_rate": 0.00019500000000000002,
|
| 554 |
+
"loss": 2.7879,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.022339523046469977,
|
| 559 |
+
"grad_norm": 0.322265625,
|
| 560 |
+
"learning_rate": 0.0001975,
|
| 561 |
+
"loss": 2.7279,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.022622301819210103,
|
| 566 |
+
"grad_norm": 0.326171875,
|
| 567 |
+
"learning_rate": 0.0002,
|
| 568 |
+
"loss": 2.7011,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.02290508059195023,
|
| 573 |
+
"grad_norm": 0.3203125,
|
| 574 |
+
"learning_rate": 0.00020250000000000002,
|
| 575 |
+
"loss": 2.8249,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.023187859364690356,
|
| 580 |
+
"grad_norm": 0.328125,
|
| 581 |
+
"learning_rate": 0.000205,
|
| 582 |
+
"loss": 2.6382,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.023470638137430482,
|
| 587 |
+
"grad_norm": 0.302734375,
|
| 588 |
+
"learning_rate": 0.0002075,
|
| 589 |
+
"loss": 2.7064,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02375341691017061,
|
| 594 |
+
"grad_norm": 0.314453125,
|
| 595 |
+
"learning_rate": 0.00021,
|
| 596 |
+
"loss": 2.6595,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.024036195682910735,
|
| 601 |
+
"grad_norm": 0.3046875,
|
| 602 |
+
"learning_rate": 0.0002125,
|
| 603 |
+
"loss": 2.7486,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02431897445565086,
|
| 608 |
+
"grad_norm": 0.322265625,
|
| 609 |
+
"learning_rate": 0.000215,
|
| 610 |
+
"loss": 2.7189,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.024601753228390987,
|
| 615 |
+
"grad_norm": 0.33203125,
|
| 616 |
+
"learning_rate": 0.0002175,
|
| 617 |
+
"loss": 2.641,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.024884532001131113,
|
| 622 |
+
"grad_norm": 0.302734375,
|
| 623 |
+
"learning_rate": 0.00022,
|
| 624 |
+
"loss": 2.7538,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.02516731077387124,
|
| 629 |
+
"grad_norm": 0.3046875,
|
| 630 |
+
"learning_rate": 0.00022250000000000001,
|
| 631 |
+
"loss": 2.7962,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.02545008954661137,
|
| 636 |
+
"grad_norm": 0.294921875,
|
| 637 |
+
"learning_rate": 0.00022500000000000002,
|
| 638 |
+
"loss": 2.6709,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.025732868319351496,
|
| 643 |
+
"grad_norm": 0.294921875,
|
| 644 |
+
"learning_rate": 0.0002275,
|
| 645 |
+
"loss": 2.7583,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.026015647092091622,
|
| 650 |
+
"grad_norm": 0.296875,
|
| 651 |
+
"learning_rate": 0.00023,
|
| 652 |
+
"loss": 2.7533,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.026298425864831748,
|
| 657 |
+
"grad_norm": 0.291015625,
|
| 658 |
+
"learning_rate": 0.0002325,
|
| 659 |
+
"loss": 2.7713,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.026581204637571874,
|
| 664 |
+
"grad_norm": 0.279296875,
|
| 665 |
+
"learning_rate": 0.000235,
|
| 666 |
+
"loss": 2.7538,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.026863983410312,
|
| 671 |
+
"grad_norm": 0.294921875,
|
| 672 |
+
"learning_rate": 0.0002375,
|
| 673 |
+
"loss": 2.6667,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.027146762183052127,
|
| 678 |
+
"grad_norm": 0.30078125,
|
| 679 |
+
"learning_rate": 0.00024,
|
| 680 |
+
"loss": 2.629,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.027429540955792253,
|
| 685 |
+
"grad_norm": 0.294921875,
|
| 686 |
+
"learning_rate": 0.00024249999999999999,
|
| 687 |
+
"loss": 2.6954,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.02771231972853238,
|
| 692 |
+
"grad_norm": 0.294921875,
|
| 693 |
+
"learning_rate": 0.000245,
|
| 694 |
+
"loss": 2.6587,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.027995098501272506,
|
| 699 |
+
"grad_norm": 0.291015625,
|
| 700 |
+
"learning_rate": 0.0002475,
|
| 701 |
+
"loss": 2.7655,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.028277877274012632,
|
| 706 |
+
"grad_norm": 0.30859375,
|
| 707 |
+
"learning_rate": 0.00025,
|
| 708 |
+
"loss": 2.7836,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.028560656046752758,
|
| 713 |
+
"grad_norm": 0.2890625,
|
| 714 |
+
"learning_rate": 0.0002525,
|
| 715 |
+
"loss": 2.7529,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.028843434819492884,
|
| 720 |
+
"grad_norm": 0.326171875,
|
| 721 |
+
"learning_rate": 0.000255,
|
| 722 |
+
"loss": 2.6644,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.02912621359223301,
|
| 727 |
+
"grad_norm": 0.322265625,
|
| 728 |
+
"learning_rate": 0.0002575,
|
| 729 |
+
"loss": 2.705,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.029408992364973137,
|
| 734 |
+
"grad_norm": 0.31640625,
|
| 735 |
+
"learning_rate": 0.00026000000000000003,
|
| 736 |
+
"loss": 2.7109,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.029691771137713263,
|
| 741 |
+
"grad_norm": 0.279296875,
|
| 742 |
+
"learning_rate": 0.00026250000000000004,
|
| 743 |
+
"loss": 2.7592,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.02997454991045339,
|
| 748 |
+
"grad_norm": 0.30078125,
|
| 749 |
+
"learning_rate": 0.00026500000000000004,
|
| 750 |
+
"loss": 2.747,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.030257328683193516,
|
| 755 |
+
"grad_norm": 0.2890625,
|
| 756 |
