Upload 10 files
Browse files- config.json +31 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +219 -0
- tokenizer_config.json +52 -0
- trainer_state.json +622 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/models/Mixtral-8x7B-v0.1-dna",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 256,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_experts_per_tok": 1,
|
| 17 |
+
"num_hidden_layers": 8,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 8,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.02,
|
| 24 |
+
"router_jitter_noise": 0.0,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.42.3",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 4096
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.42.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305dede2fdee20d047e123615cfb249528821a5e5bc8fb00d6ab6df140526b1d
|
| 3 |
+
size 33626152
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee92eb46fa92334cd0695596a0005ba047370328e120afcbe0600b3db0d3cf32
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7378136e562900ec12820c4ab10f2ec29f1c77d7f9389389f0212dc950cd09a2
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[EOS]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 100,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
| 11 |
+
"direction": "Right",
|
| 12 |
+
"pad_to_multiple_of": null,
|
| 13 |
+
"pad_id": 64,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "[EOS]"
|
| 16 |
+
},
|
| 17 |
+
"added_tokens": [
|
| 18 |
+
{
|
| 19 |
+
"id": 64,
|
| 20 |
+
"content": "[UNK]",
|
| 21 |
+
"single_word": false,
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"id": 65,
|
| 29 |
+
"content": "[CLS]",
|
| 30 |
+
"single_word": false,
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"id": 66,
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"single_word": false,
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"id": 67,
|
| 47 |
+
"content": "[PAD]",
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"id": 68,
|
| 56 |
+
"content": "[MASK]",
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"rstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"special": true
|
| 62 |
+
}
|
| 63 |
+
],
|
| 64 |
+
"normalizer": null,
|
| 65 |
+
"pre_tokenizer": {
|
| 66 |
+
"type": "Whitespace"
|
| 67 |
+
},
|
| 68 |
+
"post_processor": {
|
| 69 |
+
"type": "TemplateProcessing",
|
| 70 |
+
"single": [
|
| 71 |
+
{
|
| 72 |
+
"SpecialToken": {
|
| 73 |
+
"id": "[CLS]",
|
| 74 |
+
"type_id": 0
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"Sequence": {
|
| 79 |
+
"id": "A",
|
| 80 |
+
"type_id": 0
|
| 81 |
+
}
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"SpecialToken": {
|
| 85 |
+
"id": "[SEP]",
|
| 86 |
+
"type_id": 0
|
| 87 |
+
}
|
| 88 |
+
}
|
| 89 |
+
],
|
| 90 |
+
"pair": [
|
| 91 |
+
{
|
| 92 |
+
"SpecialToken": {
|
| 93 |
+
"id": "[CLS]",
|
| 94 |
+
"type_id": 0
|
| 95 |
+
}
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"Sequence": {
|
| 99 |
+
"id": "A",
|
| 100 |
+
"type_id": 0
|
| 101 |
+
}
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"SpecialToken": {
|
| 105 |
+
"id": "[SEP]",
|
| 106 |
+
"type_id": 0
|
| 107 |
+
}
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"Sequence": {
|
| 111 |
+
"id": "B",
|
| 112 |
+
"type_id": 1
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"SpecialToken": {
|
| 117 |
+
"id": "[SEP]",
|
| 118 |
+
"type_id": 1
|
| 119 |
+
}
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"special_tokens": {
|
| 123 |
+
