decorr midtrain
Browse files- chat_template.jinja +9 -0
- config.json +26 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- midtrain_stats.json +425 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +189 -0
- training_args.bin +3 -0
- vocab.json +0 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
|
| 2 |
+
' + message['content'] + '
|
| 3 |
+
' }}{% elif message['role'] == 'user' %}{{ '<|user|>
|
| 4 |
+
' + message['content'] + '
|
| 5 |
+
' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
|
| 6 |
+
' + message['content'] + eos_token + '
|
| 7 |
+
' }}{% else %}{{ '<|assistant|>
|
| 8 |
+
' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
|
| 9 |
+
' }}{% endif %}{% endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 100257,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8192,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "olmo2",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 16,
|
| 17 |
+
"num_key_value_heads": 16,
|
| 18 |
+
"pad_token_id": 100277,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 500000,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"transformers_version": "4.57.6",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 100352
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 100257,
|
| 4 |
+
"pad_token_id": 100277,
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
midtrain_stats.json
ADDED
|
@@ -0,0 +1,425 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "allenai/OLMo-2-0425-1B-Instruct",
|
| 3 |
+
"corpus": "/root/mt/corpus_C.jsonl.gz",
|
| 4 |
+
"out": "/root/mt/out",
|
| 5 |
+
"seed": 17,
|
| 6 |
+
"block": 1024,
|
| 7 |
+
"bs": 16,
|
| 8 |
+
"grad_accum": 2,
|
| 9 |
+
"lr": 2e-05,
|
| 10 |
+
"max_steps": 1420,
|
| 11 |
+
"global_step": 1420,
|
| 12 |
+
"total_flos": 1.6442086038626304e+17,
|
| 13 |
+
"train_runtime_s": 696.0254,
|
| 14 |
+
"train_loss_mean": 1.6962001733376946,
|
| 15 |
+
"n_docs": 11356,
|
| 16 |
+
"dataset_tokens_post_truncation": 3343028,
|
| 17 |
+
"token_len_mean": 294.3842902430433,
|
| 18 |
+
"sequences_seen": 45440,
|
| 19 |
+
"epochs_equivalent": 4.001408946812258,
|
| 20 |
+
"trained_tokens_est": 13376822,
|
| 21 |
+
"note": "trained_tokens_est excludes padding; total_flos includes padding (collator pads to batch max) so it varies with doc lengths across corpora",
|
| 22 |
+
"log_history": [
|
| 23 |
+
{
|
| 24 |
+
"loss": 2.8222,
|
| 25 |
+
"grad_norm": 4.15625,
|
| 26 |
+
"learning_rate": 1.116279069767442e-05,
|
| 27 |
+
"epoch": 0.07042253521126761,
|
| 28 |
+
"step": 25
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"loss": 2.2891,
|
| 32 |
+
"grad_norm": 2.265625,
|
| 33 |
+
"learning_rate": 1.999906309061717e-05,
|
| 34 |
+
"epoch": 0.14084507042253522,
|
| 35 |
+
"step": 50
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"loss": 2.1255,
|
| 39 |
+
"grad_norm": 2.359375,
|
| 40 |
+
"learning_rate": 1.9974999757800105e-05,
|
| 41 |
+
"epoch": 0.2112676056338028,
|
| 42 |
+
"step": 75
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 2.0548,
|
| 46 |
+
"grad_norm": 2.328125,
|
| 47 |
+
"learning_rate": 1.9918494468657112e-05,
|
| 48 |
+
"epoch": 0.28169014084507044,
|
| 49 |
+
"step": 100
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"loss": 2.0386,
|
| 53 |
+
"grad_norm": 2.375,
|
| 54 |
+
"learning_rate": 1.982973099683902e-05,
|
| 55 |
+
"epoch": 0.352112676056338,
|
| 56 |
+
"step": 125
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"loss": 1.9809,
|
| 60 |
+
"grad_norm": 2.328125,
|
| 61 |
+
"learning_rate": 1.970899803013991e-05,
|
| 62 |
+
"epoch": 0.4225352112676056,
|
| 63 |
+
"step": 150
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"loss": 1.9327,
|
| 67 |
+
"grad_norm": 2.3125,
|
| 68 |
+
"learning_rate": 1.955668823159015e-05,
|
| 69 |
+
"epoch": 0.49295774647887325,
|
| 70 |
+
"step": 175
