Upload 11 files
Browse files- config.json +196 -0
- merges.txt +0 -0
- preprocessor_config.json +43 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +79 -0
- trainer_state.json +1239 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 128,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"has_relative_attention_bias": true,
|
| 12 |
+
"has_spatial_attention_bias": true,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "others",
|
| 18 |
+
"1": "bol_nr",
|
| 19 |
+
"2": "shipper_name",
|
| 20 |
+
"3": "bol_date",
|
| 21 |
+
"4": "shipper_address",
|
| 22 |
+
"5": "shipper_state",
|
| 23 |
+
"6": "shipper_city",
|
| 24 |
+
"7": "shipper_zipcode",
|
| 25 |
+
"8": "shipper_tel",
|
| 26 |
+
"9": "shipper_fax",
|
| 27 |
+
"10": "shipper_email",
|
| 28 |
+
"11": "shipper_sid",
|
| 29 |
+
"12": "consignee_name",
|
| 30 |
+
"13": "consignee_address",
|
| 31 |
+
"14": "consignee_state",
|
| 32 |
+
"15": "consignee_city",
|
| 33 |
+
"16": "consignee_zipcode",
|
| 34 |
+
"17": "consignee_tel",
|
| 35 |
+
"18": "consignee_fax",
|
| 36 |
+
"19": "precarrier",
|
| 37 |
+
"20": "consignee_cid",
|
| 38 |
+
"21": "notify_name",
|
| 39 |
+
"22": "notify_address",
|
| 40 |
+
"23": "customs_value",
|
| 41 |
+
"24": "notify_state",
|
| 42 |
+
"25": "notify_city",
|
| 43 |
+
"26": "notify_zipcode",
|
| 44 |
+
"27": "detail_qty",
|
| 45 |
+
"28": "container_flag",
|
| 46 |
+
"29": "notify_fax",
|
| 47 |
+
"30": "notify_email",
|
| 48 |
+
"31": "order_nr",
|
| 49 |
+
"32": "tot_netweight",
|
| 50 |
+
"33": "tot_value",
|
| 51 |
+
"34": "tot_volume",
|
| 52 |
+
"35": "shipper_extra",
|
| 53 |
+
"36": "prepaid_flag",
|
| 54 |
+
"37": "carrier_name",
|
| 55 |
+
"38": "trailer_nr",
|
| 56 |
+
"39": "scac_code",
|
| 57 |
+
"40": "po_nr",
|
| 58 |
+
"41": "pro_nr",
|
| 59 |
+
"42": "detail_main_qty",
|
| 60 |
+
"43": "detail_main_packtype",
|
| 61 |
+
"44": "detail_packtype",
|
| 62 |
+
"45": "detail_weight",
|
| 63 |
+
"46": "detail_hm",
|
| 64 |
+
"47": "detail_commodity",
|
| 65 |
+
"48": "detail_notes",
|
| 66 |
+
"49": "detail_class",
|
| 67 |
+
"50": "delivery_date",
|
| 68 |
+
"51": "pickup_date",
|
| 69 |
+
"52": "driver_name",
|
| 70 |
+
"53": "driver_license",
|
| 71 |
+
"54": "tracking_nr",
|
| 72 |
+
"55": "transport_type",
|
| 73 |
+
"56": "pickup_country",
|
| 74 |
+
"57": "reference_code",
|
| 75 |
+
"58": "pickup_place",
|
| 76 |
+
"59": "vessel",
|
| 77 |
+
"60": "voyage",
|
| 78 |
+
"61": "pickup_port",
|
| 79 |
+
"62": "delivery_port",
|
| 80 |
+
"63": "export_code",
|
| 81 |
+
"64": "delivery_place",
|
| 82 |
+
"65": "delivery_terminal",
|
| 83 |
+
"66": "carrier_sign_date",
|
| 84 |
+
"67": "booking_nr",
|
| 85 |
+
"68": "container_id",
|
| 86 |
+
"69": "container_type",
|
| 87 |
+
"70": "consignee_email",
|
| 88 |
+
"71": "notify_tel",
|
| 89 |
+
"72": "tot_qty",
|
| 90 |
+
"73": "tot_grossweight",
|
| 91 |
+
"74": "shipper_sign_date",
|
| 92 |
+
"75": "detail_volume"
|
| 93 |
+
},
|
| 94 |
+
"initializer_range": 0.02,
|
| 95 |
+
"input_size": 224,
|
| 96 |
+
"intermediate_size": 3072,
|
| 97 |
+
"label2id": {
|
| 98 |
+
"bol_date": 3,
|
| 99 |
+
"bol_nr": 1,
|
| 100 |
+
"booking_nr": 67,
|
| 101 |
+
"carrier_name": 37,
|
| 102 |
+
"carrier_sign_date": 66,
|
| 103 |
+
"consignee_address": 13,
|
| 104 |
+
"consignee_cid": 20,
|
| 105 |
+
"consignee_city": 15,
|
| 106 |
+
"consignee_email": 70,
|
| 107 |
+
"consignee_fax": 18,
|
| 108 |
+
"consignee_name": 12,
|
| 109 |
+
"consignee_state": 14,
|
| 110 |
+
"consignee_tel": 17,
|
| 111 |
+
"consignee_zipcode": 16,
|
| 112 |
+
"container_flag": 28,
|
| 113 |
+
"container_id": 68,
|
| 114 |
+
"container_type": 69,
|
| 115 |
+
"customs_value": 23,
|
| 116 |
+
"delivery_date": 50,
|
| 117 |
+
"delivery_place": 64,
|
| 118 |
+
"delivery_port": 62,
|
| 119 |
+
"delivery_terminal": 65,
|
| 120 |
+
"detail_class": 49,
|
| 121 |
+
"detail_commodity": 47,
|
| 122 |
+
"detail_hm": 46,
|
| 123 |
+
"detail_main_packtype": 43,
|
| 124 |
+
"detail_main_qty": 42,
|
| 125 |
+
"detail_notes": 48,
|
| 126 |
+
"detail_packtype": 44,
|
| 127 |
+
"detail_qty": 27,
|
| 128 |
+
"detail_volume": 75,
|
| 129 |
+
"detail_weight": 45,
|
| 130 |
+
"driver_license": 53,
|
| 131 |
+
"driver_name": 52,
|
| 132 |
+
"export_code": 63,
|
| 133 |
+
"notify_address": 22,
|
| 134 |
+
"notify_city": 25,
|
| 135 |
+
"notify_email": 30,
|
| 136 |
+
"notify_fax": 29,
|
| 137 |
+
"notify_name": 21,
|
| 138 |
+
"notify_state": 24,
|
| 139 |
+
"notify_tel": 71,
|
| 140 |
+
"notify_zipcode": 26,
|
| 141 |
+
"order_nr": 31,
|
| 142 |
+
"others": 0,
|
| 143 |
+
"pickup_country": 56,
|
| 144 |
+
"pickup_date": 51,
|
| 145 |
+
"pickup_place": 58,
|
| 146 |
+
"pickup_port": 61,
|
| 147 |
+
"po_nr": 40,
|
| 148 |
+
"precarrier": 19,
|
| 149 |
+
"prepaid_flag": 36,
|
| 150 |
+
"pro_nr": 41,
|
| 151 |
+
"reference_code": 57,
|
| 152 |
+
"scac_code": 39,
|
| 153 |
+
"shipper_address": 4,
|
| 154 |
+
"shipper_city": 6,
|
| 155 |
+
"shipper_email": 10,
|
| 156 |
+
"shipper_extra": 35,
|
| 157 |
+
"shipper_fax": 9,
|
| 158 |
+
"shipper_name": 2,
|
| 159 |
+
"shipper_sid": 11,
|
| 160 |
+
"shipper_sign_date": 74,
|
| 161 |
+
"shipper_state": 5,
|
| 162 |
+
"shipper_tel": 8,
|
| 163 |
+
"shipper_zipcode": 7,
|
| 164 |
+
"tot_grossweight": 73,
|
| 165 |
+
"tot_netweight": 32,
|
| 166 |
+
"tot_qty": 72,
|
| 167 |
+
"tot_value": 33,
|
| 168 |
+
"tot_volume": 34,
|
| 169 |
+
"tracking_nr": 54,
|
| 170 |
+
"trailer_nr": 38,
|
| 171 |
+
"transport_type": 55,
|
| 172 |
+
"vessel": 59,
|
| 173 |
+
"voyage": 60
|
| 174 |
+
},
|
| 175 |
+
"layer_norm_eps": 1e-05,
|
| 176 |
+
"max_2d_position_embeddings": 1024,
|
| 177 |
+
"max_position_embeddings": 514,
|
| 178 |
+
"max_rel_2d_pos": 256,
|
| 179 |
+
"max_rel_pos": 128,
|
| 180 |
+
"model_type": "layoutlmv3",
|
| 181 |
+
"num_attention_heads": 12,
|
| 182 |
+
"num_channels": 3,
|
| 183 |
+
"num_hidden_layers": 12,
|
| 184 |
+
"pad_token_id": 1,
|
| 185 |
+
"patch_size": 16,
|
| 186 |
+
"rel_2d_pos_bins": 64,
|
| 187 |
+
"rel_pos_bins": 32,
|
| 188 |
+
"second_input_size": 112,
|
| 189 |
+
"shape_size": 128,
|
| 190 |
+
"text_embed": true,
|
| 191 |
+
"torch_dtype": "float32",
|
| 192 |
+
"transformers_version": "4.41.2",
|
| 193 |
+
"type_vocab_size": 1,
|
| 194 |
+
"visual_embed": true,
|
| 195 |
+
"vocab_size": 50265
|
| 196 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"apply_ocr",
|
| 13 |
+
"ocr_lang",
|
| 14 |
+
"tesseract_config",
|
| 15 |
+
"return_tensors",
|
| 16 |
+
"data_format",
|
| 17 |
+
"input_data_format"
|
| 18 |
+
],
|
| 19 |
+
"apply_ocr": false,
|
| 20 |
+
"do_normalize": true,
|
| 21 |
+
"do_rescale": true,
|
| 22 |
+
"do_resize": true,
|
| 23 |
+
"image_mean": [
|
| 24 |
+
0.5,
|
| 25 |
+
0.5,
|
| 26 |
+
0.5
|
| 27 |
+
],
|
| 28 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
| 29 |
+
"image_std": [
|
| 30 |
+
0.5,
|
| 31 |
+
0.5,
|
| 32 |
