Upload 7 files
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +550 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilroberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.29.2",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:708ea052ccd9e7a849d1996aae6b8dcb964857c986245dfe257a08a7500fb5ba
|
| 3 |
+
size 657423685
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7d23eaa24906ba4d3625f1194a5496f9042b12a265b4e39bc39df570d473851
|
| 3 |
+
size 328721273
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:191fa8bc45c5a8971d5fe7c55e541bbde67d9e26cbdd7014604ce098c7889fe4
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5cdb69e9300a3691c36bdd8e1eae0c655ce61ed34a28580d6828d75ac320681
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.95603827256271,
|
| 5 |
+
"global_step": 38500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 1.9741401603310062e-05,
|
| 13 |
+
"loss": 1.9914,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.26,
|
| 18 |
+
"learning_rate": 1.948280320662012e-05,
|
| 19 |
+
"loss": 1.606,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.39,
|
| 24 |
+
"learning_rate": 1.922420480993018e-05,
|
| 25 |
+
"loss": 1.4903,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.52,
|
| 30 |
+
"learning_rate": 1.896560641324024e-05,
|
| 31 |
+
"loss": 1.4065,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.65,
|
| 36 |
+
"learning_rate": 1.87070080165503e-05,
|
| 37 |
+
"loss": 1.3202,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.78,
|
| 42 |
+
"learning_rate": 1.844840961986036e-05,
|
| 43 |
+
"loss": 1.288,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.91,
|
| 48 |
+
"learning_rate": 1.8189811223170417e-05,
|
| 49 |
+
"loss": 1.2592,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_loss": 1.1307439804077148,
|
| 55 |
+
"eval_runtime": 12.893,
|
| 56 |
+
"eval_samples_per_second": 1193.128,
|
| 57 |
+
"eval_steps_per_second": 149.151,
|
| 58 |
+
"step": 3867
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.03,
|
| 62 |
+
"learning_rate": 1.7931212826480477e-05,
|
| 63 |
+
"loss": 1.2107,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.16,
|
| 68 |
+
"learning_rate": 1.7672614429790537e-05,
|
| 69 |
+
"loss": 1.1851,
|
| 70 |
+
"step": 4500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.29,
|
| 74 |
+
"learning_rate": 1.7414016033100598e-05,
|
| 75 |
+
"loss": 1.1513,
|
| 76 |
+
"step": 5000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.42,
|
| 80 |
+
"learning_rate": 1.7155417636410658e-05,
|
| 81 |
+
"loss": 1.1181,
|
| 82 |
+
"step": 5500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.55,
|
| 86 |
+
"learning_rate": 1.6896819239720715e-05,
|
| 87 |
+
"loss": 1.0948,
|
| 88 |
+
"step": 6000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.68,
|
| 92 |
+
"learning_rate": 1.6638220843030775e-05,
|
| 93 |
+
"loss": 1.0955,
|
| 94 |
+
"step": 6500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.81,
|
| 98 |
+
"learning_rate": 1.6379622446340835e-05,
|
| 99 |
+
"loss": 1.0562,
|
| 100 |
+
"step": 7000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.94,
|
| 104 |
+
"learning_rate": 1.6121024049650892e-05,
|
| 105 |
+
"loss": 1.0578,
|
| 106 |
+
"step": 7500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.0,
|
| 110 |
+
"eval_loss": 0.9538503885269165,
|
| 111 |
+
"eval_runtime": 12.8064,
|
| 112 |
+
"eval_samples_per_second": 1201.199,
|
| 113 |
+
"eval_steps_per_second": 150.16,
|
| 114 |
+
"step": 7734
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.07,
|
| 118 |
+
"learning_rate": 1.5862425652960952e-05,
|
| 119 |
+
"loss": 1.0484,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.2,
|
| 124 |
+
"learning_rate": 1.5603827256271013e-05,
|
| 125 |
+
"loss": 1.0226,
|
| 126 |
+
"step": 8500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.33,
|
| 130 |
+
"learning_rate": 1.5345228859581073e-05,
