Training in progress, epoch 17, checkpoint
Browse files- checkpoint-680/config.json +136 -0
- checkpoint-680/model.safetensors +3 -0
- checkpoint-680/optimizer.pt +3 -0
- checkpoint-680/rng_state.pth +3 -0
- checkpoint-680/scheduler.pt +3 -0
- checkpoint-680/trainer_state.json +833 -0
- checkpoint-680/training_args.bin +3 -0
checkpoint-680/config.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"adapter_attn_dim": null,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSequenceClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 256,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": false,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "sum",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": false,
|
| 48 |
+
"dtype": "float32",
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_norm": "group",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"freeze_feat_extract_train": true,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 768,
|
| 59 |
+
"id2label": {
|
| 60 |
+
"0": "water",
|
| 61 |
+
"1": "resident",
|
| 62 |
+
"2": "transient",
|
| 63 |
+
"3": "humpback",
|
| 64 |
+
"4": "vessel",
|
| 65 |
+
"5": "jingle",
|
| 66 |
+
"6": "human"
|
| 67 |
+
},
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 3072,
|
| 70 |
+
"label2id": {
|
| 71 |
+
"human": 6,
|
| 72 |
+
"humpback": 3,
|
| 73 |
+
"jingle": 5,
|
| 74 |
+
"resident": 1,
|
| 75 |
+
"transient": 2,
|
| 76 |
+
"vessel": 4,
|
| 77 |
+
"water": 0
|
| 78 |
+
},
|
| 79 |
+
"layer_norm_eps": 1e-05,
|
| 80 |
+
"layerdrop": 0.0,
|
| 81 |
+
"mask_channel_length": 10,
|
| 82 |
+
"mask_channel_min_space": 1,
|
| 83 |
+
"mask_channel_other": 0.0,
|
| 84 |
+
"mask_channel_prob": 0.0,
|
| 85 |
+
"mask_channel_selection": "static",
|
| 86 |
+
"mask_feature_length": 10,
|
| 87 |
+
"mask_feature_min_masks": 0,
|
| 88 |
+
"mask_feature_prob": 0.0,
|
| 89 |
+
"mask_time_length": 10,
|
| 90 |
+
"mask_time_min_masks": 2,
|
| 91 |
+
"mask_time_min_space": 1,
|
| 92 |
+
"mask_time_other": 0.0,
|
| 93 |
+
"mask_time_prob": 0.05,
|
| 94 |
+
"mask_time_selection": "static",
|
| 95 |
+
"model_type": "wav2vec2",
|
| 96 |
+
"no_mask_channel_overlap": false,
|
| 97 |
+
"no_mask_time_overlap": false,
|
| 98 |
+
"num_adapter_layers": 3,
|
| 99 |
+
"num_attention_heads": 12,
|
| 100 |
+
"num_codevector_groups": 2,
|
| 101 |
+
"num_codevectors_per_group": 320,
|
| 102 |
+
"num_conv_pos_embedding_groups": 16,
|
| 103 |
+
"num_conv_pos_embeddings": 128,
|
| 104 |
+
"num_feat_extract_layers": 7,
|
| 105 |
+
"num_hidden_layers": 12,
|
| 106 |
+
"num_negatives": 100,
|
| 107 |
+
"output_hidden_size": 768,
|
| 108 |
+
"pad_token_id": 0,
|
| 109 |
+
"proj_codevector_dim": 256,
|
| 110 |
+
"tdnn_dilation": [
|
| 111 |
+
1,
|
| 112 |
+
2,
|
| 113 |
+
3,
|
| 114 |
+
1,
|
| 115 |
+
1
|
| 116 |
+
],
|
| 117 |
+
"tdnn_dim": [
|
| 118 |
+
512,
|
| 119 |
+
512,
|
| 120 |
+
512,
|
| 121 |
+
512,
|
| 122 |
+
1500
|
| 123 |
+
],
|
| 124 |
+
"tdnn_kernel": [
|
| 125 |
+
5,
|
| 126 |
+
3,
|
| 127 |
+
3,
|
| 128 |
+
1,
|
| 129 |
+
1
|
| 130 |
+
],
|
| 131 |
+
"transformers_version": "5.8.1",
|
| 132 |
+
"use_cache": false,
|
| 133 |
+
"use_weighted_layer_sum": false,
|
| 134 |
+
"vocab_size": 32,
|
| 135 |
+
"xvector_output_dim": 512
|
| 136 |
+
}
|
checkpoint-680/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29ae44fba16923f788a88e3231328d1d742a775837d74e86e0dd88a4072c1fae
|
| 3 |
+
size 378307452
|
checkpoint-680/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97fc7e9afb08cca5d69aa5d4dbe7816715bd4b28d6273a1a737d258849946e40
|
| 3 |
+
size 756737291
|
checkpoint-680/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffee1d2b13173a0107f353d191e7420c4f2ad92b3e62d9acc7d1135c13a817ee
|
| 3 |
+
size 14455
|
checkpoint-680/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6be5a37d34589451b236a9d3ec56d84bc640c63dc5637576c96a28f7ec63b27b
|
| 3 |
+
size 1465
|
checkpoint-680/trainer_state.json
ADDED
|
@@ -0,0 +1,833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 680,
|
| 3 |
+
