Commit
•
1cf41e9
1
Parent(s):
77dbb7f
Upload 8 files
Browse files- checkpoint-12500/config.json +31 -0
- checkpoint-12500/generation_config.json +7 -0
- checkpoint-12500/optimizer.pt +3 -0
- checkpoint-12500/pytorch_model.bin +3 -0
- checkpoint-12500/rng_state.pth +3 -0
- checkpoint-12500/scheduler.pt +3 -0
- checkpoint-12500/trainer_state.json +428 -0
- checkpoint-12500/training_args.bin +3 -0
checkpoint-12500/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./models/checkpoint-22500",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 1024,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 8,
|
| 20 |
+
"num_heads": 6,
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"tokenizer_class": "T5Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.28.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250112
|
| 31 |
+
}
|
checkpoint-12500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0"
|
| 7 |
+
}
|
checkpoint-12500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:251bb699cbd7c1797bebb5bcedcd74292aabc09a4cb21ce122ac3a51e53ec6d3
|
| 3 |
+
size 2401525449
|
checkpoint-12500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ff5c5ded29a1d564c8afbb527177efed95588c6fa9d94ec7730f4147f3aa0d
|
| 3 |
+
size 1200770757
|
checkpoint-12500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c3cb84444af4f999d9c415841ca7c0fe71f057954a4a51d018c9df23037e5cc
|
| 3 |
+
size 14503
|
checkpoint-12500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f5c59ab51ce6acd9a1c5ded66ecbd7d577f8b4cfcb24b74f403d329eb3d28e4
|
| 3 |
+
size 623
|
checkpoint-12500/trainer_state.json
ADDED
|
@@ -0,0 +1,428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7621196070511306,
|
| 5 |
+
"global_step": 12500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.9951222486433756e-05,
|
| 13 |
+
"loss": 0.0754,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 1.990244497286751e-05,
|
| 19 |
+
"loss": 0.0747,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 1.9853667459301263e-05,
|
| 25 |
+
"loss": 0.0737,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 1.9804889945735017e-05,
|
| 31 |
+
"loss": 0.073,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"learning_rate": 1.975611243216877e-05,
|
| 37 |
+
"loss": 0.0723,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.07,
|
| 42 |
+
"learning_rate": 1.9707334918602525e-05,
|
| 43 |
+
"loss": 0.072,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"learning_rate": 1.965855740503628e-05,
|
| 49 |
+
"loss": 0.0709,
|
| 50 |
+
"step": 1400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.1,
|
| 54 |
+
"learning_rate": 1.9609779891470033e-05,
|
| 55 |
+
"loss": 0.0703,
|
| 56 |
+
"step": 1600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.11,
|
| 60 |
+
"learning_rate": 1.9561002377903787e-05,
|
| 61 |
+
"loss": 0.0708,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.12,
|
| 66 |
+
"learning_rate": 1.951222486433754e-05,
|
| 67 |
+
"loss": 0.0711,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.13,
|
| 72 |
+
"learning_rate": 1.9463447350771295e-05,
|
| 73 |
+
"loss": 0.0699,
|
| 74 |
+
"step": 2200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"learning_rate": 1.941466983720505e-05,
|
| 79 |
+
"loss": 0.0701,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15,
|
| 84 |
+
"eval_loss": 0.055753033608198166,
|
| 85 |
+
"eval_runtime": 1008.1775,
|
| 86 |
+
"eval_samples_per_second": 82.199,
|
| 87 |
+
"eval_steps_per_second": 13.7,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.16,
|
| 92 |
+
"learning_rate": 1.9365892323638806e-05,
|
| 93 |
+
"loss": 0.071,
|
| 94 |
+
"step": 2600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17,
|
| 98 |
+
"learning_rate": 1.931711481007256e-05,
|
| 99 |
+
"loss": 0.0692,
|
| 100 |
+
"step": 2800
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.18,
|
| 104 |
+
"learning_rate": 1.9268337296506314e-05,
|
| 105 |
+
"loss": 0.0687,
|
| 106 |
+
"step": 3000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.2,
|
| 110 |
+
"learning_rate": 1.9219559782940067e-05,
|
| 111 |
+
"loss": 0.0689,
|
| 112 |
+
"step": 3200
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.21,
|
| 116 |
+
"learning_rate": 1.917078226937382e-05,
|
| 117 |
+
"loss": 0.0681,
|
| 118 |
+
"step": 3400
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.22,