+
0.5
|
| 33 |
+
],
|
| 34 |
+
"ocr_lang": null,
|
| 35 |
+
"processor_class": "LayoutLMv3Processor",
|
| 36 |
+
"resample": 2,
|
| 37 |
+
"rescale_factor": 0.00392156862745098,
|
| 38 |
+
"size": {
|
| 39 |
+
"height": 224,
|
| 40 |
+
"width": 224
|
| 41 |
+
},
|
| 42 |
+
"tesseract_config": ""
|
| 43 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98852d356d6b365738fcf421dc35a9e7c8f8300ac6de98effe84696317c1e7b1
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6ff39835f6fc0ab5432bbe426fb9e017df9b359be5fad96f2d6b3dde669dc72
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"apply_ocr": false,
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"clean_up_tokenization_spaces": true,
|
| 48 |
+
"cls_token": "<s>",
|
| 49 |
+
"cls_token_box": [
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
"eos_token": "</s>",
|
| 56 |
+
"errors": "replace",
|
| 57 |
+
"mask_token": "<mask>",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"only_label_first_subword": true,
|
| 60 |
+
"pad_token": "<pad>",
|
| 61 |
+
"pad_token_box": [
|
| 62 |
+
0,
|
| 63 |
+
0,
|
| 64 |
+
0,
|
| 65 |
+
0
|
| 66 |
+
],
|
| 67 |
+
"pad_token_label": -100,
|
| 68 |
+
"processor_class": "LayoutLMv3Processor",
|
| 69 |
+
"sep_token": "</s>",
|
| 70 |
+
"sep_token_box": [
|
| 71 |
+
0,
|
| 72 |
+
0,
|
| 73 |
+
0,
|
| 74 |
+
0
|
| 75 |
+
],
|
| 76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
| 77 |
+
"trim_offsets": true,
|
| 78 |
+
"unk_token": "<unk>"
|
| 79 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6820038701354548,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/Shareddrives/Data Science Team folder-open/datasets/Lesam/BOL/combined dataset AD-656 + AD-580 /model/Bol1.0/checkpoint-8500",
|
| 4 |
+
"epoch": 12.676056338028168,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14084507042253522,
|
| 13 |
+
"eval_accuracy": 0.9531156222418359,
|
| 14 |
+
"eval_f1": 0.09613869188337273,
|
| 15 |
+
"eval_loss": 0.42083606123924255,
|
| 16 |
+
"eval_precision": 0.5083333333333333,
|
| 17 |
+
"eval_recall": 0.05308964316797215,
|
| 18 |
+
"eval_runtime": 7.3353,
|
| 19 |
+
"eval_samples_per_second": 32.718,
|
| 20 |
+
"eval_steps_per_second": 16.359,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.28169014084507044,
|
| 25 |
+
"eval_accuracy": 0.9531391585760518,
|
| 26 |
+
"eval_f1": 0.09598741148701809,
|
| 27 |
+
"eval_loss": 0.31483981013298035,
|
| 28 |
+
"eval_precision": 0.5,
|
| 29 |
+
"eval_recall": 0.05308964316797215,
|
| 30 |
+
"eval_runtime": 7.317,
|
| 31 |
+
"eval_samples_per_second": 32.801,
|
| 32 |
+
"eval_steps_per_second": 16.4,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.4225352112676056,
|
| 37 |
+
"eval_accuracy": 0.9565754633715798,
|
| 38 |
+
"eval_f1": 0.12402044293015331,
|
| 39 |
+
"eval_loss": 0.28479117155075073,
|
| 40 |
+
"eval_precision": 0.2857142857142857,
|
| 41 |
+
"eval_recall": 0.07919930374238468,
|
| 42 |
+
"eval_runtime": 7.3928,
|
| 43 |
+
"eval_samples_per_second": 32.464,
|
| 44 |
+
"eval_steps_per_second": 16.232,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.5633802816901409,
|
| 49 |
+
"eval_accuracy": 0.9590820829655781,
|
| 50 |
+
"eval_f1": 0.15186615186615188,
|
| 51 |
+
"eval_loss": 0.2616308927536011,
|
| 52 |
+
"eval_precision": 0.291358024691358,
|
| 53 |
+
"eval_recall": 0.10269799825935597,
|
| 54 |
+
"eval_runtime": 7.21,
|
| 55 |
+
"eval_samples_per_second": 33.287,
|
| 56 |
+
"eval_steps_per_second": 16.643,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.704225352112676,
|
| 61 |
+
"grad_norm": 3.1437392234802246,
|
| 62 |
+
"learning_rate": 9.444444444444445e-06,
|
| 63 |
+
"loss": 0.4533,
|
| 64 |
+
"step": 500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.704225352112676,
|
| 68 |
+
"eval_accuracy": 0.9585525154457193,
|
| 69 |
+
"eval_f1": 0.1576517150395778,
|
| 70 |
+
"eval_loss": 0.24514709413051605,
|
| 71 |
+
"eval_precision": 0.32561307901907355,
|
| 72 |
+
"eval_recall": 0.10400348128807659,
|
| 73 |
+
"eval_runtime": 7.3357,
|
| 74 |
+
"eval_samples_per_second": 32.717,
|
| 75 |
+
"eval_steps_per_second": 16.358,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.8450704225352113,
|
| 80 |
+
"eval_accuracy": 0.9594586643130333,
|
| 81 |
+
"eval_f1": 0.15076717811874582,
|
| 82 |
+
"eval_loss": 0.23794828355312347,
|
| 83 |
+
"eval_precision": 0.32285714285714284,
|
| 84 |
+
"eval_recall": 0.09834638816362054,
|
| 85 |
+
"eval_runtime": 7.345,
|
| 86 |
+
"eval_samples_per_second": 32.675,
|
| 87 |
+
"eval_steps_per_second": 16.338,
|
| 88 |
+
"step": 600
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.9859154929577465,
|
| 92 |
+
"eval_accuracy": 0.9603059723448073,
|
| 93 |
+
"eval_f1": 0.17906683480453975,
|
| 94 |
+
"eval_loss": 0.21762977540493011,
|
| 95 |
+
"eval_precision": 0.32494279176201374,
|
| 96 |
+
"eval_recall": 0.12358572671888599,
|
| 97 |
+
"eval_runtime": 7.3679,
|
| 98 |
+
"eval_samples_per_second": 32.574,
|
| 99 |
+
"eval_steps_per_second": 16.287,
|
| 100 |
+
"step": 700
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.1267605633802817,
|
| 104 |
+
"eval_accuracy": 0.9655663430420712,
|
| 105 |
+
"eval_f1": 0.2692101020956475,
|
| 106 |
+
"eval_loss": 0.20588882267475128,
|
| 107 |
+
"eval_precision": 0.3518258426966292,
|
| 108 |
+
"eval_recall": 0.21801566579634465,
|
| 109 |
+
"eval_runtime": 7.173,
|
| 110 |
+
"eval_samples_per_second": 33.459,
|
| 111 |
+
"eval_steps_per_second": 16.729,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.267605633802817,
|
| 116 |
+
"eval_accuracy": 0.9650956163577523,
|
| 117 |
+
"eval_f1": 0.2747485442032822,
|
| 118 |
+
"eval_loss": 0.20205169916152954,
|
| 119 |
+
"eval_precision": 0.3506756756756757,
|
| 120 |
+
"eval_recall": 0.2258485639686684,
|
| 121 |
+
"eval_runtime": 7.327,
|
| 122 |
+
"eval_samples_per_second": 32.755,
|
| 123 |
+
"eval_steps_per_second": 16.378,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.408450704225352,
|
| 128 |
+
"grad_norm": 0.12497588992118835,
|
| 129 |
+
"learning_rate": 8.888888888888888e-06,
|
| 130 |
+
"loss": 0.2053,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.408450704225352,
|
| 135 |
+
"eval_accuracy": 0.9687437481612239,
|
| 136 |
+
"eval_f1": 0.29104679469840417,
|
| 137 |
+
"eval_loss": 0.17978309094905853,
|
| 138 |
+
"eval_precision": 0.38456040028591854,
|
| 139 |
+
"eval_recall": 0.23411662315056572,
|
| 140 |
+
"eval_runtime": 7.3218,
|
| 141 |
+
"eval_samples_per_second": 32.779,
|
| 142 |
+
"eval_steps_per_second": 16.389,
|
| 143 |
+
"step": 1000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.5492957746478875,
|
| 147 |
+
"eval_accuracy": 0.9712621359223301,
|
| 148 |
+
"eval_f1": 0.34724021767297225,
|
| 149 |
+
"eval_loss": 0.16675764322280884,
|
| 150 |
+
"eval_precision": 0.42921204356181936,
|
| 151 |
+
"eval_recall": 0.2915578764142733,
