Added training metrics
Browse files- trainer_state.json +638 -0
- training_args.bin +3 -0
- training_metrics.json +597 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,638 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3400,
|
| 3 |
+
"best_metric": 0.8500096117258309,
|
| 4 |
+
"best_model_checkpoint": "output/PKOBP-polish-roberta-8k_lr1e-5_tb32_w0.1_ep4_wd0.03/checkpoint-3400",
|
| 5 |
+
"epoch": 3.78619153674833,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 3400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.111358574610245,
|
| 14 |
+
"grad_norm": 0.6548389792442322,
|
| 15 |
+
"learning_rate": 2.7500000000000004e-06,
|
| 16 |
+
"loss": 0.6139,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.22271714922049,
|
| 21 |
+
"grad_norm": 1.2604601383209229,
|
| 22 |
+
"learning_rate": 5.527777777777779e-06,
|
| 23 |
+
"loss": 0.4821,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.22271714922049,
|
| 28 |
+
"eval_accuracy": 0.35198329853862215,
|
| 29 |
+
"eval_f1_label_gniew": 0.6845324788814448,
|
| 30 |
+
"eval_f1_label_negatywny": 0.7949462182004439,
|
| 31 |
+
"eval_f1_label_neutralny": 0.7492940069030436,
|
| 32 |
+
"eval_f1_label_pozytywny": 0.42994241842610365,
|
| 33 |
+
"eval_f1_label_przeczuwanie": 0.0,
|
| 34 |
+
"eval_f1_label_rado\u015b\u0107": 0.19078947368421054,
|
| 35 |
+
"eval_f1_label_sarkazm": 0.0,
|
| 36 |
+
"eval_f1_label_wstr\u0119t": 0.5752023860247124,
|
| 37 |
+
"eval_f1_macro": 0.7509803650720916,
|
| 38 |
+
"eval_f1_micro": 0.8395441892832289,
|
| 39 |
+
"eval_f1_weighted": 0.8265873475311692,
|
| 40 |
+
"eval_loss": 0.41080573201179504,
|
| 41 |
+
"eval_runtime": 13.553,
|
| 42 |
+
"eval_samples_per_second": 530.14,
|
| 43 |
+
"eval_steps_per_second": 16.601,
|
| 44 |
+
"eval_subset_accuracy": 0.8395441892832289,
|
| 45 |
+
"step": 200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.33407572383073497,
|
| 49 |
+
"grad_norm": 1.7567846775054932,
|
| 50 |
+
"learning_rate": 8.305555555555557e-06,
|
| 51 |
+
"loss": 0.4129,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.44543429844098,
|
| 56 |
+
"grad_norm": 2.582125186920166,
|
| 57 |
+
"learning_rate": 9.99640768631301e-06,
|
| 58 |
+
"loss": 0.3769,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.44543429844098,
|
| 63 |
+
"eval_accuracy": 0.4321503131524008,
|
| 64 |
+
"eval_f1_label_gniew": 0.7182017543859649,
|
| 65 |
+
"eval_f1_label_negatywny": 0.8120326308633583,
|
| 66 |
+
"eval_f1_label_neutralny": 0.7886710239651417,
|
| 67 |
+
"eval_f1_label_pozytywny": 0.7161493477282951,
|
| 68 |
+
"eval_f1_label_przeczuwanie": 0.534637326813366,
|
| 69 |
+
"eval_f1_label_rado\u015b\u0107": 0.6868131868131868,
|
| 70 |
+
"eval_f1_label_sarkazm": 0.005263157894736842,
|
| 71 |
+
"eval_f1_label_wstr\u0119t": 0.6907111262334127,
|
| 72 |
+
"eval_f1_macro": 0.8079475306110289,
|
| 73 |
+
"eval_f1_micro": 0.8666144745998609,
|
| 74 |
+
"eval_f1_weighted": 0.8619885595665887,
|
| 75 |
+
"eval_loss": 0.33686527609825134,
|
| 76 |
+
"eval_runtime": 13.4667,
|
| 77 |
+
"eval_samples_per_second": 533.539,
|
| 78 |
+
"eval_steps_per_second": 16.708,
|
| 79 |
+
"eval_subset_accuracy": 0.8666144745998609,
|
| 80 |
+
"step": 400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5567928730512249,
|
| 84 |
+
"grad_norm": 2.2375481128692627,
|
| 85 |
+
"learning_rate": 9.954431380479526e-06,
|
| 86 |
+
"loss": 0.3415,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6681514476614699,
|
| 91 |
+
"grad_norm": 2.377732515335083,
|
| 92 |
+
"learning_rate": 9.86568060370307e-06,
|
| 93 |
+
"loss": 0.3359,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6681514476614699,
|
| 98 |
+
"eval_accuracy": 0.44231036882393876,
|
| 99 |
+
"eval_f1_label_gniew": 0.7346007604562738,
|
| 100 |
+
"eval_f1_label_negatywny": 0.8233744855967078,
|
| 101 |
+
"eval_f1_label_neutralny": 0.7887421820708825,
|
| 102 |
+
"eval_f1_label_pozytywny": 0.7572641931157801,
|
| 103 |
+
"eval_f1_label_przeczuwanie": 0.6198969480776853,
|
| 104 |
+
"eval_f1_label_rado\u015b\u0107": 0.7128842380640942,
|
| 105 |
+
"eval_f1_label_sarkazm": 0.18295543393275998,
|
| 106 |
+
"eval_f1_label_wstr\u0119t": 0.6842447916666666,
|
| 107 |
+
"eval_f1_macro": 0.8208003215407338,
|
| 108 |
+
"eval_f1_micro": 0.8731384829505915,
|
| 109 |
+
"eval_f1_weighted": 0.8701057540509732,
|
| 110 |
+
"eval_loss": 0.307725727558136,
|
| 111 |
+
"eval_runtime": 13.3682,
|
| 112 |
+
"eval_samples_per_second": 537.472,
|
| 113 |
+
"eval_steps_per_second": 16.831,
|
| 114 |
+
"eval_subset_accuracy": 0.8731384829505915,
|
| 115 |
+
"step": 600
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.779510022271715,
|
| 119 |
+
"grad_norm": 2.0692615509033203,
|
| 120 |
+
"learning_rate": 9.730993246411562e-06,
|
| 121 |
+
"loss": 0.3179,
|
| 122 |
+
"step": 700
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.89086859688196,
|
| 126 |
+
"grad_norm": 3.814361095428467,
|
| 127 |
+
"learning_rate": 9.551640883362268e-06,
|
| 128 |
+
"loss": 0.3184,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.89086859688196,
|
| 133 |
+
"eval_accuracy": 0.4701461377870564,
|
| 134 |
+
"eval_f1_label_gniew": 0.7435356200527704,
|
| 135 |
+
"eval_f1_label_negatywny": 0.8380327868852459,
|
| 136 |
+
"eval_f1_label_neutralny": 0.8036529680365296,
|
| 137 |
+
"eval_f1_label_pozytywny": 0.7029945999018163,
|
| 138 |
+
"eval_f1_label_przeczuwanie": 0.6724700761697497,
|
| 139 |
+
"eval_f1_label_rado\u015b\u0107": 0.6844694307800422,
|
| 140 |
+
"eval_f1_label_sarkazm": 0.3567289117836446,
|
| 141 |
+
"eval_f1_label_wstr\u0119t": 0.7084769124741558,
|
| 142 |
+
"eval_f1_macro": 0.8300609729014572,
|
| 143 |
+
"eval_f1_micro": 0.8788100208768267,
|
| 144 |
+
"eval_f1_weighted": 0.8763999627004312,
|
| 145 |
+
"eval_loss": 0.29314953088760376,
|
| 146 |
+
"eval_runtime": 13.6772,
|
| 147 |
+
"eval_samples_per_second": 525.325,
|
| 148 |
+
"eval_steps_per_second": 16.451,
|
| 149 |
+
"eval_subset_accuracy": 0.8788100208768267,
|
| 150 |
+
"step": 800
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.0022271714922049,
|
| 154 |
+
"grad_norm": 2.8335301876068115,
|
| 155 |
+
"learning_rate": 9.329316768785544e-06,
|
| 156 |
+
"loss": 0.3097,
|
| 157 |
+
"step": 900
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.1135857461024499,
|
| 161 |
+
"grad_norm": 1.909611701965332,
|
| 162 |
+