|
| 131 |
+
"loss": 1.0189,
|
| 132 |
+
"step": 9000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.46,
|
| 136 |
+
"learning_rate": 1.5086630462891131e-05,
|
| 137 |
+
"loss": 0.9812,
|
| 138 |
+
"step": 9500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.59,
|
| 142 |
+
"learning_rate": 1.482803206620119e-05,
|
| 143 |
+
"loss": 0.9543,
|
| 144 |
+
"step": 10000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.72,
|
| 148 |
+
"learning_rate": 1.456943366951125e-05,
|
| 149 |
+
"loss": 0.9917,
|
| 150 |
+
"step": 10500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.84,
|
| 154 |
+
"learning_rate": 1.431083527282131e-05,
|
| 155 |
+
"loss": 0.9423,
|
| 156 |
+
"step": 11000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.97,
|
| 160 |
+
"learning_rate": 1.4052236876131369e-05,
|
| 161 |
+
"loss": 0.9628,
|
| 162 |
+
"step": 11500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.0,
|
| 166 |
+
"eval_loss": 0.8621994256973267,
|
| 167 |
+
"eval_runtime": 12.1534,
|
| 168 |
+
"eval_samples_per_second": 1265.738,
|
| 169 |
+
"eval_steps_per_second": 158.228,
|
| 170 |
+
"step": 11601
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.1,
|
| 174 |
+
"learning_rate": 1.379363847944143e-05,
|
| 175 |
+
"loss": 0.9401,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.23,
|
| 180 |
+
"learning_rate": 1.3535040082751488e-05,
|
| 181 |
+
"loss": 0.9208,
|
| 182 |
+
"step": 12500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.36,
|
| 186 |
+
"learning_rate": 1.3276441686061548e-05,
|
| 187 |
+
"loss": 0.9068,
|
| 188 |
+
"step": 13000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.49,
|
| 192 |
+
"learning_rate": 1.3017843289371609e-05,
|
| 193 |
+
"loss": 0.9114,
|
| 194 |
+
"step": 13500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.62,
|
| 198 |
+
"learning_rate": 1.2759244892681665e-05,
|
| 199 |
+
"loss": 0.9146,
|
| 200 |
+
"step": 14000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.75,
|
| 204 |
+
"learning_rate": 1.2500646495991726e-05,
|
| 205 |
+
"loss": 0.8964,
|
| 206 |
+
"step": 14500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.88,
|
| 210 |
+
"learning_rate": 1.2242048099301784e-05,
|
| 211 |
+
"loss": 0.9084,
|
| 212 |
+
"step": 15000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.0,
|
| 216 |
+
"eval_loss": 0.8124715685844421,
|
| 217 |
+
"eval_runtime": 12.1415,
|
| 218 |
+
"eval_samples_per_second": 1266.974,
|
| 219 |
+
"eval_steps_per_second": 158.382,
|
| 220 |
+
"step": 15468
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.01,
|
| 224 |
+
"learning_rate": 1.1983449702611844e-05,
|
| 225 |
+
"loss": 0.8739,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.14,
|
| 230 |
+
"learning_rate": 1.1724851305921905e-05,
|
| 231 |
+
"loss": 0.8625,
|
| 232 |
+
"step": 16000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.27,
|
| 236 |
+
"learning_rate": 1.1466252909231963e-05,
|
| 237 |
+
"loss": 0.8507,
|
| 238 |
+
"step": 16500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.4,
|
| 242 |
+
"learning_rate": 1.1207654512542024e-05,
|
| 243 |
+
"loss": 0.8759,
|
| 244 |
+
"step": 17000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.53,
|
| 248 |
+
"learning_rate": 1.0949056115852084e-05,
|
| 249 |
+
"loss": 0.8383,
|
| 250 |
+
"step": 17500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.65,
|
| 254 |
+
"learning_rate": 1.0690457719162142e-05,
|
| 255 |
+
"loss": 0.8487,
|
| 256 |
+
"step": 18000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.78,
|
| 260 |
+
"learning_rate": 1.0431859322472203e-05,
|
| 261 |
+
"loss": 0.8595,
|
| 262 |
+
"step": 18500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.91,
|
| 266 |
+
"learning_rate": 1.017326092578226e-05,
|
| 267 |
+
"loss": 0.8374,
|
| 268 |
+
"step": 19000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.0,
|
| 272 |
+
"eval_loss": 0.7769160270690918,