"[CLS]": {
|
| 124 |
+
"id": "[CLS]",
|
| 125 |
+
"ids": [
|
| 126 |
+
65
|
| 127 |
+
],
|
| 128 |
+
"tokens": [
|
| 129 |
+
"[CLS]"
|
| 130 |
+
]
|
| 131 |
+
},
|
| 132 |
+
"[SEP]": {
|
| 133 |
+
"id": "[SEP]",
|
| 134 |
+
"ids": [
|
| 135 |
+
66
|
| 136 |
+
],
|
| 137 |
+
"tokens": [
|
| 138 |
+
"[SEP]"
|
| 139 |
+
]
|
| 140 |
+
}
|
| 141 |
+
}
|
| 142 |
+
},
|
| 143 |
+
"decoder": null,
|
| 144 |
+
"model": {
|
| 145 |
+
"type": "WordLevel",
|
| 146 |
+
"vocab": {
|
| 147 |
+
"AAA": 0,
|
| 148 |
+
"AAT": 1,
|
| 149 |
+
"AAG": 2,
|
| 150 |
+
"AAC": 3,
|
| 151 |
+
"ATA": 4,
|
| 152 |
+
"ATT": 5,
|
| 153 |
+
"ATG": 6,
|
| 154 |
+
"ATC": 7,
|
| 155 |
+
"AGA": 8,
|
| 156 |
+
"AGT": 9,
|
| 157 |
+
"AGG": 10,
|
| 158 |
+
"AGC": 11,
|
| 159 |
+
"ACA": 12,
|
| 160 |
+
"ACT": 13,
|
| 161 |
+
"ACG": 14,
|
| 162 |
+
"ACC": 15,
|
| 163 |
+
"TAA": 16,
|
| 164 |
+
"TAT": 17,
|
| 165 |
+
"TAG": 18,
|
| 166 |
+
"TAC": 19,
|
| 167 |
+
"TTA": 20,
|
| 168 |
+
"TTT": 21,
|
| 169 |
+
"TTG": 22,
|
| 170 |
+
"TTC": 23,
|
| 171 |
+
"TGA": 24,
|
| 172 |
+
"TGT": 25,
|
| 173 |
+
"TGG": 26,
|
| 174 |
+
"TGC": 27,
|
| 175 |
+
"TCA": 28,
|
| 176 |
+
"TCT": 29,
|
| 177 |
+
"TCG": 30,
|
| 178 |
+
"TCC": 31,
|
| 179 |
+
"GAA": 32,
|
| 180 |
+
"GAT": 33,
|
| 181 |
+
"GAG": 34,
|
| 182 |
+
"GAC": 35,
|
| 183 |
+
"GTA": 36,
|
| 184 |
+
"GTT": 37,
|
| 185 |
+
"GTG": 38,
|
| 186 |
+
"GTC": 39,
|
| 187 |
+
"GGA": 40,
|
| 188 |
+
"GGT": 41,
|
| 189 |
+
"GGG": 42,
|
| 190 |
+
"GGC": 43,
|
| 191 |
+
"GCA": 44,
|
| 192 |
+
"GCT": 45,
|
| 193 |
+
"GCG": 46,
|
| 194 |
+
"GCC": 47,
|
| 195 |
+
"CAA": 48,
|
| 196 |
+
"CAT": 49,
|
| 197 |
+
"CAG": 50,
|
| 198 |
+
"CAC": 51,
|
| 199 |
+
"CTA": 52,
|
| 200 |
+
"CTT": 53,
|
| 201 |
+
"CTG": 54,
|
| 202 |
+
"CTC": 55,
|
| 203 |
+
"CGA": 56,
|
| 204 |
+
"CGT": 57,
|
| 205 |
+
"CGG": 58,
|
| 206 |
+
"CGC": 59,
|
| 207 |
+
"CCA": 60,
|
| 208 |
+
"CCT": 61,
|
| 209 |
+
"CCG": 62,
|
| 210 |
+
"CCC": 63,
|
| 211 |
+
"[UNK]": 64,
|
| 212 |
+
"[CLS]": 65,
|
| 213 |
+
"[SEP]": 66,
|
| 214 |
+
"[PAD]": 67,
|
| 215 |
+
"[MASK]": 68
|
| 216 |
+
},
|
| 217 |
+
"unk_token": "[UNK]"
|
| 218 |
+
}
|
| 219 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"64": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"65": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"66": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"67": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"68": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"mask_token": "[MASK]",
|
| 47 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 48 |
+
"pad_token": "[EOS]",
|
| 49 |
+
"sep_token": "[SEP]",
|
| 50 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 51 |
+
"unk_token": "[UNK]"
|
| 52 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.7241549491882324,
|
| 3 |
+
"best_model_checkpoint": "./results/models/checkpoint-26406",
|
| 4 |
+
"epoch": 27.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 26406,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5112474437627812,
|
| 13 |
+
"grad_norm": 0.1318359375,
|
| 14 |
+
"learning_rate": 0.0009897750511247444,
|
| 15 |
+
"loss": 3.8641,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 3.6347575187683105,
|
| 21 |
+
"eval_runtime": 0.3183,
|
| 22 |
+
"eval_samples_per_second": 1571.027,
|
| 23 |
+
"eval_steps_per_second": 3.142,
|
| 24 |
+
"step": 978
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0224948875255624,
|
| 28 |
+
"grad_norm": 0.2255859375,
|
| 29 |
+
"learning_rate": 0.0009795501022494889,
