Commit
•
5b12fc5
1
Parent(s):
8119854
v1
Browse files- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +531 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "crisistransformers/CT-M1-Complete",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 130,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.36.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 64000
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02e39796f23e56f3c30a63d2429c859494268863b1b0b125d7a2f1c8a9ae3acc
|
| 3 |
+
size 539627096
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:089c335fc0e1151bef6508ebe236293b584fafa301eed36169837cf3e7ece660
|
| 3 |
+
size 1079374010
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed88393f254cc24a46e4f171d697cc6ec90c3dfc7ac20c098d9d759b7053eee6
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d93fb5204d5a7bbbe18d5f1fcdb70aa4286df3e670d61d8c2a38ccfd8a3cbd5
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,531 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9092560719066743,
|
| 3 |
+
"best_model_checkpoint": "./output_1/checkpoint-1408",
|
| 4 |
+
"epoch": 29.53846153846154,
|
| 5 |
+
"eval_steps": 64,
|
| 6 |
+
"global_step": 1920,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.98,
|
| 13 |
+
"learning_rate": 9.753846153846154e-06,
|
| 14 |
+
"loss": 0.5876,
|
| 15 |
+
"step": 64
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.98,
|
| 19 |
+
"eval_f1": 0.8264750469953308,
|
| 20 |
+
"eval_loss": 0.426924467086792,
|
| 21 |
+
"eval_precision": 0.8384115884115884,
|
| 22 |
+
"eval_recall": 0.8222047843249156,
|
| 23 |
+
"eval_runtime": 1.7863,
|
| 24 |
+
"eval_samples_per_second": 163.47,
|
| 25 |
+
"eval_steps_per_second": 5.598,
|
| 26 |
+
"step": 64
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.97,
|
| 30 |
+
"learning_rate": 9.50769230769231e-06,
|
| 31 |
+
"loss": 0.331,
|
| 32 |
+
"step": 128
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.97,
|
| 36 |
+
"eval_f1": 0.8797480620155038,
|
| 37 |
+
"eval_loss": 0.3329169452190399,
|
| 38 |
+
"eval_precision": 0.8921407595440745,
|
| 39 |
+
"eval_recall": 0.8746849289009369,
|
| 40 |
+
"eval_runtime": 1.7913,
|
| 41 |
+
"eval_samples_per_second": 163.008,
|
| 42 |
+
"eval_steps_per_second": 5.582,
|
| 43 |
+
"step": 128
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 2.95,
|
| 47 |
+
"learning_rate": 9.261538461538461e-06,
|
| 48 |
+
"loss": 0.2585,
|
| 49 |
+
"step": 192
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 2.95,
|
| 53 |
+
"eval_f1": 0.8914823472996463,
|
| 54 |
+
"eval_loss": 0.31825584173202515,
|
| 55 |
+
"eval_precision": 0.8960271317829458,
|
| 56 |
+
"eval_recall": 0.8887382888666951,
|
| 57 |
+
"eval_runtime": 1.7885,
|
| 58 |
+
"eval_samples_per_second": 163.262,
|
| 59 |
+
"eval_steps_per_second": 5.591,
|
| 60 |
+
"step": 192
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.94,
|
| 64 |
+
"learning_rate": 9.015384615384616e-06,
|
| 65 |
+
"loss": 0.2016,
|
| 66 |
+
"step": 256
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.94,
|
| 70 |
+
"eval_f1": 0.8988811005098933,