+
"learning_rate": 0.0002675,
|
| 757 |
+
"loss": 2.7356,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.030540107455933642,
|
| 762 |
+
"grad_norm": 0.283203125,
|
| 763 |
+
"learning_rate": 0.00027,
|
| 764 |
+
"loss": 2.7167,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.030822886228673768,
|
| 769 |
+
"grad_norm": 0.283203125,
|
| 770 |
+
"learning_rate": 0.0002725,
|
| 771 |
+
"loss": 2.6863,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.031105665001413894,
|
| 776 |
+
"grad_norm": 0.275390625,
|
| 777 |
+
"learning_rate": 0.000275,
|
| 778 |
+
"loss": 2.6439,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.03138844377415402,
|
| 783 |
+
"grad_norm": 0.30859375,
|
| 784 |
+
"learning_rate": 0.0002775,
|
| 785 |
+
"loss": 2.6536,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.03167122254689415,
|
| 790 |
+
"grad_norm": 0.29296875,
|
| 791 |
+
"learning_rate": 0.00028000000000000003,
|
| 792 |
+
"loss": 2.7481,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.03195400131963427,
|
| 797 |
+
"grad_norm": 0.32421875,
|
| 798 |
+
"learning_rate": 0.0002825,
|
| 799 |
+
"loss": 2.6734,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.0322367800923744,
|
| 804 |
+
"grad_norm": 0.28515625,
|
| 805 |
+
"learning_rate": 0.000285,
|
| 806 |
+
"loss": 2.7453,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.032519558865114526,
|
| 811 |
+
"grad_norm": 0.326171875,
|
| 812 |
+
"learning_rate": 0.0002875,
|
| 813 |
+
"loss": 2.8891,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.03280233763785465,
|
| 818 |
+
"grad_norm": 0.287109375,
|
| 819 |
+
"learning_rate": 0.00029,
|
| 820 |
+
"loss": 2.7235,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.03308511641059478,
|
| 825 |
+
"grad_norm": 0.28515625,
|
| 826 |
+
"learning_rate": 0.0002925,
|
| 827 |
+
"loss": 2.6824,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.033367895183334904,
|
| 832 |
+
"grad_norm": 0.28125,
|
| 833 |
+
"learning_rate": 0.000295,
|
| 834 |
+
"loss": 2.7092,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.03365067395607503,
|
| 839 |
+
"grad_norm": 0.279296875,
|
| 840 |
+
"learning_rate": 0.00029749999999999997,
|
| 841 |
+
"loss": 2.7626,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.03393345272881516,
|
| 846 |
+
"grad_norm": 0.28515625,
|
| 847 |
+
"learning_rate": 0.0003,
|
| 848 |
+
"loss": 2.6733,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03421623150155528,
|
| 853 |
+
"grad_norm": 0.287109375,
|
| 854 |
+
"learning_rate": 0.0003025,
|
| 855 |
+
"loss": 2.6709,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03449901027429541,
|
| 860 |
+
"grad_norm": 0.291015625,
|
| 861 |
+
"learning_rate": 0.000305,
|
| 862 |
+
"loss": 2.7311,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.034781789047035536,
|
| 867 |
+
"grad_norm": 0.27734375,
|
| 868 |
+
"learning_rate": 0.0003075,
|
| 869 |
+
"loss": 2.6115,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.03506456781977566,
|
| 874 |
+
"grad_norm": 0.275390625,
|
| 875 |
+
"learning_rate": 0.00031,
|
| 876 |
+
"loss": 2.7095,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.03534734659251579,
|
| 881 |
+
"grad_norm": 0.28125,
|
| 882 |
+
"learning_rate": 0.0003125,
|
| 883 |
+
"loss": 2.6627,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.035630125365255914,
|
| 888 |
+
"grad_norm": 0.279296875,
|
| 889 |
+
"learning_rate": 0.000315,
|
| 890 |
+
"loss": 2.8735,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.03591290413799604,
|
| 895 |
+
"grad_norm": 0.28125,
|
| 896 |
+
"learning_rate": 0.0003175,
|
| 897 |
+
"loss": 2.7889,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.03619568291073617,
|
| 902 |
+
"grad_norm": 0.287109375,
|
| 903 |
+
"learning_rate": 0.00032,
|
| 904 |
+
"loss": 2.6057,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03647846168347629,
|
| 909 |
+
"grad_norm": 0.28515625,
|
| 910 |
+
"learning_rate": 0.00032250000000000003,
|
| 911 |
+
"loss": 2.6387,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.03676124045621642,
|
| 916 |
+
"grad_norm": 0.28125,
|
| 917 |
+
"learning_rate": 0.00032500000000000004,
|
| 918 |
+
"loss": 2.6529,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.037044019228956546,
|
| 923 |
+
"grad_norm": 0.28125,
|
| 924 |
+
"learning_rate": 0.00032750000000000005,
|
| 925 |
+
"loss": 2.795,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.03732679800169667,
|
| 930 |
+
"grad_norm": 0.2734375,
|
| 931 |
+
"learning_rate": 0.00033,
|
| 932 |
+
"loss": 2.685,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.0376095767744368,
|
| 937 |
+
"grad_norm": 0.294921875,
|
| 938 |
+
"learning_rate": 0.0003325,
|
| 939 |
+
"loss": 2.6728,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.037892355547176924,
|
| 944 |
+
"grad_norm": 0.283203125,
|
| 945 |
+
"learning_rate": 0.000335,
|
| 946 |
+
"loss": 2.6906,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03817513431991705,
|
| 951 |
+
"grad_norm": 0.2734375,
|
| 952 |
+
"learning_rate": 0.0003375,
|
| 953 |
+
"loss": 2.6905,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03845791309265718,
|
| 958 |
+
"grad_norm": 0.2890625,
|
| 959 |
+
"learning_rate": 0.00034,
|
| 960 |
+
