Upload cleaned multilabel classifier for Dockerfile QA
Browse files- classification_report.csv +35 -0
- config.json +93 -0
- confusion_matrix_multilabel.png +0 -0
- merges.txt +0 -0
- metrics.json +206 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- thresholds.json +32 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_log.json +2675 -0
- vocab.json +0 -0
classification_report.csv
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
,precision,recall,f1-score,support
|
| 2 |
+
DL4006,0.9652173913043478,0.9652173913043478,0.9652173913043478,805.0
|
| 3 |
+
DL3008,0.9953198127925117,0.996875,0.9960967993754879,640.0
|
| 4 |
+
SC2086,0.9857369255150554,0.9703588143525741,0.9779874213836478,641.0
|
| 5 |
+
DL3003,0.9860279441117764,0.9743589743589743,0.9801587301587301,507.0
|
| 6 |
+
DL3015,0.9955456570155902,0.9824175824175824,0.9889380530973452,455.0
|
| 7 |
+
DL3047,0.9907834101382489,0.9598214285714286,0.9750566893424036,448.0
|
| 8 |
+
DL3009,0.9784688995215312,0.966903073286052,0.9726516052318668,423.0
|
| 9 |
+
DL3004,0.9937888198757764,0.9937888198757764,0.9937888198757764,322.0
|
| 10 |
+
DL4001,0.9840637450199203,0.946360153256705,0.96484375,261.0
|
| 11 |
+
DL4000,1.0,0.9964028776978417,0.9981981981981982,278.0
|
| 12 |
+
DL3059,0.9362549800796812,0.9215686274509803,0.9288537549407114,255.0
|
| 13 |
+
DL3018,1.0,0.9945945945945946,0.997289972899729,185.0
|
| 14 |
+
SC2016,0.9947916666666666,0.9794871794871794,0.9870801033591732,195.0
|
| 15 |
+
SC2046,0.8271604938271605,0.9115646258503401,0.8673139158576052,147.0
|
| 16 |
+
DL3006,0.9940828402366864,0.9882352941176471,0.9911504424778761,170.0
|
| 17 |
+
SC2028,0.9681528662420382,0.9806451612903225,0.9743589743589743,155.0
|
| 18 |
+
DL3027,0.9644970414201184,0.9760479041916168,0.9702380952380952,167.0
|
| 19 |
+
DL3020,0.9770114942528736,0.8585858585858586,0.9139784946236559,99.0
|
| 20 |
+
DL3025,0.8817204301075269,0.8631578947368421,0.8723404255319149,95.0
|
| 21 |
+
DL3042,0.8736842105263158,0.8924731182795699,0.8829787234042553,93.0
|
| 22 |
+
DL3013,0.8354430379746836,0.8461538461538461,0.8407643312101911,78.0
|
| 23 |
+
DL3007,0.9764705882352941,1.0,0.9880952380952381,83.0
|
| 24 |
+
DL3033,0.9516129032258065,0.9516129032258065,0.9516129032258065,62.0
|
| 25 |
+
SC2043,1.0,0.9594594594594594,0.9793103448275862,74.0
|
| 26 |
+
DL3019,1.0,0.9423076923076923,0.9702970297029703,52.0
|
| 27 |
+
DL3005,1.0,0.9019607843137255,0.9484536082474226,51.0
|
| 28 |
+
DL3002,0.9375,0.9375,0.9375,32.0
|
| 29 |
+
DL3048,0.9230769230769231,0.8,0.8571428571428571,45.0
|
| 30 |
+
DL3045,1.0,0.7931034482758621,0.8846153846153846,29.0
|
| 31 |
+
DL3032,0.9565217391304348,0.8461538461538461,0.8979591836734694,26.0
|
| 32 |
+
micro avg,0.9744004707959394,0.963625782045686,0.968983174835406,6873.0
|
| 33 |
+
macro avg,0.9624311273432322,0.9365705451198826,0.9484757080466906,6873.0
|
| 34 |
+
weighted avg,0.9748532029955321,0.963625782045686,0.9689648091121812,6873.0
|
| 35 |
+
samples avg,0.9761015873015874,0.9658639490139491,0.9670997601651524,6873.0
|
