Commit
•
bf53fd0
1
Parent(s):
c988763
Upload folder using huggingface_hub (#1)
Browse files- Upload folder using huggingface_hub (44c8d49cc2c3c851ac152120b6f0b7fda19ddf53)
- config.json +12 -10
- optimizer.pt +3 -0
- pytorch_model.bin +2 -2
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +650 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -8,14 +8,15 @@
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
-
"0": "
|
| 12 |
-
"1": "
|
| 13 |
-
"2": "
|
| 14 |
-
"3": "
|
| 15 |
-
"4": "
|
| 16 |
-
"5": "
|
| 17 |
-
"6": "
|
| 18 |
-
"7": "
|
|
|
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
|
@@ -27,7 +28,8 @@
|
|
| 27 |
"LABEL_4": 4,
|
| 28 |
"LABEL_5": 5,
|
| 29 |
"LABEL_6": 6,
|
| 30 |
-
"LABEL_7": 7
|
|
|
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-07,
|
| 33 |
"max_position_embeddings": 512,
|
|
@@ -49,7 +51,7 @@
|
|
| 49 |
"relative_attention": true,
|
| 50 |
"share_att_key": true,
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
-
"transformers_version": "4.
|
| 53 |
"type_vocab_size": 0,
|
| 54 |
"vocab_size": 128100
|
| 55 |
}
|
|
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8"
|
| 20 |
},
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
|
|
|
| 28 |
"LABEL_4": 4,
|
| 29 |
"LABEL_5": 5,
|
| 30 |
"LABEL_6": 6,
|
| 31 |
+
"LABEL_7": 7,
|
| 32 |
+
"LABEL_8": 8
|
| 33 |
},
|
| 34 |
"layer_norm_eps": 1e-07,
|
| 35 |
"max_position_embeddings": 512,
|
|
|
|
| 51 |
"relative_attention": true,
|
| 52 |
"share_att_key": true,
|
| 53 |
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.31.0",
|
| 55 |
"type_vocab_size": 0,
|
| 56 |
"vocab_size": 128100
|
| 57 |
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c32774f045051599e224ffdc1af9e9714d98a366bf5cd8e703d88663efa38a
|
| 3 |
+
size 1475550981
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e66aeda1581b9ec935bfc043d16fe252be9c12fb47acaebf5158d2ac9157ca0b
|
| 3 |
+
size 737785845
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7accdc88685b15ec75ad9685ebdfbcbcb719085daac37c1f0e03703b75aa0efe
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55c42c6a07c8319456d8d4702714c375b84c69d0eb73081a20d0cad687db3316
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0422136783599854,
|
| 3 |
+
"best_model_checkpoint": "models/deberta-v3-base/1691009101/checkpoint-470",
|
| 4 |
+
"epoch": 4.986737400530504,
|
| 5 |
+
"global_step": 470,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 1.9787234042553193e-05,
|
| 13 |
+
"loss": 2.1681,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 1.9574468085106384e-05,
|
| 19 |
+
"loss": 2.1189,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 1.9361702127659575e-05,
|
| 25 |
+
"loss": 2.163,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 1.914893617021277e-05,
|
| 31 |
+
"loss": 2.111,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 1.893617021276596e-05,
|
| 37 |
+
"loss": 2.1833,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.32,
|
| 42 |
+
"learning_rate": 1.872340425531915e-05,
|
| 43 |
+
"loss": 2.0812,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.37,
|
| 48 |
+
"learning_rate": 1.8510638297872342e-05,
|
| 49 |
+
"loss": 2.1295,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.42,
|
| 54 |
+
"learning_rate": 1.8297872340425533e-05,
|
| 55 |
+
"loss": 2.0143,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"learning_rate": 1.8085106382978724e-05,
|
| 61 |
+
"loss": 2.1968,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.53,
|
| 66 |
+
"learning_rate": 1.7872340425531915e-05,
|
| 67 |
+
"loss": 1.995,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.58,
|
| 72 |
+
"learning_rate": 1.765957446808511e-05,
|
| 73 |
+
"loss": 2.0799,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.64,
|
| 78 |
+
"learning_rate": 1.74468085106383e-05,
|
| 79 |
+
"loss": 1.9155,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.69,
|
| 84 |
+
"learning_rate": 1.723404255319149e-05,
|
| 85 |
+
"loss": 1.9628,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.74,