|
| 122 |
+
"learning_rate": 1.9122004755807575e-05,
|
| 123 |
+
"loss": 0.0678,
|
| 124 |
+
"step": 3600
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.23,
|
| 128 |
+
"learning_rate": 1.907322724224133e-05,
|
| 129 |
+
"loss": 0.0666,
|
| 130 |
+
"step": 3800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.24,
|
| 134 |
+
"learning_rate": 1.9024449728675083e-05,
|
| 135 |
+
"loss": 0.0676,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.26,
|
| 140 |
+
"learning_rate": 1.8975672215108837e-05,
|
| 141 |
+
"loss": 0.0662,
|
| 142 |
+
"step": 4200
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.27,
|
| 146 |
+
"learning_rate": 1.892689470154259e-05,
|
| 147 |
+
"loss": 0.0676,
|
| 148 |
+
"step": 4400
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.28,
|
| 152 |
+
"learning_rate": 1.8878117187976345e-05,
|
| 153 |
+
"loss": 0.0663,
|
| 154 |
+
"step": 4600
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.29,
|
| 158 |
+
"learning_rate": 1.88293396744101e-05,
|
| 159 |
+
"loss": 0.0661,
|
| 160 |
+
"step": 4800
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.3,
|
| 164 |
+
"learning_rate": 1.8780562160843853e-05,
|
| 165 |
+
"loss": 0.0661,
|
| 166 |
+
"step": 5000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3,
|
| 170 |
+
"eval_loss": 0.05344025790691376,
|
| 171 |
+
"eval_runtime": 1009.8843,
|
| 172 |
+
"eval_samples_per_second": 82.06,
|
| 173 |
+
"eval_steps_per_second": 13.677,
|
| 174 |
+
"step": 5000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.32,
|
| 178 |
+
"learning_rate": 1.8731784647277606e-05,
|
| 179 |
+
"loss": 0.0674,
|
| 180 |
+
"step": 5200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.33,
|
| 184 |
+
"learning_rate": 1.868300713371136e-05,
|
| 185 |
+
"loss": 0.066,
|
| 186 |
+
"step": 5400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.34,
|
| 190 |
+
"learning_rate": 1.8634229620145114e-05,
|
| 191 |
+
"loss": 0.0642,
|
| 192 |
+
"step": 5600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.35,
|
| 196 |
+
"learning_rate": 1.8585452106578868e-05,
|
| 197 |
+
"loss": 0.0655,
|
| 198 |
+
"step": 5800
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.37,
|
| 202 |
+
"learning_rate": 1.8536674593012622e-05,
|
| 203 |
+
"loss": 0.0654,
|
| 204 |
+
"step": 6000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.38,
|
| 208 |
+
"learning_rate": 1.8487897079446376e-05,
|
| 209 |
+
"loss": 0.0641,
|
| 210 |
+
"step": 6200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.39,
|
| 214 |
+
"learning_rate": 1.843911956588013e-05,
|
| 215 |
+
"loss": 0.0636,
|
| 216 |
+
"step": 6400
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.4,
|
| 220 |
+
"learning_rate": 1.8390342052313884e-05,
|
| 221 |
+
"loss": 0.0658,
|
| 222 |
+
"step": 6600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.41,
|
| 226 |
+
"learning_rate": 1.8341564538747638e-05,
|
| 227 |
+
"loss": 0.0639,
|
| 228 |
+
"step": 6800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.43,
|
| 232 |
+
"learning_rate": 1.8292787025181395e-05,
|
| 233 |
+
"loss": 0.0642,
|
| 234 |
+
"step": 7000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.44,
|
| 238 |
+
"learning_rate": 1.8244009511615145e-05,
|
| 239 |
+
"loss": 0.0648,
|
| 240 |
+
"step": 7200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.45,
|
| 244 |
+
"learning_rate": 1.8195231998048903e-05,
|
| 245 |
+
"loss": 0.0645,
|
| 246 |
+
"step": 7400
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.46,
|
| 250 |
+
"eval_loss": 0.05153830349445343,
|
| 251 |
+
"eval_runtime": 1007.6883,
|
| 252 |
+
"eval_samples_per_second": 82.239,
|
| 253 |
+
"eval_steps_per_second": 13.707,
|
| 254 |
+
"step": 7500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.46,
|
| 258 |
+
"learning_rate": 1.8146454484482653e-05,
|
| 259 |
+
"loss": 0.0639,
|
| 260 |
+
"step": 7600
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.48,
|
| 264 |
+
"learning_rate": 1.809767697091641e-05,
|
| 265 |
+
"loss": 0.0628,
|
| 266 |
+
"step": 7800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.49,
|
| 270 |
+
"learning_rate": 1.8048899457350164e-05,
|
| 271 |
+
"loss": 0.0647,
|
| 272 |
+
"step": 8000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.5,
|
| 276 |
+
"learning_rate": 1.800012194378392e-05,
|
| 277 |
+
"loss": 0.0629,
|
| 278 |
+