"loss": 2.8113,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.0387406918653973,
|
| 965 |
+
"grad_norm": 0.279296875,
|
| 966 |
+
"learning_rate": 0.00034250000000000003,
|
| 967 |
+
"loss": 2.7053,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.03902347063813743,
|
| 972 |
+
"grad_norm": 0.27734375,
|
| 973 |
+
"learning_rate": 0.000345,
|
| 974 |
+
"loss": 2.7589,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.039306249410877556,
|
| 979 |
+
"grad_norm": 0.2890625,
|
| 980 |
+
"learning_rate": 0.0003475,
|
| 981 |
+
"loss": 2.7462,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.03958902818361768,
|
| 986 |
+
"grad_norm": 0.279296875,
|
| 987 |
+
"learning_rate": 0.00035,
|
| 988 |
+
"loss": 2.801,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.03987180695635781,
|
| 993 |
+
"grad_norm": 0.27734375,
|
| 994 |
+
"learning_rate": 0.0003525,
|
| 995 |
+
"loss": 2.7696,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.040154585729097934,
|
| 1000 |
+
"grad_norm": 0.267578125,
|
| 1001 |
+
"learning_rate": 0.000355,
|
| 1002 |
+
"loss": 2.7535,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.04043736450183806,
|
| 1007 |
+
"grad_norm": 0.27734375,
|
| 1008 |
+
"learning_rate": 0.0003575,
|
| 1009 |
+
"loss": 2.6457,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.04072014327457819,
|
| 1014 |
+
"grad_norm": 0.29296875,
|
| 1015 |
+
"learning_rate": 0.00035999999999999997,
|
| 1016 |
+
"loss": 2.6899,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.04100292204731831,
|
| 1021 |
+
"grad_norm": 0.29296875,
|
| 1022 |
+
"learning_rate": 0.0003625,
|
| 1023 |
+
"loss": 2.7357,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.04128570082005844,
|
| 1028 |
+
"grad_norm": 0.279296875,
|
| 1029 |
+
"learning_rate": 0.000365,
|
| 1030 |
+
"loss": 2.7567,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.041568479592798566,
|
| 1035 |
+
"grad_norm": 0.27734375,
|
| 1036 |
+
"learning_rate": 0.0003675,
|
| 1037 |
+
"loss": 2.7435,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.04185125836553869,
|
| 1042 |
+
"grad_norm": 0.2890625,
|
| 1043 |
+
"learning_rate": 0.00037,
|
| 1044 |
+
"loss": 2.719,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.04213403713827882,
|
| 1049 |
+
"grad_norm": 0.283203125,
|
| 1050 |
+
"learning_rate": 0.0003725,
|
| 1051 |
+
"loss": 2.7422,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.042416815911018944,
|
| 1056 |
+
"grad_norm": 0.283203125,
|
| 1057 |
+
"learning_rate": 0.000375,
|
| 1058 |
+
"loss": 2.6422,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.04269959468375907,
|
| 1063 |
+
"grad_norm": 0.27734375,
|
| 1064 |
+
"learning_rate": 0.0003775,
|
| 1065 |
+
"loss": 2.6201,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.0429823734564992,
|
| 1070 |
+
"grad_norm": 0.2734375,
|
| 1071 |
+
"learning_rate": 0.00038,
|
| 1072 |
+
"loss": 2.7534,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.04326515222923932,
|
| 1077 |
+
"grad_norm": 0.294921875,
|
| 1078 |
+
"learning_rate": 0.00038250000000000003,
|
| 1079 |
+
"loss": 2.7279,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.04354793100197945,
|
| 1084 |
+
"grad_norm": 0.28515625,
|
| 1085 |
+
"learning_rate": 0.00038500000000000003,
|
| 1086 |
+
"loss": 2.6537,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.043830709774719576,
|
| 1091 |
+
"grad_norm": 0.275390625,
|
| 1092 |
+
"learning_rate": 0.00038750000000000004,
|
| 1093 |
+
"loss": 2.657,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.0441134885474597,
|
| 1098 |
+
"grad_norm": 0.279296875,
|
| 1099 |
+
"learning_rate": 0.00039000000000000005,
|
| 1100 |
+
"loss": 2.6733,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.04439626732019983,
|
| 1105 |
+
"grad_norm": 0.291015625,
|
| 1106 |
+
"learning_rate": 0.0003925,
|
| 1107 |
+
"loss": 2.6964,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.044679046092939954,
|
| 1112 |
+
"grad_norm": 0.28125,
|
| 1113 |
+
"learning_rate": 0.000395,
|
| 1114 |
+
"loss": 2.7566,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.04496182486568008,
|
| 1119 |
+
"grad_norm": 0.28125,
|
| 1120 |
+
"learning_rate": 0.0003975,
|
| 1121 |
+
"loss": 2.729,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.04524460363842021,
|
| 1126 |
+
"grad_norm": 0.322265625,
|
| 1127 |
+
"learning_rate": 0.0004,
|
| 1128 |
+
"loss": 2.6093,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.04552738241116033,
|
| 1133 |
+
"grad_norm": 0.296875,
|
| 1134 |
+
"learning_rate": 0.0004025,
|
| 1135 |
+
"loss": 2.7484,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.04581016118390046,
|
| 1140 |
+
"grad_norm": 0.287109375,
|
| 1141 |
+
"learning_rate": 0.00040500000000000003,
|
| 1142 |
+
"loss": 2.7072,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.046092939956640586,
|
| 1147 |
+
"grad_norm": 0.3046875,
|
| 1148 |
+
"learning_rate": 0.0004075,
|
| 1149 |
+
"loss": 2.7066,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.04637571872938071,
|
| 1154 |
+
"grad_norm": 0.298828125,
|
| 1155 |
+
"learning_rate": 0.00041,
|
| 1156 |
+
"loss": 2.6637,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.04665849750212084,
|
| 1161 |
+
"grad_norm": 0.302734375,
|
| 1162 |
+