|
| 71 |
+
"eval_loss": 0.3036338686943054,
|
| 72 |
+
"eval_precision": 0.9010176651305684,
|
| 73 |
+
"eval_recall": 0.8972987111808627,
|
| 74 |
+
"eval_runtime": 1.7803,
|
| 75 |
+
"eval_samples_per_second": 164.015,
|
| 76 |
+
"eval_steps_per_second": 5.617,
|
| 77 |
+
"step": 256
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.92,
|
| 81 |
+
"learning_rate": 8.76923076923077e-06,
|
| 82 |
+
"loss": 0.1733,
|
| 83 |
+
"step": 320
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.92,
|
| 87 |
+
"eval_f1": 0.8919073833036791,
|
| 88 |
+
"eval_loss": 0.31887006759643555,
|
| 89 |
+
"eval_precision": 0.8940092165898618,
|
| 90 |
+
"eval_recall": 0.890355257526038,
|
| 91 |
+
"eval_runtime": 1.7908,
|
| 92 |
+
"eval_samples_per_second": 163.059,
|
| 93 |
+
"eval_steps_per_second": 5.584,
|
| 94 |
+
"step": 320
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 5.91,
|
| 98 |
+
"learning_rate": 8.523076923076923e-06,
|
| 99 |
+
"loss": 0.1627,
|
| 100 |
+
"step": 384
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 5.91,
|
| 104 |
+
"eval_f1": 0.8975599724181316,
|
| 105 |
+
"eval_loss": 0.3417821526527405,
|
| 106 |
+
"eval_precision": 0.9093253968253968,
|
| 107 |
+
"eval_recall": 0.8924478052028344,
|
| 108 |
+
"eval_runtime": 1.7807,
|
| 109 |
+
"eval_samples_per_second": 163.98,
|
| 110 |
+
"eval_steps_per_second": 5.616,
|
| 111 |
+
"step": 384
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.89,
|
| 115 |
+
"learning_rate": 8.276923076923078e-06,
|
| 116 |
+
"loss": 0.1268,
|
| 117 |
+
"step": 448
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.89,
|
| 121 |
+
"eval_f1": 0.8907594463150018,
|
| 122 |
+
"eval_loss": 0.33714038133621216,
|
| 123 |
+
"eval_precision": 0.9003055391287207,
|
| 124 |
+
"eval_recall": 0.8863128358776811,
|
| 125 |
+
"eval_runtime": 1.7763,
|
| 126 |
+
"eval_samples_per_second": 164.386,
|
| 127 |
+
"eval_steps_per_second": 5.63,
|
| 128 |
+
"step": 448
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.88,
|
| 132 |
+
"learning_rate": 8.03076923076923e-06,
|
| 133 |
+
"loss": 0.1059,
|
| 134 |
+
"step": 512
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.88,
|
| 138 |
+
"eval_f1": 0.8910119800132443,
|
| 139 |
+
"eval_loss": 0.36000651121139526,
|
| 140 |
+
"eval_precision": 0.8987068965517242,
|
| 141 |
+
"eval_recall": 0.8871213202073525,
|
| 142 |
+
"eval_runtime": 1.809,
|
| 143 |
+
"eval_samples_per_second": 161.417,
|
| 144 |
+
"eval_steps_per_second": 5.528,
|
| 145 |
+
"step": 512
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 8.86,
|
| 149 |
+
"learning_rate": 7.784615384615385e-06,
|
| 150 |
+
"loss": 0.1036,
|
| 151 |
+
"step": 576
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.86,
|
| 155 |
+
"eval_f1": 0.9018817204301075,
|
| 156 |
+
"eval_loss": 0.3717869520187378,
|
| 157 |
+
"eval_precision": 0.9072715791518919,
|
| 158 |
+
"eval_recall": 0.8987492271840967,
|
| 159 |
+
"eval_runtime": 1.7837,
|
| 160 |
+
"eval_samples_per_second": 163.704,
|
| 161 |
+
"eval_steps_per_second": 5.606,
|
| 162 |
+
"step": 576