|
| 90 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 91 |
+
"loss": 1.9793,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 1.6808510638297873e-05,
|
| 97 |
+
"loss": 1.8198,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"learning_rate": 1.6595744680851064e-05,
|
| 103 |
+
"loss": 1.6043,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.9,
|
| 108 |
+
"learning_rate": 1.6382978723404255e-05,
|
| 109 |
+
"loss": 1.6209,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.95,
|
| 114 |
+
"learning_rate": 1.6170212765957446e-05,
|
| 115 |
+
"loss": 1.5354,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0,
|
| 120 |
+
"eval_dignity_contempt_accuracy": 0.797153024911032,
|
| 121 |
+
"eval_loss": 1.4699641466140747,
|
| 122 |
+
"eval_mae": 0.5818505338078291,
|
| 123 |
+
"eval_n_samples": 670,
|
| 124 |
+
"eval_runtime": 13.4181,
|
| 125 |
+
"eval_samples_per_second": 49.933,
|
| 126 |
+
"eval_scorable_accuracy": 0.8776119402985074,
|
| 127 |
+
"eval_steps_per_second": 6.26,
|
| 128 |
+
"eval_top_1_accuracy": 0.5223880597014925,
|
| 129 |
+
"eval_top_2_accuracy": 0.8843416370106761,
|
| 130 |
+
"step": 94
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.01,
|
| 134 |
+
"learning_rate": 1.595744680851064e-05,
|
| 135 |
+
"loss": 1.5383,
|
| 136 |
+
"step": 95
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.06,
|
| 140 |
+
"learning_rate": 1.5744680851063832e-05,
|
| 141 |
+
"loss": 1.5934,
|
| 142 |
+
"step": 100
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.11,
|
| 146 |
+
"learning_rate": 1.5531914893617023e-05,
|
| 147 |
+
"loss": 1.5562,
|
| 148 |
+
"step": 105
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.17,
|
| 152 |
+
"learning_rate": 1.5319148936170214e-05,
|
| 153 |
+
"loss": 1.4006,
|
| 154 |
+
"step": 110
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.22,
|
| 158 |
+
"learning_rate": 1.5106382978723407e-05,
|
| 159 |
+
"loss": 1.4296,
|
| 160 |
+
"step": 115
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.27,
|
| 164 |
+
"learning_rate": 1.4893617021276596e-05,
|
| 165 |
+
"loss": 1.3508,
|
| 166 |
+
"step": 120
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.33,
|
| 170 |
+
"learning_rate": 1.4680851063829789e-05,
|
| 171 |
+
"loss": 1.3246,
|
| 172 |
+
"step": 125
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.38,
|
| 176 |
+
"learning_rate": 1.4468085106382981e-05,
|
| 177 |
+
"loss": 1.2573,
|
| 178 |
+
"step": 130
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.43,
|
| 182 |
+
"learning_rate": 1.425531914893617e-05,
|
| 183 |
+
"loss": 1.4491,
|
| 184 |
+
"step": 135
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.49,
|
| 188 |
+
"learning_rate": 1.4042553191489363e-05,
|
| 189 |
+
"loss": 1.2537,
|
| 190 |
+
"step": 140
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.54,
|
| 194 |
+
"learning_rate": 1.3829787234042556e-05,
|
| 195 |
+
"loss": 1.3947,
|
| 196 |
+
"step": 145
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.59,
|
| 200 |
+
"learning_rate": 1.3617021276595745e-05,
|
| 201 |
+
"loss": 1.282,
|
| 202 |
+
"step": 150
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.64,
|
| 206 |
+
"learning_rate": 1.3404255319148938e-05,
|
| 207 |
+
"loss": 1.3167,
|
| 208 |
+
"step": 155
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.7,
|
| 212 |
+
"learning_rate": 1.3191489361702127e-05,
|
| 213 |
+
"loss": 1.3456,
|
| 214 |
+
"step": 160
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.75,
|
| 218 |
+
"learning_rate": 1.297872340425532e-05,
|
| 219 |
+
"loss": 1.2924,
|
| 220 |
+
"step": 165
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.8,
|
| 224 |
+
"learning_rate": 1.2765957446808513e-05,
|
| 225 |
+
"loss": 1.4235,
|
| 226 |
+
"step": 170
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.86,
|
| 230 |
+
"learning_rate": 1.2553191489361702e-05,
|
| 231 |
+
"loss": 1.157,
|
| 232 |
+
"step": 175
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.91,
|
| 236 |
+
"learning_rate": 1.2340425531914895e-05,