"learning_rate": 0.0004125,
|
| 1163 |
+
"loss": 2.7463,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.046941276274860964,
|
| 1168 |
+
"grad_norm": 0.28515625,
|
| 1169 |
+
"learning_rate": 0.000415,
|
| 1170 |
+
"loss": 2.6977,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04722405504760109,
|
| 1175 |
+
"grad_norm": 0.26171875,
|
| 1176 |
+
"learning_rate": 0.0004175,
|
| 1177 |
+
"loss": 2.6522,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.04750683382034122,
|
| 1182 |
+
"grad_norm": 0.279296875,
|
| 1183 |
+
"learning_rate": 0.00042,
|
| 1184 |
+
"loss": 2.728,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.04778961259308134,
|
| 1189 |
+
"grad_norm": 0.28515625,
|
| 1190 |
+
"learning_rate": 0.00042249999999999997,
|
| 1191 |
+
"loss": 2.8141,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.04807239136582147,
|
| 1196 |
+
"grad_norm": 0.267578125,
|
| 1197 |
+
"learning_rate": 0.000425,
|
| 1198 |
+
"loss": 2.7782,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.048355170138561596,
|
| 1203 |
+
"grad_norm": 0.28125,
|
| 1204 |
+
"learning_rate": 0.0004275,
|
| 1205 |
+
"loss": 2.6818,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.04863794891130172,
|
| 1210 |
+
"grad_norm": 0.275390625,
|
| 1211 |
+
"learning_rate": 0.00043,
|
| 1212 |
+
"loss": 2.7362,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.04892072768404185,
|
| 1217 |
+
"grad_norm": 0.271484375,
|
| 1218 |
+
"learning_rate": 0.0004325,
|
| 1219 |
+
"loss": 2.7075,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.049203506456781974,
|
| 1224 |
+
"grad_norm": 0.2734375,
|
| 1225 |
+
"learning_rate": 0.000435,
|
| 1226 |
+
"loss": 2.8147,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.0494862852295221,
|
| 1231 |
+
"grad_norm": 0.287109375,
|
| 1232 |
+
"learning_rate": 0.0004375,
|
| 1233 |
+
"loss": 2.5834,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.04976906400226223,
|
| 1238 |
+
"grad_norm": 0.28125,
|
| 1239 |
+
"learning_rate": 0.00044,
|
| 1240 |
+
"loss": 2.5964,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.05005184277500235,
|
| 1245 |
+
"grad_norm": 0.298828125,
|
| 1246 |
+
"learning_rate": 0.0004425,
|
| 1247 |
+
"loss": 2.7753,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.05033462154774248,
|
| 1252 |
+
"grad_norm": 0.265625,
|
| 1253 |
+
"learning_rate": 0.00044500000000000003,
|
| 1254 |
+
"loss": 2.5962,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.05061740032048261,
|
| 1259 |
+
"grad_norm": 0.279296875,
|
| 1260 |
+
"learning_rate": 0.00044750000000000004,
|
| 1261 |
+
"loss": 2.7144,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.05090017909322274,
|
| 1266 |
+
"grad_norm": 0.283203125,
|
| 1267 |
+
"learning_rate": 0.00045000000000000004,
|
| 1268 |
+
"loss": 2.6035,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.051182957865962865,
|
| 1273 |
+
"grad_norm": 0.267578125,
|
| 1274 |
+
"learning_rate": 0.00045250000000000005,
|
| 1275 |
+
"loss": 2.7479,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.05146573663870299,
|
| 1280 |
+
"grad_norm": 0.27734375,
|
| 1281 |
+
"learning_rate": 0.000455,
|
| 1282 |
+
"loss": 2.7137,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.05174851541144312,
|
| 1287 |
+
"grad_norm": 0.27734375,
|
| 1288 |
+
"learning_rate": 0.0004575,
|
| 1289 |
+
"loss": 2.8017,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.052031294184183244,
|
| 1294 |
+
"grad_norm": 0.287109375,
|
| 1295 |
+
"learning_rate": 0.00046,
|
| 1296 |
+
"loss": 2.7057,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.05231407295692337,
|
| 1301 |
+
"grad_norm": 0.296875,
|
| 1302 |
+
"learning_rate": 0.0004625,
|
| 1303 |
+
"loss": 2.6357,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.052596851729663496,
|
| 1308 |
+
"grad_norm": 0.306640625,
|
| 1309 |
+
"learning_rate": 0.000465,
|
| 1310 |
+
"loss": 2.7985,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.05287963050240362,
|
| 1315 |
+
"grad_norm": 0.2734375,
|
| 1316 |
+
"learning_rate": 0.00046750000000000003,
|
| 1317 |
+
"loss": 2.7495,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.05316240927514375,
|
| 1322 |
+
"grad_norm": 0.26953125,
|
| 1323 |
+
"learning_rate": 0.00047,
|
| 1324 |
+
"loss": 2.8081,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.053445188047883875,
|
| 1329 |
+
"grad_norm": 0.275390625,
|
| 1330 |
+
"learning_rate": 0.0004725,
|
| 1331 |
+
"loss": 2.6571,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.053727966820624,
|
| 1336 |
+
"grad_norm": 0.287109375,
|
| 1337 |
+
"learning_rate": 0.000475,
|
| 1338 |
+
"loss": 2.6884,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.05401074559336413,
|
| 1343 |
+
"grad_norm": 0.3046875,
|
| 1344 |
+
"learning_rate": 0.0004775,
|
| 1345 |
+
"loss": 2.5996,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.054293524366104254,
|
| 1350 |
+
"grad_norm": 0.2890625,
|
| 1351 |
+
"learning_rate": 0.00048,
|
| 1352 |
+
"loss": 2.7077,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.05457630313884438,
|
| 1357 |
+
"grad_norm": 0.2890625,
|
| 1358 |
+
"learning_rate": 0.0004825,
|
| 1359 |
+
"loss": 2.5899,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.054859081911584506,