|
| 152 |
+
"eval_runtime": 7.3153,
|
| 153 |
+
"eval_samples_per_second": 32.808,
|
| 154 |
+
"eval_steps_per_second": 16.404,
|
| 155 |
+
"step": 1100
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.6901408450704225,
|
| 159 |
+
"eval_accuracy": 0.9708973227419829,
|
| 160 |
+
"eval_f1": 0.33114668066124375,
|
| 161 |
+
"eval_loss": 0.1615074723958969,
|
| 162 |
+
"eval_precision": 0.4170522141440846,
|
| 163 |
+
"eval_recall": 0.27458659704090516,
|
| 164 |
+
"eval_runtime": 7.4019,
|
| 165 |
+
"eval_samples_per_second": 32.424,
|
| 166 |
+
"eval_steps_per_second": 16.212,
|
| 167 |
+
"step": 1200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.8309859154929577,
|
| 171 |
+
"eval_accuracy": 0.9715563401000294,
|
| 172 |
+
"eval_f1": 0.37593984962406013,
|
| 173 |
+
"eval_loss": 0.1544044315814972,
|
| 174 |
+
"eval_precision": 0.4246575342465753,
|
| 175 |
+
"eval_recall": 0.3372497824194952,
|
| 176 |
+
"eval_runtime": 7.2284,
|
| 177 |
+
"eval_samples_per_second": 33.202,
|
| 178 |
+
"eval_steps_per_second": 16.601,
|
| 179 |
+
"step": 1300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.971830985915493,
|
| 183 |
+
"eval_accuracy": 0.9729685201529862,
|
| 184 |
+
"eval_f1": 0.354788877445932,
|
| 185 |
+
"eval_loss": 0.14469194412231445,
|
| 186 |
+
"eval_precision": 0.4344262295081967,
|
| 187 |
+
"eval_recall": 0.2998259355961706,
|
| 188 |
+
"eval_runtime": 7.2572,
|
| 189 |
+
"eval_samples_per_second": 33.07,
|
| 190 |
+
"eval_steps_per_second": 16.535,
|
| 191 |
+
"step": 1400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.112676056338028,
|
| 195 |
+
"grad_norm": 3.3000364303588867,
|
| 196 |
+
"learning_rate": 8.333333333333334e-06,
|
| 197 |
+
"loss": 0.1633,
|
| 198 |
+
"step": 1500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.112676056338028,
|
| 202 |
+
"eval_accuracy": 0.9744866137099146,
|
| 203 |
+
"eval_f1": 0.4306997742663657,
|
| 204 |
+
"eval_loss": 0.14256681501865387,
|
| 205 |
+
"eval_precision": 0.4474671669793621,
|
| 206 |
+
"eval_recall": 0.4151436031331593,
|
| 207 |
+
"eval_runtime": 7.3087,
|
| 208 |
+
"eval_samples_per_second": 32.838,
|
| 209 |
+
"eval_steps_per_second": 16.419,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.2535211267605635,
|
| 214 |
+
"eval_accuracy": 0.9750632538982054,
|
| 215 |
+
"eval_f1": 0.41274369947693773,
|
| 216 |
+
"eval_loss": 0.13538698852062225,
|
| 217 |
+
"eval_precision": 0.4549266247379455,
|
| 218 |
+
"eval_recall": 0.3777197563098346,
|
| 219 |
+
"eval_runtime": 7.3667,
|
| 220 |
+
"eval_samples_per_second": 32.579,
|
| 221 |
+
"eval_steps_per_second": 16.29,
|
| 222 |
+
"step": 1600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.3943661971830985,
|
| 226 |
+
"eval_accuracy": 0.9748631950573698,
|
| 227 |
+
"eval_f1": 0.4427480916030535,
|
| 228 |
+
"eval_loss": 0.1301625669002533,
|
| 229 |
+
"eval_precision": 0.45732838589981445,
|
| 230 |
+
"eval_recall": 0.4290687554395126,
|
| 231 |
+
"eval_runtime": 7.3457,
|
| 232 |
+
"eval_samples_per_second": 32.672,
|
| 233 |
+
"eval_steps_per_second": 16.336,
|
| 234 |
+
"step": 1700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.535211267605634,
|
| 238 |
+
"eval_accuracy": 0.9771226831421006,
|
| 239 |
+
"eval_f1": 0.4529600734281781,
|
| 240 |
+
"eval_loss": 0.12118236720561981,
|
| 241 |
+
"eval_precision": 0.479126213592233,
|
| 242 |
+
"eval_recall": 0.42950391644908614,
|
| 243 |
+
"eval_runtime": 7.3572,
|
| 244 |
+
"eval_samples_per_second": 32.621,
|
| 245 |
+
"eval_steps_per_second": 16.311,
|
| 246 |
+
"step": 1800
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.676056338028169,
|
| 250 |
+
"eval_accuracy": 0.9772285966460724,
|
| 251 |
+
"eval_f1": 0.4805283534502391,
|
| 252 |
+
"eval_loss": 0.12013120204210281,
|
| 253 |
+
"eval_precision": 0.5040611562350693,
|
| 254 |
+
"eval_recall": 0.459094865100087,
|
| 255 |
+
"eval_runtime": 7.2756,
|
| 256 |
+
"eval_samples_per_second": 32.987,
|
| 257 |
+
"eval_steps_per_second": 16.494,
|
| 258 |
+
"step": 1900
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.816901408450704,
|
| 262 |
+
"grad_norm": 4.632040500640869,
|
| 263 |
+
"learning_rate": 7.77777777777778e-06,
|
| 264 |
+
"loss": 0.116,
|
| 265 |
+
"step": 2000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.816901408450704,
|
| 269 |
+
"eval_accuracy": 0.9765695792880259,
|
| 270 |
+
"eval_f1": 0.46877098723975824,
|
| 271 |
+
"eval_loss": 0.12145345658063889,
|
| 272 |
+
"eval_precision": 0.4827109266943292,
|
| 273 |
+
"eval_recall": 0.4556135770234987,
|
| 274 |
+
"eval_runtime": 7.3168,
|
| 275 |
+
"eval_samples_per_second": 32.801,
|
| 276 |
+
"eval_steps_per_second": 16.401,
|
| 277 |
+
"step": 2000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.9577464788732395,
|
| 281 |
+
"eval_accuracy": 0.9755104442483084,
|
| 282 |
+
"eval_f1": 0.4675658317276814,
|
| 283 |
+
"eval_loss": 0.12608888745307922,
|
| 284 |
+
"eval_precision": 0.46017699115044247,
|
| 285 |
+
"eval_recall": 0.4751958224543081,
|
| 286 |
+
"eval_runtime": 7.3583,
|
| 287 |
+
"eval_samples_per_second": 32.616,
|
| 288 |
+
"eval_steps_per_second": 16.308,
|
| 289 |
+
"step": 2100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.0985915492957745,
|
| 293 |
+
"eval_accuracy": 0.9789938217122683,
|
| 294 |
+
"eval_f1": 0.4885803851321093,
|
| 295 |
+
"eval_loss": 0.11443355679512024,
|
| 296 |
+
"eval_precision": 0.5032287822878229,
|
| 297 |
+
"eval_recall": 0.47476066144473456,
|
| 298 |
+
"eval_runtime": 7.3495,
|
| 299 |
+
"eval_samples_per_second": 32.655,
|
| 300 |
+
"eval_steps_per_second": 16.328,
|
| 301 |
+
"step": 2200
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 3.23943661971831,
|
| 305 |
+
"eval_accuracy": 0.9794880847308032,
|
| 306 |
+
"eval_f1": 0.501056586053064,
|
| 307 |
+
"eval_loss": 0.10821868479251862,
|
| 308 |
+
"eval_precision": 0.5441101478837328,
|
| 309 |
+
"eval_recall": 0.46431679721496955,
|
| 310 |
+
"eval_runtime": 7.3804,
|
| 311 |
+
"eval_samples_per_second": 32.519,
|
| 312 |
+
"eval_steps_per_second": 16.259,
|
| 313 |
+
"step": 2300
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.380281690140845,
|
| 317 |
+
"eval_accuracy": 0.9779935275080907,
|
| 318 |
+
"eval_f1": 0.49851360621998636,
|
| 319 |
+
"eval_loss": 0.11080476641654968,
|
| 320 |
+
"eval_precision": 0.5253012048192771,
|
| 321 |
+
"eval_recall": 0.47432550043516103,
|
| 322 |
+
"eval_runtime": 7.2629,
|
| 323 |
+
"eval_samples_per_second": 33.045,
|
| 324 |
+
"eval_steps_per_second": 16.522,
|
| 325 |
+
"step": 2400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.52112676056338,
|
| 329 |
+
"grad_norm": 0.7869037985801697,
|
| 330 |
+
"learning_rate": 7.222222222222223e-06,
|
| 331 |
+
"loss": 0.0909,
|
| 332 |
+
"step": 2500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.52112676056338,
|