|
| 237 |
+
"loss": 1.1315,
|
| 238 |
+
"step": 180
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.96,
|
| 242 |
+
"learning_rate": 1.2127659574468087e-05,
|
| 243 |
+
"loss": 1.2265,
|
| 244 |
+
"step": 185
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.99,
|
| 248 |
+
"eval_dignity_contempt_accuracy": 0.8087248322147651,
|
| 249 |
+
"eval_loss": 1.1996970176696777,
|
| 250 |
+
"eval_mae": 0.5134228187919463,
|
| 251 |
+
"eval_n_samples": 670,
|
| 252 |
+
"eval_runtime": 13.4177,
|
| 253 |
+
"eval_samples_per_second": 49.934,
|
| 254 |
+
"eval_scorable_accuracy": 0.9313432835820895,
|
| 255 |
+
"eval_steps_per_second": 6.26,
|
| 256 |
+
"eval_top_1_accuracy": 0.5492537313432836,
|
| 257 |
+
"eval_top_2_accuracy": 0.9328859060402684,
|
| 258 |
+
"step": 188
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.02,
|
| 262 |
+
"learning_rate": 1.1914893617021277e-05,
|
| 263 |
+
"loss": 1.1528,
|
| 264 |
+
"step": 190
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.07,
|
| 268 |
+
"learning_rate": 1.170212765957447e-05,
|
| 269 |
+
"loss": 1.1732,
|
| 270 |
+
"step": 195
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.12,
|
| 274 |
+
"learning_rate": 1.1489361702127662e-05,
|
| 275 |
+
"loss": 1.1946,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.18,
|
| 280 |
+
"learning_rate": 1.1276595744680851e-05,
|
| 281 |
+
"loss": 1.0079,
|
| 282 |
+
"step": 205
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.23,
|
| 286 |
+
"learning_rate": 1.1063829787234044e-05,
|
| 287 |
+
"loss": 0.9267,
|
| 288 |
+
"step": 210
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.28,
|
| 292 |
+
"learning_rate": 1.0851063829787233e-05,
|
| 293 |
+
"loss": 1.06,
|
| 294 |
+
"step": 215
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.33,
|
| 298 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 299 |
+
"loss": 1.0085,
|
| 300 |
+
"step": 220
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.39,
|
| 304 |
+
"learning_rate": 1.0425531914893619e-05,
|
| 305 |
+
"loss": 1.0053,
|
| 306 |
+
"step": 225
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.44,
|
| 310 |
+
"learning_rate": 1.0212765957446808e-05,
|
| 311 |
+
"loss": 1.0857,
|
| 312 |
+
"step": 230
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.49,
|
| 316 |
+
"learning_rate": 1e-05,
|
| 317 |
+
"loss": 0.8903,
|
| 318 |
+
"step": 235
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.55,
|
| 322 |
+
"learning_rate": 9.787234042553192e-06,
|
| 323 |
+
"loss": 1.1211,
|
| 324 |
+
"step": 240
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.6,
|
| 328 |
+
"learning_rate": 9.574468085106385e-06,
|
| 329 |
+
"loss": 1.0351,
|
| 330 |
+
"step": 245
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.65,
|
| 334 |
+
"learning_rate": 9.361702127659576e-06,
|
| 335 |
+
"loss": 0.9636,
|
| 336 |
+
"step": 250
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.71,
|
| 340 |
+
"learning_rate": 9.148936170212767e-06,
|
| 341 |
+
"loss": 0.9087,
|
| 342 |
+
"step": 255
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.76,
|
| 346 |
+
"learning_rate": 8.936170212765958e-06,
|
| 347 |
+
"loss": 0.9624,
|
| 348 |
+
"step": 260
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.81,
|
| 352 |
+
"learning_rate": 8.72340425531915e-06,
|
| 353 |
+
"loss": 0.9403,
|
| 354 |
+
"step": 265
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.86,
|
| 358 |
+
"learning_rate": 8.510638297872341e-06,
|
| 359 |
+
"loss": 0.9479,
|
| 360 |
+
"step": 270
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.92,
|
| 364 |
+
"learning_rate": 8.297872340425532e-06,
|
| 365 |
+
"loss": 0.8829,
|
| 366 |
+
"step": 275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.97,
|
| 370 |
+
"learning_rate": 8.085106382978723e-06,
|
| 371 |
+
"loss": 0.992,
|
| 372 |
+
"step": 280
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.99,
|
| 376 |
+
"eval_dignity_contempt_accuracy": 0.8266199649737302,
|
| 377 |
+
"eval_loss": 1.091895580291748,
|
| 378 |
+