"learning_rate": 9.066119850479551e-06,
|
| 163 |
+
"loss": 0.2756,
|
| 164 |
+
"step": 1000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.1135857461024499,
|
| 168 |
+
"eval_accuracy": 0.4810020876826722,
|
| 169 |
+
"eval_f1_label_gniew": 0.7485624673288029,
|
| 170 |
+
"eval_f1_label_negatywny": 0.8409730266423961,
|
| 171 |
+
"eval_f1_label_neutralny": 0.8091783364265227,
|
| 172 |
+
"eval_f1_label_pozytywny": 0.7727272727272727,
|
| 173 |
+
"eval_f1_label_przeczuwanie": 0.681491618200479,
|
| 174 |
+
"eval_f1_label_rado\u015b\u0107": 0.7310513447432763,
|
| 175 |
+
"eval_f1_label_sarkazm": 0.3149171270718232,
|
| 176 |
+
"eval_f1_label_wstr\u0119t": 0.7109237794169301,
|
| 177 |
+
"eval_f1_macro": 0.8361271998835582,
|
| 178 |
+
"eval_f1_micro": 0.8823938761308281,
|
| 179 |
+
"eval_f1_weighted": 0.8804578924937377,
|
| 180 |
+
"eval_loss": 0.28486499190330505,
|
| 181 |
+
"eval_runtime": 14.7594,
|
| 182 |
+
"eval_samples_per_second": 486.807,
|
| 183 |
+
"eval_steps_per_second": 15.244,
|
| 184 |
+
"eval_subset_accuracy": 0.8823938761308281,
|
| 185 |
+
"step": 1000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.2249443207126949,
|
| 189 |
+
"grad_norm": 4.029219150543213,
|
| 190 |
+
"learning_rate": 8.764534953777842e-06,
|
| 191 |
+
"loss": 0.2685,
|
| 192 |
+
"step": 1100
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.3363028953229399,
|
| 196 |
+
"grad_norm": 1.7298495769500732,
|
| 197 |
+
"learning_rate": 8.427409322471743e-06,
|
| 198 |
+
"loss": 0.2622,
|
| 199 |
+
"step": 1200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.3363028953229399,
|
| 203 |
+
"eval_accuracy": 0.4683368128044537,
|
| 204 |
+
"eval_f1_label_gniew": 0.7479035639412998,
|
| 205 |
+
"eval_f1_label_negatywny": 0.8449914316871787,
|
| 206 |
+
"eval_f1_label_neutralny": 0.7788461538461539,
|
| 207 |
+
"eval_f1_label_pozytywny": 0.7732656514382402,
|
| 208 |
+
"eval_f1_label_przeczuwanie": 0.7060367454068242,
|
| 209 |
+
"eval_f1_label_rado\u015b\u0107": 0.7399756986634265,
|
| 210 |
+
"eval_f1_label_sarkazm": 0.4,
|
| 211 |
+
"eval_f1_label_wstr\u0119t": 0.7199725463280714,
|
| 212 |
+
"eval_f1_macro": 0.8361219089623048,
|
| 213 |
+
"eval_f1_micro": 0.881419624217119,
|
| 214 |
+
"eval_f1_weighted": 0.8799866455346702,
|
| 215 |
+
"eval_loss": 0.28199732303619385,
|
| 216 |
+
"eval_runtime": 13.3959,
|
| 217 |
+
"eval_samples_per_second": 536.358,
|
| 218 |
+
"eval_steps_per_second": 16.796,
|
| 219 |
+
"eval_subset_accuracy": 0.881419624217119,
|
| 220 |
+
"step": 1200
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.447661469933185,
|
| 224 |
+
"grad_norm": 2.291908025741577,
|
| 225 |
+
"learning_rate": 8.057925738163153e-06,
|
| 226 |
+
"loss": 0.2689,
|
| 227 |
+
"step": 1300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.5590200445434297,
|
| 231 |
+
"grad_norm": 2.64717960357666,
|
| 232 |
+
"learning_rate": 7.659572471826265e-06,
|
| 233 |
+
"loss": 0.2653,
|
| 234 |
+
"step": 1400
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.5590200445434297,
|
| 238 |
+
"eval_accuracy": 0.48434237995824636,
|
| 239 |
+
"eval_f1_label_gniew": 0.7580278128950695,
|
| 240 |
+
"eval_f1_label_negatywny": 0.8478637868516475,
|
| 241 |
+
"eval_f1_label_neutralny": 0.8011984490659148,
|
| 242 |
+
"eval_f1_label_pozytywny": 0.777292576419214,
|
| 243 |
+
"eval_f1_label_przeczuwanie": 0.6951871657754011,
|
| 244 |
+
"eval_f1_label_rado\u015b\u0107": 0.7375621890547264,
|
| 245 |
+
"eval_f1_label_sarkazm": 0.47809206877426513,
|
| 246 |
+
"eval_f1_label_wstr\u0119t": 0.7300771208226221,
|
| 247 |
+
"eval_f1_macro": 0.8415650899916123,
|
| 248 |
+
"eval_f1_micro": 0.8838726513569938,
|
| 249 |
+
"eval_f1_weighted": 0.8832473603278248,
|
| 250 |
+
"eval_loss": 0.27665975689888,
|
| 251 |
+
"eval_runtime": 13.39,
|
| 252 |
+
"eval_samples_per_second": 536.594,
|
| 253 |
+
"eval_steps_per_second": 16.804,
|
| 254 |
+
"eval_subset_accuracy": 0.8838726513569938,
|
| 255 |
+
"step": 1400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.670378619153675,
|
| 259 |
+
"grad_norm": 2.742314100265503,
|
| 260 |
+
"learning_rate": 7.236110351263578e-06,
|
| 261 |
+
"loss": 0.2551,
|
| 262 |
+
"step": 1500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.7817371937639197,
|
| 266 |
+
"grad_norm": 2.0853464603424072,
|
| 267 |
+
"learning_rate": 6.7915372553702926e-06,
|
| 268 |
+
"loss": 0.253,
|
| 269 |
+
"step": 1600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.7817371937639197,
|
| 273 |
+
"eval_accuracy": 0.49255393180236606,
|
| 274 |
+
"eval_f1_label_gniew": 0.745141588006663,
|
| 275 |
+
"eval_f1_label_negatywny": 0.8427041499330656,
|
| 276 |
+
"eval_f1_label_neutralny": 0.8148646376324197,
|
| 277 |
+
"eval_f1_label_pozytywny": 0.7725178047758693,
|
| 278 |
+
"eval_f1_label_przeczuwanie": 0.7135483870967742,
|
| 279 |
+
"eval_f1_label_rado\u015b\u0107": 0.7449786975045648,
|
| 280 |
+
"eval_f1_label_sarkazm": 0.45395894428152495,
|
| 281 |
+
"eval_f1_label_wstr\u0119t": 0.7020958083832335,
|
| 282 |
+
"eval_f1_macro": 0.8419394716369004,
|
| 283 |
+
"eval_f1_micro": 0.8862908837856646,
|
| 284 |
+
"eval_f1_weighted": 0.8845662361245985,
|
| 285 |
+
"eval_loss": 0.27193114161491394,
|
| 286 |
+
"eval_runtime": 13.4458,
|
| 287 |
+
"eval_samples_per_second": 534.368,
|
| 288 |
+
"eval_steps_per_second": 16.734,
|
| 289 |
+
"eval_subset_accuracy": 0.8862908837856646,
|
| 290 |
+
"step": 1600
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.893095768374165,
|
| 294 |
+
"grad_norm": 2.6639328002929688,
|
| 295 |
+
"learning_rate": 6.330050370414403e-06,
|
| 296 |
+
"loss": 0.2502,
|
| 297 |
+
"step": 1700
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.0044543429844097,
|
| 301 |
+
"grad_norm": 2.5934195518493652,
|
| 302 |
+
"learning_rate": 5.856006564668624e-06,
|
| 303 |
+
"loss": 0.2511,
|
| 304 |
+
"step": 1800
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.0044543429844097,
|
| 308 |
+
"eval_accuracy": 0.46583159359777315,
|
| 309 |
+
"eval_f1_label_gniew": 0.7512172501738928,
|
| 310 |
+
"eval_f1_label_negatywny": 0.8434200743494423,
|
| 311 |
+
"eval_f1_label_neutralny": 0.7797117724125023,
|
| 312 |
+
"eval_f1_label_pozytywny": 0.7771623348956114,
|
| 313 |
+
"eval_f1_label_przeczuwanie": 0.7179814755669115,
|
| 314 |
+
"eval_f1_label_rado\u015b\u0107": 0.7299448867115738,
|
| 315 |
+
"eval_f1_label_sarkazm": 0.5232903865213082,