config.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/codebert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6",
|
| 21 |
+
"7": "LABEL_7",
|
| 22 |
+
"8": "LABEL_8",
|
| 23 |
+
"9": "LABEL_9",
|
| 24 |
+
"10": "LABEL_10",
|
| 25 |
+
"11": "LABEL_11",
|
| 26 |
+
"12": "LABEL_12",
|
| 27 |
+
"13": "LABEL_13",
|
| 28 |
+
"14": "LABEL_14",
|
| 29 |
+
"15": "LABEL_15",
|
| 30 |
+
"16": "LABEL_16",
|
| 31 |
+
"17": "LABEL_17",
|
| 32 |
+
"18": "LABEL_18",
|
| 33 |
+
"19": "LABEL_19",
|
| 34 |
+
"20": "LABEL_20",
|
| 35 |
+
"21": "LABEL_21",
|
| 36 |
+
"22": "LABEL_22",
|
| 37 |
+
"23": "LABEL_23",
|
| 38 |
+
"24": "LABEL_24",
|
| 39 |
+
"25": "LABEL_25",
|
| 40 |
+
"26": "LABEL_26",
|
| 41 |
+
"27": "LABEL_27",
|
| 42 |
+
"28": "LABEL_28",
|
| 43 |
+
"29": "LABEL_29"
|
| 44 |
+
},
|
| 45 |
+
"initializer_range": 0.02,
|
| 46 |
+
"intermediate_size": 3072,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"LABEL_0": 0,
|
| 49 |
+
"LABEL_1": 1,
|
| 50 |
+
"LABEL_10": 10,
|
| 51 |
+
"LABEL_11": 11,
|
| 52 |
+
"LABEL_12": 12,
|
| 53 |
+
"LABEL_13": 13,
|
| 54 |
+
"LABEL_14": 14,
|
| 55 |
+
"LABEL_15": 15,
|
| 56 |
+
"LABEL_16": 16,
|
| 57 |
+
"LABEL_17": 17,
|
| 58 |
+
"LABEL_18": 18,
|
| 59 |
+
"LABEL_19": 19,
|
| 60 |
+
"LABEL_2": 2,
|
| 61 |
+
"LABEL_20": 20,
|
| 62 |
+
"LABEL_21": 21,
|
| 63 |
+
"LABEL_22": 22,
|
| 64 |
+
"LABEL_23": 23,
|
| 65 |
+
"LABEL_24": 24,
|
| 66 |
+
"LABEL_25": 25,
|
| 67 |
+
"LABEL_26": 26,
|
| 68 |
+
"LABEL_27": 27,
|
| 69 |
+
"LABEL_28": 28,
|
| 70 |
+
"LABEL_29": 29,
|
| 71 |
+
"LABEL_3": 3,
|
| 72 |
+
"LABEL_4": 4,
|
| 73 |
+
"LABEL_5": 5,
|
| 74 |
+
"LABEL_6": 6,
|
| 75 |
+
"LABEL_7": 7,
|
| 76 |
+
"LABEL_8": 8,
|
| 77 |
+
"LABEL_9": 9
|
| 78 |
+
},
|
| 79 |
+
"layer_norm_eps": 1e-05,
|
| 80 |
+
"max_position_embeddings": 514,
|
| 81 |
+
"model_type": "roberta",
|
| 82 |
+
"num_attention_heads": 12,
|
| 83 |
+
"num_hidden_layers": 12,
|
| 84 |
+
"output_past": true,
|
| 85 |
+
"pad_token_id": 1,
|
| 86 |
+
"position_embedding_type": "absolute",
|
| 87 |
+
"problem_type": "multi_label_classification",
|
| 88 |
+
"torch_dtype": "float32",
|
| 89 |
+
"transformers_version": "4.38.2",
|
| 90 |
+
"type_vocab_size": 1,
|
| 91 |
+
"use_cache": true,
|
| 92 |
+
"vocab_size": 50265
|
| 93 |
+
}
|
confusion_matrix_multilabel.png
ADDED
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
metrics.json
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"DL4006": {
|
| 3 |
+
"precision": 0.9652173913043478,
|
| 4 |
+
"recall": 0.9652173913043478,
|
| 5 |
+
"f1-score": 0.9652173913043478,
|
| 6 |
+
"support": 805.0
|
| 7 |
+
},
|
| 8 |
+
"DL3008": {
|
| 9 |
+
"precision": 0.9953198127925117,
|
| 10 |
+
"recall": 0.996875,
|
| 11 |
+
"f1-score": 0.9960967993754879,
|
| 12 |
+
"support": 640.0
|
| 13 |
+
},
|
| 14 |
+
"SC2086": {
|
| 15 |
+
"precision": 0.9857369255150554,
|
| 16 |
+
"recall": 0.9703588143525741,
|
| 17 |
+
"f1-score": 0.9779874213836478,
|
| 18 |
+
"support": 641.0
|
| 19 |
+
},
|
| 20 |
+
"DL3003": {
|
| 21 |
+
"precision": 0.9860279441117764,
|
| 22 |
+
"recall": 0.9743589743589743,
|
| 23 |
+
"f1-score": 0.9801587301587301,