"eval_mae": 0.4658493870402802,
|
| 379 |
+
"eval_n_samples": 670,
|
| 380 |
+
"eval_runtime": 13.4128,
|
| 381 |
+
"eval_samples_per_second": 49.952,
|
| 382 |
+
"eval_scorable_accuracy": 0.9059701492537313,
|
| 383 |
+
"eval_steps_per_second": 6.263,
|
| 384 |
+
"eval_top_1_accuracy": 0.5776119402985075,
|
| 385 |
+
"eval_top_2_accuracy": 0.9316987740805605,
|
| 386 |
+
"step": 282
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.02,
|
| 390 |
+
"learning_rate": 7.872340425531916e-06,
|
| 391 |
+
"loss": 0.9552,
|
| 392 |
+
"step": 285
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.08,
|
| 396 |
+
"learning_rate": 7.659574468085107e-06,
|
| 397 |
+
"loss": 0.8174,
|
| 398 |
+
"step": 290
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.13,
|
| 402 |
+
"learning_rate": 7.446808510638298e-06,
|
| 403 |
+
"loss": 0.766,
|
| 404 |
+
"step": 295
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.18,
|
| 408 |
+
"learning_rate": 7.234042553191491e-06,
|
| 409 |
+
"loss": 0.7773,
|
| 410 |
+
"step": 300
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.24,
|
| 414 |
+
"learning_rate": 7.021276595744682e-06,
|
| 415 |
+
"loss": 0.9016,
|
| 416 |
+
"step": 305
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.29,
|
| 420 |
+
"learning_rate": 6.808510638297873e-06,
|
| 421 |
+
"loss": 0.8505,
|
| 422 |
+
"step": 310
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.34,
|
| 426 |
+
"learning_rate": 6.595744680851064e-06,
|
| 427 |
+
"loss": 0.9318,
|
| 428 |
+
"step": 315
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.4,
|
| 432 |
+
"learning_rate": 6.382978723404256e-06,
|
| 433 |
+
"loss": 0.7373,
|
| 434 |
+
"step": 320
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.45,
|
| 438 |
+
"learning_rate": 6.170212765957447e-06,
|
| 439 |
+
"loss": 0.7445,
|
| 440 |
+
"step": 325
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.5,
|
| 444 |
+
"learning_rate": 5.957446808510638e-06,
|
| 445 |
+
"loss": 0.8805,
|
| 446 |
+
"step": 330
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.55,
|
| 450 |
+
"learning_rate": 5.744680851063831e-06,
|
| 451 |
+
"loss": 0.7931,
|
| 452 |
+
"step": 335
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.61,
|
| 456 |
+
"learning_rate": 5.531914893617022e-06,
|
| 457 |
+
"loss": 0.8024,
|
| 458 |
+
"step": 340
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.66,
|
| 462 |
+
"learning_rate": 5.319148936170213e-06,
|
| 463 |
+
"loss": 0.7106,
|
| 464 |
+
"step": 345
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.71,
|
| 468 |
+
"learning_rate": 5.106382978723404e-06,
|
| 469 |
+
"loss": 0.7161,
|
| 470 |
+
"step": 350
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.77,
|
| 474 |
+
"learning_rate": 4.893617021276596e-06,
|
| 475 |
+
"loss": 0.7998,
|
| 476 |
+
"step": 355
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.82,
|
| 480 |
+
"learning_rate": 4.680851063829788e-06,
|
| 481 |
+
"loss": 0.6772,
|
| 482 |
+
"step": 360
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.87,
|
| 486 |
+
"learning_rate": 4.468085106382979e-06,
|
| 487 |
+
"loss": 0.7802,
|
| 488 |
+
"step": 365
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.93,
|
| 492 |
+
"learning_rate": 4.255319148936171e-06,
|
| 493 |
+
"loss": 0.7525,
|
| 494 |
+
"step": 370
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.98,
|
| 498 |
+
"learning_rate": 4.042553191489362e-06,
|
| 499 |
+
"loss": 0.7967,
|
| 500 |
+
"step": 375
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.0,
|
| 504 |
+
"eval_dignity_contempt_accuracy": 0.8305084745762712,
|
| 505 |
+
"eval_loss": 1.0538846254348755,
|
| 506 |
+
"eval_mae": 0.43559322033898307,
|
| 507 |
+
"eval_n_samples": 670,
|
| 508 |
+
"eval_runtime": 13.4019,
|
| 509 |
+
"eval_samples_per_second": 49.993,
|
| 510 |
+
"eval_scorable_accuracy": 0.926865671641791,
|
| 511 |
+
"eval_steps_per_second": 6.268,
|
| 512 |
+
"eval_top_1_accuracy": 0.6044776119402985,
|
| 513 |
+
"eval_top_2_accuracy": 0.9372881355932203,
|
| 514 |
+
"step": 377