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.85,
|
| 166 |
+
"learning_rate": 7.538461538461539e-06,
|
| 167 |
+
"loss": 0.0901,
|
| 168 |
+
"step": 640
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.85,
|
| 172 |
+
"eval_f1": 0.8978072239720984,
|
| 173 |
+
"eval_loss": 0.3917124569416046,
|
| 174 |
+
"eval_precision": 0.9075004928050463,
|
| 175 |
+
"eval_recall": 0.8932562895325058,
|
| 176 |
+
"eval_runtime": 1.816,
|
| 177 |
+
"eval_samples_per_second": 160.796,
|
| 178 |
+
"eval_steps_per_second": 5.507,
|
| 179 |
+
"step": 640
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 10.83,
|
| 183 |
+
"learning_rate": 7.292307692307693e-06,
|
| 184 |
+
"loss": 0.0859,
|
| 185 |
+
"step": 704
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 10.83,
|
| 189 |
+
"eval_f1": 0.8944069431051109,
|
| 190 |
+
"eval_loss": 0.3997272551059723,
|
| 191 |
+
"eval_precision": 0.9030704986489806,
|
| 192 |
+
"eval_recall": 0.8901888048699291,
|
| 193 |
+
"eval_runtime": 1.7905,
|
| 194 |
+
"eval_samples_per_second": 163.086,
|
| 195 |
+
"eval_steps_per_second": 5.585,
|
| 196 |
+
"step": 704
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 11.82,
|
| 200 |
+
"learning_rate": 7.046153846153847e-06,
|
| 201 |
+
"loss": 0.0559,
|
| 202 |
+
"step": 768
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 11.82,
|
| 206 |
+
"eval_f1": 0.9027916488324536,
|
| 207 |
+
"eval_loss": 0.4531518518924713,
|
| 208 |
+
"eval_precision": 0.9027916488324536,
|
| 209 |
+
"eval_recall": 0.9027916488324536,
|
| 210 |
+
"eval_runtime": 1.7898,
|
| 211 |
+
"eval_samples_per_second": 163.144,
|
| 212 |
+
"eval_steps_per_second": 5.587,
|
| 213 |
+
"step": 768
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.8,
|
| 217 |
+
"learning_rate": 6.800000000000001e-06,
|
| 218 |
+
"loss": 0.0593,
|
| 219 |
+
"step": 832
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.8,
|
| 223 |
+
"eval_f1": 0.8808563748079878,
|
| 224 |
+
"eval_loss": 0.47470441460609436,
|
| 225 |
+
"eval_precision": 0.8859960169038714,
|
| 226 |
+
"eval_recall": 0.8779188662196225,
|
| 227 |
+
"eval_runtime": 1.7809,
|
| 228 |
+
"eval_samples_per_second": 163.966,
|
| 229 |
+
"eval_steps_per_second": 5.615,
|
| 230 |
+
"step": 832
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 13.78,
|
| 234 |
+
"learning_rate": 6.553846153846154e-06,
|
| 235 |
+
"loss": 0.0448,
|
| 236 |
+
"step": 896
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 13.78,
|
| 240 |
+
"eval_f1": 0.8958481951776287,
|
| 241 |
+
"eval_loss": 0.4653804302215576,
|
| 242 |
+
"eval_precision": 0.8958481951776287,
|
| 243 |
+
"eval_recall": 0.8958481951776287,
|
| 244 |
+
"eval_runtime": 1.7817,
|
| 245 |
+
"eval_samples_per_second": 163.887,
|
| 246 |
+
"eval_steps_per_second": 5.613,
|
| 247 |
+
"step": 896
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 14.77,
|
| 251 |
+
"learning_rate": 6.307692307692308e-06,
|
| 252 |
+
"loss": 0.035,
|
| 253 |
+
"step": 960
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 14.77,
|
| 257 |
+
"eval_f1": 0.9024576473395372,
|
| 258 |
+