"best_metric": 0.7774170274170275,
|
| 4 |
+
"best_model_checkpoint": "/home/runner/work/pods-ai/pods-ai/model/multiclass/checkpoint-680",
|
| 5 |
+
"epoch": 17.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 680,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.25,
|
| 14 |
+
"grad_norm": 1.8668311834335327,
|
| 15 |
+
"learning_rate": 3.3750000000000003e-06,
|
| 16 |
+
"loss": 1.9396303176879883,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5,
|
| 21 |
+
"grad_norm": 2.939877986907959,
|
| 22 |
+
"learning_rate": 7.1249999999999995e-06,
|
| 23 |
+
"loss": 1.9260967254638672,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.75,
|
| 28 |
+
"grad_norm": 1.882246971130371,
|
| 29 |
+
"learning_rate": 1.0875e-05,
|
| 30 |
+
"loss": 1.9058483123779297,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"grad_norm": 2.8229551315307617,
|
| 36 |
+
"learning_rate": 1.4625e-05,
|
| 37 |
+
"loss": 1.857316780090332,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_accuracy": 0.2875,
|
| 43 |
+
"eval_f1": 0.1488673139158576,
|
| 44 |
+
"eval_f1_human": 0.0,
|
| 45 |
+
"eval_f1_humpback": 0.0,
|
| 46 |
+
"eval_f1_jingle": 0.0,
|
| 47 |
+
"eval_f1_resident": 0.44660194174757284,
|
| 48 |
+
"eval_f1_transient": 0.0,
|
| 49 |
+
"eval_f1_vessel": 0.0,
|
| 50 |
+
"eval_f1_water": 0.0,
|
| 51 |
+
"eval_loss": 1.8598134517669678,
|
| 52 |
+
"eval_precision": 0.08265625,
|
| 53 |
+
"eval_recall": 0.2875,
|
| 54 |
+
"eval_runtime": 24.6324,
|
| 55 |
+
"eval_samples_per_second": 3.248,
|
| 56 |
+
"eval_steps_per_second": 0.406,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.25,
|
| 61 |
+
"grad_norm": 4.461022853851318,
|
| 62 |
+
"learning_rate": 1.8375000000000003e-05,
|
| 63 |
+
"loss": 1.8402133941650392,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.5,
|
| 68 |
+
"grad_norm": 2.3800013065338135,
|
| 69 |
+
"learning_rate": 2.2125000000000002e-05,
|
| 70 |
+
"loss": 1.7940902709960938,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.75,
|
| 75 |
+
"grad_norm": 2.871340274810791,
|
| 76 |
+
"learning_rate": 2.5875000000000002e-05,
|
| 77 |
+
"loss": 1.7933925628662108,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"grad_norm": 13.321478843688965,
|
| 83 |
+
"learning_rate": 2.9625000000000002e-05,
|
| 84 |
+
"loss": 1.8077194213867187,
|
| 85 |
+
"step": 80
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.0,
|
| 89 |
+
"eval_accuracy": 0.3375,
|
| 90 |
+
"eval_f1": 0.1631205673758865,
|
| 91 |
+
"eval_f1_human": 0.46153846153846156,
|
| 92 |
+
"eval_f1_humpback": 0.0,
|
| 93 |
+
"eval_f1_jingle": 0.0,
|
| 94 |
+
"eval_f1_resident": 0.48936170212765956,
|
| 95 |
+
"eval_f1_transient": 0.0,
|
| 96 |
+
"eval_f1_vessel": 0.13333333333333333,
|
| 97 |
+
"eval_f1_water": 0.0,
|
| 98 |
+
"eval_loss": 1.8714452981948853,
|
| 99 |
+
"eval_precision": 0.2025088028169014,
|
| 100 |
+
"eval_recall": 0.3375,
|
| 101 |
+
"eval_runtime": 24.7133,
|
| 102 |
+
"eval_samples_per_second": 3.237,
|
| 103 |
+
"eval_steps_per_second": 0.405,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.25,
|
| 108 |
+
"grad_norm": 8.10289192199707,
|
| 109 |
+
"learning_rate": 2.9625000000000002e-05,
|
| 110 |
+
"loss": 1.7730058670043944,
|
| 111 |
+
"step": 90
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.5,
|
| 115 |
+
"grad_norm": 5.406036853790283,
|
| 116 |
+
"learning_rate": 2.9208333333333333e-05,
|
| 117 |
+
"loss": 1.691044235229492,
|
| 118 |
+
"step": 100
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.75,
|
| 122 |
+
"grad_norm": 3.6219217777252197,
|
| 123 |
+
"learning_rate": 2.8791666666666667e-05,
|
| 124 |
+
"loss": 1.7048904418945312,
|
| 125 |
+
"step": 110
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"grad_norm": 5.970705509185791,
|
| 130 |
+
"learning_rate": 2.8375e-05,
|
| 131 |
+
"loss": 1.6433557510375976,
|
| 132 |
+
"step": 120
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.0,
|
| 136 |
+
"eval_accuracy": 0.3375,
|
| 137 |
+
"eval_f1": 0.21201814058956917,
|
| 138 |
+