|
| 1364 |
+
"grad_norm": 0.26953125,
|
| 1365 |
+
"learning_rate": 0.00048499999999999997,
|
| 1366 |
+
"loss": 2.6607,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.05514186068432463,
|
| 1371 |
+
"grad_norm": 0.2890625,
|
| 1372 |
+
"learning_rate": 0.0004875,
|
| 1373 |
+
"loss": 2.6953,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.05542463945706476,
|
| 1378 |
+
"grad_norm": 0.32421875,
|
| 1379 |
+
"learning_rate": 0.00049,
|
| 1380 |
+
"loss": 2.7074,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.055707418229804885,
|
| 1385 |
+
"grad_norm": 0.28515625,
|
| 1386 |
+
"learning_rate": 0.0004925,
|
| 1387 |
+
"loss": 2.7335,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.05599019700254501,
|
| 1392 |
+
"grad_norm": 0.306640625,
|
| 1393 |
+
"learning_rate": 0.000495,
|
| 1394 |
+
"loss": 2.6951,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.05627297577528514,
|
| 1399 |
+
"grad_norm": 0.27734375,
|
| 1400 |
+
"learning_rate": 0.0004975,
|
| 1401 |
+
"loss": 2.6671,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.056555754548025264,
|
| 1406 |
+
"grad_norm": 0.275390625,
|
| 1407 |
+
"learning_rate": 0.0005,
|
| 1408 |
+
"loss": 2.6488,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.05683853332076539,
|
| 1413 |
+
"grad_norm": 0.2890625,
|
| 1414 |
+
"learning_rate": 0.0005024999999999999,
|
| 1415 |
+
"loss": 2.6969,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.057121312093505516,
|
| 1420 |
+
"grad_norm": 0.296875,
|
| 1421 |
+
"learning_rate": 0.000505,
|
| 1422 |
+
"loss": 2.7266,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.05740409086624564,
|
| 1427 |
+
"grad_norm": 0.291015625,
|
| 1428 |
+
"learning_rate": 0.0005074999999999999,
|
| 1429 |
+
"loss": 2.7185,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.05768686963898577,
|
| 1434 |
+
"grad_norm": 0.29296875,
|
| 1435 |
+
"learning_rate": 0.00051,
|
| 1436 |
+
"loss": 2.6981,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.057969648411725895,
|
| 1441 |
+
"grad_norm": 0.275390625,
|
| 1442 |
+
"learning_rate": 0.0005124999999999999,
|
| 1443 |
+
"loss": 2.7895,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.05825242718446602,
|
| 1448 |
+
"grad_norm": 0.2734375,
|
| 1449 |
+
"learning_rate": 0.000515,
|
| 1450 |
+
"loss": 2.6501,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.05853520595720615,
|
| 1455 |
+
"grad_norm": 0.2890625,
|
| 1456 |
+
"learning_rate": 0.0005175,
|
| 1457 |
+
"loss": 2.7063,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.058817984729946274,
|
| 1462 |
+
"grad_norm": 0.3046875,
|
| 1463 |
+
"learning_rate": 0.0005200000000000001,
|
| 1464 |
+
"loss": 2.6494,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.0591007635026864,
|
| 1469 |
+
"grad_norm": 0.29296875,
|
| 1470 |
+
"learning_rate": 0.0005225,
|
| 1471 |
+
"loss": 2.7103,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.059383542275426526,
|
| 1476 |
+
"grad_norm": 0.28515625,
|
| 1477 |
+
"learning_rate": 0.0005250000000000001,
|
| 1478 |
+
"loss": 2.737,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.05966632104816665,
|
| 1483 |
+
"grad_norm": 0.27734375,
|
| 1484 |
+
"learning_rate": 0.0005275,
|
| 1485 |
+
"loss": 2.767,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.05994909982090678,
|
| 1490 |
+
"grad_norm": 0.283203125,
|
| 1491 |
+
"learning_rate": 0.0005300000000000001,
|
| 1492 |
+
"loss": 2.7649,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.060231878593646905,
|
| 1497 |
+
"grad_norm": 0.283203125,
|
| 1498 |
+
"learning_rate": 0.0005325,
|
| 1499 |
+
"loss": 2.7723,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.06051465736638703,
|
| 1504 |
+
"grad_norm": 0.27734375,
|
| 1505 |
+
"learning_rate": 0.000535,
|
| 1506 |
+
"loss": 2.7049,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.06079743613912716,
|
| 1511 |
+
"grad_norm": 0.28125,
|
| 1512 |
+
"learning_rate": 0.0005375,
|
| 1513 |
+
"loss": 2.718,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.061080214911867284,
|
| 1518 |
+
"grad_norm": 0.271484375,
|
| 1519 |
+
"learning_rate": 0.00054,
|
| 1520 |
+
"loss": 2.7322,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.06136299368460741,
|
| 1525 |
+
"grad_norm": 0.279296875,
|
| 1526 |
+
"learning_rate": 0.0005425,
|
| 1527 |
+
"loss": 2.8249,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.061645772457347536,
|
| 1532 |
+
"grad_norm": 0.287109375,
|
| 1533 |
+
"learning_rate": 0.000545,
|
| 1534 |
+
"loss": 2.597,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.06192855123008766,
|
| 1539 |
+
"grad_norm": 0.283203125,
|
| 1540 |
+
"learning_rate": 0.0005475,
|
| 1541 |
+
"loss": 2.6562,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.06221133000282779,
|
| 1546 |
+
"grad_norm": 0.265625,
|
| 1547 |
+
"learning_rate": 0.00055,
|
| 1548 |
+
"loss": 2.6592,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.062494108775567915,
|
| 1553 |
+
"grad_norm": 0.294921875,
|
| 1554 |
+
"learning_rate": 0.0005525,
|
| 1555 |
+
"loss": 2.6218,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.06277688754830804,
|
| 1560 |
+
"grad_norm": 0.275390625,
|
| 1561 |
+
"learning_rate": 0.000555,
|
| 1562 |
+