"eval_loss": 0.4710945188999176,
|
| 259 |
+
"eval_precision": 0.9040958083832336,
|
| 260 |
+
"eval_recall": 0.9011746801731108,
|
| 261 |
+
"eval_runtime": 1.8119,
|
| 262 |
+
"eval_samples_per_second": 161.155,
|
| 263 |
+
"eval_steps_per_second": 5.519,
|
| 264 |
+
"step": 960
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 15.75,
|
| 268 |
+
"learning_rate": 6.061538461538462e-06,
|
| 269 |
+
"loss": 0.0372,
|
| 270 |
+
"step": 1024
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 15.75,
|
| 274 |
+
"eval_f1": 0.8839804948528084,
|
| 275 |
+
"eval_loss": 0.5761662125587463,
|
| 276 |
+
"eval_precision": 0.8915556426332288,
|
| 277 |
+
"eval_recall": 0.8801778665525277,
|
| 278 |
+
"eval_runtime": 1.7874,
|
| 279 |
+
"eval_samples_per_second": 163.369,
|
| 280 |
+
"eval_steps_per_second": 5.595,
|
| 281 |
+
"step": 1024
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 16.74,
|
| 285 |
+
"learning_rate": 5.815384615384616e-06,
|
| 286 |
+
"loss": 0.0341,
|
| 287 |
+
"step": 1088
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 16.74,
|
| 291 |
+
"eval_f1": 0.9020838323353293,
|
| 292 |
+
"eval_loss": 0.5446054339408875,
|
| 293 |
+
"eval_precision": 0.9060461070030448,
|
| 294 |
+
"eval_recall": 0.8995577115137681,
|
| 295 |
+
"eval_runtime": 1.7858,
|
| 296 |
+
"eval_samples_per_second": 163.512,
|
| 297 |
+
"eval_steps_per_second": 5.6,
|
| 298 |
+
"step": 1088
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 17.72,
|
| 302 |
+
"learning_rate": 5.56923076923077e-06,
|
| 303 |
+
"loss": 0.0321,
|
| 304 |
+
"step": 1152
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 17.72,
|
| 308 |
+
"eval_f1": 0.9058548177161077,
|
| 309 |
+
"eval_loss": 0.5152109265327454,
|
| 310 |
+
"eval_precision": 0.908026113671275,
|
| 311 |
+
"eval_recall": 0.9042421648356874,
|
| 312 |
+
"eval_runtime": 1.7852,
|
| 313 |
+
"eval_samples_per_second": 163.569,
|
| 314 |
+
"eval_steps_per_second": 5.602,
|
| 315 |
+
"step": 1152
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 18.71,
|
| 319 |
+
"learning_rate": 5.323076923076923e-06,
|
| 320 |
+
"loss": 0.0171,
|
| 321 |
+
"step": 1216
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 18.71,
|
| 325 |
+
"eval_f1": 0.887100671789667,
|
| 326 |
+
"eval_loss": 0.6121218204498291,
|
| 327 |
+
"eval_precision": 0.897562663766253,
|
| 328 |
+
"eval_recall": 0.882436866885433,
|
| 329 |
+
"eval_runtime": 1.7977,
|
| 330 |
+
"eval_samples_per_second": 162.431,
|
| 331 |
+
"eval_steps_per_second": 5.563,
|
| 332 |
+
"step": 1216
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 19.69,
|
| 336 |
+
"learning_rate": 5.076923076923077e-06,
|
| 337 |
+
"loss": 0.0261,
|
| 338 |
+
"step": 1280
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 19.69,
|
| 342 |
+
"eval_f1": 0.9024576473395372,
|
| 343 |
+
"eval_loss": 0.5516932010650635,
|
| 344 |
+
"eval_precision": 0.9040958083832336,
|
| 345 |
+
"eval_recall": 0.9011746801731108,
|
| 346 |
+
"eval_runtime": 1.7934,
|
| 347 |
+
"eval_samples_per_second": 162.821,
|
| 348 |
+
"eval_steps_per_second": 5.576,
|
| 349 |
