Upload 7 files
Browse files- config.json +55 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +455 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "IDEA-CCNL/Erlangshen-DeBERTa-v2-320M-Chinese",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"conv_act": "gelu",
|
| 8 |
+
"conv_kernel_size": 3,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0,
|
| 25 |
+
"LABEL_1": 1,
|
| 26 |
+
"LABEL_2": 2,
|
| 27 |
+
"LABEL_3": 3,
|
| 28 |
+
"LABEL_4": 4,
|
| 29 |
+
"LABEL_5": 5,
|
| 30 |
+
"LABEL_6": 6
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-07,
|
| 33 |
+
"max_position_embeddings": 512,
|
| 34 |
+
"max_relative_positions": -1,
|
| 35 |
+
"model_type": "deberta-v2",
|
| 36 |
+
"norm_rel_ebd": "layer_norm",
|
| 37 |
+
"num_attention_heads": 16,
|
| 38 |
+
"num_hidden_layers": 24,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"pooler_dropout": 0,
|
| 41 |
+
"pooler_hidden_act": "gelu",
|
| 42 |
+
"pooler_hidden_size": 1024,
|
| 43 |
+
"pos_att_type": [
|
| 44 |
+
"c2p",
|
| 45 |
+
"p2c"
|
| 46 |
+
],
|
| 47 |
+
"position_biased_input": false,
|
| 48 |
+
"position_buckets": 256,
|
| 49 |
+
"relative_attention": true,
|
| 50 |
+
"share_att_key": true,
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.39.3",
|
| 53 |
+
"type_vocab_size": 0,
|
| 54 |
+
"vocab_size": 12800
|
| 55 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d25aa6140ed4b2d72ce0f4e5d1d88c168938042a3b58e634ed8160b51e0ca083
|
| 3 |
+
size 1280651436
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bfdccdb1d1ae0e5544a7a20f5becd4c6192a9c7f336dccdf15c070a62410f9d
|
| 3 |
+
size 2561537340
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28489139e1e95de773495fd7a149c1d0795a7f2a165720f3a2989ae391bd644e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b8f05025975eda8c6fd7151df997f2fdf1334b654149418d27c46930a65f882
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8554500158408583,
|
| 3 |
+
"best_model_checkpoint": "cn_output/run-0/checkpoint-5775",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5775,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 43.52214813232422,
|
| 14 |
+
"learning_rate": 2.7348179693000015e-05,
|
| 15 |
+
"loss": 1.6704,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 16.620838165283203,
|
| 21 |
+
"learning_rate": 2.6866273442903096e-05,
|
| 22 |
+
"loss": 1.3854,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"grad_norm": 14.869579315185547,
|
| 28 |
+
"learning_rate": 2.638436719280618e-05,
|
| 29 |
+
"loss": 1.2394,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"grad_norm": 16.870759963989258,
|
| 35 |
+
"learning_rate": 2.5902460942709264e-05,
|
| 36 |
+
"loss": 1.1392,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.26,
|
| 41 |
+
"grad_norm": 12.891343116760254,
|
| 42 |
+
"learning_rate": 2.542055469261235e-05,
|
| 43 |
+
"loss": 1.0319,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"grad_norm": 7.518686771392822,
|
| 49 |
+
"learning_rate": 2.493864844251543e-05,
|
| 50 |
+
"loss": 1.0726,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.36,
|
| 55 |
+
"grad_norm": 9.59931755065918,
|
| 56 |
+
"learning_rate": 2.4456742192418514e-05,
|
| 57 |
+
"loss": 1.0907,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.42,
|
| 62 |
+
"grad_norm": 15.09188461303711,
|
| 63 |
+
"learning_rate": 2.3974835942321598e-05,
|
| 64 |
+
"loss": 1.038,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.47,
|
| 69 |
+
"grad_norm": 12.715774536132812,
|
| 70 |
+
"learning_rate": 2.3492929692224682e-05,
|
| 71 |
+
"loss": 0.9121,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.52,
|
| 76 |
+
"grad_norm": 23.419095993041992,
|
| 77 |
+
"learning_rate": 2.3011023442127766e-05,
|
| 78 |
+