|
| 30 |
+
"loss": 3.6938,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.5337423312883436,
|
| 35 |
+
"grad_norm": 0.263671875,
|
| 36 |
+
"learning_rate": 0.0009693251533742331,
|
| 37 |
+
"loss": 3.488,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.0,
|
| 42 |
+
"eval_loss": 3.214155912399292,
|
| 43 |
+
"eval_runtime": 0.95,
|
| 44 |
+
"eval_samples_per_second": 526.301,
|
| 45 |
+
"eval_steps_per_second": 1.053,
|
| 46 |
+
"step": 1956
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.044989775051125,
|
| 50 |
+
"grad_norm": 0.224609375,
|
| 51 |
+
"learning_rate": 0.0009591002044989775,
|
| 52 |
+
"loss": 3.2879,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.556237218813906,
|
| 57 |
+
"grad_norm": 0.2373046875,
|
| 58 |
+
"learning_rate": 0.0009488752556237219,
|
| 59 |
+
"loss": 3.1641,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.0,
|
| 64 |
+
"eval_loss": 3.0714735984802246,
|
| 65 |
+
"eval_runtime": 0.9223,
|
| 66 |
+
"eval_samples_per_second": 542.135,
|
| 67 |
+
"eval_steps_per_second": 1.084,
|
| 68 |
+
"step": 2934
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.067484662576687,
|
| 72 |
+
"grad_norm": 0.29296875,
|
| 73 |
+
"learning_rate": 0.0009386503067484663,
|
| 74 |
+
"loss": 3.0912,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.5787321063394684,
|
| 79 |
+
"grad_norm": 0.255859375,
|
| 80 |
+
"learning_rate": 0.0009284253578732107,
|
| 81 |
+
"loss": 3.0323,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.0,
|
| 86 |
+
"eval_loss": 2.990953207015991,
|
| 87 |
+
"eval_runtime": 1.0538,
|
| 88 |
+
"eval_samples_per_second": 474.475,
|
| 89 |
+
"eval_steps_per_second": 0.949,
|
| 90 |
+
"step": 3912
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.08997955010225,
|
| 94 |
+
"grad_norm": 0.259765625,
|
| 95 |
+
"learning_rate": 0.000918200408997955,
|
| 96 |
+
"loss": 2.9912,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.601226993865031,
|
| 101 |
+
"grad_norm": 0.337890625,
|
| 102 |
+
"learning_rate": 0.0009079754601226994,
|
| 103 |
+
"loss": 2.9553,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.0,
|
| 108 |
+
"eval_loss": 2.9412269592285156,
|
| 109 |
+
"eval_runtime": 1.0599,
|
| 110 |
+
"eval_samples_per_second": 471.73,
|
| 111 |
+
"eval_steps_per_second": 0.943,
|
| 112 |
+
"step": 4890
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.112474437627812,
|
| 116 |
+
"grad_norm": 0.26953125,
|
| 117 |
+
"learning_rate": 0.0008977505112474438,
|
| 118 |
+
"loss": 2.9255,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 5.623721881390593,
|
| 123 |
+
"grad_norm": 0.25390625,
|
| 124 |
+
"learning_rate": 0.0008875255623721882,
|
| 125 |
+
"loss": 2.8991,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.0,
|
| 130 |
+
"eval_loss": 2.905097723007202,
|
| 131 |
+
"eval_runtime": 1.0476,
|
| 132 |
+
"eval_samples_per_second": 477.298,
|
| 133 |
+
"eval_steps_per_second": 0.955,
|
| 134 |
+
"step": 5868
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.134969325153374,
|
| 138 |
+
"grad_norm": 0.3203125,
|
| 139 |
+
"learning_rate": 0.0008773006134969325,
|
| 140 |
+
"loss": 2.8794,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.6462167689161555,
|
| 145 |
+
"grad_norm": 0.29296875,
|
| 146 |
+
"learning_rate": 0.0008670756646216768,
|
| 147 |
+
"loss": 2.8577,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.0,
|
| 152 |
+
"eval_loss": 2.8703627586364746,
|
| 153 |
+
"eval_runtime": 1.0515,
|
| 154 |
+
"eval_samples_per_second": 475.508,