| 336 |
+
"eval_accuracy": 0.9786525448661371,
|
| 337 |
+
"eval_f1": 0.5188613746817866,
|
| 338 |
+
"eval_loss": 0.11673837155103683,
|
| 339 |
+
"eval_precision": 0.5541275333662877,
|
| 340 |
+
"eval_recall": 0.48781549173194083,
|
| 341 |
+
"eval_runtime": 7.2497,
|
| 342 |
+
"eval_samples_per_second": 33.105,
|
| 343 |
+
"eval_steps_per_second": 16.552,
|
| 344 |
+
"step": 2500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.6619718309859155,
|
| 348 |
+
"eval_accuracy": 0.979982347749338,
|
| 349 |
+
"eval_f1": 0.5242311276794035,
|
| 350 |
+
"eval_loss": 0.11096884310245514,
|
| 351 |
+
"eval_precision": 0.5641925777331996,
|
| 352 |
+
"eval_recall": 0.489556135770235,
|
| 353 |
+
"eval_runtime": 7.3912,
|
| 354 |
+
"eval_samples_per_second": 32.471,
|
| 355 |
+
"eval_steps_per_second": 16.236,
|
| 356 |
+
"step": 2600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.802816901408451,
|
| 360 |
+
"eval_accuracy": 0.9792644895557517,
|
| 361 |
+
"eval_f1": 0.5294117647058825,
|
| 362 |
+
"eval_loss": 0.10684900730848312,
|
| 363 |
+
"eval_precision": 0.5382194244604317,
|
| 364 |
+
"eval_recall": 0.52088772845953,
|
| 365 |
+
"eval_runtime": 7.4198,
|
| 366 |
+
"eval_samples_per_second": 32.346,
|
| 367 |
+
"eval_steps_per_second": 16.173,
|
| 368 |
+
"step": 2700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.943661971830986,
|
| 372 |
+
"eval_accuracy": 0.9792527213886437,
|
| 373 |
+
"eval_f1": 0.5260178532549532,
|
| 374 |
+
"eval_loss": 0.10498978942632675,
|
| 375 |
+
"eval_precision": 0.5263616557734205,
|
| 376 |
+
"eval_recall": 0.525674499564839,
|
| 377 |
+
"eval_runtime": 7.3935,
|
| 378 |
+
"eval_samples_per_second": 32.461,
|
| 379 |
+
"eval_steps_per_second": 16.23,
|
| 380 |
+
"step": 2800
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.084507042253521,
|
| 384 |
+
"eval_accuracy": 0.9806178287731686,
|
| 385 |
+
"eval_f1": 0.537687318273317,
|
| 386 |
+
"eval_loss": 0.10101501643657684,
|
| 387 |
+
"eval_precision": 0.55315232397607,
|
| 388 |
+
"eval_recall": 0.5230635335073978,
|
| 389 |
+
"eval_runtime": 7.3652,
|
| 390 |
+
"eval_samples_per_second": 32.586,
|
| 391 |
+
"eval_steps_per_second": 16.293,
|
| 392 |
+
"step": 2900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.225352112676056,
|
| 396 |
+
"grad_norm": 3.056248426437378,
|
| 397 |
+
"learning_rate": 6.666666666666667e-06,
|
| 398 |
+
"loss": 0.08,
|
| 399 |
+
"step": 3000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.225352112676056,
|
| 403 |
+
"eval_accuracy": 0.9793350985583995,
|
| 404 |
+
"eval_f1": 0.534056399132321,
|
| 405 |
+
"eval_loss": 0.1095050647854805,
|
| 406 |
+
"eval_precision": 0.532439446366782,
|
| 407 |
+
"eval_recall": 0.5356832027850305,
|
| 408 |
+
"eval_runtime": 7.3022,
|
| 409 |
+
"eval_samples_per_second": 32.867,
|
| 410 |
+
"eval_steps_per_second": 16.433,
|
| 411 |
+
"step": 3000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.366197183098592,
|
| 415 |
+
"eval_accuracy": 0.9807355104442483,
|
| 416 |
+
"eval_f1": 0.5566556655665567,
|
| 417 |
+
"eval_loss": 0.10490421205759048,
|
| 418 |
+
"eval_precision": 0.5629728526924789,
|
| 419 |
+
"eval_recall": 0.5504786771105309,
|
| 420 |
+
"eval_runtime": 7.3941,
|
| 421 |
+
"eval_samples_per_second": 32.458,
|
| 422 |
+
"eval_steps_per_second": 16.229,
|
| 423 |
+
"step": 3100
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.507042253521127,
|
| 427 |
+
"eval_accuracy": 0.9806884377758164,
|
| 428 |
+
"eval_f1": 0.5487348734873487,
|
| 429 |
+
"eval_loss": 0.0985017642378807,
|
| 430 |
+
"eval_precision": 0.5549621717846017,
|
| 431 |
+
"eval_recall": 0.5426457789382071,
|
| 432 |
+
"eval_runtime": 7.3897,
|
| 433 |
+
"eval_samples_per_second": 32.478,
|
| 434 |
+
"eval_steps_per_second": 16.239,
|
| 435 |
+
"step": 3200
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.647887323943662,
|
| 439 |
+
"eval_accuracy": 0.9803118564283613,
|
| 440 |
+
"eval_f1": 0.5325077399380805,
|
| 441 |
+
"eval_loss": 0.10188236087560654,
|
| 442 |
+
"eval_precision": 0.5413669064748201,
|
| 443 |
+
"eval_recall": 0.5239338555265448,
|
| 444 |
+
"eval_runtime": 7.3669,
|
| 445 |
+
"eval_samples_per_second": 32.578,
|
| 446 |
+
"eval_steps_per_second": 16.289,
|
| 447 |
+
"step": 3300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.788732394366197,
|
| 451 |
+
"eval_accuracy": 0.9811591644601353,
|
| 452 |
+
"eval_f1": 0.5600684053014109,
|
| 453 |
+
"eval_loss": 0.09488189220428467,
|
| 454 |
+
"eval_precision": 0.5504201680672269,
|
| 455 |
+
"eval_recall": 0.5700609225413403,
|
| 456 |
+
"eval_runtime": 7.3775,
|
| 457 |
+
"eval_samples_per_second": 32.531,
|
| 458 |
+
"eval_steps_per_second": 16.266,
|
| 459 |
+
"step": 3400
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.929577464788732,
|
| 463 |
+
"grad_norm": 0.00509398290887475,
|
| 464 |
+
"learning_rate": 6.111111111111112e-06,
|
| 465 |
+
"loss": 0.0671,
|
| 466 |
+
"step": 3500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 4.929577464788732,
|
| 470 |
+
"eval_accuracy": 0.9823477493380406,
|
| 471 |
+
"eval_f1": 0.5749396532806671,
|
| 472 |
+
"eval_loss": 0.09079114347696304,
|
| 473 |
+
"eval_precision": 0.5799026117751217,
|
| 474 |
+
"eval_recall": 0.5700609225413403,
|
| 475 |
+
"eval_runtime": 7.2549,
|
| 476 |
+
"eval_samples_per_second": 33.081,
|
| 477 |
+
"eval_steps_per_second": 16.54,
|
| 478 |
+
"step": 3500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 5.070422535211268,
|
| 482 |
+
"eval_accuracy": 0.9842188879082083,
|
| 483 |
+
"eval_f1": 0.5980850590069028,
|
| 484 |
+
"eval_loss": 0.08618247509002686,
|
| 485 |
+
"eval_precision": 0.6124031007751938,
|
| 486 |
+
"eval_recall": 0.5844212358572672,
|
| 487 |
+
"eval_runtime": 7.3833,
|
| 488 |
+
"eval_samples_per_second": 32.506,
|
| 489 |
+
"eval_steps_per_second": 16.253,
|
| 490 |
+
"step": 3600
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 5.211267605633803,
|
| 494 |
+
"eval_accuracy": 0.98177110914975,
|
| 495 |
+
"eval_f1": 0.5608871827681807,
|
| 496 |
+
"eval_loss": 0.09391660988330841,
|
| 497 |
+
"eval_precision": 0.5499790882475951,
|
| 498 |
+
"eval_recall": 0.572236727589208,
|
| 499 |
+
"eval_runtime": 7.376,
|
| 500 |
+
"eval_samples_per_second": 32.538,
|
| 501 |
+
"eval_steps_per_second": 16.269,
|
| 502 |
+
"step": 3700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.352112676056338,
|
| 506 |
+
"eval_accuracy": 0.9824889673433362,
|
| 507 |
+
"eval_f1": 0.5940507436570428,
|
| 508 |
+
"eval_loss": 0.09653446823358536,
|
| 509 |
+
"eval_precision": 0.5971855760773966,
|
| 510 |
+
"eval_recall": 0.5909486510008704,
|
| 511 |
+
"eval_runtime": 7.386,
|
| 512 |
+
"eval_samples_per_second": 32.494,
|
| 513 |
+
"eval_steps_per_second": 16.247,
|
| 514 |
+
"step": 3800
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 5.492957746478873,