|
| 316 |
+
"eval_f1_label_wstr\u0119t": 0.7176891006551519,
|
| 317 |
+
"eval_f1_macro": 0.8367166256068449,
|
| 318 |
+
"eval_f1_micro": 0.8771746694502436,
|
| 319 |
+
"eval_f1_weighted": 0.8780966128511206,
|
| 320 |
+
"eval_loss": 0.2889347970485687,
|
| 321 |
+
"eval_runtime": 13.5639,
|
| 322 |
+
"eval_samples_per_second": 529.716,
|
| 323 |
+
"eval_steps_per_second": 16.588,
|
| 324 |
+
"eval_subset_accuracy": 0.8771746694502436,
|
| 325 |
+
"step": 1800
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.115812917594655,
|
| 329 |
+
"grad_norm": 2.778862714767456,
|
| 330 |
+
"learning_rate": 5.373881255494652e-06,
|
| 331 |
+
"loss": 0.2128,
|
| 332 |
+
"step": 1900
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.2271714922048997,
|
| 336 |
+
"grad_norm": 2.1749610900878906,
|
| 337 |
+
"learning_rate": 4.888226157213061e-06,
|
| 338 |
+
"loss": 0.2068,
|
| 339 |
+
"step": 2000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.2271714922048997,
|
| 343 |
+
"eval_accuracy": 0.5082811412665275,
|
| 344 |
+
"eval_f1_label_gniew": 0.7617009895694036,
|
| 345 |
+
"eval_f1_label_negatywny": 0.8477131847880717,
|
| 346 |
+
"eval_f1_label_neutralny": 0.8223467369808833,
|
| 347 |
+
"eval_f1_label_pozytywny": 0.7810858143607706,
|
| 348 |
+
"eval_f1_label_przeczuwanie": 0.7022071307300509,
|
| 349 |
+
"eval_f1_label_rado\u015b\u0107": 0.7382636655948553,
|
| 350 |
+
"eval_f1_label_sarkazm": 0.46941176470588236,
|
| 351 |
+
"eval_f1_label_wstr\u0119t": 0.7270175438596491,
|
| 352 |
+
"eval_f1_macro": 0.8469364739492785,
|
| 353 |
+
"eval_f1_micro": 0.8896659707724426,
|
| 354 |
+
"eval_f1_weighted": 0.8881098685832289,
|
| 355 |
+
"eval_loss": 0.2712438106536865,
|
| 356 |
+
"eval_runtime": 13.4837,
|
| 357 |
+
"eval_samples_per_second": 532.864,
|
| 358 |
+
"eval_steps_per_second": 16.687,
|
| 359 |
+
"eval_subset_accuracy": 0.8896659707724426,
|
| 360 |
+
"step": 2000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.338530066815145,
|
| 364 |
+
"grad_norm": 3.2917253971099854,
|
| 365 |
+
"learning_rate": 4.403626308658459e-06,
|
| 366 |
+
"loss": 0.2042,
|
| 367 |
+
"step": 2100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.4498886414253898,
|
| 371 |
+
"grad_norm": 2.2220280170440674,
|
| 372 |
+
"learning_rate": 3.9246567861200166e-06,
|
| 373 |
+
"loss": 0.2097,
|
| 374 |
+
"step": 2200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.4498886414253898,
|
| 378 |
+
"eval_accuracy": 0.4989561586638831,
|
| 379 |
+
"eval_f1_label_gniew": 0.75792897804283,
|
| 380 |
+
"eval_f1_label_negatywny": 0.8532080362929358,
|
| 381 |
+
"eval_f1_label_neutralny": 0.8129346314325452,
|
| 382 |
+
"eval_f1_label_pozytywny": 0.7774578362813657,
|
| 383 |
+
"eval_f1_label_przeczuwanie": 0.7263442475217783,
|
| 384 |
+
"eval_f1_label_rado\u015b\u0107": 0.7484811664641555,
|
| 385 |
+
"eval_f1_label_sarkazm": 0.5211047420531527,
|
| 386 |
+
"eval_f1_label_wstr\u0119t": 0.7377866400797607,
|
| 387 |
+
"eval_f1_macro": 0.8475632085047498,
|
| 388 |
+
"eval_f1_micro": 0.8878044537230341,
|
| 389 |
+
"eval_f1_weighted": 0.8874379181538837,
|
| 390 |
+
"eval_loss": 0.2748867869377136,
|
| 391 |
+
"eval_runtime": 13.5472,
|
| 392 |
+
"eval_samples_per_second": 530.369,
|
| 393 |
+
"eval_steps_per_second": 16.609,
|
| 394 |
+
"eval_subset_accuracy": 0.8878044537230341,
|
| 395 |
+
"step": 2200
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.5612472160356345,
|
| 399 |
+
"grad_norm": 4.778714179992676,
|
| 400 |
+
"learning_rate": 3.4558395103377882e-06,
|
| 401 |
+
"loss": 0.202,
|
| 402 |
+
"step": 2300
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.6726057906458798,
|
| 406 |
+
"grad_norm": 2.9350364208221436,
|
| 407 |
+
"learning_rate": 3.0016005553371464e-06,
|
| 408 |
+
"loss": 0.2042,
|
| 409 |
+
"step": 2400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.6726057906458798,
|
| 413 |
+
"eval_accuracy": 0.5029923451635352,
|
| 414 |
+
"eval_f1_label_gniew": 0.7653221581980094,
|
| 415 |
+
"eval_f1_label_negatywny": 0.8546814044213265,
|
| 416 |
+
"eval_f1_label_neutralny": 0.8173642338291248,
|
| 417 |
+
"eval_f1_label_pozytywny": 0.7812627291242362,
|
| 418 |
+
"eval_f1_label_przeczuwanie": 0.7192023158571889,
|
| 419 |
+
"eval_f1_label_rado\u015b\u0107": 0.7540394973070018,
|
| 420 |
+
"eval_f1_label_sarkazm": 0.5525328330206379,
|
| 421 |
+
"eval_f1_label_wstr\u0119t": 0.7323117052494295,
|
| 422 |
+
"eval_f1_macro": 0.8486039951352532,
|
| 423 |
+
"eval_f1_micro": 0.8879262352122478,
|
| 424 |
+
"eval_f1_weighted": 0.8878859652865869,
|
| 425 |
+
"eval_loss": 0.27490347623825073,
|
| 426 |
+
"eval_runtime": 13.5014,
|
| 427 |
+
"eval_samples_per_second": 532.167,
|
| 428 |
+
"eval_steps_per_second": 16.665,
|
| 429 |
+
"eval_subset_accuracy": 0.8879262352122478,
|
| 430 |
+
"step": 2400
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.7839643652561246,
|
| 434 |
+
"grad_norm": 3.124579906463623,
|
| 435 |
+
"learning_rate": 2.566228362145968e-06,
|
| 436 |
+
"loss": 0.1985,
|
| 437 |
+
"step": 2500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.89532293986637,
|
| 441 |
+
"grad_norm": 2.5567288398742676,
|
| 442 |
+
"learning_rate": 2.1538332518961635e-06,
|
| 443 |
+
"loss": 0.2071,
|
| 444 |
+
"step": 2600
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.89532293986637,
|
| 448 |
+
"eval_accuracy": 0.5102296450939457,
|
| 449 |
+
"eval_f1_label_gniew": 0.7664253150978815,
|
| 450 |
+
"eval_f1_label_negatywny": 0.8534298404342819,
|
| 451 |
+
"eval_f1_label_neutralny": 0.8198167628096369,
|
| 452 |
+
"eval_f1_label_pozytywny": 0.7838400666389005,
|
| 453 |
+
"eval_f1_label_przeczuwanie": 0.7165740438051651,
|
| 454 |
+
"eval_f1_label_rado\u015b\u0107": 0.7517985611510791,
|
| 455 |
+
"eval_f1_label_sarkazm": 0.4584795321637427,
|
| 456 |
+
"eval_f1_label_wstr\u0119t": 0.7267462902642056,
|
| 457 |
+
"eval_f1_macro": 0.8485724561583636,
|
| 458 |
+
"eval_f1_micro": 0.8903096729297146,
|
| 459 |
+
"eval_f1_weighted": 0.8890469205384153,
|
| 460 |
+
"eval_loss": 0.2728336453437805,
|
| 461 |
+
"eval_runtime": 13.4,
|
| 462 |
+
"eval_samples_per_second": 536.194,
|
| 463 |
+
"eval_steps_per_second": 16.791,
|
| 464 |
+
"eval_subset_accuracy": 0.8903096729297146,
|
| 465 |
+
"step": 2600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0066815144766146,
|
| 469 |
+