|
| 155 |
+
"eval_steps_per_second": 0.951,
|
| 156 |
+
"step": 6846
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 7.157464212678937,
|
| 160 |
+
"grad_norm": 0.29296875,
|
| 161 |
+
"learning_rate": 0.0008568507157464213,
|
| 162 |
+
"loss": 2.8435,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.668711656441718,
|
| 167 |
+
"grad_norm": 0.30078125,
|
| 168 |
+
"learning_rate": 0.0008466257668711657,
|
| 169 |
+
"loss": 2.8289,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.0,
|
| 174 |
+
"eval_loss": 2.847052812576294,
|
| 175 |
+
"eval_runtime": 1.0464,
|
| 176 |
+
"eval_samples_per_second": 477.826,
|
| 177 |
+
"eval_steps_per_second": 0.956,
|
| 178 |
+
"step": 7824
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 8.1799591002045,
|
| 182 |
+
"grad_norm": 0.3046875,
|
| 183 |
+
"learning_rate": 0.0008364008179959101,
|
| 184 |
+
"loss": 2.8131,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.69120654396728,
|
| 189 |
+
"grad_norm": 0.359375,
|
| 190 |
+
"learning_rate": 0.0008261758691206544,
|
| 191 |
+
"loss": 2.8022,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 9.0,
|
| 196 |
+
"eval_loss": 2.8293135166168213,
|
| 197 |
+
"eval_runtime": 0.9764,
|
| 198 |
+
"eval_samples_per_second": 512.074,
|
| 199 |
+
"eval_steps_per_second": 1.024,
|
| 200 |
+
"step": 8802
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 9.202453987730062,
|
| 204 |
+
"grad_norm": 0.310546875,
|
| 205 |
+
"learning_rate": 0.0008159509202453987,
|
| 206 |
+
"loss": 2.7914,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 9.713701431492842,
|
| 211 |
+
"grad_norm": 0.314453125,
|
| 212 |
+
"learning_rate": 0.0008057259713701431,
|
| 213 |
+
"loss": 2.7813,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.0,
|
| 218 |
+
"eval_loss": 2.8122880458831787,
|
| 219 |
+
"eval_runtime": 1.0064,
|
| 220 |
+
"eval_samples_per_second": 496.84,
|
| 221 |
+
"eval_steps_per_second": 0.994,
|
| 222 |
+
"step": 9780
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 10.224948875255624,
|
| 226 |
+
"grad_norm": 0.296875,
|
| 227 |
+
"learning_rate": 0.0007955010224948876,
|
| 228 |
+
"loss": 2.7682,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 10.736196319018404,
|
| 233 |
+
"grad_norm": 0.328125,
|
| 234 |
+
"learning_rate": 0.0007852760736196319,
|
| 235 |
+
"loss": 2.7607,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 11.0,
|
| 240 |
+
"eval_loss": 2.8023903369903564,
|
| 241 |
+
"eval_runtime": 1.0601,
|
| 242 |
+
"eval_samples_per_second": 471.642,
|
| 243 |
+
"eval_steps_per_second": 0.943,
|
| 244 |
+
"step": 10758
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 11.247443762781186,
|
| 248 |
+
"grad_norm": 0.294921875,
|
| 249 |
+
"learning_rate": 0.0007750511247443763,
|
| 250 |
+
"loss": 2.7527,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 11.758691206543967,
|
| 255 |
+
"grad_norm": 0.3046875,
|
| 256 |
+
"learning_rate": 0.0007648261758691206,
|
| 257 |
+
"loss": 2.7443,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 12.0,
|
| 262 |
+
"eval_loss": 2.7869932651519775,
|
| 263 |
+
"eval_runtime": 1.0222,
|
| 264 |
+
"eval_samples_per_second": 489.149,
|
| 265 |
+
"eval_steps_per_second": 0.978,
|
| 266 |
+
"step": 11736
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 12.269938650306749,
|
| 270 |
+
"grad_norm": 0.298828125,
|
| 271 |
+
"learning_rate": 0.000754601226993865,
|
| 272 |
+
"loss": 2.7366,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.781186094069529,
|