"eval_f1_human": 0.46153846153846156,
|
| 139 |
+
"eval_f1_humpback": 0.16666666666666666,
|
| 140 |
+
"eval_f1_jingle": 0.0,
|
| 141 |
+
"eval_f1_resident": 0.46938775510204084,
|
| 142 |
+
"eval_f1_transient": 0.0,
|
| 143 |
+
"eval_f1_vessel": 0.0,
|
| 144 |
+
"eval_f1_water": 0.0,
|
| 145 |
+
"eval_loss": 1.6715224981307983,
|
| 146 |
+
"eval_precision": 0.31004166666666666,
|
| 147 |
+
"eval_recall": 0.3375,
|
| 148 |
+
"eval_runtime": 24.7734,
|
| 149 |
+
"eval_samples_per_second": 3.229,
|
| 150 |
+
"eval_steps_per_second": 0.404,
|
| 151 |
+
"step": 120
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.25,
|
| 155 |
+
"grad_norm": 10.863486289978027,
|
| 156 |
+
"learning_rate": 2.7958333333333333e-05,
|
| 157 |
+
"loss": 1.5631604194641113,
|
| 158 |
+
"step": 130
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.5,
|
| 162 |
+
"grad_norm": 8.574637413024902,
|
| 163 |
+
"learning_rate": 2.7541666666666668e-05,
|
| 164 |
+
"loss": 1.5334065437316895,
|
| 165 |
+
"step": 140
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.75,
|
| 169 |
+
"grad_norm": 7.105515003204346,
|
| 170 |
+
"learning_rate": 2.7125000000000002e-05,
|
| 171 |
+
"loss": 1.5497626304626464,
|
| 172 |
+
"step": 150
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 4.0,
|
| 176 |
+
"grad_norm": 16.305498123168945,
|
| 177 |
+
"learning_rate": 2.6708333333333333e-05,
|
| 178 |
+
"loss": 1.5918970108032227,
|
| 179 |
+
"step": 160
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.0,
|
| 183 |
+
"eval_accuracy": 0.4625,
|
| 184 |
+
"eval_f1": 0.5654970760233918,
|
| 185 |
+
"eval_f1_human": 0.4444444444444444,
|
| 186 |
+
"eval_f1_humpback": 0.5,
|
| 187 |
+
"eval_f1_jingle": 0.0,
|
| 188 |
+
"eval_f1_resident": 0.5964912280701754,
|
| 189 |
+
"eval_f1_transient": 0.6,
|
| 190 |
+
"eval_f1_vessel": 0.0,
|
| 191 |
+
"eval_f1_water": 0.0,
|
| 192 |
+
"eval_loss": 1.6689106225967407,
|
| 193 |
+
"eval_precision": 0.35366379310344825,
|
| 194 |
+
"eval_recall": 0.4625,
|
| 195 |
+
"eval_runtime": 24.6211,
|
| 196 |
+
"eval_samples_per_second": 3.249,
|
| 197 |
+
"eval_steps_per_second": 0.406,
|
| 198 |
+
"step": 160
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.25,
|
| 202 |
+
"grad_norm": 22.159957885742188,
|
| 203 |
+
"learning_rate": 2.6291666666666668e-05,
|
| 204 |
+
"loss": 1.458185577392578,
|
| 205 |
+
"step": 170
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.5,
|
| 209 |
+
"grad_norm": 5.997427940368652,
|
| 210 |
+
"learning_rate": 2.5875000000000002e-05,
|
| 211 |
+
"loss": 1.4319477081298828,
|
| 212 |
+
"step": 180
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.75,
|
| 216 |
+
"grad_norm": 15.294506072998047,
|
| 217 |
+
"learning_rate": 2.5458333333333333e-05,
|
| 218 |
+
"loss": 1.4154382705688477,
|
| 219 |
+
"step": 190
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.0,
|
| 223 |
+
"grad_norm": 14.528937339782715,
|
| 224 |
+
"learning_rate": 2.5041666666666668e-05,
|
| 225 |
+
"loss": 1.3779909133911132,
|
| 226 |
+
"step": 200
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.0,
|
| 230 |
+
"eval_accuracy": 0.5875,
|
| 231 |
+
"eval_f1": 0.6944318983209324,
|
| 232 |
+
"eval_f1_human": 0.6666666666666666,
|
| 233 |
+
"eval_f1_humpback": 0.7096774193548387,
|
| 234 |
+
"eval_f1_jingle": 0.0,
|
| 235 |
+
"eval_f1_resident": 0.6779661016949152,
|
| 236 |
+
"eval_f1_transient": 0.6956521739130435,
|
| 237 |
+
"eval_f1_vessel": 0.0,
|
| 238 |
+
"eval_f1_water": 0.2222222222222222,
|
| 239 |
+
"eval_loss": 1.3697296380996704,
|
| 240 |
+
"eval_precision": 0.5100631313131313,
|
| 241 |
+
"eval_recall": 0.5875,
|
| 242 |
+
"eval_runtime": 24.6436,
|
| 243 |
+
"eval_samples_per_second": 3.246,
|
| 244 |
+
"eval_steps_per_second": 0.406,
|
| 245 |
+
"step": 200
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.25,
|
| 249 |
+
"grad_norm": 14.52349853515625,
|
| 250 |
+
"learning_rate": 2.4625e-05,
|
| 251 |
+
"loss": 1.2567331314086914,
|
| 252 |
+
"step": 210
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.5,