|
| 518 |
+
"eval_accuracy": 0.9821006178287731,
|
| 519 |
+
"eval_f1": 0.5902280130293159,
|
| 520 |
+
"eval_loss": 0.09449278563261032,
|
| 521 |
+
"eval_precision": 0.5890767230169051,
|
| 522 |
+
"eval_recall": 0.5913838120104439,
|
| 523 |
+
"eval_runtime": 7.3734,
|
| 524 |
+
"eval_samples_per_second": 32.549,
|
| 525 |
+
"eval_steps_per_second": 16.275,
|
| 526 |
+
"step": 3900
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.633802816901408,
|
| 530 |
+
"grad_norm": 0.8984728455543518,
|
| 531 |
+
"learning_rate": 5.555555555555557e-06,
|
| 532 |
+
"loss": 0.059,
|
| 533 |
+
"step": 4000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.633802816901408,
|
| 537 |
+
"eval_accuracy": 0.982171226831421,
|
| 538 |
+
"eval_f1": 0.5924487594390507,
|
| 539 |
+
"eval_loss": 0.09081266820430756,
|
| 540 |
+
"eval_precision": 0.5875053487376979,
|
| 541 |
+
"eval_recall": 0.5974760661444735,
|
| 542 |
+
"eval_runtime": 7.3677,
|
| 543 |
+
"eval_samples_per_second": 32.575,
|
| 544 |
+
"eval_steps_per_second": 16.287,
|
| 545 |
+
"step": 4000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 5.774647887323944,
|
| 549 |
+
"eval_accuracy": 0.983030303030303,
|
| 550 |
+
"eval_f1": 0.5897771952817825,
|
| 551 |
+
"eval_loss": 0.08924023061990738,
|
| 552 |
+
"eval_precision": 0.5921052631578947,
|
| 553 |
+
"eval_recall": 0.587467362924282,
|
| 554 |
+
"eval_runtime": 7.278,
|
| 555 |
+
"eval_samples_per_second": 32.976,
|
| 556 |
+
"eval_steps_per_second": 16.488,
|
| 557 |
+
"step": 4100
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 5.915492957746479,
|
| 561 |
+
"eval_accuracy": 0.9837010885554575,
|
| 562 |
+
"eval_f1": 0.6034408602150538,
|
| 563 |
+
"eval_loss": 0.0901557207107544,
|
| 564 |
+
"eval_precision": 0.5965136054421769,
|
| 565 |
+
"eval_recall": 0.6105308964316797,
|
| 566 |
+
"eval_runtime": 7.4615,
|
| 567 |
+
"eval_samples_per_second": 32.165,
|
| 568 |
+
"eval_steps_per_second": 16.083,
|
| 569 |
+
"step": 4200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.056338028169014,
|
| 573 |
+
"eval_accuracy": 0.9843836422477199,
|
| 574 |
+
"eval_f1": 0.6253776435045316,
|
| 575 |
+
"eval_loss": 0.08598857372999191,
|
| 576 |
+
"eval_precision": 0.620291095890411,
|
| 577 |
+
"eval_recall": 0.6305483028720626,
|
| 578 |
+
"eval_runtime": 7.367,
|
| 579 |
+
"eval_samples_per_second": 32.578,
|
| 580 |
+
"eval_steps_per_second": 16.289,
|
| 581 |
+
"step": 4300
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.197183098591549,
|
| 585 |
+
"eval_accuracy": 0.9844307149161519,
|
| 586 |
+
"eval_f1": 0.6058235549760974,
|
| 587 |
+
"eval_loss": 0.08827093243598938,
|
| 588 |
+
"eval_precision": 0.6050347222222222,
|
| 589 |
+
"eval_recall": 0.6066144473455178,
|
| 590 |
+
"eval_runtime": 7.3941,
|
| 591 |
+
"eval_samples_per_second": 32.458,
|
| 592 |
+
"eval_steps_per_second": 16.229,
|
| 593 |
+
"step": 4400
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 6.338028169014084,
|
| 597 |
+
"grad_norm": 2.909140110015869,
|
| 598 |
+
"learning_rate": 5e-06,
|
| 599 |
+
"loss": 0.0516,
|
| 600 |
+
"step": 4500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 6.338028169014084,
|
| 604 |
+
"eval_accuracy": 0.9840894380700206,
|
| 605 |
+
"eval_f1": 0.5963083604777416,
|
| 606 |
+
"eval_loss": 0.09003057330846786,
|
| 607 |
+
"eval_precision": 0.5951452102297355,
|
| 608 |
+
"eval_recall": 0.5974760661444735,
|
| 609 |
+
"eval_runtime": 7.3583,
|
| 610 |
+
"eval_samples_per_second": 32.616,
|
| 611 |
+
"eval_steps_per_second": 16.308,
|
| 612 |
+
"step": 4500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 6.47887323943662,
|
| 616 |
+
"eval_accuracy": 0.9842541924095323,
|
| 617 |
+
"eval_f1": 0.5947252747252747,
|
| 618 |
+
"eval_loss": 0.08872821182012558,
|
| 619 |
+
"eval_precision": 0.6007992895204263,
|
| 620 |
+
"eval_recall": 0.5887728459530026,
|
| 621 |
+
"eval_runtime": 7.2679,
|
| 622 |
+
"eval_samples_per_second": 33.022,
|
| 623 |
+
"eval_steps_per_second": 16.511,
|
| 624 |
+
"step": 4600
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 6.619718309859155,
|
| 628 |
+
"eval_accuracy": 0.9841835834068844,
|
| 629 |
+
"eval_f1": 0.6222998036220816,
|
| 630 |
+
"eval_loss": 0.08372443169355392,
|
| 631 |
+
"eval_precision": 0.624070021881838,
|
| 632 |
+
"eval_recall": 0.6205395996518712,
|
| 633 |
+
"eval_runtime": 7.4046,
|
| 634 |
+
"eval_samples_per_second": 32.412,
|
| 635 |
+
"eval_steps_per_second": 16.206,
|
| 636 |
+
"step": 4700
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 6.76056338028169,
|
| 640 |
+
"eval_accuracy": 0.9844777875845837,
|
| 641 |
+
"eval_f1": 0.6397756686798964,
|
| 642 |
+
"eval_loss": 0.08945748209953308,
|
| 643 |
+
"eval_precision": 0.6343028229255774,
|
| 644 |
+
"eval_recall": 0.6453437771975631,
|
| 645 |
+
"eval_runtime": 7.3826,
|
| 646 |
+
"eval_samples_per_second": 32.509,
|
| 647 |
+
"eval_steps_per_second": 16.254,
|
| 648 |
+
"step": 4800
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 6.901408450704225,
|
| 652 |
+
"eval_accuracy": 0.9840541335686966,
|
| 653 |
+
"eval_f1": 0.6284970722186076,
|
| 654 |
+
"eval_loss": 0.08736680448055267,
|
| 655 |
+
"eval_precision": 0.6264591439688716,
|
| 656 |
+
"eval_recall": 0.6305483028720626,
|
| 657 |
+
"eval_runtime": 7.3836,
|
| 658 |
+
"eval_samples_per_second": 32.505,
|
| 659 |
+
"eval_steps_per_second": 16.252,
|
| 660 |
+
"step": 4900
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.042253521126761,
|
| 664 |
+
"grad_norm": 0.0029603431466966867,
|
| 665 |
+
"learning_rate": 4.444444444444444e-06,
|
| 666 |
+
"loss": 0.0494,
|
| 667 |
+
"step": 5000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.042253521126761,
|
| 671 |
+
"eval_accuracy": 0.9837481612238894,
|
| 672 |
+
"eval_f1": 0.6307495741056218,
|
| 673 |
+
"eval_loss": 0.08429873734712601,
|
| 674 |
+
"eval_precision": 0.6175979983319433,
|
| 675 |
+
"eval_recall": 0.644473455178416,
|
| 676 |
+
"eval_runtime": 7.4187,
|
| 677 |
+
"eval_samples_per_second": 32.351,
|
| 678 |
+
"eval_steps_per_second": 16.175,
|
| 679 |
+
"step": 5000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 7.183098591549296,
|
| 683 |
+
"eval_accuracy": 0.9844542512503678,
|
| 684 |
+
"eval_f1": 0.6298800436205015,
|
| 685 |
+
"eval_loss": 0.0860215276479721,
|
| 686 |
+
"eval_precision": 0.6313948404022737,
|
| 687 |
+
"eval_recall": 0.6283724978241949,
|
| 688 |
+
"eval_runtime": 7.3007,
|
| 689 |
+
"eval_samples_per_second": 32.874,
|
| 690 |
+
"eval_steps_per_second": 16.437,
|
| 691 |
+
"step": 5100
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 7.323943661971831,
|
| 695 |
+
"eval_accuracy": 0.9841835834068844,
|
| 696 |
+
"eval_f1": 0.6415256053139062,
|
| 697 |
+
"eval_loss": 0.08662400394678116,
|
| 698 |
+
"eval_precision": 0.6319121992401857,
|
| 699 |
+