"grad_norm": 3.9624898433685303,
|
| 470 |
+
"learning_rate": 1.76830862054381e-06,
|
| 471 |
+
"loss": 0.2014,
|
| 472 |
+
"step": 2700
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.11804008908686,
|
| 476 |
+
"grad_norm": 1.9180693626403809,
|
| 477 |
+
"learning_rate": 1.4132941815660222e-06,
|
| 478 |
+
"loss": 0.1767,
|
| 479 |
+
"step": 2800
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.11804008908686,
|
| 483 |
+
"eval_accuracy": 0.5039665970772442,
|
| 484 |
+
"eval_f1_label_gniew": 0.7623196297304655,
|
| 485 |
+
"eval_f1_label_negatywny": 0.8542283645936163,
|
| 486 |
+
"eval_f1_label_neutralny": 0.8082359099633571,
|
| 487 |
+
"eval_f1_label_pozytywny": 0.7777777777777778,
|
| 488 |
+
"eval_f1_label_przeczuwanie": 0.7178329571106095,
|
| 489 |
+
"eval_f1_label_rado\u015b\u0107": 0.745920745920746,
|
| 490 |
+
"eval_f1_label_sarkazm": 0.5346432264736298,
|
| 491 |
+
"eval_f1_label_wstr\u0119t": 0.7262289199856476,
|
| 492 |
+
"eval_f1_macro": 0.8473642910777622,
|
| 493 |
+
"eval_f1_micro": 0.8887265135699374,
|
| 494 |
+
"eval_f1_weighted": 0.8878169372581985,
|
| 495 |
+
"eval_loss": 0.2742355167865753,
|
| 496 |
+
"eval_runtime": 16.0479,
|
| 497 |
+
"eval_samples_per_second": 447.723,
|
| 498 |
+
"eval_steps_per_second": 14.021,
|
| 499 |
+
"eval_subset_accuracy": 0.8887265135699374,
|
| 500 |
+
"step": 2800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.2293986636971046,
|
| 504 |
+
"grad_norm": 2.348484992980957,
|
| 505 |
+
"learning_rate": 1.092141603657972e-06,
|
| 506 |
+
"loss": 0.1773,
|
| 507 |
+
"step": 2900
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.34075723830735,
|
| 511 |
+
"grad_norm": 2.2864317893981934,
|
| 512 |
+
"learning_rate": 8.078828678422995e-07,
|
| 513 |
+
"loss": 0.173,
|
| 514 |
+
"step": 3000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.34075723830735,
|
| 518 |
+
"eval_accuracy": 0.508141962421712,
|
| 519 |
+
"eval_f1_label_gniew": 0.7665431445209105,
|
| 520 |
+
"eval_f1_label_negatywny": 0.8550937245313773,
|
| 521 |
+
"eval_f1_label_neutralny": 0.8155373032169747,
|
| 522 |
+
"eval_f1_label_pozytywny": 0.781314592806945,
|
| 523 |
+
"eval_f1_label_przeczuwanie": 0.7226675216415518,
|
| 524 |
+
"eval_f1_label_rado\u015b\u0107": 0.7475728155339806,
|
| 525 |
+
"eval_f1_label_sarkazm": 0.5287713841368584,
|
| 526 |
+
"eval_f1_label_wstr\u0119t": 0.7339011925042589,
|
| 527 |
+
"eval_f1_macro": 0.8494136493629865,
|
| 528 |
+
"eval_f1_micro": 0.889544189283229,
|
| 529 |
+
"eval_f1_weighted": 0.8889910470048148,
|
| 530 |
+
"eval_loss": 0.27491486072540283,
|
| 531 |
+
"eval_runtime": 13.5687,
|
| 532 |
+
"eval_samples_per_second": 529.527,
|
| 533 |
+
"eval_steps_per_second": 16.582,
|
| 534 |
+
"eval_subset_accuracy": 0.889544189283229,
|
| 535 |
+
"step": 3000
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 3.4521158129175946,
|
| 539 |
+
"grad_norm": 2.671910524368286,
|
| 540 |
+
"learning_rate": 5.632016427295134e-07,
|
| 541 |
+
"loss": 0.1756,
|
| 542 |
+
"step": 3100
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.5634743875278394,
|
| 546 |
+
"grad_norm": 3.2793824672698975,
|
| 547 |
+
"learning_rate": 3.6040794817364335e-07,
|
| 548 |
+
"loss": 0.1695,
|
| 549 |
+
"step": 3200
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.5634743875278394,
|
| 553 |
+
"eval_accuracy": 0.511482254697286,
|
| 554 |
+
"eval_f1_label_gniew": 0.7687056970333421,
|
| 555 |
+
"eval_f1_label_negatywny": 0.8545868575146389,
|
| 556 |
+
"eval_f1_label_neutralny": 0.8166494668042655,
|
| 557 |
+
"eval_f1_label_pozytywny": 0.7816091954022989,
|
| 558 |
+
"eval_f1_label_przeczuwanie": 0.7237728585178056,
|
| 559 |
+
"eval_f1_label_rado\u015b\u0107": 0.7479091995221028,
|
| 560 |
+
"eval_f1_label_sarkazm": 0.527850078084331,
|
| 561 |
+
"eval_f1_label_wstr\u0119t": 0.731740614334471,
|
| 562 |
+
"eval_f1_macro": 0.8495682589006989,
|
| 563 |
+
"eval_f1_micro": 0.889544189283229,
|
| 564 |
+
"eval_f1_weighted": 0.8890490603152431,
|
| 565 |
+
"eval_loss": 0.27663180232048035,
|
| 566 |
+
"eval_runtime": 13.4661,
|
| 567 |
+
"eval_samples_per_second": 533.56,
|
| 568 |
+
"eval_steps_per_second": 16.709,
|
| 569 |
+
"eval_subset_accuracy": 0.889544189283229,
|
| 570 |
+
"step": 3200
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.6748329621380846,
|
| 574 |
+
"grad_norm": 1.78013277053833,
|
| 575 |
+
"learning_rate": 2.0141634652200205e-07,
|
| 576 |
+
"loss": 0.167,
|
| 577 |
+
"step": 3300
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 3.78619153674833,
|
| 581 |
+
"grad_norm": 2.706618070602417,
|
| 582 |
+
"learning_rate": 8.772786735407601e-08,
|
| 583 |
+
"loss": 0.172,
|
| 584 |
+
"step": 3400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.78619153674833,
|
| 588 |
+
"eval_accuracy": 0.5124565066109952,
|
| 589 |
+
"eval_f1_label_gniew": 0.7693124502256438,
|
| 590 |
+
"eval_f1_label_negatywny": 0.8553212358999509,
|
| 591 |
+
"eval_f1_label_neutralny": 0.8172006167551824,
|
| 592 |
+
"eval_f1_label_pozytywny": 0.7813649366571311,
|
| 593 |
+
"eval_f1_label_przeczuwanie": 0.7220240025948751,
|
| 594 |
+
"eval_f1_label_rado\u015b\u0107": 0.7476190476190476,
|
| 595 |
+
"eval_f1_label_sarkazm": 0.5337423312883436,
|
| 596 |
+
"eval_f1_label_wstr\u0119t": 0.7336787564766839,
|
| 597 |
+
"eval_f1_macro": 0.8500096117258309,
|
| 598 |
+
"eval_f1_micro": 0.8900487125956854,
|
| 599 |
+
"eval_f1_weighted": 0.8894635900360007,
|
| 600 |
+
"eval_loss": 0.2760503590106964,
|
| 601 |
+
"eval_runtime": 13.4196,
|
| 602 |
+
"eval_samples_per_second": 535.411,
|
| 603 |
+
"eval_steps_per_second": 16.767,
|
| 604 |
+
"eval_subset_accuracy": 0.8900487125956854,
|
| 605 |
+
"step": 3400
|
| 606 |
+
}
|
| 607 |
+
],
|
| 608 |
+
"logging_steps": 100,
|
| 609 |
+
"max_steps": 3592,
|
| 610 |
+
"num_input_tokens_seen": 0,
|
| 611 |
+
"num_train_epochs": 4,
|
| 612 |
+
"save_steps": 200,
|
| 613 |
+
"stateful_callbacks": {
|
| 614 |
+
"EarlyStoppingCallback": {
|
| 615 |
+
"args": {
|
| 616 |
+
"early_stopping_patience": 3,
|
| 617 |
+
"early_stopping_threshold": 0.0001
|
| 618 |
+
},
|
| 619 |
+
"attributes": {
|
| 620 |
+
"early_stopping_patience_counter": 0
|
| 621 |
+
}
|
| 622 |
+
},
|
| 623 |
+
"TrainerControl": {
|
| 624 |
+
"args": {
|
| 625 |
+
"should_epoch_stop": false,
|
| 626 |
+
"should_evaluate": false,
|
| 627 |
+
"should_log": false,
|
| 628 |
+