|
| 256 |
+
"grad_norm": 3.960951805114746,
|
| 257 |
+
"learning_rate": 2.4208333333333333e-05,
|
| 258 |
+
"loss": 1.1996272087097168,
|
| 259 |
+
"step": 220
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.75,
|
| 263 |
+
"grad_norm": 15.082646369934082,
|
| 264 |
+
"learning_rate": 2.3791666666666664e-05,
|
| 265 |
+
"loss": 1.195827102661133,
|
| 266 |
+
"step": 230
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"grad_norm": 4.821845531463623,
|
| 271 |
+
"learning_rate": 2.3375000000000002e-05,
|
| 272 |
+
"loss": 1.2418400764465332,
|
| 273 |
+
"step": 240
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0,
|
| 277 |
+
"eval_accuracy": 0.5125,
|
| 278 |
+
"eval_f1": 0.5613756613756614,
|
| 279 |
+
"eval_f1_human": 0.46153846153846156,
|
| 280 |
+
"eval_f1_humpback": 0.5555555555555556,
|
| 281 |
+
"eval_f1_jingle": 0.0,
|
| 282 |
+
"eval_f1_resident": 0.6285714285714286,
|
| 283 |
+
"eval_f1_transient": 0.5,
|
| 284 |
+
"eval_f1_vessel": 0.3333333333333333,
|
| 285 |
+
"eval_f1_water": 0.3333333333333333,
|
| 286 |
+
"eval_loss": 1.4040424823760986,
|
| 287 |
+
"eval_precision": 0.5577887537993921,
|
| 288 |
+
"eval_recall": 0.5125,
|
| 289 |
+
"eval_runtime": 24.5561,
|
| 290 |
+
"eval_samples_per_second": 3.258,
|
| 291 |
+
"eval_steps_per_second": 0.407,
|
| 292 |
+
"step": 240
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 6.25,
|
| 296 |
+
"grad_norm": 8.668111801147461,
|
| 297 |
+
"learning_rate": 2.2958333333333333e-05,
|
| 298 |
+
"loss": 1.0798751831054687,
|
| 299 |
+
"step": 250
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 6.5,
|
| 303 |
+
"grad_norm": 40.171241760253906,
|
| 304 |
+
"learning_rate": 2.2541666666666668e-05,
|
| 305 |
+
"loss": 1.1611945152282714,
|
| 306 |
+
"step": 260
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 6.75,
|
| 310 |
+
"grad_norm": 7.711854457855225,
|
| 311 |
+
"learning_rate": 2.2125000000000002e-05,
|
| 312 |
+
"loss": 1.20938138961792,
|
| 313 |
+
"step": 270
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 7.0,
|
| 317 |
+
"grad_norm": 32.661705017089844,
|
| 318 |
+
"learning_rate": 2.1708333333333334e-05,
|
| 319 |
+
"loss": 1.181071662902832,
|
| 320 |
+
"step": 280
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.0,
|
| 324 |
+
"eval_accuracy": 0.575,
|
| 325 |
+
"eval_f1": 0.5869708994708994,
|
| 326 |
+
"eval_f1_human": 0.5714285714285714,
|
| 327 |
+
"eval_f1_humpback": 0.5,
|
| 328 |
+
"eval_f1_jingle": 0.2222222222222222,
|
| 329 |
+
"eval_f1_resident": 0.6984126984126984,
|
| 330 |
+
"eval_f1_transient": 0.5625,
|
| 331 |
+
"eval_f1_vessel": 0.46153846153846156,
|
| 332 |
+
"eval_f1_water": 0.46153846153846156,
|
| 333 |
+
"eval_loss": 1.371209979057312,
|
| 334 |
+
"eval_precision": 0.6543750000000002,
|
| 335 |
+
"eval_recall": 0.575,
|
| 336 |
+
"eval_runtime": 24.6292,
|
| 337 |
+
"eval_samples_per_second": 3.248,
|
| 338 |
+
"eval_steps_per_second": 0.406,
|
| 339 |
+
"step": 280
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.25,
|
| 343 |
+
"grad_norm": 21.662912368774414,
|
| 344 |
+
"learning_rate": 2.1291666666666668e-05,
|
| 345 |
+
"loss": 1.0008769035339355,
|
| 346 |
+
"step": 290
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 7.5,
|
| 350 |
+
"grad_norm": 23.016326904296875,
|
| 351 |
+
"learning_rate": 2.0875e-05,
|
| 352 |
+
"loss": 1.0207538604736328,
|
| 353 |
+
"step": 300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.75,
|
| 357 |
+
"grad_norm": 6.426280975341797,
|
| 358 |
+
"learning_rate": 2.0458333333333334e-05,
|
| 359 |
+
"loss": 0.9328726768493653,
|
| 360 |
+
"step": 310
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 8.0,
|
| 364 |
+
"grad_norm": 21.511892318725586,
|
| 365 |
+
"learning_rate": 2.0041666666666665e-05,
|
| 366 |
+
"loss": 1.0631596565246582,
|
| 367 |
+
"step": 320
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 8.0,
|
| 371 |
+
"eval_accuracy": 0.5625,
|
| 372 |
+
"eval_f1": 0.6611394557823129,
|
| 373 |
+
"eval_f1_human": 0.5333333333333333,