"eval_recall": 0.6514360313315927,
|
| 700 |
+
"eval_runtime": 7.2401,
|
| 701 |
+
"eval_samples_per_second": 33.149,
|
| 702 |
+
"eval_steps_per_second": 16.574,
|
| 703 |
+
"step": 5200
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 7.464788732394366,
|
| 707 |
+
"eval_accuracy": 0.9846072374227715,
|
| 708 |
+
"eval_f1": 0.6500537056928034,
|
| 709 |
+
"eval_loss": 0.08784898370504379,
|
| 710 |
+
"eval_precision": 0.6419176919813322,
|
| 711 |
+
"eval_recall": 0.6583986074847694,
|
| 712 |
+
"eval_runtime": 7.4104,
|
| 713 |
+
"eval_samples_per_second": 32.387,
|
| 714 |
+
"eval_steps_per_second": 16.193,
|
| 715 |
+
"step": 5300
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 7.605633802816901,
|
| 719 |
+
"eval_accuracy": 0.9842541924095323,
|
| 720 |
+
"eval_f1": 0.6414596614640581,
|
| 721 |
+
"eval_loss": 0.09084232151508331,
|
| 722 |
+
"eval_precision": 0.6481563749444691,
|
| 723 |
+
"eval_recall": 0.6348999129677981,
|
| 724 |
+
"eval_runtime": 7.3975,
|
| 725 |
+
"eval_samples_per_second": 32.443,
|
| 726 |
+
"eval_steps_per_second": 16.222,
|
| 727 |
+
"step": 5400
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 7.746478873239437,
|
| 731 |
+
"grad_norm": 0.0023182749282568693,
|
| 732 |
+
"learning_rate": 3.88888888888889e-06,
|
| 733 |
+
"loss": 0.0471,
|
| 734 |
+
"step": 5500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 7.746478873239437,
|
| 738 |
+
"eval_accuracy": 0.9840188290673727,
|
| 739 |
+
"eval_f1": 0.6452567082188886,
|
| 740 |
+
"eval_loss": 0.08999249339103699,
|
| 741 |
+
"eval_precision": 0.6271047227926078,
|
| 742 |
+
"eval_recall": 0.664490861618799,
|
| 743 |
+
"eval_runtime": 7.3891,
|
| 744 |
+
"eval_samples_per_second": 32.48,
|
| 745 |
+
"eval_steps_per_second": 16.24,
|
| 746 |
+
"step": 5500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 7.887323943661972,
|
| 750 |
+
"eval_accuracy": 0.9845601647543395,
|
| 751 |
+
"eval_f1": 0.6460348162475823,
|
| 752 |
+
"eval_loss": 0.08533038198947906,
|
| 753 |
+
"eval_precision": 0.6382165605095541,
|
| 754 |
+
"eval_recall": 0.6540469973890339,
|
| 755 |
+
"eval_runtime": 7.4541,
|
| 756 |
+
"eval_samples_per_second": 32.197,
|
| 757 |
+
"eval_steps_per_second": 16.099,
|
| 758 |
+
"step": 5600
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.028169014084508,
|
| 762 |
+
"eval_accuracy": 0.9839835245660489,
|
| 763 |
+
"eval_f1": 0.6473011055712118,
|
| 764 |
+
"eval_loss": 0.08411037921905518,
|
| 765 |
+
"eval_precision": 0.6449244060475162,
|
| 766 |
+
"eval_recall": 0.6496953872932986,
|
| 767 |
+
"eval_runtime": 7.2873,
|
| 768 |
+
"eval_samples_per_second": 32.934,
|
| 769 |
+
"eval_steps_per_second": 16.467,
|
| 770 |
+
"step": 5700
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 8.169014084507042,
|
| 774 |
+
"eval_accuracy": 0.9845837010885554,
|
| 775 |
+
"eval_f1": 0.6499032882011605,
|
| 776 |
+
"eval_loss": 0.08550503104925156,
|
| 777 |
+
"eval_precision": 0.6420382165605095,
|
| 778 |
+
"eval_recall": 0.6579634464751958,
|
| 779 |
+
"eval_runtime": 7.4063,
|
| 780 |
+
"eval_samples_per_second": 32.405,
|
| 781 |
+
"eval_steps_per_second": 16.203,
|
| 782 |
+
"step": 5800
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 8.309859154929578,
|
| 786 |
+
"eval_accuracy": 0.9845719329214475,
|
| 787 |
+
"eval_f1": 0.6492411467116358,
|
| 788 |
+
"eval_loss": 0.08611707389354706,
|
| 789 |
+
"eval_precision": 0.6295993458708095,
|
| 790 |
+
"eval_recall": 0.6701479547432551,
|
| 791 |
+
"eval_runtime": 7.4327,
|
| 792 |
+
"eval_samples_per_second": 32.29,
|
| 793 |
+
"eval_steps_per_second": 16.145,
|
| 794 |
+
"step": 5900
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.450704225352112,
|
| 798 |
+
"grad_norm": 1.646479606628418,
|
| 799 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 800 |
+
"loss": 0.0372,
|
| 801 |
+
"step": 6000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 8.450704225352112,
|
| 805 |
+
"eval_accuracy": 0.9843365695792881,
|
| 806 |
+
"eval_f1": 0.6446173800259403,
|
| 807 |
+
"eval_loss": 0.08737049251794815,
|
| 808 |
+
"eval_precision": 0.6404639175257731,
|
| 809 |
+
"eval_recall": 0.6488250652741514,
|
| 810 |
+
"eval_runtime": 7.382,
|
| 811 |
+
"eval_samples_per_second": 32.511,
|
| 812 |
+
"eval_steps_per_second": 16.256,
|
| 813 |
+
"step": 6000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 8.591549295774648,
|
| 817 |
+
"eval_accuracy": 0.9844424830832598,
|
| 818 |
+
"eval_f1": 0.6449305847707194,
|
| 819 |
+
"eval_loss": 0.08426456153392792,
|
| 820 |
+
"eval_precision": 0.624185667752443,
|
| 821 |
+
"eval_recall": 0.6671018276762402,
|
| 822 |
+
"eval_runtime": 7.3893,
|
| 823 |
+
"eval_samples_per_second": 32.479,
|
| 824 |
+
"eval_steps_per_second": 16.24,
|
| 825 |
+
"step": 6100
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 8.732394366197184,
|
| 829 |
+
"eval_accuracy": 0.9846778464254192,
|
| 830 |
+
"eval_f1": 0.6556962025316455,
|
| 831 |
+
"eval_loss": 0.08480408787727356,
|
| 832 |
+
"eval_precision": 0.6363636363636364,
|
| 833 |
+
"eval_recall": 0.6762402088772846,
|
| 834 |
+
"eval_runtime": 7.2354,
|
| 835 |
+
"eval_samples_per_second": 33.17,
|
| 836 |
+
"eval_steps_per_second": 16.585,
|
| 837 |
+
"step": 6200
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.873239436619718,
|
| 841 |
+
"eval_accuracy": 0.9845601647543395,
|
| 842 |
+
"eval_f1": 0.6470588235294118,
|
| 843 |
+
"eval_loss": 0.08321469277143478,
|
| 844 |
+
"eval_precision": 0.6385593220338983,
|
| 845 |
+
"eval_recall": 0.6557876414273281,
|
| 846 |
+
"eval_runtime": 7.4183,
|
| 847 |
+
"eval_samples_per_second": 32.352,
|
| 848 |
+
"eval_steps_per_second": 16.176,
|
| 849 |
+
"step": 6300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 9.014084507042254,
|
| 853 |
+
"eval_accuracy": 0.9850779641070904,
|
| 854 |
+
"eval_f1": 0.6635009712928988,
|
| 855 |
+
"eval_loss": 0.08342073112726212,
|
| 856 |
+
"eval_precision": 0.6582441113490364,
|
| 857 |
+
"eval_recall": 0.6688424717145344,
|
| 858 |
+
"eval_runtime": 7.3864,
|
| 859 |
+
"eval_samples_per_second": 32.492,
|
| 860 |
+
"eval_steps_per_second": 16.246,
|
| 861 |
+
"step": 6400
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 9.154929577464788,
|
| 865 |
+
"grad_norm": 2.369316339492798,
|
| 866 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 867 |
+
"loss": 0.0376,
|
| 868 |
+
"step": 6500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 9.154929577464788,
|
| 872 |
+
"eval_accuracy": 0.9844777875845837,
|
| 873 |
+
"eval_f1": 0.6438267614738203,
|
| 874 |
+
"eval_loss": 0.08599114418029785,
|
| 875 |
+
"eval_precision": 0.6376440460947503,
|
| 876 |
+
"eval_recall": 0.6501305483028721,
|
| 877 |
+
"eval_runtime": 7.4336,
|
| 878 |
+
"eval_samples_per_second": 32.286,
|
| 879 |
+
"eval_steps_per_second": 16.143,
|
| 880 |
+