| 277 |
+
"grad_norm": 0.34375,
|
| 278 |
+
"learning_rate": 0.0007443762781186095,
|
| 279 |
+
"loss": 2.7313,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 13.0,
|
| 284 |
+
"eval_loss": 2.785067081451416,
|
| 285 |
+
"eval_runtime": 1.051,
|
| 286 |
+
"eval_samples_per_second": 475.716,
|
| 287 |
+
"eval_steps_per_second": 0.951,
|
| 288 |
+
"step": 12714
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.292433537832311,
|
| 292 |
+
"grad_norm": 0.33203125,
|
| 293 |
+
"learning_rate": 0.0007341513292433538,
|
| 294 |
+
"loss": 2.7223,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 13.803680981595091,
|
| 299 |
+
"grad_norm": 0.33203125,
|
| 300 |
+
"learning_rate": 0.0007239263803680982,
|
| 301 |
+
"loss": 2.7179,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.0,
|
| 306 |
+
"eval_loss": 2.772521495819092,
|
| 307 |
+
"eval_runtime": 1.0385,
|
| 308 |
+
"eval_samples_per_second": 481.485,
|
| 309 |
+
"eval_steps_per_second": 0.963,
|
| 310 |
+
"step": 13692
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 14.314928425357873,
|
| 314 |
+
"grad_norm": 0.330078125,
|
| 315 |
+
"learning_rate": 0.0007137014314928425,
|
| 316 |
+
"loss": 2.7088,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 14.826175869120654,
|
| 321 |
+
"grad_norm": 0.34375,
|
| 322 |
+
"learning_rate": 0.0007034764826175869,
|
| 323 |
+
"loss": 2.7051,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 15.0,
|
| 328 |
+
"eval_loss": 2.7638583183288574,
|
| 329 |
+
"eval_runtime": 0.9397,
|
| 330 |
+
"eval_samples_per_second": 532.097,
|
| 331 |
+
"eval_steps_per_second": 1.064,
|
| 332 |
+
"step": 14670
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.337423312883436,
|
| 336 |
+
"grad_norm": 0.3203125,
|
| 337 |
+
"learning_rate": 0.0006932515337423313,
|
| 338 |
+
"loss": 2.6999,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 15.848670756646216,
|
| 343 |
+
"grad_norm": 0.31640625,
|
| 344 |
+
"learning_rate": 0.0006830265848670757,
|
| 345 |
+
"loss": 2.6961,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 16.0,
|
| 350 |
+
"eval_loss": 2.7651634216308594,
|
| 351 |
+
"eval_runtime": 0.9625,
|
| 352 |
+
"eval_samples_per_second": 519.471,
|
| 353 |
+
"eval_steps_per_second": 1.039,
|
| 354 |
+
"step": 15648
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.359918200409,
|
| 358 |
+
"grad_norm": 0.388671875,
|
| 359 |
+
"learning_rate": 0.0006728016359918201,
|
| 360 |
+
"loss": 2.6903,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 16.87116564417178,
|
| 365 |
+
"grad_norm": 0.345703125,
|
| 366 |
+
"learning_rate": 0.0006625766871165644,
|
| 367 |
+
"loss": 2.6905,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 17.0,
|
| 372 |
+
"eval_loss": 2.75215744972229,
|
| 373 |
+
"eval_runtime": 0.8724,
|
| 374 |
+
"eval_samples_per_second": 573.163,
|
| 375 |
+
"eval_steps_per_second": 1.146,
|
| 376 |
+
"step": 16626
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 17.38241308793456,
|
| 380 |
+
"grad_norm": 0.337890625,
|
| 381 |
+
"learning_rate": 0.0006523517382413088,
|
| 382 |
+
"loss": 2.6791,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 17.893660531697343,
|
| 387 |
+
"grad_norm": 0.328125,
|
| 388 |
+
"learning_rate": 0.0006421267893660531,
|
| 389 |
+
"loss": 2.6817,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 18.0,
|
| 394 |
+
"eval_loss": 2.750427722930908,
|
| 395 |
+
"eval_runtime": 1.0601,
|
| 396 |
+
"eval_samples_per_second": 471.655,
|
| 397 |
+
"eval_steps_per_second": 0.943,