|
| 374 |
+
"eval_f1_humpback": 0.6875,
|
| 375 |
+
"eval_f1_jingle": 0.42857142857142855,
|
| 376 |
+
"eval_f1_resident": 0.6530612244897959,
|
| 377 |
+
"eval_f1_transient": 0.6428571428571429,
|
| 378 |
+
"eval_f1_vessel": 0.16666666666666666,
|
| 379 |
+
"eval_f1_water": 0.2,
|
| 380 |
+
"eval_loss": 1.2977354526519775,
|
| 381 |
+
"eval_precision": 0.5583218864468865,
|
| 382 |
+
"eval_recall": 0.5625,
|
| 383 |
+
"eval_runtime": 24.5826,
|
| 384 |
+
"eval_samples_per_second": 3.254,
|
| 385 |
+
"eval_steps_per_second": 0.407,
|
| 386 |
+
"step": 320
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.25,
|
| 390 |
+
"grad_norm": 23.638885498046875,
|
| 391 |
+
"learning_rate": 1.9625e-05,
|
| 392 |
+
"loss": 0.945561695098877,
|
| 393 |
+
"step": 330
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.5,
|
| 397 |
+
"grad_norm": 21.955652236938477,
|
| 398 |
+
"learning_rate": 1.9208333333333334e-05,
|
| 399 |
+
"loss": 0.8307452201843262,
|
| 400 |
+
"step": 340
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 8.75,
|
| 404 |
+
"grad_norm": 37.24247360229492,
|
| 405 |
+
"learning_rate": 1.8791666666666668e-05,
|
| 406 |
+
"loss": 0.8966250419616699,
|
| 407 |
+
"step": 350
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 9.0,
|
| 411 |
+
"grad_norm": 34.65521240234375,
|
| 412 |
+
"learning_rate": 1.8375000000000003e-05,
|
| 413 |
+
"loss": 1.0554585456848145,
|
| 414 |
+
"step": 360
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.0,
|
| 418 |
+
"eval_accuracy": 0.5875,
|
| 419 |
+
"eval_f1": 0.5537155434440834,
|
| 420 |
+
"eval_f1_human": 0.5333333333333333,
|
| 421 |
+
"eval_f1_humpback": 0.42857142857142855,
|
| 422 |
+
"eval_f1_jingle": 0.6666666666666666,
|
| 423 |
+
"eval_f1_resident": 0.6808510638297872,
|
| 424 |
+
"eval_f1_transient": 0.5517241379310345,
|
| 425 |
+
"eval_f1_vessel": 0.47058823529411764,
|
| 426 |
+
"eval_f1_water": 0.6086956521739131,
|
| 427 |
+
"eval_loss": 1.3107037544250488,
|
| 428 |
+
"eval_precision": 0.6475376400560224,
|
| 429 |
+
"eval_recall": 0.5875,
|
| 430 |
+
"eval_runtime": 24.6061,
|
| 431 |
+
"eval_samples_per_second": 3.251,
|
| 432 |
+
"eval_steps_per_second": 0.406,
|
| 433 |
+
"step": 360
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 9.25,
|
| 437 |
+
"grad_norm": 3.1358461380004883,
|
| 438 |
+
"learning_rate": 1.7958333333333334e-05,
|
| 439 |
+
"loss": 0.9766130447387695,
|
| 440 |
+
"step": 370
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.5,
|
| 444 |
+
"grad_norm": 16.83808135986328,
|
| 445 |
+
"learning_rate": 1.754166666666667e-05,
|
| 446 |
+
"loss": 0.7928431987762451,
|
| 447 |
+
"step": 380
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.75,
|
| 451 |
+
"grad_norm": 19.454648971557617,
|
| 452 |
+
"learning_rate": 1.7125e-05,
|
| 453 |
+
"loss": 0.8157154083251953,
|
| 454 |
+
"step": 390
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 10.0,
|
| 458 |
+
"grad_norm": 48.8062858581543,
|
| 459 |
+
"learning_rate": 1.6708333333333334e-05,
|
| 460 |
+
"loss": 0.6693048477172852,
|
| 461 |
+
"step": 400
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 10.0,
|
| 465 |
+
"eval_accuracy": 0.6125,
|
| 466 |
+
"eval_f1": 0.6450635386119258,
|
| 467 |
+
"eval_f1_human": 0.5882352941176471,
|
| 468 |
+
"eval_f1_humpback": 0.7,
|
| 469 |
+
"eval_f1_jingle": 0.5454545454545454,
|
| 470 |
+
"eval_f1_resident": 0.6545454545454545,
|
| 471 |
+
"eval_f1_transient": 0.5806451612903226,
|
| 472 |
+
"eval_f1_vessel": 0.46153846153846156,
|
| 473 |
+
"eval_f1_water": 0.6153846153846154,
|
| 474 |
+
"eval_loss": 1.231101393699646,
|
| 475 |
+
"eval_precision": 0.6806533260233918,
|
| 476 |
+
"eval_recall": 0.6125,
|
| 477 |
+
"eval_runtime": 24.5768,
|
| 478 |
+
"eval_samples_per_second": 3.255,
|
| 479 |
+
"eval_steps_per_second": 0.407,
|
| 480 |
+
"step": 400
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 10.25,
|
| 484 |
+
"grad_norm": 23.585220336914062,
|
| 485 |
+
"learning_rate": 1.6291666666666665e-05,
