Tribbiani
commited on
Commit
•
c8740e1
1
Parent(s):
33e0263
upload models
Browse files- all_results.json +8 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +391 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.845892040975895,
|
| 4 |
+
"train_runtime": 30624.5115,
|
| 5 |
+
"train_samples": 78628,
|
| 6 |
+
"train_samples_per_second": 2.567,
|
| 7 |
+
"train_steps_per_second": 0.04
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pinkmanlove/llama-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "bfloat16",
|
| 20 |
+
"transformers_version": "4.28.0.dev0",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0.dev0"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd566f4ed5d8557f561b88018f6d2bc2600353aaa903316d01a0d7c0dd313930
|
| 3 |
+
size 13476942241
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "</s>"
|
| 3 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"eos_token": "",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"special_tokens_map_file": "/home/hanze/.cache/hub/models--pinkmanlove--llama-7b-hf/snapshots/b3cde76468bad3c085ead29707ee7481121a4ca0/special_tokens_map.json",
|
| 7 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 8 |
+
"unk_token": ""
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.845892040975895,
|
| 4 |
+
"train_runtime": 30624.5115,
|
| 5 |
+
"train_samples": 78628,
|
| 6 |
+
"train_samples_per_second": 2.567,
|
| 7 |
+
"train_steps_per_second": 0.04
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 1229,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 5.405405405405406e-05,
|
| 13 |
+
"loss": 1.1849,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 9.99984371133188e-05,
|
| 19 |
+
"loss": 1.049,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 9.990816464160552e-05,
|
| 25 |
+
"loss": 1.0047,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 9.967925545267647e-05,
|
| 31 |
+
"loss": 1.0005,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 9.931234541881273e-05,
|
| 37 |
+
"loss": 0.9733,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"learning_rate": 9.880845375606788e-05,
|
| 43 |
+
"loss": 0.9806,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 9.81689801930526e-05,
|
| 49 |
+
"loss": 0.9689,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.13,
|
| 54 |
+
"learning_rate": 9.739570108271755e-05,
|
| 55 |
+
"loss": 0.9475,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.15,
|
| 60 |
+
"learning_rate": 9.649076446793543e-05,
|
| 61 |
+
"loss": 0.9538,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.16,
|
| 66 |
+
"learning_rate": 9.545668411458928e-05,
|
| 67 |
+
"loss": 0.946,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.18,
|
| 72 |
+
"learning_rate": 9.42963325287421e-05,
|
| 73 |
+
"loss": 1.2086,
|
| 74 |
+
"step": 220
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.2,
|
| 78 |
+
"learning_rate": 9.301293297728486e-05,
|
| 79 |
+
"loss": 0.956,
|
| 80 |
+
"step": 240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21,
|
| 84 |
+
"learning_rate": 9.161005053422832e-05,
|
| 85 |
+
"loss": 0.9414,
|
| 86 |
+
"step": 260
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.23,
|
| 90 |
+
"learning_rate": 9.009158217751071e-05,
|
| 91 |
+
"loss": 0.9282,
|
| 92 |
+
"step": 280
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.24,
|
| 96 |
+
"learning_rate": 8.846174596383044e-05,
|
| 97 |
+
"loss": 0.9125,
|
| 98 |
+
"step": 300
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.26,
|
| 102 |
+
"learning_rate": 8.672506931157457e-05,
|
| 103 |
+
"loss": 0.9019,
|
| 104 |
+
"step": 320
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.28,
|
| 108 |
+
"learning_rate": 8.488637642439121e-05,
|
| 109 |
+
"loss": 0.9036,
|
| 110 |
+
"step": 340
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.29,
|
| 114 |
+
"learning_rate": 8.295077489034092e-05,