|
| 24 |
+
"support": 507.0
|
| 25 |
+
},
|
| 26 |
+
"DL3015": {
|
| 27 |
+
"precision": 0.9955456570155902,
|
| 28 |
+
"recall": 0.9824175824175824,
|
| 29 |
+
"f1-score": 0.9889380530973452,
|
| 30 |
+
"support": 455.0
|
| 31 |
+
},
|
| 32 |
+
"DL3047": {
|
| 33 |
+
"precision": 0.9907834101382489,
|
| 34 |
+
"recall": 0.9598214285714286,
|
| 35 |
+
"f1-score": 0.9750566893424036,
|
| 36 |
+
"support": 448.0
|
| 37 |
+
},
|
| 38 |
+
"DL3009": {
|
| 39 |
+
"precision": 0.9784688995215312,
|
| 40 |
+
"recall": 0.966903073286052,
|
| 41 |
+
"f1-score": 0.9726516052318668,
|
| 42 |
+
"support": 423.0
|
| 43 |
+
},
|
| 44 |
+
"DL3004": {
|
| 45 |
+
"precision": 0.9937888198757764,
|
| 46 |
+
"recall": 0.9937888198757764,
|
| 47 |
+
"f1-score": 0.9937888198757764,
|
| 48 |
+
"support": 322.0
|
| 49 |
+
},
|
| 50 |
+
"DL4001": {
|
| 51 |
+
"precision": 0.9840637450199203,
|
| 52 |
+
"recall": 0.946360153256705,
|
| 53 |
+
"f1-score": 0.96484375,
|
| 54 |
+
"support": 261.0
|
| 55 |
+
},
|
| 56 |
+
"DL4000": {
|
| 57 |
+
"precision": 1.0,
|
| 58 |
+
"recall": 0.9964028776978417,
|
| 59 |
+
"f1-score": 0.9981981981981982,
|
| 60 |
+
"support": 278.0
|
| 61 |
+
},
|
| 62 |
+
"DL3059": {
|
| 63 |
+
"precision": 0.9362549800796812,
|
| 64 |
+
"recall": 0.9215686274509803,
|
| 65 |
+
"f1-score": 0.9288537549407114,
|
| 66 |
+
"support": 255.0
|
| 67 |
+
},
|
| 68 |
+
"DL3018": {
|
| 69 |
+
"precision": 1.0,
|
| 70 |
+
"recall": 0.9945945945945946,
|
| 71 |
+
"f1-score": 0.997289972899729,
|
| 72 |
+
"support": 185.0
|
| 73 |
+
},
|
| 74 |
+
"SC2016": {
|
| 75 |
+
"precision": 0.9947916666666666,
|
| 76 |
+
"recall": 0.9794871794871794,
|
| 77 |
+
"f1-score": 0.9870801033591732,
|
| 78 |
+
"support": 195.0
|
| 79 |
+
},
|
| 80 |
+
"SC2046": {
|
| 81 |
+
"precision": 0.8271604938271605,
|
| 82 |
+
"recall": 0.9115646258503401,
|
| 83 |
+
"f1-score": 0.8673139158576052,
|
| 84 |
+
"support": 147.0
|
| 85 |
+
},
|
| 86 |
+
"DL3006": {
|
| 87 |
+
"precision": 0.9940828402366864,
|
| 88 |
+
"recall": 0.9882352941176471,
|
| 89 |
+
"f1-score": 0.9911504424778761,
|
| 90 |
+
"support": 170.0
|
| 91 |
+
},
|
| 92 |
+
"SC2028": {
|
| 93 |
+
"precision": 0.9681528662420382,
|
| 94 |
+
"recall": 0.9806451612903225,
|
| 95 |
+
"f1-score": 0.9743589743589743,
|
| 96 |
+
"support": 155.0
|
| 97 |
+
},
|
| 98 |
+
"DL3027": {
|
| 99 |
+
"precision": 0.9644970414201184,
|
| 100 |
+
"recall": 0.9760479041916168,
|
| 101 |
+
"f1-score": 0.9702380952380952,
|
| 102 |
+
"support": 167.0
|
| 103 |
+
},
|
| 104 |
+
"DL3020": {
|
| 105 |
+
"precision": 0.9770114942528736,
|
| 106 |
+
"recall": 0.8585858585858586,
|
| 107 |
+
"f1-score": 0.9139784946236559,
|
| 108 |
+
"support": 99.0
|
| 109 |
+
},
|
| 110 |
+
"DL3025": {
|
| 111 |
+
"precision": 0.8817204301075269,
|
| 112 |
+
"recall": 0.8631578947368421,
|
| 113 |
+
"f1-score": 0.8723404255319149,
|
| 114 |
+
"support": 95.0
|
| 115 |
+
},
|
| 116 |
+
"DL3042": {
|
| 117 |
+
"precision": 0.8736842105263158,
|
| 118 |
+
"recall": 0.8924731182795699,
|
| 119 |
+
"f1-score": 0.8829787234042553,
|
| 120 |
+