+
"step": 1280
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 20.68,
|
| 353 |
+
"learning_rate": 4.830769230769231e-06,
|
| 354 |
+
"loss": 0.0153,
|
| 355 |
+
"step": 1344
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 20.68,
|
| 359 |
+
"eval_f1": 0.89848348618354,
|
| 360 |
+
"eval_loss": 0.5832306146621704,
|
| 361 |
+
"eval_precision": 0.9031007751937985,
|
| 362 |
+
"eval_recall": 0.89568174252152,
|
| 363 |
+
"eval_runtime": 1.7807,
|
| 364 |
+
"eval_samples_per_second": 163.978,
|
| 365 |
+
"eval_steps_per_second": 5.616,
|
| 366 |
+
"step": 1344
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 21.66,
|
| 370 |
+
"learning_rate": 4.5846153846153855e-06,
|
| 371 |
+
"loss": 0.0183,
|
| 372 |
+
"step": 1408
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 21.66,
|
| 376 |
+
"eval_f1": 0.9092560719066743,
|
| 377 |
+
"eval_loss": 0.5685573220252991,
|
| 378 |
+
"eval_precision": 0.9120123153894261,
|
| 379 |
+
"eval_recall": 0.9073096494982642,
|
| 380 |
+
"eval_runtime": 1.8067,
|
| 381 |
+
"eval_samples_per_second": 161.617,
|
| 382 |
+
"eval_steps_per_second": 5.535,
|
| 383 |
+
"step": 1408
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 22.65,
|
| 387 |
+
"learning_rate": 4.338461538461539e-06,
|
| 388 |
+
"loss": 0.0098,
|
| 389 |
+
"step": 1472
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 22.65,
|
| 393 |
+
"eval_f1": 0.9058548177161077,
|
| 394 |
+
"eval_loss": 0.5791997909545898,
|
| 395 |
+
"eval_precision": 0.908026113671275,
|
| 396 |
+
"eval_recall": 0.9042421648356874,
|
| 397 |
+
"eval_runtime": 1.7948,
|
| 398 |
+
"eval_samples_per_second": 162.694,
|
| 399 |
+
"eval_steps_per_second": 5.572,
|
| 400 |
+
"step": 1472
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 23.63,
|
| 404 |
+
"learning_rate": 4.0923076923076925e-06,
|
| 405 |
+
"loss": 0.0216,
|
| 406 |
+
"step": 1536
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 23.63,
|
| 410 |
+
"eval_f1": 0.8948732718894008,
|
| 411 |
+
"eval_loss": 0.6078387498855591,
|
| 412 |
+
"eval_precision": 0.9001797250692184,
|
| 413 |
+
"eval_recall": 0.8918057735292719,
|
| 414 |
+
"eval_runtime": 1.7897,
|
| 415 |
+
"eval_samples_per_second": 163.158,
|
| 416 |
+
"eval_steps_per_second": 5.588,
|
| 417 |
+
"step": 1536
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 24.62,
|
| 421 |
+
"learning_rate": 3.846153846153847e-06,
|
| 422 |
+
"loss": 0.0076,
|
| 423 |
+
"step": 1600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 24.62,
|
| 427 |
+
"eval_f1": 0.8950898203592814,
|
| 428 |
+
"eval_loss": 0.6126357913017273,
|
| 429 |
+
"eval_precision": 0.898989898989899,
|
| 430 |
+
"eval_recall": 0.8926142578589432,
|
| 431 |
+
"eval_runtime": 1.7831,
|
| 432 |
+
"eval_samples_per_second": 163.755,
|
| 433 |
+
"eval_steps_per_second": 5.608,
|
| 434 |
+
"step": 1600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 25.6,
|
| 438 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 439 |
+
"loss": 0.0073,
|
| 440 |
+
"step": 1664
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 25.6,
|
| 444 |