|
| 273 |
+
"eval_runtime": 12.8439,
|
| 274 |
+
"eval_samples_per_second": 1197.691,
|
| 275 |
+
"eval_steps_per_second": 149.721,
|
| 276 |
+
"step": 19335
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.04,
|
| 280 |
+
"learning_rate": 9.91466252909232e-06,
|
| 281 |
+
"loss": 0.8352,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.17,
|
| 286 |
+
"learning_rate": 9.65606413240238e-06,
|
| 287 |
+
"loss": 0.8663,
|
| 288 |
+
"step": 20000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.3,
|
| 292 |
+
"learning_rate": 9.397465735712439e-06,
|
| 293 |
+
"loss": 0.8169,
|
| 294 |
+
"step": 20500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.43,
|
| 298 |
+
"learning_rate": 9.138867339022499e-06,
|
| 299 |
+
"loss": 0.8187,
|
| 300 |
+
"step": 21000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.56,
|
| 304 |
+
"learning_rate": 8.880268942332558e-06,
|
| 305 |
+
"loss": 0.8153,
|
| 306 |
+
"step": 21500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.69,
|
| 310 |
+
"learning_rate": 8.621670545642618e-06,
|
| 311 |
+
"loss": 0.8133,
|
| 312 |
+
"step": 22000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.82,
|
| 316 |
+
"learning_rate": 8.363072148952676e-06,
|
| 317 |
+
"loss": 0.7901,
|
| 318 |
+
"step": 22500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 5.95,
|
| 322 |
+
"learning_rate": 8.104473752262737e-06,
|
| 323 |
+
"loss": 0.8139,
|
| 324 |
+
"step": 23000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 6.0,
|
| 328 |
+
"eval_loss": 0.7311471104621887,
|
| 329 |
+
"eval_runtime": 12.8348,
|
| 330 |
+
"eval_samples_per_second": 1198.535,
|
| 331 |
+
"eval_steps_per_second": 149.827,
|
| 332 |
+
"step": 23202
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.08,
|
| 336 |
+
"learning_rate": 7.845875355572797e-06,
|
| 337 |
+
"loss": 0.7811,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.21,
|
| 342 |
+
"learning_rate": 7.5872769588828555e-06,
|
| 343 |
+
"loss": 0.8063,
|
| 344 |
+
"step": 24000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.34,
|
| 348 |
+
"learning_rate": 7.328678562192915e-06,
|
| 349 |
+
"loss": 0.785,
|
| 350 |
+
"step": 24500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.46,
|
| 354 |
+
"learning_rate": 7.070080165502975e-06,
|
| 355 |
+
"loss": 0.7909,
|
| 356 |
+
"step": 25000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.59,
|
| 360 |
+
"learning_rate": 6.811481768813034e-06,
|
| 361 |
+
"loss": 0.7727,
|
| 362 |
+
"step": 25500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.72,
|
| 366 |
+
"learning_rate": 6.552883372123093e-06,
|
| 367 |
+
"loss": 0.7779,
|
| 368 |
+
"step": 26000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.85,
|
| 372 |
+
"learning_rate": 6.294284975433153e-06,
|
| 373 |
+
"loss": 0.7627,
|
| 374 |
+
"step": 26500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.98,
|
| 378 |
+
"learning_rate": 6.035686578743212e-06,
|
| 379 |
+
"loss": 0.7577,
|
| 380 |
+
"step": 27000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.0,
|
| 384 |
+
"eval_loss": 0.6985681653022766,
|
| 385 |
+
"eval_runtime": 12.1148,
|
| 386 |
+
"eval_samples_per_second": 1269.772,
|
| 387 |
+
"eval_steps_per_second": 158.732,
|
| 388 |
+
"step": 27069
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 7.11,
|
| 392 |
+
"learning_rate": 5.777088182053272e-06,
|
| 393 |
+
"loss": 0.7761,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 7.24,
|
| 398 |
+
"learning_rate": 5.518489785363331e-06,
|
| 399 |
+
"loss": 0.7782,
|
| 400 |
+
"step": 28000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 7.37,
|
| 404 |
+
"learning_rate": 5.25989138867339e-06,
|
| 405 |
+
"loss": 0.7335,
|
| 406 |
+
"step": 28500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 7.5,
|
| 410 |
+
"learning_rate": 5.00129299198345e-06,
|
| 411 |
+
"loss": 0.7656,
|
| 412 |
+
"step": 29000