|
| 115 |
+
"loss": 0.8963,
|
| 116 |
+
"step": 360
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.31,
|
| 120 |
+
"learning_rate": 8.092364149385254e-05,
|
| 121 |
+
"loss": 0.8834,
|
| 122 |
+
"step": 380
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.33,
|
| 126 |
+
"learning_rate": 7.881060727989571e-05,
|
| 127 |
+
"loss": 0.8846,
|
| 128 |
+
"step": 400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.34,
|
| 132 |
+
"learning_rate": 7.661754191185898e-05,
|
| 133 |
+
"loss": 0.8722,
|
| 134 |
+
"step": 420
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.36,
|
| 138 |
+
"learning_rate": 7.435053736658517e-05,
|
| 139 |
+
"loss": 0.8661,
|
| 140 |
+
"step": 440
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.37,
|
| 144 |
+
"learning_rate": 7.201589101185622e-05,
|
| 145 |
+
"loss": 0.8648,
|
| 146 |
+
"step": 460
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.39,
|
| 150 |
+
"learning_rate": 6.962008811333567e-05,
|
| 151 |
+
"loss": 0.8414,
|
| 152 |
+
"step": 480
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.41,
|
| 156 |
+
"learning_rate": 6.716978381956145e-05,
|
| 157 |
+
"loss": 0.8499,
|
| 158 |
+
"step": 500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.42,
|
| 162 |
+
"learning_rate": 6.467178467503203e-05,
|
| 163 |
+
"loss": 0.8432,
|
| 164 |
+
"step": 520
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.44,
|
| 168 |
+
"learning_rate": 6.213302971273911e-05,
|
| 169 |
+
"loss": 0.8425,
|
| 170 |
+
"step": 540
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.46,
|
| 174 |
+
"learning_rate": 5.956057117866922e-05,
|
| 175 |
+
"loss": 0.8231,
|
| 176 |
+
"step": 560
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.47,
|
| 180 |
+
"learning_rate": 5.696155494181792e-05,
|
| 181 |
+
"loss": 0.8331,
|
| 182 |
+
"step": 580
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.49,
|
| 186 |
+
"learning_rate": 5.434320064413464e-05,
|
| 187 |
+
"loss": 0.8198,
|
| 188 |
+
"step": 600
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.5,
|
| 192 |
+
"learning_rate": 5.1712781645538485e-05,
|
| 193 |
+
"loss": 0.8124,
|
| 194 |
+
"step": 620
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.52,
|
| 198 |
+
"learning_rate": 4.9077604819714065e-05,
|
| 199 |
+
"loss": 0.8078,
|
| 200 |
+
"step": 640
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.54,
|
| 204 |
+
"learning_rate": 4.644499025681171e-05,
|
| 205 |
+
"loss": 0.816,
|
| 206 |
+
"step": 660
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.55,
|
| 210 |
+
"learning_rate": 4.382225092943455e-05,
|
| 211 |
+
"loss": 0.7996,
|
| 212 |
+
"step": 680
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.57,
|
| 216 |
+
"learning_rate": 4.121667237839683e-05,
|
| 217 |
+
"loss": 0.8034,
|
| 218 |
+
"step": 700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.59,
|
| 222 |
+
"learning_rate": 3.863549247468331e-05,
|
| 223 |
+
"loss": 0.7956,
|
| 224 |
+
"step": 720
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.6,
|
| 228 |
+
"learning_rate": 3.6085881313827754e-05,
|
| 229 |
+
"loss": 0.7855,
|
| 230 |
+
"step": 740
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.62,
|
| 234 |
+
"learning_rate": 3.357492129856037e-05,
|
| 235 |
+
"loss": 0.7896,
|
| 236 |
+
"step": 760
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.63,
|
| 240 |
+
"learning_rate": 3.110958746505165e-05,
|
| 241 |
+
"loss": 0.7968,
|
| 242 |
+
"step": 780
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.65,
|
| 246 |
+
"learning_rate": 2.8696728107402794e-05,
|
| 247 |
+
"loss": 0.7792,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.67,
|
| 252 |
+
"learning_rate": 2.6343045754205053e-05,
|
| 253 |
+
"loss": 0.7691,
|
| 254 |
+
"step": 820
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.68,
|
| 258 |
+