|
| 486 |
+
"loss": 0.8009570121765137,
|
| 487 |
+
"step": 410
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 10.5,
|
| 491 |
+
"grad_norm": 52.430931091308594,
|
| 492 |
+
"learning_rate": 1.5875e-05,
|
| 493 |
+
"loss": 0.6774312019348144,
|
| 494 |
+
"step": 420
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 10.75,
|
| 498 |
+
"grad_norm": 12.286913871765137,
|
| 499 |
+
"learning_rate": 1.545833333333333e-05,
|
| 500 |
+
"loss": 0.6904989719390869,
|
| 501 |
+
"step": 430
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 11.0,
|
| 505 |
+
"grad_norm": 2.2310545444488525,
|
| 506 |
+
"learning_rate": 1.5041666666666667e-05,
|
| 507 |
+
"loss": 0.6417029857635498,
|
| 508 |
+
"step": 440
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 11.0,
|
| 512 |
+
"eval_accuracy": 0.675,
|
| 513 |
+
"eval_f1": 0.7315462315462314,
|
| 514 |
+
"eval_f1_human": 0.6666666666666666,
|
| 515 |
+
"eval_f1_humpback": 0.8461538461538461,
|
| 516 |
+
"eval_f1_jingle": 0.6,
|
| 517 |
+
"eval_f1_resident": 0.6818181818181818,
|
| 518 |
+
"eval_f1_transient": 0.6666666666666666,
|
| 519 |
+
"eval_f1_vessel": 0.5833333333333334,
|
| 520 |
+
"eval_f1_water": 0.5454545454545454,
|
| 521 |
+
"eval_loss": 1.1498925685882568,
|
| 522 |
+
"eval_precision": 0.7211904761904762,
|
| 523 |
+
"eval_recall": 0.675,
|
| 524 |
+
"eval_runtime": 24.6377,
|
| 525 |
+
"eval_samples_per_second": 3.247,
|
| 526 |
+
"eval_steps_per_second": 0.406,
|
| 527 |
+
"step": 440
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 11.25,
|
| 531 |
+
"grad_norm": 20.12211799621582,
|
| 532 |
+
"learning_rate": 1.4625e-05,
|
| 533 |
+
"loss": 0.5296733379364014,
|
| 534 |
+
"step": 450
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 11.5,
|
| 538 |
+
"grad_norm": 8.15372085571289,
|
| 539 |
+
"learning_rate": 1.4208333333333333e-05,
|
| 540 |
+
"loss": 0.5555210590362549,
|
| 541 |
+
"step": 460
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 11.75,
|
| 545 |
+
"grad_norm": 2.4559547901153564,
|
| 546 |
+
"learning_rate": 1.3791666666666667e-05,
|
| 547 |
+
"loss": 0.5045695304870605,
|
| 548 |
+
"step": 470
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 12.0,
|
| 552 |
+
"grad_norm": 3.179777145385742,
|
| 553 |
+
"learning_rate": 1.3375000000000002e-05,
|
| 554 |
+
"loss": 0.5730883598327636,
|
| 555 |
+
"step": 480
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 12.0,
|
| 559 |
+
"eval_accuracy": 0.7125,
|
| 560 |
+
"eval_f1": 0.7511142387989679,
|
| 561 |
+
"eval_f1_human": 0.75,
|
| 562 |
+
"eval_f1_humpback": 0.8571428571428571,
|
| 563 |
+
"eval_f1_jingle": 0.6,
|
| 564 |
+
"eval_f1_resident": 0.7755102040816326,
|
| 565 |
+
"eval_f1_transient": 0.6206896551724138,
|
| 566 |
+
"eval_f1_vessel": 0.5,
|
| 567 |
+
"eval_f1_water": 0.7368421052631579,
|
| 568 |
+
"eval_loss": 1.0407167673110962,
|
| 569 |
+
"eval_precision": 0.7441561869503046,
|
| 570 |
+
"eval_recall": 0.7125,
|
| 571 |
+
"eval_runtime": 24.5853,
|
| 572 |
+
"eval_samples_per_second": 3.254,
|
| 573 |
+
"eval_steps_per_second": 0.407,
|
| 574 |
+
"step": 480
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 12.25,
|
| 578 |
+
"grad_norm": 29.25799560546875,
|
| 579 |
+
"learning_rate": 1.2958333333333334e-05,
|
| 580 |
+
"loss": 0.44350547790527345,
|
| 581 |
+
"step": 490
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 12.5,
|
| 585 |
+
"grad_norm": 1.266361117362976,
|
| 586 |
+
"learning_rate": 1.2541666666666667e-05,
|
| 587 |
+
"loss": 0.4634674549102783,
|
| 588 |
+
"step": 500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 12.75,
|
| 592 |
+
"grad_norm": 29.000402450561523,
|
| 593 |
+
"learning_rate": 1.2125e-05,
|
| 594 |
+
"loss": 0.48257694244384763,
|
| 595 |
+
"step": 510
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 13.0,
|
| 599 |
+
"grad_norm": 19.07715606689453,
|
| 600 |
+
"learning_rate": 1.1708333333333334e-05,
|
| 601 |
+
"loss": 0.44806995391845705,
|
| 602 |
+
"step": 520
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 13.0,