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 1.9075,
|
| 74 |
+
"grad_norm": 2.34375,
|
| 75 |
+
"learning_rate": 1.9373296962387988e-05,
|
| 76 |
+
"epoch": 0.5633802816901409,
|
| 77 |
+
"step": 200
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"loss": 1.9071,
|
| 81 |
+
"grad_norm": 2.171875,
|
| 82 |
+
"learning_rate": 1.915942067082319e-05,
|
| 83 |
+
"epoch": 0.6338028169014085,
|
| 84 |
+
"step": 225
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 1.8791,
|
| 88 |
+
"grad_norm": 2.390625,
|
| 89 |
+
"learning_rate": 1.8915754952432456e-05,
|
| 90 |
+
"epoch": 0.704225352112676,
|
| 91 |
+
"step": 250
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"loss": 1.8542,
|
| 95 |
+
"grad_norm": 2.40625,
|
| 96 |
+
"learning_rate": 1.8643092287695604e-05,
|
| 97 |
+
"epoch": 0.7746478873239436,
|
| 98 |
+
"step": 275
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"loss": 1.8437,
|
| 102 |
+
"grad_norm": 2.375,
|
| 103 |
+
"learning_rate": 1.8342319464630258e-05,
|
| 104 |
+
"epoch": 0.8450704225352113,
|
| 105 |
+
"step": 300
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"loss": 1.8306,
|
| 109 |
+
"grad_norm": 2.328125,
|
| 110 |
+
"learning_rate": 1.8014414694667685e-05,
|
| 111 |
+
"epoch": 0.9154929577464789,
|
| 112 |
+
"step": 325
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"loss": 1.8437,
|
| 116 |
+
"grad_norm": 2.359375,
|
| 117 |
+
"learning_rate": 1.766044443118978e-05,
|
| 118 |
+
"epoch": 0.9859154929577465,
|
| 119 |
+
"step": 350
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"loss": 1.7285,
|
| 123 |
+
"grad_norm": 2.484375,
|
| 124 |
+
"learning_rate": 1.7281559901074474e-05,
|
| 125 |
+
"epoch": 1.056338028169014,
|
| 126 |
+
"step": 375
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"loss": 1.6873,
|
| 130 |
+
"grad_norm": 2.546875,
|
| 131 |
+
"learning_rate": 1.6878993360529985e-05,
|
| 132 |
+
"epoch": 1.1267605633802817,
|
| 133 |
+
"step": 400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"loss": 1.6908,
|
| 137 |
+
"grad_norm": 2.5,
|
| 138 |
+
"learning_rate": 1.6454054087395284e-05,
|
| 139 |
+
"epoch": 1.1971830985915493,
|
| 140 |
+
"step": 425
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"loss": 1.6845,
|
| 144 |
+
"grad_norm": 2.515625,
|
| 145 |
+
"learning_rate": 1.6008124122941038e-05,
|
| 146 |
+
"epoch": 1.267605633802817,
|
| 147 |
+
"step": 450
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"loss": 1.6805,
|
| 151 |
+
"grad_norm": 2.328125,
|
| 152 |
+
"learning_rate": 1.554265377702014e-05,
|
| 153 |
+
"epoch": 1.3380281690140845,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"loss": 1.6821,
|
| 158 |
+
"grad_norm": 2.359375,
|
| 159 |
+
"learning_rate": 1.5059156911186465e-05,
|
| 160 |
+
"epoch": 1.408450704225352,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"loss": 1.6664,
|
| 165 |
+
"grad_norm": 2.40625,
|
| 166 |
+
"learning_rate": 1.455920601512283e-05,
|
| 167 |
+
"epoch": 1.4788732394366197,
|
| 168 |
+
"step": 525
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"loss": 1.684,
|
| 172 |
+
"grad_norm": 2.3125,
|
| 173 |
+
"learning_rate": 1.4044427092391031e-05,
|
| 174 |
+
"epoch": 1.5492957746478875,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"loss": 1.6615,
|
| 179 |
+
"grad_norm": 2.40625,
|
| 180 |
+
"learning_rate": 1.3516494372137368e-05,
|
| 181 |
+
"epoch": 1.619718309859155,
|
| 182 |
+
"step": 575
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"loss": 1.667,
|
| 186 |
+
"grad_norm": 2.4375,
|
| 187 |
+
"learning_rate": 1.2977124863952753e-05,
|
| 188 |
+
"epoch": 1.6901408450704225,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"loss": 1.6239,
|
| 193 |
+
"grad_norm": 2.5625,
|
| 194 |
+
"learning_rate": 1.2428072773596875e-05,
|
| 195 |
+
"epoch": 1.76056338028169,
|
| 196 |
+
"step": 625