"learning_rate": 2.4055078550011774e-05,
|
| 259 |
+
"loss": 0.7663,
|
| 260 |
+
"step": 840
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.7,
|
| 264 |
+
"learning_rate": 2.183918209344215e-05,
|
| 265 |
+
"loss": 0.7622,
|
| 266 |
+
"step": 860
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.72,
|
| 270 |
+
"learning_rate": 1.970151178236821e-05,
|
| 271 |
+
"loss": 0.7635,
|
| 272 |
+
"step": 880
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.73,
|
| 276 |
+
"learning_rate": 1.764800571522622e-05,
|
| 277 |
+
"loss": 0.7565,
|
| 278 |
+
"step": 900
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.75,
|
| 282 |
+
"learning_rate": 1.568436819595077e-05,
|
| 283 |
+
"loss": 0.7531,
|
| 284 |
+
"step": 920
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.76,
|
| 288 |
+
"learning_rate": 1.3816053888351405e-05,
|
| 289 |
+
"loss": 0.7566,
|
| 290 |
+
"step": 940
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.78,
|
| 294 |
+
"learning_rate": 1.2048252663949039e-05,
|
| 295 |
+
"loss": 0.7593,
|
| 296 |
+
"step": 960
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8,
|
| 300 |
+
"learning_rate": 1.038587518536172e-05,
|
| 301 |
+
"loss": 0.7548,
|
| 302 |
+
"step": 980
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.81,
|
| 306 |
+
"learning_rate": 8.833539265287217e-06,
|
| 307 |
+
"loss": 0.7468,
|
| 308 |
+
"step": 1000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.83,
|
| 312 |
+
"learning_rate": 7.395557038974749e-06,
|
| 313 |
+
"loss": 0.7507,
|
| 314 |
+
"step": 1020
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.85,
|
| 318 |
+
"learning_rate": 6.075922985818683e-06,
|
| 319 |
+
"loss": 0.7552,
|
| 320 |
+
"step": 1040
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.86,
|
| 324 |
+
"learning_rate": 4.8783028333481525e-06,
|
| 325 |
+
"loss": 0.7534,
|
| 326 |
+
"step": 1060
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.88,
|
| 330 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 331 |
+
"loss": 0.7528,
|
| 332 |
+
"step": 1080
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9,
|
| 336 |
+
"learning_rate": 2.8620632260107195e-06,
|
| 337 |
+
"loss": 0.7431,
|
| 338 |
+
"step": 1100
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.91,
|
| 342 |
+
"learning_rate": 2.0490445549492197e-06,
|
| 343 |
+
"loss": 0.7524,
|
| 344 |
+
"step": 1120
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.93,
|
| 348 |
+
"learning_rate": 1.3692257941228193e-06,
|
| 349 |
+
"loss": 0.7412,
|
| 350 |
+
"step": 1140
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.94,
|
| 354 |
+
"learning_rate": 8.244953688418822e-07,
|
| 355 |
+
"loss": 0.7275,
|
| 356 |
+
"step": 1160
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.96,
|
| 360 |
+
"learning_rate": 4.1636645111886583e-07,
|
| 361 |
+
"loss": 0.7526,
|
| 362 |
+
"step": 1180
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.98,
|
| 366 |
+
"learning_rate": 1.4597275632398655e-07,
|
| 367 |
+
"loss": 0.7362,
|
| 368 |
+
"step": 1200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.99,
|
| 372 |
+
"learning_rate": 1.4065393909407087e-08,
|
| 373 |
+
"loss": 0.7286,
|
| 374 |
+
"step": 1220
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.0,
|
| 378 |
+
"step": 1229,
|
| 379 |
+
"total_flos": 257039699804160.0,
|
| 380 |
+
"train_loss": 0.845892040975895,
|
| 381 |
+
"train_runtime": 30624.5115,
|
| 382 |
+
"train_samples_per_second": 2.567,
|
| 383 |
+
"train_steps_per_second": 0.04
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"max_steps": 1229,
|
| 387 |
+
"num_train_epochs": 1,
|
| 388 |
+
"total_flos": 257039699804160.0,
|
| 389 |
+
"trial_name": null,
|
| 390 |
+
"trial_params": null
|
| 391 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed1dfb4643b9150005f9a521726bea3396255a33d6e83160ac5499e7c1a2577f
|
| 3 |
+
size 4795
|