|
| 606 |
+
"eval_accuracy": 0.6375,
|
| 607 |
+
"eval_f1": 0.5983333333333333,
|
| 608 |
+
"eval_f1_human": 0.8,
|
| 609 |
+
"eval_f1_humpback": 0.625,
|
| 610 |
+
"eval_f1_jingle": 0.7272727272727273,
|
| 611 |
+
"eval_f1_resident": 0.72,
|
| 612 |
+
"eval_f1_transient": 0.45,
|
| 613 |
+
"eval_f1_vessel": 0.625,
|
| 614 |
+
"eval_f1_water": 0.6666666666666666,
|
| 615 |
+
"eval_loss": 1.2673215866088867,
|
| 616 |
+
"eval_precision": 0.781547619047619,
|
| 617 |
+
"eval_recall": 0.6375,
|
| 618 |
+
"eval_runtime": 24.6097,
|
| 619 |
+
"eval_samples_per_second": 3.251,
|
| 620 |
+
"eval_steps_per_second": 0.406,
|
| 621 |
+
"step": 520
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 13.25,
|
| 625 |
+
"grad_norm": 1.2666140794754028,
|
| 626 |
+
"learning_rate": 1.1291666666666667e-05,
|
| 627 |
+
"loss": 0.40395755767822267,
|
| 628 |
+
"step": 530
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 13.5,
|
| 632 |
+
"grad_norm": 1.897343397140503,
|
| 633 |
+
"learning_rate": 1.0875e-05,
|
| 634 |
+
"loss": 0.36233084201812743,
|
| 635 |
+
"step": 540
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 13.75,
|
| 639 |
+
"grad_norm": 9.512198448181152,
|
| 640 |
+
"learning_rate": 1.0458333333333333e-05,
|
| 641 |
+
"loss": 0.4046651840209961,
|
| 642 |
+
"step": 550
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 14.0,
|
| 646 |
+
"grad_norm": 1.0725066661834717,
|
| 647 |
+
"learning_rate": 1.0041666666666666e-05,
|
| 648 |
+
"loss": 0.443222713470459,
|
| 649 |
+
"step": 560
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 14.0,
|
| 653 |
+
"eval_accuracy": 0.6875,
|
| 654 |
+
"eval_f1": 0.7554737695714554,
|
| 655 |
+
"eval_f1_human": 0.7058823529411765,
|
| 656 |
+
"eval_f1_humpback": 0.9565217391304348,
|
| 657 |
+
"eval_f1_jingle": 0.6,
|
| 658 |
+
"eval_f1_resident": 0.7804878048780488,
|
| 659 |
+
"eval_f1_transient": 0.5294117647058824,
|
| 660 |
+
"eval_f1_vessel": 0.47619047619047616,
|
| 661 |
+
"eval_f1_water": 0.7142857142857143,
|
| 662 |
+
"eval_loss": 1.0391490459442139,
|
| 663 |
+
"eval_precision": 0.7549873737373737,
|
| 664 |
+
"eval_recall": 0.6875,
|
| 665 |
+
"eval_runtime": 24.598,
|
| 666 |
+
"eval_samples_per_second": 3.252,
|
| 667 |
+
"eval_steps_per_second": 0.407,
|
| 668 |
+
"step": 560
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 14.25,
|
| 672 |
+
"grad_norm": 1.366147756576538,
|
| 673 |
+
"learning_rate": 9.625000000000002e-06,
|
| 674 |
+
"loss": 0.3922883987426758,
|
| 675 |
+
"step": 570
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 14.5,
|
| 679 |
+
"grad_norm": 3.1276583671569824,
|
| 680 |
+
"learning_rate": 9.208333333333335e-06,
|
| 681 |
+
"loss": 0.2765415906906128,
|
| 682 |
+
"step": 580
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 14.75,
|
| 686 |
+
"grad_norm": 29.363941192626953,
|
| 687 |
+
"learning_rate": 8.791666666666667e-06,
|
| 688 |
+
"loss": 0.28803434371948244,
|
| 689 |
+
"step": 590
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 15.0,
|
| 693 |
+
"grad_norm": 1.404604434967041,
|
| 694 |
+
"learning_rate": 8.375e-06,
|
| 695 |
+
"loss": 0.22552995681762694,
|
| 696 |
+
"step": 600
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 15.0,
|
| 700 |
+
"eval_accuracy": 0.7,
|
| 701 |
+
"eval_f1": 0.7393939393939394,
|
| 702 |
+
"eval_f1_human": 0.75,
|
| 703 |
+
"eval_f1_humpback": 0.8181818181818182,
|
| 704 |
+
"eval_f1_jingle": 0.5454545454545454,
|
| 705 |
+
"eval_f1_resident": 0.8,
|
| 706 |
+
"eval_f1_transient": 0.6,
|
| 707 |
+
"eval_f1_vessel": 0.5,
|
| 708 |
+
"eval_f1_water": 0.75,
|
| 709 |
+
"eval_loss": 0.9604784250259399,
|
| 710 |
+
"eval_precision": 0.7222808441558441,
|
| 711 |
+
"eval_recall": 0.7,
|
| 712 |
+
"eval_runtime": 24.6142,
|
| 713 |
+
"eval_samples_per_second": 3.25,
|
| 714 |
+
"eval_steps_per_second": 0.406,
|
| 715 |
+
"step": 600
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 15.25,
|
| 719 |
+
"grad_norm": 2.0040385723114014,
|
| 720 |
+
"learning_rate": 7.958333333333333e-06,