"step": 6500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 9.295774647887324,
|
| 884 |
+
"eval_accuracy": 0.9851838776110621,
|
| 885 |
+
"eval_f1": 0.6749455337690632,
|
| 886 |
+
"eval_loss": 0.0860476940870285,
|
| 887 |
+
"eval_precision": 0.6758289703315882,
|
| 888 |
+
"eval_recall": 0.6740644038294169,
|
| 889 |
+
"eval_runtime": 7.3997,
|
| 890 |
+
"eval_samples_per_second": 32.434,
|
| 891 |
+
"eval_steps_per_second": 16.217,
|
| 892 |
+
"step": 6600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 9.43661971830986,
|
| 896 |
+
"eval_accuracy": 0.9851132686084142,
|
| 897 |
+
"eval_f1": 0.6611642050390965,
|
| 898 |
+
"eval_loss": 0.08599450439214706,
|
| 899 |
+
"eval_precision": 0.6600173460537727,
|
| 900 |
+
"eval_recall": 0.6623150565709313,
|
| 901 |
+
"eval_runtime": 7.2459,
|
| 902 |
+
"eval_samples_per_second": 33.122,
|
| 903 |
+
"eval_steps_per_second": 16.561,
|
| 904 |
+
"step": 6700
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 9.577464788732394,
|
| 908 |
+
"eval_accuracy": 0.9855486907914093,
|
| 909 |
+
"eval_f1": 0.661723009814613,
|
| 910 |
+
"eval_loss": 0.0859636440873146,
|
| 911 |
+
"eval_precision": 0.6633143856580673,
|
| 912 |
+
"eval_recall": 0.6601392515230635,
|
| 913 |
+
"eval_runtime": 7.2743,
|
| 914 |
+
"eval_samples_per_second": 32.993,
|
| 915 |
+
"eval_steps_per_second": 16.496,
|
| 916 |
+
"step": 6800
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 9.71830985915493,
|
| 920 |
+
"eval_accuracy": 0.985642836128273,
|
| 921 |
+
"eval_f1": 0.6686567164179105,
|
| 922 |
+
"eval_loss": 0.08458743244409561,
|
| 923 |
+
"eval_precision": 0.6555183946488294,
|
| 924 |
+
"eval_recall": 0.6823324630113142,
|
| 925 |
+
"eval_runtime": 7.4204,
|
| 926 |
+
"eval_samples_per_second": 32.343,
|
| 927 |
+
"eval_steps_per_second": 16.172,
|
| 928 |
+
"step": 6900
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 9.859154929577464,
|
| 932 |
+
"grad_norm": 0.0017794760642573237,
|
| 933 |
+
"learning_rate": 2.222222222222222e-06,
|
| 934 |
+
"loss": 0.0352,
|
| 935 |
+
"step": 7000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 9.859154929577464,
|
| 939 |
+
"eval_accuracy": 0.9853250956163577,
|
| 940 |
+
"eval_f1": 0.6703601108033241,
|
| 941 |
+
"eval_loss": 0.08406654000282288,
|
| 942 |
+
"eval_precision": 0.6567849686847599,
|
| 943 |
+
"eval_recall": 0.6845082680591819,
|
| 944 |
+
"eval_runtime": 7.4608,
|
| 945 |
+
"eval_samples_per_second": 32.168,
|
| 946 |
+
"eval_steps_per_second": 16.084,
|
| 947 |
+
"step": 7000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 10.0,
|
| 951 |
+
"eval_accuracy": 0.9856310679611651,
|
| 952 |
+
"eval_f1": 0.6696619597774925,
|
| 953 |
+
"eval_loss": 0.08345002681016922,
|
| 954 |
+
"eval_precision": 0.6586700336700336,
|
| 955 |
+
"eval_recall": 0.6810269799825935,
|
| 956 |
+
"eval_runtime": 7.4149,
|
| 957 |
+
"eval_samples_per_second": 32.367,
|
| 958 |
+
"eval_steps_per_second": 16.184,
|
| 959 |
+
"step": 7100
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 10.140845070422536,
|
| 963 |
+
"eval_accuracy": 0.9852427184466019,
|
| 964 |
+
"eval_f1": 0.6715548846236791,
|
| 965 |
+
"eval_loss": 0.0879812017083168,
|
| 966 |
+
"eval_precision": 0.6656690893544249,
|
| 967 |
+
"eval_recall": 0.6775456919060052,
|
| 968 |
+
"eval_runtime": 7.4442,
|
| 969 |
+
"eval_samples_per_second": 32.24,
|
| 970 |
+
"eval_steps_per_second": 16.12,
|
| 971 |
+
"step": 7200
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 10.28169014084507,
|
| 975 |
+
"eval_accuracy": 0.9859723448072962,
|
| 976 |
+
"eval_f1": 0.6685272649205668,
|
| 977 |
+
"eval_loss": 0.08136157691478729,
|
| 978 |
+
"eval_precision": 0.6597457627118644,
|
| 979 |
+
"eval_recall": 0.6775456919060052,
|
| 980 |
+
"eval_runtime": 7.376,
|
| 981 |
+
"eval_samples_per_second": 32.538,
|
| 982 |
+
"eval_steps_per_second": 16.269,
|
| 983 |
+
"step": 7300
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 10.422535211267606,
|
| 987 |
+
"eval_accuracy": 0.9856781406295969,
|
| 988 |
+
"eval_f1": 0.6621363346782757,
|
| 989 |
+
"eval_loss": 0.08381623774766922,
|
| 990 |
+
"eval_precision": 0.646619659892161,
|
| 991 |
+
"eval_recall": 0.6784160139251523,
|
| 992 |
+
"eval_runtime": 7.4024,
|
| 993 |
+
"eval_samples_per_second": 32.422,
|
| 994 |
+
"eval_steps_per_second": 16.211,
|
| 995 |
+
"step": 7400
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 10.56338028169014,
|
| 999 |
+
"grad_norm": 7.505336761474609,
|
| 1000 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 1001 |
+
"loss": 0.0316,
|
| 1002 |
+
"step": 7500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 10.56338028169014,
|
| 1006 |
+
"eval_accuracy": 0.9855722271256252,
|
| 1007 |
+
"eval_f1": 0.6696619597774925,
|
| 1008 |
+
"eval_loss": 0.08473847806453705,
|
| 1009 |
+
"eval_precision": 0.6586700336700336,
|
| 1010 |
+
"eval_recall": 0.6810269799825935,
|
| 1011 |
+
"eval_runtime": 7.4244,
|
| 1012 |
+
"eval_samples_per_second": 32.326,
|
| 1013 |
+
"eval_steps_per_second": 16.163,
|
| 1014 |
+
"step": 7500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 10.704225352112676,
|
| 1018 |
+
"eval_accuracy": 0.9857252132980289,
|
| 1019 |
+
"eval_f1": 0.6789620416041175,
|
| 1020 |
+
"eval_loss": 0.08409886062145233,
|
| 1021 |
+
"eval_precision": 0.6693446088794927,
|
| 1022 |
+
"eval_recall": 0.6888598781549173,
|
| 1023 |
+
"eval_runtime": 7.4216,
|
| 1024 |
+
"eval_samples_per_second": 32.338,
|
| 1025 |
+
"eval_steps_per_second": 16.169,
|
| 1026 |
+
"step": 7600
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 10.845070422535212,
|
| 1030 |
+
"eval_accuracy": 0.9858546631362165,
|
| 1031 |
+
"eval_f1": 0.6777609682299546,
|
| 1032 |
+
"eval_loss": 0.08510851860046387,
|
| 1033 |
+
"eval_precision": 0.6732503220266208,
|
| 1034 |
+
"eval_recall": 0.6823324630113142,
|
| 1035 |
+
"eval_runtime": 7.4269,
|
| 1036 |
+
"eval_samples_per_second": 32.315,
|
| 1037 |
+
"eval_steps_per_second": 16.157,
|
| 1038 |
+
"step": 7700
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 10.985915492957746,
|
| 1042 |
+
"eval_accuracy": 0.985219182112386,
|
| 1043 |
+
"eval_f1": 0.663824344489448,
|
| 1044 |
+
"eval_loss": 0.08504322916269302,
|
| 1045 |
+
"eval_precision": 0.6506477225240285,
|
| 1046 |
+
"eval_recall": 0.6775456919060052,
|
| 1047 |
+
"eval_runtime": 7.297,
|
| 1048 |
+
"eval_samples_per_second": 32.89,
|
| 1049 |
+
"eval_steps_per_second": 16.445,
|
| 1050 |
+
"step": 7800
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 11.126760563380282,
|
| 1054 |
+
"eval_accuracy": 0.9855133862900853,
|
| 1055 |
+
"eval_f1": 0.6787174521196471,
|
| 1056 |
+
"eval_loss": 0.08639871329069138,
|
| 1057 |
+
"eval_precision": 0.6713495104299702,
|
| 1058 |
+
"eval_recall": 0.6862489120974761,
|
| 1059 |
+
"eval_runtime": 7.3134,
|
| 1060 |
+