|
| 398 |
+
"step": 17604
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 18.404907975460123,
|
| 402 |
+
"grad_norm": 0.33984375,
|
| 403 |
+
"learning_rate": 0.0006319018404907975,
|
| 404 |
+
"loss": 2.6712,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 18.916155419222903,
|
| 409 |
+
"grad_norm": 0.349609375,
|
| 410 |
+
"learning_rate": 0.000621676891615542,
|
| 411 |
+
"loss": 2.6721,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 19.0,
|
| 416 |
+
"eval_loss": 2.740670919418335,
|
| 417 |
+
"eval_runtime": 0.9797,
|
| 418 |
+
"eval_samples_per_second": 510.381,
|
| 419 |
+
"eval_steps_per_second": 1.021,
|
| 420 |
+
"step": 18582
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 19.427402862985684,
|
| 424 |
+
"grad_norm": 0.328125,
|
| 425 |
+
"learning_rate": 0.0006114519427402863,
|
| 426 |
+
"loss": 2.6632,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 19.938650306748468,
|
| 431 |
+
"grad_norm": 0.36328125,
|
| 432 |
+
"learning_rate": 0.0006012269938650307,
|
| 433 |
+
"loss": 2.6677,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 20.0,
|
| 438 |
+
"eval_loss": 2.740766763687134,
|
| 439 |
+
"eval_runtime": 0.9358,
|
| 440 |
+
"eval_samples_per_second": 534.326,
|
| 441 |
+
"eval_steps_per_second": 1.069,
|
| 442 |
+
"step": 19560
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 20.449897750511248,
|
| 446 |
+
"grad_norm": 0.345703125,
|
| 447 |
+
"learning_rate": 0.000591002044989775,
|
| 448 |
+
"loss": 2.6576,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 20.961145194274028,
|
| 453 |
+
"grad_norm": 0.349609375,
|
| 454 |
+
"learning_rate": 0.0005807770961145194,
|
| 455 |
+
"loss": 2.6624,
|
| 456 |
+
"step": 20500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 21.0,
|
| 460 |
+
"eval_loss": 2.7370216846466064,
|
| 461 |
+
"eval_runtime": 0.9579,
|
| 462 |
+
"eval_samples_per_second": 521.987,
|
| 463 |
+
"eval_steps_per_second": 1.044,
|
| 464 |
+
"step": 20538
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 21.47239263803681,
|
| 468 |
+
"grad_norm": 0.314453125,
|
| 469 |
+
"learning_rate": 0.0005705521472392639,
|
| 470 |
+
"loss": 2.65,
|
| 471 |
+
"step": 21000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.983640081799592,
|
| 475 |
+
"grad_norm": 0.341796875,
|
| 476 |
+
"learning_rate": 0.0005603271983640082,
|
| 477 |
+
"loss": 2.6575,
|
| 478 |
+
"step": 21500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 22.0,
|
| 482 |
+
"eval_loss": 2.734588384628296,
|
| 483 |
+
"eval_runtime": 0.8297,
|
| 484 |
+
"eval_samples_per_second": 602.609,
|
| 485 |
+
"eval_steps_per_second": 1.205,
|
| 486 |
+
"step": 21516
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.494887525562373,
|
| 490 |
+
"grad_norm": 0.349609375,
|
| 491 |
+
"learning_rate": 0.0005501022494887526,
|
| 492 |
+
"loss": 2.6453,
|
| 493 |
+
"step": 22000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 23.0,
|
| 497 |
+
"eval_loss": 2.73508882522583,
|
| 498 |
+
"eval_runtime": 1.0104,
|
| 499 |
+
"eval_samples_per_second": 494.868,
|
| 500 |
+
"eval_steps_per_second": 0.99,
|
| 501 |
+
"step": 22494
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 23.006134969325153,
|
| 505 |
+
"grad_norm": 0.345703125,
|
| 506 |
+
"learning_rate": 0.0005398773006134969,
|
| 507 |
+
"loss": 2.6533,
|
| 508 |
+
"step": 22500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 23.517382413087933,
|
| 512 |
+
"grad_norm": 0.33984375,
|
| 513 |
+
"learning_rate": 0.0005296523517382413,