"loss": 2.7255,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.06305966632104816,
|
| 1567 |
+
"grad_norm": 0.271484375,
|
| 1568 |
+
"learning_rate": 0.0005575,
|
| 1569 |
+
"loss": 2.8204,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.0633424450937883,
|
| 1574 |
+
"grad_norm": 0.287109375,
|
| 1575 |
+
"learning_rate": 0.0005600000000000001,
|
| 1576 |
+
"loss": 2.7503,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.06362522386652841,
|
| 1581 |
+
"grad_norm": 0.298828125,
|
| 1582 |
+
"learning_rate": 0.0005625000000000001,
|
| 1583 |
+
"loss": 2.659,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.06390800263926855,
|
| 1588 |
+
"grad_norm": 0.2890625,
|
| 1589 |
+
"learning_rate": 0.000565,
|
| 1590 |
+
"loss": 2.8152,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.06419078141200867,
|
| 1595 |
+
"grad_norm": 0.27734375,
|
| 1596 |
+
"learning_rate": 0.0005675,
|
| 1597 |
+
"loss": 2.7683,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.0644735601847488,
|
| 1602 |
+
"grad_norm": 0.275390625,
|
| 1603 |
+
"learning_rate": 0.00057,
|
| 1604 |
+
"loss": 2.6908,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.06475633895748892,
|
| 1609 |
+
"grad_norm": 0.302734375,
|
| 1610 |
+
"learning_rate": 0.0005725,
|
| 1611 |
+
"loss": 2.7206,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.06503911773022905,
|
| 1616 |
+
"grad_norm": 0.28125,
|
| 1617 |
+
"learning_rate": 0.000575,
|
| 1618 |
+
"loss": 2.6713,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.06532189650296917,
|
| 1623 |
+
"grad_norm": 0.296875,
|
| 1624 |
+
"learning_rate": 0.0005775,
|
| 1625 |
+
"loss": 2.5687,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.0656046752757093,
|
| 1630 |
+
"grad_norm": 0.275390625,
|
| 1631 |
+
"learning_rate": 0.00058,
|
| 1632 |
+
"loss": 2.7068,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.06588745404844942,
|
| 1637 |
+
"grad_norm": 0.29296875,
|
| 1638 |
+
"learning_rate": 0.0005825,
|
| 1639 |
+
"loss": 2.7664,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.06617023282118956,
|
| 1644 |
+
"grad_norm": 0.306640625,
|
| 1645 |
+
"learning_rate": 0.000585,
|
| 1646 |
+
"loss": 2.7705,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.06645301159392968,
|
| 1651 |
+
"grad_norm": 0.32421875,
|
| 1652 |
+
"learning_rate": 0.0005875,
|
| 1653 |
+
"loss": 2.6366,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.06673579036666981,
|
| 1658 |
+
"grad_norm": 0.310546875,
|
| 1659 |
+
"learning_rate": 0.00059,
|
| 1660 |
+
"loss": 2.6913,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.06701856913940993,
|
| 1665 |
+
"grad_norm": 0.2890625,
|
| 1666 |
+
"learning_rate": 0.0005925,
|
| 1667 |
+
"loss": 2.6292,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.06730134791215006,
|
| 1672 |
+
"grad_norm": 0.275390625,
|
| 1673 |
+
"learning_rate": 0.0005949999999999999,
|
| 1674 |
+
"loss": 2.6452,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.0675841266848902,
|
| 1679 |
+
"grad_norm": 0.279296875,
|
| 1680 |
+
"learning_rate": 0.0005975,
|
| 1681 |
+
"loss": 2.5264,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.06786690545763031,
|
| 1686 |
+
"grad_norm": 0.2890625,
|
| 1687 |
+
"learning_rate": 0.0006,
|
| 1688 |
+
"loss": 2.7456,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.06814968423037045,
|
| 1693 |
+
"grad_norm": 0.283203125,
|
| 1694 |
+
"learning_rate": 0.0006025000000000001,
|
| 1695 |
+
"loss": 2.6951,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.06843246300311057,
|
| 1700 |
+
"grad_norm": 0.33203125,
|
| 1701 |
+
"learning_rate": 0.000605,
|
| 1702 |
+
"loss": 2.7262,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.0687152417758507,
|
| 1707 |
+
"grad_norm": 0.294921875,
|
| 1708 |
+
"learning_rate": 0.0006075000000000001,
|
| 1709 |
+
"loss": 2.7282,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.06899802054859082,
|
| 1714 |
+
"grad_norm": 0.291015625,
|
| 1715 |
+
"learning_rate": 0.00061,
|
| 1716 |
+
"loss": 2.7134,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.06928079932133095,
|
| 1721 |
+
"grad_norm": 0.28515625,
|
| 1722 |
+
"learning_rate": 0.0006125000000000001,
|
| 1723 |
+
"loss": 2.6794,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.06956357809407107,
|
| 1728 |
+
"grad_norm": 0.298828125,
|
| 1729 |
+
"learning_rate": 0.000615,
|
| 1730 |
+
"loss": 2.7105,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.0698463568668112,
|
| 1735 |
+
"grad_norm": 0.3046875,
|
| 1736 |
+
"learning_rate": 0.0006175000000000001,
|
| 1737 |
+
"loss": 2.6656,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.07012913563955132,
|
| 1742 |
+
"grad_norm": 0.271484375,
|
| 1743 |
+
"learning_rate": 0.00062,
|
| 1744 |
+
"loss": 2.669,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.07041191441229146,
|
| 1749 |
+
"grad_norm": 0.294921875,
|
| 1750 |
+
"learning_rate": 0.0006225000000000001,
|
| 1751 |
+
"loss": 2.7143,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.07069469318503158,
|
| 1756 |
+
"grad_norm": 0.28515625,
|
| 1757 |
+
"learning_rate": 0.000625,
|
| 1758 |
+
"loss": 2.7088,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.07097747195777171,
|
| 1763 |
+
"grad_norm": 0.3125,
|
| 1764 |
+