"should_save": true,
|
| 629 |
+
"should_training_stop": false
|
| 630 |
+
},
|
| 631 |
+
"attributes": {}
|
| 632 |
+
}
|
| 633 |
+
},
|
| 634 |
+
"total_flos": 1.9578702215192064e+16,
|
| 635 |
+
"train_batch_size": 32,
|
| 636 |
+
"trial_name": null,
|
| 637 |
+
"trial_params": null
|
| 638 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c834b05f52939aa47c12cd51a9577354cfafe406ffc22a4600df23a467b0155e
|
| 3 |
+
size 5432
|
training_metrics.json
ADDED
|
@@ -0,0 +1,597 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"step": 100,
|
| 4 |
+
"epoch": 0.111358574610245,
|
| 5 |
+
"loss": 0.6139,
|
| 6 |
+
"grad_norm": 0.6548389792442322,
|
| 7 |
+
"learning_rate": 2.7500000000000004e-06
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"step": 200,
|
| 11 |
+
"epoch": 0.22271714922049,
|
| 12 |
+
"loss": 0.4821,
|
| 13 |
+
"grad_norm": 1.2604601383209229,
|
| 14 |
+
"learning_rate": 5.527777777777779e-06
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"step": 200,
|
| 18 |
+
"epoch": 0.22271714922049,
|
| 19 |
+
"eval_loss": 0.41080573201179504,
|
| 20 |
+
"eval_f1_micro": 0.8395441892832289,
|
| 21 |
+
"eval_f1_macro": 0.7509803650720916,
|
| 22 |
+
"eval_f1_weighted": 0.8265873475311692,
|
| 23 |
+
"eval_accuracy": 0.35198329853862215,
|
| 24 |
+
"eval_subset_accuracy": 0.8395441892832289,
|
| 25 |
+
"eval_f1_label_rado\u015b\u0107": 0.19078947368421054,
|
| 26 |
+
"eval_f1_label_wstr\u0119t": 0.5752023860247124,
|
| 27 |
+
"eval_f1_label_gniew": 0.6845324788814448,
|
| 28 |
+
"eval_f1_label_przeczuwanie": 0.0,
|
| 29 |
+
"eval_f1_label_pozytywny": 0.42994241842610365,
|
| 30 |
+
"eval_f1_label_negatywny": 0.7949462182004439,
|
| 31 |
+
"eval_f1_label_neutralny": 0.7492940069030436,
|
| 32 |
+
"eval_f1_label_sarkazm": 0.0,
|
| 33 |
+
"eval_runtime": 13.553,
|
| 34 |
+
"eval_samples_per_second": 530.14,
|
| 35 |
+
"eval_steps_per_second": 16.601
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"step": 300,
|
| 39 |
+
"epoch": 0.33407572383073497,
|
| 40 |
+
"loss": 0.4129,
|
| 41 |
+
"grad_norm": 1.7567846775054932,
|
| 42 |
+
"learning_rate": 8.305555555555557e-06
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"step": 400,
|
| 46 |
+
"epoch": 0.44543429844098,
|
| 47 |
+
"loss": 0.3769,
|
| 48 |
+
"grad_norm": 2.582125186920166,
|
| 49 |
+
"learning_rate": 9.99640768631301e-06
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"step": 400,
|
| 53 |
+
"epoch": 0.44543429844098,
|
| 54 |
+
"eval_loss": 0.33686527609825134,
|
| 55 |
+
"eval_f1_micro": 0.8666144745998609,
|
| 56 |
+
"eval_f1_macro": 0.8079475306110289,
|
| 57 |
+
"eval_f1_weighted": 0.8619885595665887,
|
| 58 |
+
"eval_accuracy": 0.4321503131524008,
|
| 59 |
+
"eval_subset_accuracy": 0.8666144745998609,
|
| 60 |
+
"eval_f1_label_rado\u015b\u0107": 0.6868131868131868,
|
| 61 |
+
"eval_f1_label_wstr\u0119t": 0.6907111262334127,
|
| 62 |
+
"eval_f1_label_gniew": 0.7182017543859649,
|
| 63 |
+
"eval_f1_label_przeczuwanie": 0.534637326813366,
|
| 64 |
+
"eval_f1_label_pozytywny": 0.7161493477282951,
|
| 65 |
+
"eval_f1_label_negatywny": 0.8120326308633583,
|
| 66 |
+
"eval_f1_label_neutralny": 0.7886710239651417,
|
| 67 |
+
"eval_f1_label_sarkazm": 0.005263157894736842,
|
| 68 |
+
"eval_runtime": 13.4667,
|
| 69 |
+
"eval_samples_per_second": 533.539,
|
| 70 |
+
"eval_steps_per_second": 16.708
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"step": 500,
|
| 74 |
+
"epoch": 0.5567928730512249,
|
| 75 |
+
"loss": 0.3415,
|
| 76 |
+
"grad_norm": 2.2375481128692627,
|
| 77 |
+
"learning_rate": 9.954431380479526e-06
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 600,
|
| 81 |
+
"epoch": 0.6681514476614699,
|
| 82 |
+
"loss": 0.3359,
|
| 83 |
+
"grad_norm": 2.377732515335083,
|
| 84 |
+
"learning_rate": 9.86568060370307e-06
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"step": 600,
|
| 88 |
+
"epoch": 0.6681514476614699,
|
| 89 |
+
"eval_loss": 0.307725727558136,
|
| 90 |
+
"eval_f1_micro": 0.8731384829505915,
|
| 91 |
+
"eval_f1_macro": 0.8208003215407338,
|
| 92 |
+
"eval_f1_weighted": 0.8701057540509732,
|
| 93 |
+
"eval_accuracy": 0.44231036882393876,
|
| 94 |
+
"eval_subset_accuracy": 0.8731384829505915,
|
| 95 |
+
"eval_f1_label_rado\u015b\u0107": 0.7128842380640942,
|
| 96 |
+
"eval_f1_label_wstr\u0119t": 0.6842447916666666,
|
| 97 |
+
"eval_f1_label_gniew": 0.7346007604562738,
|
| 98 |
+
"eval_f1_label_przeczuwanie": 0.6198969480776853,
|
| 99 |
+
"eval_f1_label_pozytywny": 0.7572641931157801,
|
| 100 |
+
"eval_f1_label_negatywny": 0.8233744855967078,
|
| 101 |
+
"eval_f1_label_neutralny": 0.7887421820708825,
|
| 102 |
+
"eval_f1_label_sarkazm": 0.18295543393275998,
|
| 103 |
+
"eval_runtime": 13.3682,
|
| 104 |
+
"eval_samples_per_second": 537.472,
|
| 105 |
+
"eval_steps_per_second": 16.831
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"step": 700,
|
| 109 |
+
"epoch": 0.779510022271715,
|
| 110 |
+
"loss": 0.3179,
|
| 111 |
+
"grad_norm": 2.0692615509033203,
|
| 112 |
+
"learning_rate": 9.730993246411562e-06
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"step": 800,
|
| 116 |
+
"epoch": 0.89086859688196,
|
| 117 |
+
"loss": 0.3184,
|
| 118 |
+
"grad_norm": 3.814361095428467,
|
| 119 |
+
"learning_rate": 9.551640883362268e-06
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"step": 800,
|
| 123 |
+
"epoch": 0.89086859688196,
|
| 124 |
+
"eval_loss": 0.29314953088760376,
|
| 125 |
+
"eval_f1_micro": 0.8788100208768267,
|
| 126 |
+
"eval_f1_macro": 0.8300609729014572,
|
| 127 |
+
"eval_f1_weighted": 0.8763999627004312,
|
| 128 |
+
"eval_accuracy": 0.4701461377870564,
|
| 129 |
+
"eval_subset_accuracy": 0.8788100208768267,
|
| 130 |
+
"eval_f1_label_rado\u015b\u0107": 0.6844694307800422,
|
| 131 |
+
"eval_f1_label_wstr\u0119t": 0.7084769124741558,
|
| 132 |
+
"eval_f1_label_gniew": 0.7435356200527704,
|
| 133 |
+
"eval_f1_label_przeczuwanie": 0.6724700761697497,
|
| 134 |
+
"eval_f1_label_pozytywny": 0.7029945999018163,
|
| 135 |
+
"eval_f1_label_negatywny": 0.8380327868852459,
|
| 136 |
+
"eval_f1_label_neutralny": 0.8036529680365296,
|
| 137 |
+
"eval_f1_label_sarkazm": 0.3567289117836446,
|
| 138 |
+
"eval_runtime": 13.6772,
|
| 139 |
+
"eval_samples_per_second": 525.325,
|
| 140 |
+
"eval_steps_per_second": 16.451
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"step": 900,
|
| 144 |
+
"epoch": 1.0022271714922049,
|