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.03,
|
| 518 |
+
"learning_rate": 3.8297872340425535e-06,
|
| 519 |
+
"loss": 0.7263,
|
| 520 |
+
"step": 380
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.08,
|
| 524 |
+
"learning_rate": 3.6170212765957453e-06,
|
| 525 |
+
"loss": 0.7746,
|
| 526 |
+
"step": 385
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.14,
|
| 530 |
+
"learning_rate": 3.4042553191489363e-06,
|
| 531 |
+
"loss": 0.7231,
|
| 532 |
+
"step": 390
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.19,
|
| 536 |
+
"learning_rate": 3.191489361702128e-06,
|
| 537 |
+
"loss": 0.7129,
|
| 538 |
+
"step": 395
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 4.24,
|
| 542 |
+
"learning_rate": 2.978723404255319e-06,
|
| 543 |
+
"loss": 0.7609,
|
| 544 |
+
"step": 400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.3,
|
| 548 |
+
"learning_rate": 2.765957446808511e-06,
|
| 549 |
+
"loss": 0.7708,
|
| 550 |
+
"step": 405
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 4.35,
|
| 554 |
+
"learning_rate": 2.553191489361702e-06,
|
| 555 |
+
"loss": 0.6699,
|
| 556 |
+
"step": 410
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.4,
|
| 560 |
+
"learning_rate": 2.340425531914894e-06,
|
| 561 |
+
"loss": 0.5928,
|
| 562 |
+
"step": 415
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.46,
|
| 566 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 567 |
+
"loss": 0.6845,
|
| 568 |
+
"step": 420
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 4.51,
|
| 572 |
+
"learning_rate": 1.9148936170212767e-06,
|
| 573 |
+
"loss": 0.6752,
|
| 574 |
+
"step": 425
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.56,
|
| 578 |
+
"learning_rate": 1.7021276595744682e-06,
|
| 579 |
+
"loss": 0.5874,
|
| 580 |
+
"step": 430
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 4.62,
|
| 584 |
+
"learning_rate": 1.4893617021276596e-06,
|
| 585 |
+
"loss": 0.6781,
|
| 586 |
+
"step": 435
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 4.67,
|
| 590 |
+
"learning_rate": 1.276595744680851e-06,
|
| 591 |
+
"loss": 0.6023,
|
| 592 |
+
"step": 440
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 4.72,
|
| 596 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 597 |
+
"loss": 0.5626,
|
| 598 |
+
"step": 445
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.77,
|
| 602 |
+
"learning_rate": 8.510638297872341e-07,
|
| 603 |
+
"loss": 0.6321,
|
| 604 |
+
"step": 450
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.83,
|
| 608 |
+
"learning_rate": 6.382978723404255e-07,
|
| 609 |
+
"loss": 0.6318,
|
| 610 |
+
"step": 455
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.88,
|
| 614 |
+
"learning_rate": 4.2553191489361704e-07,
|
| 615 |
+
"loss": 0.5816,
|
| 616 |
+
"step": 460
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.93,
|
| 620 |
+
"learning_rate": 2.1276595744680852e-07,
|
| 621 |
+
"loss": 0.7118,
|
| 622 |
+
"step": 465
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 4.99,
|
| 626 |
+
"learning_rate": 0.0,
|
| 627 |
+
"loss": 0.6383,
|
| 628 |
+
"step": 470
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.99,
|
| 632 |
+
"eval_dignity_contempt_accuracy": 0.8398637137989778,
|
| 633 |
+
"eval_loss": 1.0422136783599854,
|
| 634 |
+
"eval_mae": 0.42759795570698467,
|
| 635 |
+
"eval_n_samples": 670,
|
| 636 |
+
"eval_runtime": 13.4143,
|
| 637 |
+
"eval_samples_per_second": 49.947,
|
| 638 |
+
"eval_scorable_accuracy": 0.9223880597014925,
|
| 639 |
+
"eval_steps_per_second": 6.262,
|
| 640 |
+
"eval_top_1_accuracy": 0.6119402985074627,
|
| 641 |
+
"eval_top_2_accuracy": 0.9369676320272572,
|
| 642 |
+
"step": 470
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"max_steps": 470,
|
| 646 |
+
"num_train_epochs": 5,
|
| 647 |
+
"total_flos": 7904494608261120.0,
|
| 648 |
+
"trial_name": null,
|
| 649 |
+
"trial_params": null
|
| 650 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29dfdab16090b73b24c6d9632b5dc452f2c65616e861cc77cef737ef36112f3c
|
| 3 |
+
size 4027
|