"learning_rate": 0.0006274999999999999,
|
| 1765 |
+
"loss": 2.6446,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.07126025073051183,
|
| 1770 |
+
"grad_norm": 0.30078125,
|
| 1771 |
+
"learning_rate": 0.00063,
|
| 1772 |
+
"loss": 2.6527,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.07154302950325196,
|
| 1777 |
+
"grad_norm": 0.279296875,
|
| 1778 |
+
"learning_rate": 0.0006324999999999999,
|
| 1779 |
+
"loss": 2.7882,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.07182580827599208,
|
| 1784 |
+
"grad_norm": 0.2734375,
|
| 1785 |
+
"learning_rate": 0.000635,
|
| 1786 |
+
"loss": 2.711,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.07210858704873221,
|
| 1791 |
+
"grad_norm": 0.29296875,
|
| 1792 |
+
"learning_rate": 0.0006374999999999999,
|
| 1793 |
+
"loss": 2.733,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.07239136582147233,
|
| 1798 |
+
"grad_norm": 0.283203125,
|
| 1799 |
+
"learning_rate": 0.00064,
|
| 1800 |
+
"loss": 2.5823,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.07267414459421247,
|
| 1805 |
+
"grad_norm": 0.33203125,
|
| 1806 |
+
"learning_rate": 0.0006425,
|
| 1807 |
+
"loss": 2.6286,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.07295692336695259,
|
| 1812 |
+
"grad_norm": 0.302734375,
|
| 1813 |
+
"learning_rate": 0.0006450000000000001,
|
| 1814 |
+
"loss": 2.6986,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.07323970213969272,
|
| 1819 |
+
"grad_norm": 0.27734375,
|
| 1820 |
+
"learning_rate": 0.0006475,
|
| 1821 |
+
"loss": 2.7071,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.07352248091243284,
|
| 1826 |
+
"grad_norm": 0.275390625,
|
| 1827 |
+
"learning_rate": 0.0006500000000000001,
|
| 1828 |
+
"loss": 2.6763,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.07380525968517297,
|
| 1833 |
+
"grad_norm": 0.328125,
|
| 1834 |
+
"learning_rate": 0.0006525,
|
| 1835 |
+
"loss": 2.759,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.07408803845791309,
|
| 1840 |
+
"grad_norm": 0.2890625,
|
| 1841 |
+
"learning_rate": 0.0006550000000000001,
|
| 1842 |
+
"loss": 2.735,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.07437081723065322,
|
| 1847 |
+
"grad_norm": 0.296875,
|
| 1848 |
+
"learning_rate": 0.0006575,
|
| 1849 |
+
"loss": 2.7129,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.07465359600339334,
|
| 1854 |
+
"grad_norm": 0.283203125,
|
| 1855 |
+
"learning_rate": 0.00066,
|
| 1856 |
+
"loss": 2.7521,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.07493637477613348,
|
| 1861 |
+
"grad_norm": 0.2734375,
|
| 1862 |
+
"learning_rate": 0.0006625,
|
| 1863 |
+
"loss": 2.6918,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.0752191535488736,
|
| 1868 |
+
"grad_norm": 0.28125,
|
| 1869 |
+
"learning_rate": 0.000665,
|
| 1870 |
+
"loss": 2.6264,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.07550193232161373,
|
| 1875 |
+
"grad_norm": 0.298828125,
|
| 1876 |
+
"learning_rate": 0.0006675,
|
| 1877 |
+
"loss": 2.7115,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.07578471109435385,
|
| 1882 |
+
"grad_norm": 0.298828125,
|
| 1883 |
+
"learning_rate": 0.00067,
|
| 1884 |
+
"loss": 2.7494,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.07606748986709398,
|
| 1889 |
+
"grad_norm": 0.283203125,
|
| 1890 |
+
"learning_rate": 0.0006725,
|
| 1891 |
+
"loss": 2.6134,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.0763502686398341,
|
| 1896 |
+
"grad_norm": 0.298828125,
|
| 1897 |
+
"learning_rate": 0.000675,
|
| 1898 |
+
"loss": 2.6015,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.07663304741257423,
|
| 1903 |
+
"grad_norm": 0.31640625,
|
| 1904 |
+
"learning_rate": 0.0006775,
|
| 1905 |
+
"loss": 2.6864,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.07691582618531435,
|
| 1910 |
+
"grad_norm": 0.2890625,
|
| 1911 |
+
"learning_rate": 0.00068,
|
| 1912 |
+
"loss": 2.6564,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.07719860495805449,
|
| 1917 |
+
"grad_norm": 0.275390625,
|
| 1918 |
+
"learning_rate": 0.0006825000000000001,
|
| 1919 |
+
"loss": 2.6775,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.0774813837307946,
|
| 1924 |
+
"grad_norm": 0.29296875,
|
| 1925 |
+
"learning_rate": 0.0006850000000000001,
|
| 1926 |
+
"loss": 2.6788,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.07776416250353474,
|
| 1931 |
+
"grad_norm": 0.283203125,
|
| 1932 |
+
"learning_rate": 0.0006875,
|
| 1933 |
+
"loss": 2.6712,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.07804694127627486,
|
| 1938 |
+
"grad_norm": 0.28125,
|
| 1939 |
+
"learning_rate": 0.00069,
|
| 1940 |
+
"loss": 2.7014,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.07832972004901499,
|
| 1945 |
+
"grad_norm": 0.2734375,
|
| 1946 |
+
"learning_rate": 0.0006925,
|
| 1947 |
+
"loss": 2.6744,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.07861249882175511,
|
| 1952 |
+
"grad_norm": 0.28125,
|
| 1953 |
+
"learning_rate": 0.000695,
|
| 1954 |
+
"loss": 2.7591,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.07889527759449524,
|
| 1959 |
+
"grad_norm": 0.3203125,
|
| 1960 |
+
"learning_rate": 0.0006975,
|
| 1961 |
+
"loss": 2.7315,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.07917805636723536,