| 145 |
+
"loss": 0.3097,
|
| 146 |
+
"grad_norm": 2.8335301876068115,
|
| 147 |
+
"learning_rate": 9.329316768785544e-06
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"step": 1000,
|
| 151 |
+
"epoch": 1.1135857461024499,
|
| 152 |
+
"loss": 0.2756,
|
| 153 |
+
"grad_norm": 1.909611701965332,
|
| 154 |
+
"learning_rate": 9.066119850479551e-06
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"step": 1000,
|
| 158 |
+
"epoch": 1.1135857461024499,
|
| 159 |
+
"eval_loss": 0.28486499190330505,
|
| 160 |
+
"eval_f1_micro": 0.8823938761308281,
|
| 161 |
+
"eval_f1_macro": 0.8361271998835582,
|
| 162 |
+
"eval_f1_weighted": 0.8804578924937377,
|
| 163 |
+
"eval_accuracy": 0.4810020876826722,
|
| 164 |
+
"eval_subset_accuracy": 0.8823938761308281,
|
| 165 |
+
"eval_f1_label_rado\u015b\u0107": 0.7310513447432763,
|
| 166 |
+
"eval_f1_label_wstr\u0119t": 0.7109237794169301,
|
| 167 |
+
"eval_f1_label_gniew": 0.7485624673288029,
|
| 168 |
+
"eval_f1_label_przeczuwanie": 0.681491618200479,
|
| 169 |
+
"eval_f1_label_pozytywny": 0.7727272727272727,
|
| 170 |
+
"eval_f1_label_negatywny": 0.8409730266423961,
|
| 171 |
+
"eval_f1_label_neutralny": 0.8091783364265227,
|
| 172 |
+
"eval_f1_label_sarkazm": 0.3149171270718232,
|
| 173 |
+
"eval_runtime": 14.7594,
|
| 174 |
+
"eval_samples_per_second": 486.807,
|
| 175 |
+
"eval_steps_per_second": 15.244
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"step": 1100,
|
| 179 |
+
"epoch": 1.2249443207126949,
|
| 180 |
+
"loss": 0.2685,
|
| 181 |
+
"grad_norm": 4.029219150543213,
|
| 182 |
+
"learning_rate": 8.764534953777842e-06
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"step": 1200,
|
| 186 |
+
"epoch": 1.3363028953229399,
|
| 187 |
+
"loss": 0.2622,
|
| 188 |
+
"grad_norm": 1.7298495769500732,
|
| 189 |
+
"learning_rate": 8.427409322471743e-06
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"step": 1200,
|
| 193 |
+
"epoch": 1.3363028953229399,
|
| 194 |
+
"eval_loss": 0.28199732303619385,
|
| 195 |
+
"eval_f1_micro": 0.881419624217119,
|
| 196 |
+
"eval_f1_macro": 0.8361219089623048,
|
| 197 |
+
"eval_f1_weighted": 0.8799866455346702,
|
| 198 |
+
"eval_accuracy": 0.4683368128044537,
|
| 199 |
+
"eval_subset_accuracy": 0.881419624217119,
|
| 200 |
+
"eval_f1_label_rado\u015b\u0107": 0.7399756986634265,
|
| 201 |
+
"eval_f1_label_wstr\u0119t": 0.7199725463280714,
|
| 202 |
+
"eval_f1_label_gniew": 0.7479035639412998,
|
| 203 |
+
"eval_f1_label_przeczuwanie": 0.7060367454068242,
|
| 204 |
+
"eval_f1_label_pozytywny": 0.7732656514382402,
|
| 205 |
+
"eval_f1_label_negatywny": 0.8449914316871787,
|
| 206 |
+
"eval_f1_label_neutralny": 0.7788461538461539,
|
| 207 |
+
"eval_f1_label_sarkazm": 0.4,
|
| 208 |
+
"eval_runtime": 13.3959,
|
| 209 |
+
"eval_samples_per_second": 536.358,
|
| 210 |
+
"eval_steps_per_second": 16.796
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"step": 1300,
|
| 214 |
+
"epoch": 1.447661469933185,
|
| 215 |
+
"loss": 0.2689,
|
| 216 |
+
"grad_norm": 2.291908025741577,
|
| 217 |
+
"learning_rate": 8.057925738163153e-06
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"step": 1400,
|
| 221 |
+
"epoch": 1.5590200445434297,
|
| 222 |
+
"loss": 0.2653,
|
| 223 |
+
"grad_norm": 2.64717960357666,
|
| 224 |
+
"learning_rate": 7.659572471826265e-06
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"step": 1400,
|
| 228 |
+
"epoch": 1.5590200445434297,
|
| 229 |
+
"eval_loss": 0.27665975689888,
|
| 230 |
+
"eval_f1_micro": 0.8838726513569938,
|
| 231 |
+
"eval_f1_macro": 0.8415650899916123,
|
| 232 |
+
"eval_f1_weighted": 0.8832473603278248,
|
| 233 |
+
"eval_accuracy": 0.48434237995824636,
|
| 234 |
+
"eval_subset_accuracy": 0.8838726513569938,
|
| 235 |
+
"eval_f1_label_rado\u015b\u0107": 0.7375621890547264,
|
| 236 |
+
"eval_f1_label_wstr\u0119t": 0.7300771208226221,
|
| 237 |
+
"eval_f1_label_gniew": 0.7580278128950695,
|
| 238 |
+
"eval_f1_label_przeczuwanie": 0.6951871657754011,
|
| 239 |
+
"eval_f1_label_pozytywny": 0.777292576419214,
|
| 240 |
+
"eval_f1_label_negatywny": 0.8478637868516475,
|
| 241 |
+
"eval_f1_label_neutralny": 0.8011984490659148,
|
| 242 |
+
"eval_f1_label_sarkazm": 0.47809206877426513,
|
| 243 |
+
"eval_runtime": 13.39,
|
| 244 |
+
"eval_samples_per_second": 536.594,
|
| 245 |
+
"eval_steps_per_second": 16.804
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"step": 1500,
|
| 249 |
+
"epoch": 1.670378619153675,
|
| 250 |
+
"loss": 0.2551,
|
| 251 |
+
"grad_norm": 2.742314100265503,
|
| 252 |
+
"learning_rate": 7.236110351263578e-06
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"step": 1600,
|
| 256 |
+
"epoch": 1.7817371937639197,
|
| 257 |
+
"loss": 0.253,
|
| 258 |
+
"grad_norm": 2.0853464603424072,
|
| 259 |
+
"learning_rate": 6.7915372553702926e-06
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"step": 1600,
|
| 263 |
+
"epoch": 1.7817371937639197,
|
| 264 |
+
"eval_loss": 0.27193114161491394,
|
| 265 |
+
"eval_f1_micro": 0.8862908837856646,
|
| 266 |
+
"eval_f1_macro": 0.8419394716369004,
|
| 267 |
+
"eval_f1_weighted": 0.8845662361245985,
|
| 268 |
+
"eval_accuracy": 0.49255393180236606,
|
| 269 |
+
"eval_subset_accuracy": 0.8862908837856646,
|
| 270 |
+
"eval_f1_label_rado\u015b\u0107": 0.7449786975045648,
|
| 271 |
+
"eval_f1_label_wstr\u0119t": 0.7020958083832335,
|
| 272 |
+
"eval_f1_label_gniew": 0.745141588006663,
|
| 273 |
+
"eval_f1_label_przeczuwanie": 0.7135483870967742,
|
| 274 |
+
"eval_f1_label_pozytywny": 0.7725178047758693,
|
| 275 |
+
"eval_f1_label_negatywny": 0.8427041499330656,
|
| 276 |
+
"eval_f1_label_neutralny": 0.8148646376324197,
|
| 277 |
+
"eval_f1_label_sarkazm": 0.45395894428152495,
|
| 278 |
+
"eval_runtime": 13.4458,
|
| 279 |
+
"eval_samples_per_second": 534.368,
|
| 280 |
+
"eval_steps_per_second": 16.734
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"step": 1700,
|
| 284 |
+
"epoch": 1.893095768374165,
|
| 285 |
+
"loss": 0.2502,
|
| 286 |
+
"grad_norm": 2.6639328002929688,
|
| 287 |
+
"learning_rate": 6.330050370414403e-06
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"step": 1800,
|
| 291 |
+
"epoch": 2.0044543429844097,
|
| 292 |
+
"loss": 0.2511,
|
| 293 |
+
"grad_norm": 2.5934195518493652,
|
| 294 |
+
"learning_rate": 5.856006564668624e-06
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"step": 1800,
|
| 298 |
+
"epoch": 2.0044543429844097,
|
| 299 |