"step": 8200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.51,
|
| 282 |
+
"learning_rate": 1.7951344430217672e-05,
|
| 283 |
+
"loss": 0.0638,
|
| 284 |
+
"step": 8400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.52,
|
| 288 |
+
"learning_rate": 1.7902566916651426e-05,
|
| 289 |
+
"loss": 0.0635,
|
| 290 |
+
"step": 8600
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.54,
|
| 294 |
+
"learning_rate": 1.785378940308518e-05,
|
| 295 |
+
"loss": 0.0628,
|
| 296 |
+
"step": 8800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.55,
|
| 300 |
+
"learning_rate": 1.7805011889518934e-05,
|
| 301 |
+
"loss": 0.063,
|
| 302 |
+
"step": 9000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.56,
|
| 306 |
+
"learning_rate": 1.7756234375952688e-05,
|
| 307 |
+
"loss": 0.0636,
|
| 308 |
+
"step": 9200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.57,
|
| 312 |
+
"learning_rate": 1.7707456862386442e-05,
|
| 313 |
+
"loss": 0.0633,
|
| 314 |
+
"step": 9400
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.59,
|
| 318 |
+
"learning_rate": 1.7658679348820196e-05,
|
| 319 |
+
"loss": 0.0624,
|
| 320 |
+
"step": 9600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.6,
|
| 324 |
+
"learning_rate": 1.760990183525395e-05,
|
| 325 |
+
"loss": 0.0615,
|
| 326 |
+
"step": 9800
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.61,
|
| 330 |
+
"learning_rate": 1.7561124321687703e-05,
|
| 331 |
+
"loss": 0.062,
|
| 332 |
+
"step": 10000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.61,
|
| 336 |
+
"eval_loss": 0.05109347030520439,
|
| 337 |
+
"eval_runtime": 1005.611,
|
| 338 |
+
"eval_samples_per_second": 82.409,
|
| 339 |
+
"eval_steps_per_second": 13.735,
|
| 340 |
+
"step": 10000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.62,
|
| 344 |
+
"learning_rate": 1.7512346808121457e-05,
|
| 345 |
+
"loss": 0.0616,
|
| 346 |
+
"step": 10200
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.63,
|
| 350 |
+
"learning_rate": 1.746356929455521e-05,
|
| 351 |
+
"loss": 0.0613,
|
| 352 |
+
"step": 10400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.65,
|
| 356 |
+
"learning_rate": 1.7414791780988965e-05,
|
| 357 |
+
"loss": 0.0616,
|
| 358 |
+
"step": 10600
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.66,
|
| 362 |
+
"learning_rate": 1.736601426742272e-05,
|
| 363 |
+
"loss": 0.0623,
|
| 364 |
+
"step": 10800
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.67,
|
| 368 |
+
"learning_rate": 1.7317236753856473e-05,
|
| 369 |
+
"loss": 0.062,
|
| 370 |
+
"step": 11000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.68,
|
| 374 |
+
"learning_rate": 1.7268459240290227e-05,
|
| 375 |
+
"loss": 0.0632,
|
| 376 |
+
"step": 11200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.7,
|
| 380 |
+
"learning_rate": 1.7219681726723984e-05,
|
| 381 |
+
"loss": 0.0623,
|
| 382 |
+
"step": 11400
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.71,
|
| 386 |
+
"learning_rate": 1.7170904213157735e-05,
|
| 387 |
+
"loss": 0.0608,
|
| 388 |
+
"step": 11600
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.72,
|
| 392 |
+
"learning_rate": 1.7122126699591492e-05,
|
| 393 |
+
"loss": 0.061,
|
| 394 |
+
"step": 11800
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.73,
|
| 398 |
+
"learning_rate": 1.7073349186025242e-05,
|
| 399 |
+
"loss": 0.061,
|
| 400 |
+
"step": 12000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.74,
|
| 404 |
+
"learning_rate": 1.7024571672459e-05,
|
| 405 |
+
"loss": 0.0605,
|
| 406 |
+
"step": 12200
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.76,
|
| 410 |
+
"learning_rate": 1.697579415889275e-05,
|
| 411 |
+
"loss": 0.0607,
|
| 412 |
+
"step": 12400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.76,
|
| 416 |
+
"eval_loss": 0.04968786612153053,
|
| 417 |
+
"eval_runtime": 1006.7134,
|
| 418 |
+
"eval_samples_per_second": 82.318,
|
| 419 |
+
"eval_steps_per_second": 13.72,
|
| 420 |
+
"step": 12500
|
| 421 |
+
}
|
| 422 |
+
],
|
| 423 |
+
"max_steps": 82005,
|
| 424 |
+
"num_train_epochs": 5,
|
| 425 |
+
"total_flos": 6.34499629056e+17,
|
| 426 |
+
"trial_name": null,
|
| 427 |
+
"trial_params": null
|
| 428 |
+
}
|
checkpoint-12500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69cea6267551e6c3db2312cb16b8e111ea7cc82c9a729b741a0cc0164750a77c
|
| 3 |
+
size 3695
|