|
| 1966 |
+
"grad_norm": 0.291015625,
|
| 1967 |
+
"learning_rate": 0.0007,
|
| 1968 |
+
"loss": 2.6955,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.0794608351399755,
|
| 1973 |
+
"grad_norm": 0.29296875,
|
| 1974 |
+
"learning_rate": 0.0007025,
|
| 1975 |
+
"loss": 2.6846,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.07974361391271562,
|
| 1980 |
+
"grad_norm": 0.2890625,
|
| 1981 |
+
"learning_rate": 0.000705,
|
| 1982 |
+
"loss": 2.5973,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.08002639268545575,
|
| 1987 |
+
"grad_norm": 0.27734375,
|
| 1988 |
+
"learning_rate": 0.0007075,
|
| 1989 |
+
"loss": 2.671,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.08030917145819587,
|
| 1994 |
+
"grad_norm": 0.29296875,
|
| 1995 |
+
"learning_rate": 0.00071,
|
| 1996 |
+
"loss": 2.7698,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.080591950230936,
|
| 2001 |
+
"grad_norm": 0.29296875,
|
| 2002 |
+
"learning_rate": 0.0007125,
|
| 2003 |
+
"loss": 2.6023,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.08087472900367612,
|
| 2008 |
+
"grad_norm": 0.26953125,
|
| 2009 |
+
"learning_rate": 0.000715,
|
| 2010 |
+
"loss": 2.5578,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.08115750777641625,
|
| 2015 |
+
"grad_norm": 0.30078125,
|
| 2016 |
+
"learning_rate": 0.0007175,
|
| 2017 |
+
"loss": 2.7082,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.08144028654915637,
|
| 2022 |
+
"grad_norm": 0.287109375,
|
| 2023 |
+
"learning_rate": 0.0007199999999999999,
|
| 2024 |
+
"loss": 2.6585,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.08172306532189651,
|
| 2029 |
+
"grad_norm": 0.296875,
|
| 2030 |
+
"learning_rate": 0.0007225,
|
| 2031 |
+
"loss": 2.6401,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.08200584409463663,
|
| 2036 |
+
"grad_norm": 0.296875,
|
| 2037 |
+
"learning_rate": 0.000725,
|
| 2038 |
+
"loss": 2.6788,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.08228862286737676,
|
| 2043 |
+
"grad_norm": 0.26953125,
|
| 2044 |
+
"learning_rate": 0.0007275000000000001,
|
| 2045 |
+
"loss": 2.681,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.08257140164011688,
|
| 2050 |
+
"grad_norm": 0.302734375,
|
| 2051 |
+
"learning_rate": 0.00073,
|
| 2052 |
+
"loss": 2.7276,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.08285418041285701,
|
| 2057 |
+
"grad_norm": 0.28515625,
|
| 2058 |
+
"learning_rate": 0.0007325000000000001,
|
| 2059 |
+
"loss": 2.6946,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.08313695918559713,
|
| 2064 |
+
"grad_norm": 0.283203125,
|
| 2065 |
+
"learning_rate": 0.000735,
|
| 2066 |
+
"loss": 2.6882,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.08341973795833726,
|
| 2071 |
+
"grad_norm": 0.291015625,
|
| 2072 |
+
"learning_rate": 0.0007375000000000001,
|
| 2073 |
+
"loss": 2.6571,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.08370251673107738,
|
| 2078 |
+
"grad_norm": 0.27734375,
|
| 2079 |
+
"learning_rate": 0.00074,
|
| 2080 |
+
"loss": 2.7716,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.08398529550381752,
|
| 2085 |
+
"grad_norm": 0.3125,
|
| 2086 |
+
"learning_rate": 0.0007425000000000001,
|
| 2087 |
+
"loss": 2.7189,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.08426807427655764,
|
| 2092 |
+
"grad_norm": 0.294921875,
|
| 2093 |
+
"learning_rate": 0.000745,
|
| 2094 |
+
"loss": 2.6868,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.08455085304929777,
|
| 2099 |
+
"grad_norm": 0.28515625,
|
| 2100 |
+
"learning_rate": 0.0007475000000000001,
|
| 2101 |
+
"loss": 2.6705,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.08483363182203789,
|
| 2106 |
+
"grad_norm": 0.28125,
|
| 2107 |
+
"learning_rate": 0.00075,
|
| 2108 |
+
"loss": 2.7242,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.08483363182203789,
|
| 2113 |
+
"eval_loss": 1.8609898090362549,
|
| 2114 |
+
"eval_runtime": 74.934,
|
| 2115 |
+
"eval_samples_per_second": 13.665,
|
| 2116 |
+
"eval_steps_per_second": 0.427,
|
| 2117 |
+
"step": 300
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.08483363182203789,
|
| 2121 |
+
"eval/hellaswag_acc": 0.37572196773551086,
|
| 2122 |
+
"eval/hellaswag_acc_norm": 0.4715196176060546,
|
| 2123 |
+
"eval_hellaswag_elapsed_time": 331.94735646247864,
|
| 2124 |
+
"step": 300
|
| 2125 |
+
}
|
| 2126 |
+
],
|
| 2127 |
+
"logging_steps": 1,
|
| 2128 |
+
"max_steps": 3536,
|
| 2129 |
+
"num_input_tokens_seen": 0,
|
| 2130 |
+
"num_train_epochs": 1,
|
| 2131 |
+
"save_steps": 300,
|
| 2132 |
+
"stateful_callbacks": {
|
| 2133 |
+
"TrainerControl": {
|
| 2134 |
+
"args": {
|
| 2135 |
+
"should_epoch_stop": false,
|
| 2136 |
+
"should_evaluate": false,
|
| 2137 |
+
"should_log": false,
|
| 2138 |
+
"should_save": true,
|
| 2139 |
+
"should_training_stop": false
|
| 2140 |
+
},
|
| 2141 |
+
"attributes": {}
|
| 2142 |
+
}
|
| 2143 |
+
},
|
| 2144 |
+
"total_flos": 1.0466845500899328e+18,
|
| 2145 |
+
"train_batch_size": 36,
|
| 2146 |
+
"trial_name": null,
|
| 2147 |
+
"trial_params": null
|
| 2148 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8013b814259602ed6ff882614208872ab7a8454b694cebafcd4203b1c1554ba8
|
| 3 |
+
size 7992
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|