+
"eval_loss": 0.2889347970485687,
|
| 300 |
+
"eval_f1_micro": 0.8771746694502436,
|
| 301 |
+
"eval_f1_macro": 0.8367166256068449,
|
| 302 |
+
"eval_f1_weighted": 0.8780966128511206,
|
| 303 |
+
"eval_accuracy": 0.46583159359777315,
|
| 304 |
+
"eval_subset_accuracy": 0.8771746694502436,
|
| 305 |
+
"eval_f1_label_rado\u015b\u0107": 0.7299448867115738,
|
| 306 |
+
"eval_f1_label_wstr\u0119t": 0.7176891006551519,
|
| 307 |
+
"eval_f1_label_gniew": 0.7512172501738928,
|
| 308 |
+
"eval_f1_label_przeczuwanie": 0.7179814755669115,
|
| 309 |
+
"eval_f1_label_pozytywny": 0.7771623348956114,
|
| 310 |
+
"eval_f1_label_negatywny": 0.8434200743494423,
|
| 311 |
+
"eval_f1_label_neutralny": 0.7797117724125023,
|
| 312 |
+
"eval_f1_label_sarkazm": 0.5232903865213082,
|
| 313 |
+
"eval_runtime": 13.5639,
|
| 314 |
+
"eval_samples_per_second": 529.716,
|
| 315 |
+
"eval_steps_per_second": 16.588
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"step": 1900,
|
| 319 |
+
"epoch": 2.115812917594655,
|
| 320 |
+
"loss": 0.2128,
|
| 321 |
+
"grad_norm": 2.778862714767456,
|
| 322 |
+
"learning_rate": 5.373881255494652e-06
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"step": 2000,
|
| 326 |
+
"epoch": 2.2271714922048997,
|
| 327 |
+
"loss": 0.2068,
|
| 328 |
+
"grad_norm": 2.1749610900878906,
|
| 329 |
+
"learning_rate": 4.888226157213061e-06
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"step": 2000,
|
| 333 |
+
"epoch": 2.2271714922048997,
|
| 334 |
+
"eval_loss": 0.2712438106536865,
|
| 335 |
+
"eval_f1_micro": 0.8896659707724426,
|
| 336 |
+
"eval_f1_macro": 0.8469364739492785,
|
| 337 |
+
"eval_f1_weighted": 0.8881098685832289,
|
| 338 |
+
"eval_accuracy": 0.5082811412665275,
|
| 339 |
+
"eval_subset_accuracy": 0.8896659707724426,
|
| 340 |
+
"eval_f1_label_rado\u015b\u0107": 0.7382636655948553,
|
| 341 |
+
"eval_f1_label_wstr\u0119t": 0.7270175438596491,
|
| 342 |
+
"eval_f1_label_gniew": 0.7617009895694036,
|
| 343 |
+
"eval_f1_label_przeczuwanie": 0.7022071307300509,
|
| 344 |
+
"eval_f1_label_pozytywny": 0.7810858143607706,
|
| 345 |
+
"eval_f1_label_negatywny": 0.8477131847880717,
|
| 346 |
+
"eval_f1_label_neutralny": 0.8223467369808833,
|
| 347 |
+
"eval_f1_label_sarkazm": 0.46941176470588236,
|
| 348 |
+
"eval_runtime": 13.4837,
|
| 349 |
+
"eval_samples_per_second": 532.864,
|
| 350 |
+
"eval_steps_per_second": 16.687
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"step": 2100,
|
| 354 |
+
"epoch": 2.338530066815145,
|
| 355 |
+
"loss": 0.2042,
|
| 356 |
+
"grad_norm": 3.2917253971099854,
|
| 357 |
+
"learning_rate": 4.403626308658459e-06
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"step": 2200,
|
| 361 |
+
"epoch": 2.4498886414253898,
|
| 362 |
+
"loss": 0.2097,
|
| 363 |
+
"grad_norm": 2.2220280170440674,
|
| 364 |
+
"learning_rate": 3.9246567861200166e-06
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"step": 2200,
|
| 368 |
+
"epoch": 2.4498886414253898,
|
| 369 |
+
"eval_loss": 0.2748867869377136,
|
| 370 |
+
"eval_f1_micro": 0.8878044537230341,
|
| 371 |
+
"eval_f1_macro": 0.8475632085047498,
|
| 372 |
+
"eval_f1_weighted": 0.8874379181538837,
|
| 373 |
+
"eval_accuracy": 0.4989561586638831,
|
| 374 |
+
"eval_subset_accuracy": 0.8878044537230341,
|
| 375 |
+
"eval_f1_label_rado\u015b\u0107": 0.7484811664641555,
|
| 376 |
+
"eval_f1_label_wstr\u0119t": 0.7377866400797607,
|
| 377 |
+
"eval_f1_label_gniew": 0.75792897804283,
|
| 378 |
+
"eval_f1_label_przeczuwanie": 0.7263442475217783,
|
| 379 |
+
"eval_f1_label_pozytywny": 0.7774578362813657,
|
| 380 |
+
"eval_f1_label_negatywny": 0.8532080362929358,
|
| 381 |
+
"eval_f1_label_neutralny": 0.8129346314325452,
|
| 382 |
+
"eval_f1_label_sarkazm": 0.5211047420531527,
|
| 383 |
+
"eval_runtime": 13.5472,
|
| 384 |
+
"eval_samples_per_second": 530.369,
|
| 385 |
+
"eval_steps_per_second": 16.609
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"step": 2300,
|
| 389 |
+
"epoch": 2.5612472160356345,
|
| 390 |
+
"loss": 0.202,
|
| 391 |
+
"grad_norm": 4.778714179992676,
|
| 392 |
+
"learning_rate": 3.4558395103377882e-06
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"step": 2400,
|
| 396 |
+
"epoch": 2.6726057906458798,
|
| 397 |
+
"loss": 0.2042,
|
| 398 |
+
"grad_norm": 2.9350364208221436,
|
| 399 |
+
"learning_rate": 3.0016005553371464e-06
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"step": 2400,
|
| 403 |
+
"epoch": 2.6726057906458798,
|
| 404 |
+
"eval_loss": 0.27490347623825073,
|
| 405 |
+
"eval_f1_micro": 0.8879262352122478,
|
| 406 |
+
"eval_f1_macro": 0.8486039951352532,
|
| 407 |
+
"eval_f1_weighted": 0.8878859652865869,
|
| 408 |
+
"eval_accuracy": 0.5029923451635352,
|
| 409 |
+
"eval_subset_accuracy": 0.8879262352122478,
|
| 410 |
+
"eval_f1_label_rado\u015b\u0107": 0.7540394973070018,
|
| 411 |
+
"eval_f1_label_wstr\u0119t": 0.7323117052494295,
|
| 412 |
+
"eval_f1_label_gniew": 0.7653221581980094,
|
| 413 |
+
"eval_f1_label_przeczuwanie": 0.7192023158571889,
|
| 414 |
+
"eval_f1_label_pozytywny": 0.7812627291242362,
|
| 415 |
+
"eval_f1_label_negatywny": 0.8546814044213265,
|
| 416 |
+
"eval_f1_label_neutralny": 0.8173642338291248,
|
| 417 |
+
"eval_f1_label_sarkazm": 0.5525328330206379,
|
| 418 |
+
"eval_runtime": 13.5014,
|
| 419 |
+
"eval_samples_per_second": 532.167,
|
| 420 |
+
"eval_steps_per_second": 16.665
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"step": 2500,
|
| 424 |
+
"epoch": 2.7839643652561246,
|
| 425 |
+
"loss": 0.1985,
|
| 426 |
+
"grad_norm": 3.124579906463623,
|
| 427 |
+
"learning_rate": 2.566228362145968e-06
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"step": 2600,
|
| 431 |
+
"epoch": 2.89532293986637,
|
| 432 |
+
"loss": 0.2071,
|
| 433 |
+
"grad_norm": 2.5567288398742676,
|
| 434 |
+
"learning_rate": 2.1538332518961635e-06
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"step": 2600,
|
| 438 |
+
"epoch": 2.89532293986637,
|
| 439 |
+
"eval_loss": 0.2728336453437805,
|
| 440 |
+
"eval_f1_micro": 0.8903096729297146,
|
| 441 |
+
"eval_f1_macro": 0.8485724561583636,
|
| 442 |
+
"eval_f1_weighted": 0.8890469205384153,
|
| 443 |
+
"eval_accuracy": 0.5102296450939457,
|
| 444 |
+
"eval_subset_accuracy": 0.8903096729297146,
|
| 445 |
+
"eval_f1_label_rado\u015b\u0107": 0.7517985611510791,
|
| 446 |
+
"eval_f1_label_wstr\u0119t": 0.7267462902642056,
|
| 447 |
+