"loss": 0.8541,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.57,
|
| 83 |
+
"grad_norm": 24.277725219726562,
|
| 84 |
+
"learning_rate": 2.252911719203085e-05,
|
| 85 |
+
"loss": 0.8723,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"grad_norm": 22.929729461669922,
|
| 91 |
+
"learning_rate": 2.2047210941933934e-05,
|
| 92 |
+
"loss": 0.8625,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.68,
|
| 97 |
+
"grad_norm": 12.207918167114258,
|
| 98 |
+
"learning_rate": 2.1565304691837015e-05,
|
| 99 |
+
"loss": 0.8384,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.73,
|
| 104 |
+
"grad_norm": 26.28716278076172,
|
| 105 |
+
"learning_rate": 2.10833984417401e-05,
|
| 106 |
+
"loss": 0.8521,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.78,
|
| 111 |
+
"grad_norm": 9.733681678771973,
|
| 112 |
+
"learning_rate": 2.0601492191643184e-05,
|
| 113 |
+
"loss": 0.7984,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.83,
|
| 118 |
+
"grad_norm": 25.5473690032959,
|
| 119 |
+
"learning_rate": 2.0119585941546264e-05,
|
| 120 |
+
"loss": 0.7452,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.88,
|
| 125 |
+
"grad_norm": 28.462318420410156,
|
| 126 |
+
"learning_rate": 1.963767969144935e-05,
|
| 127 |
+
"loss": 0.7016,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.94,
|
| 132 |
+
"grad_norm": 30.851057052612305,
|
| 133 |
+
"learning_rate": 1.9155773441352433e-05,
|
| 134 |
+
"loss": 0.6933,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.99,
|
| 139 |
+
"grad_norm": 20.66396141052246,
|
| 140 |
+
"learning_rate": 1.8673867191255517e-05,
|
| 141 |
+
"loss": 0.6987,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"eval_accuracy": 0.7933753943217665,
|
| 147 |
+
"eval_f1": 0.7855091479380132,
|
| 148 |
+
"eval_loss": 0.635335385799408,
|
| 149 |
+
"eval_runtime": 15.4807,
|
| 150 |
+
"eval_samples_per_second": 122.863,
|
| 151 |
+
"eval_steps_per_second": 3.876,
|
| 152 |
+
"step": 1925
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.04,
|
| 156 |
+
"grad_norm": 18.86337661743164,
|
| 157 |
+
"learning_rate": 1.8191960941158598e-05,
|
| 158 |
+
"loss": 0.5131,
|
| 159 |
+
"step": 2000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.09,
|
| 163 |
+
"grad_norm": 23.430830001831055,
|
| 164 |
+
"learning_rate": 1.7710054691061682e-05,
|
| 165 |
+
"loss": 0.4268,
|
| 166 |
+
"step": 2100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.14,
|
| 170 |
+
"grad_norm": 11.48133373260498,
|
| 171 |
+
"learning_rate": 1.7228148440964766e-05,
|
| 172 |
+
"loss": 0.4388,
|
| 173 |
+
"step": 2200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.19,
|
| 177 |
+
"grad_norm": 21.7901668548584,
|
| 178 |
+
"learning_rate": 1.674624219086785e-05,
|
| 179 |
+
"loss": 0.4276,
|
| 180 |
+
"step": 2300
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.25,
|
| 184 |
+
"grad_norm": 3.37796688079834,
|
| 185 |
+
"learning_rate": 1.6264335940770934e-05,
|
| 186 |
+
"loss": 0.3975,
|
| 187 |
+
"step": 2400
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.3,
|
| 191 |
+
"grad_norm": 1.8390240669250488,
|
| 192 |
+
"learning_rate": 1.578242969067402e-05,
|
| 193 |
+
"loss": 0.4863,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.35,
|
| 198 |
+
"grad_norm": 0.9483298063278198,
|
| 199 |
+
"learning_rate": 1.5300523440577103e-05,
|
| 200 |
+
"loss": 0.4216,
|
| 201 |
+
"step": 2600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.4,
|
| 205 |
+
"grad_norm": 13.241854667663574,
|
| 206 |
+
"learning_rate": 1.4818617190480184e-05,
|
| 207 |
+
"loss": 0.4522,
|
| 208 |
+
"step": 2700
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.45,
|
| 212 |
+
"grad_norm": 13.804593086242676,
|
| 213 |
+
"learning_rate": 1.4336710940383268e-05,