+
"eval_f1": 0.9058548177161077,
|
| 445 |
+
"eval_loss": 0.6077719926834106,
|
| 446 |
+
"eval_precision": 0.908026113671275,
|
| 447 |
+
"eval_recall": 0.9042421648356874,
|
| 448 |
+
"eval_runtime": 1.7913,
|
| 449 |
+
"eval_samples_per_second": 163.011,
|
| 450 |
+
"eval_steps_per_second": 5.583,
|
| 451 |
+
"step": 1664
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 26.58,
|
| 455 |
+
"learning_rate": 3.353846153846154e-06,
|
| 456 |
+
"loss": 0.0257,
|
| 457 |
+
"step": 1728
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 26.58,
|
| 461 |
+
"eval_f1": 0.9020838323353293,
|
| 462 |
+
"eval_loss": 0.6265017986297607,
|
| 463 |
+
"eval_precision": 0.9060461070030448,
|
| 464 |
+
"eval_recall": 0.8995577115137681,
|
| 465 |
+
"eval_runtime": 1.8318,
|
| 466 |
+
"eval_samples_per_second": 159.409,
|
| 467 |
+
"eval_steps_per_second": 5.459,
|
| 468 |
+
"step": 1728
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 27.57,
|
| 472 |
+
"learning_rate": 3.1076923076923076e-06,
|
| 473 |
+
"loss": 0.0047,
|
| 474 |
+
"step": 1792
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 27.57,
|
| 478 |
+
"eval_f1": 0.891252898280854,
|
| 479 |
+
"eval_loss": 0.6706699728965759,
|
| 480 |
+
"eval_precision": 0.8972822910578608,
|
| 481 |
+
"eval_recall": 0.8879298045370239,
|
| 482 |
+
"eval_runtime": 1.7836,
|
| 483 |
+
"eval_samples_per_second": 163.716,
|
| 484 |
+
"eval_steps_per_second": 5.607,
|
| 485 |
+
"step": 1792
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 28.55,
|
| 489 |
+
"learning_rate": 2.8615384615384615e-06,
|
| 490 |
+
"loss": 0.0063,
|
| 491 |
+
"step": 1856
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 28.55,
|
| 495 |
+
"eval_f1": 0.89848348618354,
|
| 496 |
+
"eval_loss": 0.6434349417686462,
|
| 497 |
+
"eval_precision": 0.9031007751937985,
|
| 498 |
+
"eval_recall": 0.89568174252152,
|
| 499 |
+
"eval_runtime": 1.8097,
|
| 500 |
+
"eval_samples_per_second": 161.353,
|
| 501 |
+
"eval_steps_per_second": 5.526,
|
| 502 |
+
"step": 1856
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 29.54,
|
| 506 |
+
"learning_rate": 2.615384615384616e-06,
|
| 507 |
+
"loss": 0.0045,
|
| 508 |
+
"step": 1920
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 29.54,
|
| 512 |
+
"eval_f1": 0.9092560719066743,
|
| 513 |
+
"eval_loss": 0.6284749507904053,
|
| 514 |
+
"eval_precision": 0.9120123153894261,
|
| 515 |
+
"eval_recall": 0.9073096494982642,
|
| 516 |
+
"eval_runtime": 1.7895,
|
| 517 |
+
"eval_samples_per_second": 163.173,
|
| 518 |
+
"eval_steps_per_second": 5.588,
|
| 519 |
+
"step": 1920
|
| 520 |
+
}
|
| 521 |
+
],
|
| 522 |
+
"logging_steps": 64,
|
| 523 |
+
"max_steps": 2600,
|
| 524 |
+
"num_input_tokens_seen": 0,
|
| 525 |
+
"num_train_epochs": 40,
|
| 526 |
+
"save_steps": 64,
|
| 527 |
+
"total_flos": 2249673523312320.0,
|
| 528 |
+
"train_batch_size": 32,
|
| 529 |
+
"trial_name": null,
|
| 530 |
+
"trial_params": null
|
| 531 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842dac18de31e7b25b3f64e230c94e086f188da05c6d39f8d137f30f9e831131
|
| 3 |
+
size 4664
|