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 7.63,
|
| 416 |
+
"learning_rate": 4.742694595293509e-06,
|
| 417 |
+
"loss": 0.761,
|
| 418 |
+
"step": 29500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 7.76,
|
| 422 |
+
"learning_rate": 4.484096198603569e-06,
|
| 423 |
+
"loss": 0.7517,
|
| 424 |
+
"step": 30000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 7.89,
|
| 428 |
+
"learning_rate": 4.225497801913628e-06,
|
| 429 |
+
"loss": 0.75,
|
| 430 |
+
"step": 30500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 8.0,
|
| 434 |
+
"eval_loss": 0.6888388991355896,
|
| 435 |
+
"eval_runtime": 12.1237,
|
| 436 |
+
"eval_samples_per_second": 1268.839,
|
| 437 |
+
"eval_steps_per_second": 158.615,
|
| 438 |
+
"step": 30936
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 8.02,
|
| 442 |
+
"learning_rate": 3.966899405223688e-06,
|
| 443 |
+
"loss": 0.7545,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 8.15,
|
| 448 |
+
"learning_rate": 3.708301008533747e-06,
|
| 449 |
+
"loss": 0.723,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 8.28,
|
| 454 |
+
"learning_rate": 3.449702611843807e-06,
|
| 455 |
+
"loss": 0.7352,
|
| 456 |
+
"step": 32000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 8.4,
|
| 460 |
+
"learning_rate": 3.191104215153866e-06,
|
| 461 |
+
"loss": 0.7253,
|
| 462 |
+
"step": 32500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 8.53,
|
| 466 |
+
"learning_rate": 2.932505818463926e-06,
|
| 467 |
+
"loss": 0.7248,
|
| 468 |
+
"step": 33000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 8.66,
|
| 472 |
+
"learning_rate": 2.6739074217739853e-06,
|
| 473 |
+
"loss": 0.7371,
|
| 474 |
+
"step": 33500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 8.79,
|
| 478 |
+
"learning_rate": 2.4153090250840447e-06,
|
| 479 |
+
"loss": 0.7284,
|
| 480 |
+
"step": 34000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 8.92,
|
| 484 |
+
"learning_rate": 2.156710628394104e-06,
|
| 485 |
+
"loss": 0.7205,
|
| 486 |
+
"step": 34500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 9.0,
|
| 490 |
+
"eval_loss": 0.6802728772163391,
|
| 491 |
+
"eval_runtime": 12.1115,
|
| 492 |
+
"eval_samples_per_second": 1270.111,
|
| 493 |
+
"eval_steps_per_second": 158.774,
|
| 494 |
+
"step": 34803
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 9.05,
|
| 498 |
+
"learning_rate": 1.8981122317041636e-06,
|
| 499 |
+
"loss": 0.7059,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 9.18,
|
| 504 |
+
"learning_rate": 1.6395138350142232e-06,
|
| 505 |
+
"loss": 0.7321,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 9.31,
|
| 510 |
+
"learning_rate": 1.3809154383242826e-06,
|
| 511 |
+
"loss": 0.7392,
|
| 512 |
+
"step": 36000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 9.44,
|
| 516 |
+
"learning_rate": 1.122317041634342e-06,
|
| 517 |
+
"loss": 0.7314,
|
| 518 |
+
"step": 36500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 9.57,
|
| 522 |
+
"learning_rate": 8.637186449444015e-07,
|
| 523 |
+
"loss": 0.73,
|
| 524 |
+
"step": 37000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 9.7,
|
| 528 |
+
"learning_rate": 6.051202482544609e-07,
|
| 529 |
+
"loss": 0.7199,
|
| 530 |
+
"step": 37500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 9.83,
|
| 534 |
+
"learning_rate": 3.465218515645203e-07,
|
| 535 |
+
"loss": 0.7258,
|
| 536 |
+
"step": 38000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 9.96,
|
| 540 |
+
"learning_rate": 8.792345487457979e-08,
|
| 541 |
+
"loss": 0.7562,
|
| 542 |
+
"step": 38500
|
| 543 |
+
}
|
| 544 |
+
],
|
| 545 |
+
"max_steps": 38670,
|
| 546 |
+
"num_train_epochs": 10,
|
| 547 |
+
"total_flos": 1994099670728550.0,
|
| 548 |
+
"trial_name": null,
|
| 549 |
+
"trial_params": null
|
| 550 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e865e111c033ba88540c2ee9cd8f8ff3925894b1823fb5e55c1dfac2c22959ef
|
| 3 |
+
size 3899
|