|
| 721 |
+
"loss": 0.3015956163406372,
|
| 722 |
+
"step": 610
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 15.5,
|
| 726 |
+
"grad_norm": 0.7820137739181519,
|
| 727 |
+
"learning_rate": 7.541666666666667e-06,
|
| 728 |
+
"loss": 0.2632955312728882,
|
| 729 |
+
"step": 620
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 15.75,
|
| 733 |
+
"grad_norm": 2.9510080814361572,
|
| 734 |
+
"learning_rate": 7.1249999999999995e-06,
|
| 735 |
+
"loss": 0.2560471296310425,
|
| 736 |
+
"step": 630
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 16.0,
|
| 740 |
+
"grad_norm": 0.9953803420066833,
|
| 741 |
+
"learning_rate": 6.708333333333334e-06,
|
| 742 |
+
"loss": 0.17468478679656982,
|
| 743 |
+
"step": 640
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 16.0,
|
| 747 |
+
"eval_accuracy": 0.6625,
|
| 748 |
+
"eval_f1": 0.7507989907485282,
|
| 749 |
+
"eval_f1_human": 0.7058823529411765,
|
| 750 |
+
"eval_f1_humpback": 0.9,
|
| 751 |
+
"eval_f1_jingle": 0.625,
|
| 752 |
+
"eval_f1_resident": 0.7317073170731707,
|
| 753 |
+
"eval_f1_transient": 0.6206896551724138,
|
| 754 |
+
"eval_f1_vessel": 0.5384615384615384,
|
| 755 |
+
"eval_f1_water": 0.36363636363636365,
|
| 756 |
+
"eval_loss": 1.155379056930542,
|
| 757 |
+
"eval_precision": 0.7108353758169935,
|
| 758 |
+
"eval_recall": 0.6625,
|
| 759 |
+
"eval_runtime": 24.5906,
|
| 760 |
+
"eval_samples_per_second": 3.253,
|
| 761 |
+
"eval_steps_per_second": 0.407,
|
| 762 |
+
"step": 640
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 16.25,
|
| 766 |
+
"grad_norm": 2.6758124828338623,
|
| 767 |
+
"learning_rate": 6.291666666666667e-06,
|
| 768 |
+
"loss": 0.23684515953063964,
|
| 769 |
+
"step": 650
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 16.5,
|
| 773 |
+
"grad_norm": 25.291175842285156,
|
| 774 |
+
"learning_rate": 5.8750000000000005e-06,
|
| 775 |
+
"loss": 0.21341469287872314,
|
| 776 |
+
"step": 660
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 16.75,
|
| 780 |
+
"grad_norm": 2.370605230331421,
|
| 781 |
+
"learning_rate": 5.458333333333333e-06,
|
| 782 |
+
"loss": 0.22325022220611573,
|
| 783 |
+
"step": 670
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 17.0,
|
| 787 |
+
"grad_norm": 10.337233543395996,
|
| 788 |
+
"learning_rate": 5.041666666666667e-06,
|
| 789 |
+
"loss": 0.1329780101776123,
|
| 790 |
+
"step": 680
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 17.0,
|
| 794 |
+
"eval_accuracy": 0.7375,
|
| 795 |
+
"eval_f1": 0.7774170274170275,
|
| 796 |
+
"eval_f1_human": 0.75,
|
| 797 |
+
"eval_f1_humpback": 0.9166666666666666,
|
| 798 |
+
"eval_f1_jingle": 0.7272727272727273,
|
| 799 |
+
"eval_f1_resident": 0.7727272727272727,
|
| 800 |
+
"eval_f1_transient": 0.6428571428571429,
|
| 801 |
+
"eval_f1_vessel": 0.5714285714285714,
|
| 802 |
+
"eval_f1_water": 0.75,
|
| 803 |
+
"eval_loss": 1.025275468826294,
|
| 804 |
+
"eval_precision": 0.7605696386946387,
|
| 805 |
+
"eval_recall": 0.7375,
|
| 806 |
+
"eval_runtime": 24.6098,
|
| 807 |
+
"eval_samples_per_second": 3.251,
|
| 808 |
+
"eval_steps_per_second": 0.406,
|
| 809 |
+
"step": 680
|
| 810 |
+
}
|
| 811 |
+
],
|
| 812 |
+
"logging_steps": 10,
|
| 813 |
+
"max_steps": 800,
|
| 814 |
+
"num_input_tokens_seen": 0,
|
| 815 |
+
"num_train_epochs": 20,
|
| 816 |
+
"save_steps": 500,
|
| 817 |
+
"stateful_callbacks": {
|
| 818 |
+
"TrainerControl": {
|
| 819 |
+
"args": {
|
| 820 |
+
"should_epoch_stop": false,
|
| 821 |
+
"should_evaluate": false,
|
| 822 |
+
"should_log": false,
|
| 823 |
+
"should_save": true,
|
| 824 |
+
"should_training_stop": false
|
| 825 |
+
},
|
| 826 |
+
"attributes": {}
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"total_flos": 1.46776248252e+17,
|
| 830 |
+
"train_batch_size": 8,
|
| 831 |
+
"trial_name": null,
|
| 832 |
+
"trial_params": null
|
| 833 |
+
}
|
checkpoint-680/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eacba371db8e703397a0ed872eaf7f526989f7fa3a293cf644b4fa8d0bead78
|
| 3 |
+
size 5329
|