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"loss": 1.6079,
|
| 200 |
+
"grad_norm": 2.453125,
|
| 201 |
+
"learning_rate": 1.1871123797748285e-05,
|
| 202 |
+
"epoch": 1.8309859154929577,
|
| 203 |
+
"step": 650
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"loss": 1.6291,
|
| 207 |
+
"grad_norm": 2.546875,
|
| 208 |
+
"learning_rate": 1.1308089316335695e-05,
|
| 209 |
+
"epoch": 1.9014084507042255,
|
| 210 |
+
"step": 675
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"loss": 1.625,
|
| 214 |
+
"grad_norm": 2.375,
|
| 215 |
+
"learning_rate": 1.0740800501339009e-05,
|
| 216 |
+
"epoch": 1.971830985915493,
|
| 217 |
+
"step": 700
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"loss": 1.5886,
|
| 221 |
+
"grad_norm": 2.34375,
|
| 222 |
+
"learning_rate": 1.0171102361220093e-05,
|
| 223 |
+
"epoch": 2.0422535211267605,
|
| 224 |
+
"step": 725
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"loss": 1.5726,
|
| 228 |
+
"grad_norm": 2.53125,
|
| 229 |
+
"learning_rate": 9.600847740352834e-06,
|
| 230 |
+
"epoch": 2.112676056338028,
|
| 231 |
+
"step": 750
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"loss": 1.5689,
|
| 235 |
+
"grad_norm": 2.375,
|
| 236 |
+
"learning_rate": 9.03189129296821e-06,
|
| 237 |
+
"epoch": 2.183098591549296,
|
| 238 |
+
"step": 775
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"loss": 1.564,
|
| 242 |
+
"grad_norm": 2.59375,
|
| 243 |
+
"learning_rate": 8.466083451213145e-06,
|
| 244 |
+
"epoch": 2.2535211267605635,
|
| 245 |
+
"step": 800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"loss": 1.5592,
|
| 249 |
+
"grad_norm": 2.375,
|
| 250 |
+
"learning_rate": 7.90526440694096e-06,
|
| 251 |
+
"epoch": 2.323943661971831,
|
| 252 |
+
"step": 825
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"loss": 1.5616,
|
| 256 |
+
"grad_norm": 2.328125,
|
| 257 |
+
"learning_rate": 7.351258126806556e-06,
|
| 258 |
+
"epoch": 2.3943661971830985,
|
| 259 |
+
"step": 850
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"loss": 1.5456,
|
| 263 |
+
"grad_norm": 2.515625,
|
| 264 |
+
"learning_rate": 6.80586642013133e-06,
|
| 265 |
+
"epoch": 2.464788732394366,
|
| 266 |
+
"step": 875
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"loss": 1.5657,
|
| 270 |
+
"grad_norm": 2.546875,
|
| 271 |
+
"learning_rate": 6.2708630788308754e-06,
|
| 272 |
+
"epoch": 2.535211267605634,
|
| 273 |
+
"step": 900
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"loss": 1.5398,
|
| 277 |
+
"grad_norm": 2.625,
|
| 278 |
+
"learning_rate": 5.747988108464501e-06,
|
| 279 |
+
"epoch": 2.6056338028169015,
|
| 280 |
+
"step": 925
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"loss": 1.5779,
|
| 284 |
+
"grad_norm": 2.40625,
|
| 285 |
+
"learning_rate": 5.238942069169e-06,
|
| 286 |
+
"epoch": 2.676056338028169,
|
| 287 |
+
"step": 950
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"loss": 1.566,
|
| 291 |
+
"grad_norm": 2.40625,
|
| 292 |
+
"learning_rate": 4.745380544881779e-06,
|
| 293 |
+
"epoch": 2.7464788732394365,
|
| 294 |
+
"step": 975
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"loss": 1.5517,
|
| 298 |
+
"grad_norm": 2.34375,
|
| 299 |
+
"learning_rate": 4.268908758841318e-06,
|
| 300 |
+
"epoch": 2.816901408450704,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"loss": 1.544,
|
| 305 |
+
"grad_norm": 2.5625,
|
| 306 |
+
"learning_rate": 3.8110763528770543e-06,
|
| 307 |
+
"epoch": 2.887323943661972,
|
| 308 |
+
"step": 1025
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"loss": 1.5717,
|
| 312 |
+
"grad_norm": 2.546875,
|
| 313 |
+
"learning_rate": 3.373372347468141e-06,
|
| 314 |
+
"epoch": 2.9577464788732395,
|
| 315 |
+
"step": 1050
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"loss": 1.5512,
|
| 319 |
+
"grad_norm": 2.5,
|
| 320 |
+
"learning_rate": 2.9572202989626406e-06,