"eval_samples_per_second": 32.817,
|
| 1061 |
+
"eval_steps_per_second": 16.408,
|
| 1062 |
+
"step": 7900
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 11.267605633802816,
|
| 1066 |
+
"grad_norm": 0.0015932625392451882,
|
| 1067 |
+
"learning_rate": 1.111111111111111e-06,
|
| 1068 |
+
"loss": 0.0323,
|
| 1069 |
+
"step": 8000
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 11.267605633802816,
|
| 1073 |
+
"eval_accuracy": 0.9859605766401883,
|
| 1074 |
+
"eval_f1": 0.671434763762462,
|
| 1075 |
+
"eval_loss": 0.08427204191684723,
|
| 1076 |
+
"eval_precision": 0.668825561312608,
|
| 1077 |
+
"eval_recall": 0.6740644038294169,
|
| 1078 |
+
"eval_runtime": 7.4224,
|
| 1079 |
+
"eval_samples_per_second": 32.335,
|
| 1080 |
+
"eval_steps_per_second": 16.167,
|
| 1081 |
+
"step": 8000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 11.408450704225352,
|
| 1085 |
+
"eval_accuracy": 0.9853368637834657,
|
| 1086 |
+
"eval_f1": 0.6679487179487179,
|
| 1087 |
+
"eval_loss": 0.08620592951774597,
|
| 1088 |
+
"eval_precision": 0.6561712846347607,
|
| 1089 |
+
"eval_recall": 0.6801566579634465,
|
| 1090 |
+
"eval_runtime": 7.52,
|
| 1091 |
+
"eval_samples_per_second": 31.915,
|
| 1092 |
+
"eval_steps_per_second": 15.957,
|
| 1093 |
+
"step": 8100
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 11.549295774647888,
|
| 1097 |
+
"eval_accuracy": 0.9859723448072962,
|
| 1098 |
+
"eval_f1": 0.6735661923242777,
|
| 1099 |
+
"eval_loss": 0.08543656021356583,
|
| 1100 |
+
"eval_precision": 0.6675213675213675,
|
| 1101 |
+
"eval_recall": 0.679721496953873,
|
| 1102 |
+
"eval_runtime": 7.4397,
|
| 1103 |
+
"eval_samples_per_second": 32.259,
|
| 1104 |
+
"eval_steps_per_second": 16.13,
|
| 1105 |
+
"step": 8200
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 11.690140845070422,
|
| 1109 |
+
"eval_accuracy": 0.986090026478376,
|
| 1110 |
+
"eval_f1": 0.679860809047412,
|
| 1111 |
+
"eval_loss": 0.0849027931690216,
|
| 1112 |
+
"eval_precision": 0.6795652173913044,
|
| 1113 |
+
"eval_recall": 0.6801566579634465,
|
| 1114 |
+
"eval_runtime": 7.4695,
|
| 1115 |
+
"eval_samples_per_second": 32.131,
|
| 1116 |
+
"eval_steps_per_second": 16.065,
|
| 1117 |
+
"step": 8300
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 11.830985915492958,
|
| 1121 |
+
"eval_accuracy": 0.9858899676375404,
|
| 1122 |
+
"eval_f1": 0.6754684838160135,
|
| 1123 |
+
"eval_loss": 0.08420813083648682,
|
| 1124 |
+
"eval_precision": 0.6613844870725605,
|
| 1125 |
+
"eval_recall": 0.6901653611836379,
|
| 1126 |
+
"eval_runtime": 7.2972,
|
| 1127 |
+
"eval_samples_per_second": 32.889,
|
| 1128 |
+
"eval_steps_per_second": 16.445,
|
| 1129 |
+
"step": 8400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 11.971830985915492,
|
| 1133 |
+
"grad_norm": 4.900869369506836,
|
| 1134 |
+
"learning_rate": 5.555555555555555e-07,
|
| 1135 |
+
"loss": 0.0307,
|
| 1136 |
+
"step": 8500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 11.971830985915492,
|
| 1140 |
+
"eval_accuracy": 0.9861488673139158,
|
| 1141 |
+
"eval_f1": 0.6820038701354548,
|
| 1142 |
+
"eval_loss": 0.08459390699863434,
|
| 1143 |
+
"eval_precision": 0.6740331491712708,
|
| 1144 |
+
"eval_recall": 0.6901653611836379,
|
| 1145 |
+
"eval_runtime": 7.4228,
|
| 1146 |
+
"eval_samples_per_second": 32.333,
|
| 1147 |
+
"eval_steps_per_second": 16.166,
|
| 1148 |
+
"step": 8500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 12.112676056338028,
|
| 1152 |
+
"eval_accuracy": 0.9863371579876434,
|
| 1153 |
+
"eval_f1": 0.6822409690677049,
|
| 1154 |
+
"eval_loss": 0.08515108376741409,
|
| 1155 |
+
"eval_precision": 0.6782795698924731,
|
| 1156 |
+
"eval_recall": 0.6862489120974761,
|
| 1157 |
+
"eval_runtime": 7.4273,
|
| 1158 |
+
"eval_samples_per_second": 32.313,
|
| 1159 |
+
"eval_steps_per_second": 16.157,
|
| 1160 |
+
"step": 8600
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 12.253521126760564,
|
| 1164 |
+
"eval_accuracy": 0.9860076493086202,
|
| 1165 |
+
"eval_f1": 0.6782646048109965,
|
| 1166 |
+
"eval_loss": 0.08560565114021301,
|
| 1167 |
+
"eval_precision": 0.6696352841391009,
|
| 1168 |
+
"eval_recall": 0.6871192341166231,
|
| 1169 |
+
"eval_runtime": 7.5069,
|
| 1170 |
+
"eval_samples_per_second": 31.97,
|
| 1171 |
+
"eval_steps_per_second": 15.985,
|
| 1172 |
+
"step": 8700
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 12.394366197183098,
|
| 1176 |
+
"eval_accuracy": 0.9859017358046485,
|
| 1177 |
+
"eval_f1": 0.6775580395528805,
|
| 1178 |
+
"eval_loss": 0.08563963323831558,
|
| 1179 |
+
"eval_precision": 0.6694987255734919,
|
| 1180 |
+
"eval_recall": 0.6858137510879025,
|
| 1181 |
+
"eval_runtime": 7.5078,
|
| 1182 |
+
"eval_samples_per_second": 31.967,
|
| 1183 |
+
"eval_steps_per_second": 15.983,
|
| 1184 |
+
"step": 8800
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 12.535211267605634,
|
| 1188 |
+
"eval_accuracy": 0.9858546631362165,
|
| 1189 |
+
"eval_f1": 0.6785791173304628,
|
| 1190 |
+
"eval_loss": 0.08600553870201111,
|
| 1191 |
+
"eval_precision": 0.6714955262036643,
|
| 1192 |
+
"eval_recall": 0.6858137510879025,
|
| 1193 |
+
"eval_runtime": 7.3022,
|
| 1194 |
+
"eval_samples_per_second": 32.867,
|
| 1195 |
+
"eval_steps_per_second": 16.433,
|
| 1196 |
+
"step": 8900
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 12.676056338028168,
|
| 1200 |
+
"grad_norm": 0.2440214604139328,
|
| 1201 |
+
"learning_rate": 0.0,
|
| 1202 |
+
"loss": 0.028,
|
| 1203 |
+
"step": 9000
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 12.676056338028168,
|
| 1207 |
+
"eval_accuracy": 0.9859252721388644,
|
| 1208 |
+
"eval_f1": 0.6791559000861327,
|
| 1209 |
+
"eval_loss": 0.08589298278093338,
|
| 1210 |
+
"eval_precision": 0.6722080136402387,
|
| 1211 |
+
"eval_recall": 0.6862489120974761,
|
| 1212 |
+
"eval_runtime": 7.3893,
|
| 1213 |
+
"eval_samples_per_second": 32.479,
|
| 1214 |
+
"eval_steps_per_second": 16.24,
|
| 1215 |
+
"step": 9000
|
| 1216 |
+
}
|
| 1217 |
+
],
|
| 1218 |
+
"logging_steps": 500,
|
| 1219 |
+
"max_steps": 9000,
|
| 1220 |
+
"num_input_tokens_seen": 0,
|
| 1221 |
+
"num_train_epochs": 13,
|
| 1222 |
+
"save_steps": 500,
|
| 1223 |
+
"stateful_callbacks": {
|
| 1224 |
+
"TrainerControl": {
|
| 1225 |
+
"args": {
|
| 1226 |
+
"should_epoch_stop": false,
|
| 1227 |
+
"should_evaluate": false,
|
| 1228 |
+
"should_log": false,
|
| 1229 |
+
"should_save": true,
|
| 1230 |
+
"should_training_stop": true
|
| 1231 |
+
},
|
| 1232 |
+
"attributes": {}
|
| 1233 |
+
}
|
| 1234 |
+
},
|
| 1235 |
+
"total_flos": 4780487614464000.0,
|
| 1236 |
+
"train_batch_size": 2,
|
| 1237 |
+
"trial_name": null,
|
| 1238 |
+
"trial_params": null
|
| 1239 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad150db3ee7b4043591f1b32f50ee2d4318e49f25327ce56ec378d6d5d04250a
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|