|
| 214 |
+
"loss": 0.3998,
|
| 215 |
+
"step": 2800
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.51,
|
| 219 |
+
"grad_norm": 20.864044189453125,
|
| 220 |
+
"learning_rate": 1.3854804690286352e-05,
|
| 221 |
+
"loss": 0.3561,
|
| 222 |
+
"step": 2900
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.56,
|
| 226 |
+
"grad_norm": 11.546530723571777,
|
| 227 |
+
"learning_rate": 1.3372898440189434e-05,
|
| 228 |
+
"loss": 0.4525,
|
| 229 |
+
"step": 3000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.61,
|
| 233 |
+
"grad_norm": 21.35649871826172,
|
| 234 |
+
"learning_rate": 1.2890992190092519e-05,
|
| 235 |
+
"loss": 0.422,
|
| 236 |
+
"step": 3100
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.66,
|
| 240 |
+
"grad_norm": 9.798705101013184,
|
| 241 |
+
"learning_rate": 1.2409085939995601e-05,
|
| 242 |
+
"loss": 0.3685,
|
| 243 |
+
"step": 3200
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.71,
|
| 247 |
+
"grad_norm": 1.4076740741729736,
|
| 248 |
+
"learning_rate": 1.1927179689898684e-05,
|
| 249 |
+
"loss": 0.3969,
|
| 250 |
+
"step": 3300
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.77,
|
| 254 |
+
"grad_norm": 2.5313684940338135,
|
| 255 |
+
"learning_rate": 1.1445273439801768e-05,
|
| 256 |
+
"loss": 0.3632,
|
| 257 |
+
"step": 3400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.82,
|
| 261 |
+
"grad_norm": 4.284488677978516,
|
| 262 |
+
"learning_rate": 1.0963367189704852e-05,
|
| 263 |
+
"loss": 0.3758,
|
| 264 |
+
"step": 3500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.87,
|
| 268 |
+
"grad_norm": 87.45575714111328,
|
| 269 |
+
"learning_rate": 1.0481460939607936e-05,
|
| 270 |
+
"loss": 0.3407,
|
| 271 |
+
"step": 3600
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.92,
|
| 275 |
+
"grad_norm": 18.49854850769043,
|
| 276 |
+
"learning_rate": 9.999554689511019e-06,
|
| 277 |
+
"loss": 0.4158,
|
| 278 |
+
"step": 3700
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.97,
|
| 282 |
+
"grad_norm": 10.284146308898926,
|
| 283 |
+
"learning_rate": 9.517648439414103e-06,
|
| 284 |
+
"loss": 0.3669,
|
| 285 |
+
"step": 3800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.0,
|
| 289 |
+
"eval_accuracy": 0.8496319663512093,
|
| 290 |
+
"eval_f1": 0.8396298133039037,
|
| 291 |
+
"eval_loss": 0.6180713176727295,
|
| 292 |
+
"eval_runtime": 15.5038,
|
| 293 |
+
"eval_samples_per_second": 122.679,
|
| 294 |
+
"eval_steps_per_second": 3.87,
|
| 295 |
+
"step": 3850
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.03,
|
| 299 |
+
"grad_norm": 2.4232983589172363,
|
| 300 |
+
"learning_rate": 9.035742189317185e-06,
|
| 301 |
+
"loss": 0.2593,
|
| 302 |
+
"step": 3900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.08,
|
| 306 |
+
"grad_norm": 14.904269218444824,
|
| 307 |
+
"learning_rate": 8.553835939220268e-06,
|
| 308 |
+
"loss": 0.1672,
|
| 309 |
+
"step": 4000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.13,
|
| 313 |
+
"grad_norm": 0.02660948596894741,
|
| 314 |
+
"learning_rate": 8.071929689123352e-06,
|
| 315 |
+
"loss": 0.1319,
|
| 316 |
+
"step": 4100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.18,
|
| 320 |
+
"grad_norm": 0.1543588936328888,
|
| 321 |
+
"learning_rate": 7.590023439026435e-06,
|
| 322 |
+
"loss": 0.1873,
|
| 323 |
+
"step": 4200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.23,
|
| 327 |
+
"grad_norm": 0.04116074740886688,
|
| 328 |
+
"learning_rate": 7.108117188929519e-06,
|
| 329 |
+
"loss": 0.1706,
|
| 330 |
+
"step": 4300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.29,
|
| 334 |
+
"grad_norm": 21.272350311279297,
|
| 335 |
+
"learning_rate": 6.626210938832602e-06,
|
| 336 |
+
"loss": 0.2408,
|
| 337 |