|
| 514 |
+
"loss": 2.6441,
|
| 515 |
+
"step": 23000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 24.0,
|
| 519 |
+
"eval_loss": 2.731626033782959,
|
| 520 |
+
"eval_runtime": 0.674,
|
| 521 |
+
"eval_samples_per_second": 741.886,
|
| 522 |
+
"eval_steps_per_second": 1.484,
|
| 523 |
+
"step": 23472
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 24.028629856850717,
|
| 527 |
+
"grad_norm": 0.322265625,
|
| 528 |
+
"learning_rate": 0.0005194274028629857,
|
| 529 |
+
"loss": 2.6442,
|
| 530 |
+
"step": 23500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 24.539877300613497,
|
| 534 |
+
"grad_norm": 0.330078125,
|
| 535 |
+
"learning_rate": 0.00050920245398773,
|
| 536 |
+
"loss": 2.637,
|
| 537 |
+
"step": 24000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 25.0,
|
| 541 |
+
"eval_loss": 2.731029510498047,
|
| 542 |
+
"eval_runtime": 0.7022,
|
| 543 |
+
"eval_samples_per_second": 712.014,
|
| 544 |
+
"eval_steps_per_second": 1.424,
|
| 545 |
+
"step": 24450
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 25.051124744376278,
|
| 549 |
+
"grad_norm": 0.326171875,
|
| 550 |
+
"learning_rate": 0.0004989775051124745,
|
| 551 |
+
"loss": 2.6437,
|
| 552 |
+
"step": 24500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 25.562372188139058,
|
| 556 |
+
"grad_norm": 0.333984375,
|
| 557 |
+
"learning_rate": 0.0004887525562372188,
|
| 558 |
+
"loss": 2.6364,
|
| 559 |
+
"step": 25000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 26.0,
|
| 563 |
+
"eval_loss": 2.7300286293029785,
|
| 564 |
+
"eval_runtime": 0.8078,
|
| 565 |
+
"eval_samples_per_second": 618.965,
|
| 566 |
+
"eval_steps_per_second": 1.238,
|
| 567 |
+
"step": 25428
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 26.073619631901842,
|
| 571 |
+
"grad_norm": 0.357421875,
|
| 572 |
+
"learning_rate": 0.0004785276073619632,
|
| 573 |
+
"loss": 2.6382,
|
| 574 |
+
"step": 25500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 26.584867075664622,
|
| 578 |
+
"grad_norm": 0.330078125,
|
| 579 |
+
"learning_rate": 0.0004683026584867076,
|
| 580 |
+
"loss": 2.632,
|
| 581 |
+
"step": 26000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 27.0,
|
| 585 |
+
"eval_loss": 2.7241549491882324,
|
| 586 |
+
"eval_runtime": 0.8157,
|
| 587 |
+
"eval_samples_per_second": 612.964,
|
| 588 |
+
"eval_steps_per_second": 1.226,
|
| 589 |
+
"step": 26406
|
| 590 |
+
}
|
| 591 |
+
],
|
| 592 |
+
"logging_steps": 500,
|
| 593 |
+
"max_steps": 48900,
|
| 594 |
+
"num_input_tokens_seen": 0,
|
| 595 |
+
"num_train_epochs": 50,
|
| 596 |
+
"save_steps": 500,
|
| 597 |
+
"stateful_callbacks": {
|
| 598 |
+
"EarlyStoppingCallback": {
|
| 599 |
+
"args": {
|
| 600 |
+
"early_stopping_patience": 3,
|
| 601 |
+
"early_stopping_threshold": 0.0
|
| 602 |
+
},
|
| 603 |
+
"attributes": {
|
| 604 |
+
"early_stopping_patience_counter": 0
|
| 605 |
+
}
|
| 606 |
+
},
|
| 607 |
+
"TrainerControl": {
|
| 608 |
+
"args": {
|
| 609 |
+
"should_epoch_stop": false,
|
| 610 |
+
"should_evaluate": false,
|
| 611 |
+
"should_log": false,
|
| 612 |
+
"should_save": true,
|
| 613 |
+
"should_training_stop": false
|
| 614 |
+
},
|
| 615 |
+
"attributes": {}
|
| 616 |
+
}
|
| 617 |
+
},
|
| 618 |
+
"total_flos": 2.553177237041664e+17,
|
| 619 |
+
"train_batch_size": 1024,
|
| 620 |
+
"trial_name": null,
|
| 621 |
+
"trial_params": null
|
| 622 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:994a3cbb8e4c8cbd2d0a1c5129132fe1751fd6126e7e06527db71e8d30027b9a
|
| 3 |
+
size 5048
|