"eval_f1_label_gniew": 0.7664253150978815,
|
| 448 |
+
"eval_f1_label_przeczuwanie": 0.7165740438051651,
|
| 449 |
+
"eval_f1_label_pozytywny": 0.7838400666389005,
|
| 450 |
+
"eval_f1_label_negatywny": 0.8534298404342819,
|
| 451 |
+
"eval_f1_label_neutralny": 0.8198167628096369,
|
| 452 |
+
"eval_f1_label_sarkazm": 0.4584795321637427,
|
| 453 |
+
"eval_runtime": 13.4,
|
| 454 |
+
"eval_samples_per_second": 536.194,
|
| 455 |
+
"eval_steps_per_second": 16.791
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"step": 2700,
|
| 459 |
+
"epoch": 3.0066815144766146,
|
| 460 |
+
"loss": 0.2014,
|
| 461 |
+
"grad_norm": 3.9624898433685303,
|
| 462 |
+
"learning_rate": 1.76830862054381e-06
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"step": 2800,
|
| 466 |
+
"epoch": 3.11804008908686,
|
| 467 |
+
"loss": 0.1767,
|
| 468 |
+
"grad_norm": 1.9180693626403809,
|
| 469 |
+
"learning_rate": 1.4132941815660222e-06
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"step": 2800,
|
| 473 |
+
"epoch": 3.11804008908686,
|
| 474 |
+
"eval_loss": 0.2742355167865753,
|
| 475 |
+
"eval_f1_micro": 0.8887265135699374,
|
| 476 |
+
"eval_f1_macro": 0.8473642910777622,
|
| 477 |
+
"eval_f1_weighted": 0.8878169372581985,
|
| 478 |
+
"eval_accuracy": 0.5039665970772442,
|
| 479 |
+
"eval_subset_accuracy": 0.8887265135699374,
|
| 480 |
+
"eval_f1_label_rado\u015b\u0107": 0.745920745920746,
|
| 481 |
+
"eval_f1_label_wstr\u0119t": 0.7262289199856476,
|
| 482 |
+
"eval_f1_label_gniew": 0.7623196297304655,
|
| 483 |
+
"eval_f1_label_przeczuwanie": 0.7178329571106095,
|
| 484 |
+
"eval_f1_label_pozytywny": 0.7777777777777778,
|
| 485 |
+
"eval_f1_label_negatywny": 0.8542283645936163,
|
| 486 |
+
"eval_f1_label_neutralny": 0.8082359099633571,
|
| 487 |
+
"eval_f1_label_sarkazm": 0.5346432264736298,
|
| 488 |
+
"eval_runtime": 16.0479,
|
| 489 |
+
"eval_samples_per_second": 447.723,
|
| 490 |
+
"eval_steps_per_second": 14.021
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"step": 2900,
|
| 494 |
+
"epoch": 3.2293986636971046,
|
| 495 |
+
"loss": 0.1773,
|
| 496 |
+
"grad_norm": 2.348484992980957,
|
| 497 |
+
"learning_rate": 1.092141603657972e-06
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"step": 3000,
|
| 501 |
+
"epoch": 3.34075723830735,
|
| 502 |
+
"loss": 0.173,
|
| 503 |
+
"grad_norm": 2.2864317893981934,
|
| 504 |
+
"learning_rate": 8.078828678422995e-07
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"step": 3000,
|
| 508 |
+
"epoch": 3.34075723830735,
|
| 509 |
+
"eval_loss": 0.27491486072540283,
|
| 510 |
+
"eval_f1_micro": 0.889544189283229,
|
| 511 |
+
"eval_f1_macro": 0.8494136493629865,
|
| 512 |
+
"eval_f1_weighted": 0.8889910470048148,
|
| 513 |
+
"eval_accuracy": 0.508141962421712,
|
| 514 |
+
"eval_subset_accuracy": 0.889544189283229,
|
| 515 |
+
"eval_f1_label_rado\u015b\u0107": 0.7475728155339806,
|
| 516 |
+
"eval_f1_label_wstr\u0119t": 0.7339011925042589,
|
| 517 |
+
"eval_f1_label_gniew": 0.7665431445209105,
|
| 518 |
+
"eval_f1_label_przeczuwanie": 0.7226675216415518,
|
| 519 |
+
"eval_f1_label_pozytywny": 0.781314592806945,
|
| 520 |
+
"eval_f1_label_negatywny": 0.8550937245313773,
|
| 521 |
+
"eval_f1_label_neutralny": 0.8155373032169747,
|
| 522 |
+
"eval_f1_label_sarkazm": 0.5287713841368584,
|
| 523 |
+
"eval_runtime": 13.5687,
|
| 524 |
+
"eval_samples_per_second": 529.527,
|
| 525 |
+
"eval_steps_per_second": 16.582
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"step": 3100,
|
| 529 |
+
"epoch": 3.4521158129175946,
|
| 530 |
+
"loss": 0.1756,
|
| 531 |
+
"grad_norm": 2.671910524368286,
|
| 532 |
+
"learning_rate": 5.632016427295134e-07
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"step": 3200,
|
| 536 |
+
"epoch": 3.5634743875278394,
|
| 537 |
+
"loss": 0.1695,
|
| 538 |
+
"grad_norm": 3.2793824672698975,
|
| 539 |
+
"learning_rate": 3.6040794817364335e-07
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"step": 3200,
|
| 543 |
+
"epoch": 3.5634743875278394,
|
| 544 |
+
"eval_loss": 0.27663180232048035,
|
| 545 |
+
"eval_f1_micro": 0.889544189283229,
|
| 546 |
+
"eval_f1_macro": 0.8495682589006989,
|
| 547 |
+
"eval_f1_weighted": 0.8890490603152431,
|
| 548 |
+
"eval_accuracy": 0.511482254697286,
|
| 549 |
+
"eval_subset_accuracy": 0.889544189283229,
|
| 550 |
+
"eval_f1_label_rado\u015b\u0107": 0.7479091995221028,
|
| 551 |
+
"eval_f1_label_wstr\u0119t": 0.731740614334471,
|
| 552 |
+
"eval_f1_label_gniew": 0.7687056970333421,
|
| 553 |
+
"eval_f1_label_przeczuwanie": 0.7237728585178056,
|
| 554 |
+
"eval_f1_label_pozytywny": 0.7816091954022989,
|
| 555 |
+
"eval_f1_label_negatywny": 0.8545868575146389,
|
| 556 |
+
"eval_f1_label_neutralny": 0.8166494668042655,
|
| 557 |
+
"eval_f1_label_sarkazm": 0.527850078084331,
|
| 558 |
+
"eval_runtime": 13.4661,
|
| 559 |
+
"eval_samples_per_second": 533.56,
|
| 560 |
+
"eval_steps_per_second": 16.709
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"step": 3300,
|
| 564 |
+
"epoch": 3.6748329621380846,
|
| 565 |
+
"loss": 0.167,
|
| 566 |
+
"grad_norm": 1.78013277053833,
|
| 567 |
+
"learning_rate": 2.0141634652200205e-07
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"step": 3400,
|
| 571 |
+
"epoch": 3.78619153674833,
|
| 572 |
+
"loss": 0.172,
|
| 573 |
+
"grad_norm": 2.706618070602417,
|
| 574 |
+
"learning_rate": 8.772786735407601e-08
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"step": 3400,
|
| 578 |
+
"epoch": 3.78619153674833,
|
| 579 |
+
"eval_loss": 0.2760503590106964,
|
| 580 |
+
"eval_f1_micro": 0.8900487125956854,
|
| 581 |
+
"eval_f1_macro": 0.8500096117258309,
|
| 582 |
+
"eval_f1_weighted": 0.8894635900360007,
|
| 583 |
+
"eval_accuracy": 0.5124565066109952,
|
| 584 |
+
"eval_subset_accuracy": 0.8900487125956854,
|
| 585 |
+
"eval_f1_label_rado\u015b\u0107": 0.7476190476190476,
|
| 586 |
+
"eval_f1_label_wstr\u0119t": 0.7336787564766839,
|
| 587 |
+
"eval_f1_label_gniew": 0.7693124502256438,
|
| 588 |
+
"eval_f1_label_przeczuwanie": 0.7220240025948751,
|
| 589 |
+
"eval_f1_label_pozytywny": 0.7813649366571311,
|
| 590 |
+
"eval_f1_label_negatywny": 0.8553212358999509,
|
| 591 |
+
"eval_f1_label_neutralny": 0.8172006167551824,
|
| 592 |
+
"eval_f1_label_sarkazm": 0.5337423312883436,
|
| 593 |
+
"eval_runtime": 13.4196,
|
| 594 |
+
"eval_samples_per_second": 535.411,
|
| 595 |
+
"eval_steps_per_second": 16.767
|
| 596 |
+
}
|
| 597 |
+
]
|