|
| 321 |
+
"epoch": 3.028169014084507,
|
| 322 |
+
"step": 1075
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"loss": 1.5375,
|
| 326 |
+
"grad_norm": 2.4375,
|
| 327 |
+
"learning_rate": 2.5639736697074525e-06,
|
| 328 |
+
"epoch": 3.0985915492957745,
|
| 329 |
+
"step": 1100
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"loss": 1.545,
|
| 333 |
+
"grad_norm": 2.390625,
|
| 334 |
+
"learning_rate": 2.1949114261468307e-06,
|
| 335 |
+
"epoch": 3.169014084507042,
|
| 336 |
+
"step": 1125
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"loss": 1.5284,
|
| 340 |
+
"grad_norm": 2.515625,
|
| 341 |
+
"learning_rate": 1.8512338792058749e-06,
|
| 342 |
+
"epoch": 3.23943661971831,
|
| 343 |
+
"step": 1150
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"loss": 1.5388,
|
| 347 |
+
"grad_norm": 2.484375,
|
| 348 |
+
"learning_rate": 1.5340587804874662e-06,
|
| 349 |
+
"epoch": 3.3098591549295775,
|
| 350 |
+
"step": 1175
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"loss": 1.5482,
|
| 354 |
+
"grad_norm": 2.484375,
|
| 355 |
+
"learning_rate": 1.2444176869790925e-06,
|
| 356 |
+
"epoch": 3.380281690140845,
|
| 357 |
+
"step": 1200
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"loss": 1.562,
|
| 361 |
+
"grad_norm": 2.546875,
|
| 362 |
+
"learning_rate": 9.83252606092675e-07,
|
| 363 |
+
"epoch": 3.4507042253521125,
|
| 364 |
+
"step": 1225
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"loss": 1.5496,
|
| 368 |
+
"grad_norm": 2.453125,
|
| 369 |
+
"learning_rate": 7.514129319488839e-07,
|
| 370 |
+
"epoch": 3.52112676056338,
|
| 371 |
+
"step": 1250
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"loss": 1.5414,
|
| 375 |
+
"grad_norm": 2.5,
|
| 376 |
+
"learning_rate": 5.496526828701076e-07,
|
| 377 |
+
"epoch": 3.591549295774648,
|
| 378 |
+
"step": 1275
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"loss": 1.554,
|
| 382 |
+
"grad_norm": 2.578125,
|
| 383 |
+
"learning_rate": 3.786280490666605e-07,
|
| 384 |
+
"epoch": 3.6619718309859155,
|
| 385 |
+
"step": 1300
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"loss": 1.5301,
|
| 389 |
+
"grad_norm": 2.5625,
|
| 390 |
+
"learning_rate": 2.3889525849194573e-07,
|
| 391 |
+
"epoch": 3.732394366197183,
|
| 392 |
+
"step": 1325
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"loss": 1.5406,
|
| 396 |
+
"grad_norm": 2.359375,
|
| 397 |
+
"learning_rate": 1.3090876780753715e-07,
|
| 398 |
+
"epoch": 3.802816901408451,
|
| 399 |
+
"step": 1350
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"loss": 1.5475,
|
| 403 |
+
"grad_norm": 2.46875,
|
| 404 |
+
"learning_rate": 5.501978434171884e-08,
|
| 405 |
+
"epoch": 3.873239436619718,
|
| 406 |
+
"step": 1375
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"loss": 1.5372,
|
| 410 |
+
"grad_norm": 2.53125,
|
| 411 |
+
"learning_rate": 1.147512384857663e-08,
|
| 412 |
+
"epoch": 3.943661971830986,
|
| 413 |
+
"step": 1400
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"train_runtime": 696.0254,
|
| 417 |
+
"train_samples_per_second": 65.285,
|
| 418 |
+
"train_steps_per_second": 2.04,
|
| 419 |
+
"total_flos": 1.6442086038626304e+17,
|
| 420 |
+
"train_loss": 1.6962001733376946,
|
| 421 |
+
"epoch": 4.0,
|
| 422 |
+
"step": 1420
|
| 423 |
+
}
|
| 424 |
+
]
|
| 425 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff0dd61272e9ccc93f81a515359bfb8ce2e93b6830f8d6245408831bab63f8f
|
| 3 |
+
size 2969854224
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 186 |
+
"pad_token": "<|pad|>",
|
| 187 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 188 |
+
"unk_token": "<|endoftext|>"
|
| 189 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e14e292a33d5148462da9c28ec45f55fd60d735ac954d63bde3f906760ff71f
|
| 3 |
+
size 5368
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|