+
"step": 4400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.34,
|
| 341 |
+
"grad_norm": 0.016322173178195953,
|
| 342 |
+
"learning_rate": 6.144304688735686e-06,
|
| 343 |
+
"loss": 0.1878,
|
| 344 |
+
"step": 4500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.39,
|
| 348 |
+
"grad_norm": 0.12828181684017181,
|
| 349 |
+
"learning_rate": 5.662398438638769e-06,
|
| 350 |
+
"loss": 0.1664,
|
| 351 |
+
"step": 4600
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.44,
|
| 355 |
+
"grad_norm": 20.833871841430664,
|
| 356 |
+
"learning_rate": 5.180492188541853e-06,
|
| 357 |
+
"loss": 0.1066,
|
| 358 |
+
"step": 4700
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.49,
|
| 362 |
+
"grad_norm": 0.006888058967888355,
|
| 363 |
+
"learning_rate": 4.698585938444936e-06,
|
| 364 |
+
"loss": 0.1298,
|
| 365 |
+
"step": 4800
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.55,
|
| 369 |
+
"grad_norm": 0.0369136743247509,
|
| 370 |
+
"learning_rate": 4.21667968834802e-06,
|
| 371 |
+
"loss": 0.1151,
|
| 372 |
+
"step": 4900
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.6,
|
| 376 |
+
"grad_norm": 0.13510233163833618,
|
| 377 |
+
"learning_rate": 3.7347734382511036e-06,
|
| 378 |
+
"loss": 0.173,
|
| 379 |
+
"step": 5000
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.65,
|
| 383 |
+
"grad_norm": 0.05811930075287819,
|
| 384 |
+
"learning_rate": 3.252867188154187e-06,
|
| 385 |
+
"loss": 0.1359,
|
| 386 |
+
"step": 5100
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.7,
|
| 390 |
+
"grad_norm": 0.07640138268470764,
|
| 391 |
+
"learning_rate": 2.7709609380572702e-06,
|
| 392 |
+
"loss": 0.1293,
|
| 393 |
+
"step": 5200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.75,
|
| 397 |
+
"grad_norm": 0.019262025132775307,
|
| 398 |
+
"learning_rate": 2.289054687960354e-06,
|
| 399 |
+
"loss": 0.1205,
|
| 400 |
+
"step": 5300
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.81,
|
| 404 |
+
"grad_norm": 16.199689865112305,
|
| 405 |
+
"learning_rate": 1.8071484378634369e-06,
|
| 406 |
+
"loss": 0.1713,
|
| 407 |
+
"step": 5400
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.86,
|
| 411 |
+
"grad_norm": 0.010484320111572742,
|
| 412 |
+
"learning_rate": 1.3252421877665204e-06,
|
| 413 |
+
"loss": 0.145,
|
| 414 |
+
"step": 5500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.91,
|
| 418 |
+
"grad_norm": 0.06876770406961441,
|
| 419 |
+
"learning_rate": 8.43335937669604e-07,
|
| 420 |
+
"loss": 0.1405,
|
| 421 |
+
"step": 5600
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.96,
|
| 425 |
+
"grad_norm": 0.3863673210144043,
|
| 426 |
+
"learning_rate": 3.6142968757268745e-07,
|
| 427 |
+
"loss": 0.1295,
|
| 428 |
+
"step": 5700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.0,
|
| 432 |
+
"eval_accuracy": 0.8654048370136698,
|
| 433 |
+
"eval_f1": 0.8554500158408583,
|
| 434 |
+
"eval_loss": 0.7277432680130005,
|
| 435 |
+
"eval_runtime": 15.4912,
|
| 436 |
+
"eval_samples_per_second": 122.779,
|
| 437 |
+
"eval_steps_per_second": 3.873,
|
| 438 |
+
"step": 5775
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 100,
|
| 442 |
+
"max_steps": 5775,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 3,
|
| 445 |
+
"save_steps": 500,
|
| 446 |
+
"total_flos": 4219575531135264.0,
|
| 447 |
+
"train_batch_size": 8,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": {
|
| 450 |
+
"learning_rate": 2.783008594309693e-05,
|
| 451 |
+
"lr_scheduler_type": "linear",
|
| 452 |
+
"num_train_epochs": 3,
|
| 453 |
+
"per_device_train_batch_size": 8
|
| 454 |
+
}
|
| 455 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f29ef3614e8dc39f7548f4c40ef000ff35bec5715582ffcddd443752ddbd2a5
|
| 3 |
+
size 4920
|