"support": 93.0
|
| 121 |
+
},
|
| 122 |
+
"DL3013": {
|
| 123 |
+
"precision": 0.8354430379746836,
|
| 124 |
+
"recall": 0.8461538461538461,
|
| 125 |
+
"f1-score": 0.8407643312101911,
|
| 126 |
+
"support": 78.0
|
| 127 |
+
},
|
| 128 |
+
"DL3007": {
|
| 129 |
+
"precision": 0.9764705882352941,
|
| 130 |
+
"recall": 1.0,
|
| 131 |
+
"f1-score": 0.9880952380952381,
|
| 132 |
+
"support": 83.0
|
| 133 |
+
},
|
| 134 |
+
"DL3033": {
|
| 135 |
+
"precision": 0.9516129032258065,
|
| 136 |
+
"recall": 0.9516129032258065,
|
| 137 |
+
"f1-score": 0.9516129032258065,
|
| 138 |
+
"support": 62.0
|
| 139 |
+
},
|
| 140 |
+
"SC2043": {
|
| 141 |
+
"precision": 1.0,
|
| 142 |
+
"recall": 0.9594594594594594,
|
| 143 |
+
"f1-score": 0.9793103448275862,
|
| 144 |
+
"support": 74.0
|
| 145 |
+
},
|
| 146 |
+
"DL3019": {
|
| 147 |
+
"precision": 1.0,
|
| 148 |
+
"recall": 0.9423076923076923,
|
| 149 |
+
"f1-score": 0.9702970297029703,
|
| 150 |
+
"support": 52.0
|
| 151 |
+
},
|
| 152 |
+
"DL3005": {
|
| 153 |
+
"precision": 1.0,
|
| 154 |
+
"recall": 0.9019607843137255,
|
| 155 |
+
"f1-score": 0.9484536082474226,
|
| 156 |
+
"support": 51.0
|
| 157 |
+
},
|
| 158 |
+
"DL3002": {
|
| 159 |
+
"precision": 0.9375,
|
| 160 |
+
"recall": 0.9375,
|
| 161 |
+
"f1-score": 0.9375,
|
| 162 |
+
"support": 32.0
|
| 163 |
+
},
|
| 164 |
+
"DL3048": {
|
| 165 |
+
"precision": 0.9230769230769231,
|
| 166 |
+
"recall": 0.8,
|
| 167 |
+
"f1-score": 0.8571428571428571,
|
| 168 |
+
"support": 45.0
|
| 169 |
+
},
|
| 170 |
+
"DL3045": {
|
| 171 |
+
"precision": 1.0,
|
| 172 |
+
"recall": 0.7931034482758621,
|
| 173 |
+
"f1-score": 0.8846153846153846,
|
| 174 |
+
"support": 29.0
|
| 175 |
+
},
|
| 176 |
+
"DL3032": {
|
| 177 |
+
"precision": 0.9565217391304348,
|
| 178 |
+
"recall": 0.8461538461538461,
|
| 179 |
+
"f1-score": 0.8979591836734694,
|
| 180 |
+
"support": 26.0
|
| 181 |
+
},
|
| 182 |
+
"micro avg": {
|
| 183 |
+
"precision": 0.9744004707959394,
|
| 184 |
+
"recall": 0.963625782045686,
|
| 185 |
+
"f1-score": 0.968983174835406,
|
| 186 |
+
"support": 6873.0
|
| 187 |
+
},
|
| 188 |
+
"macro avg": {
|
| 189 |
+
"precision": 0.9624311273432322,
|
| 190 |
+
"recall": 0.9365705451198826,
|
| 191 |
+
"f1-score": 0.9484757080466906,
|
| 192 |
+
"support": 6873.0
|
| 193 |
+
},
|
| 194 |
+
"weighted avg": {
|
| 195 |
+
"precision": 0.9748532029955321,
|
| 196 |
+
"recall": 0.963625782045686,
|
| 197 |
+
"f1-score": 0.9689648091121812,
|
| 198 |
+
"support": 6873.0
|
| 199 |
+
},
|
| 200 |
+
"samples avg": {
|
| 201 |
+
"precision": 0.9761015873015874,
|
| 202 |
+
"recall": 0.9658639490139491,
|
| 203 |
+
"f1-score": 0.9670997601651524,
|
| 204 |
+
"support": 6873.0
|
| 205 |
+
}
|
| 206 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:489841db15d6703e6761fb633c9b825dd9393dc286d7d6c8f34bc6aef8e3e7f5
|
| 3 |
+
size 498698952
|
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": false,
|
| 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 |
+
}
|
thresholds.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"DL4006": 0.55,
|
| 3 |
+
"DL3008": 0.5,
|
| 4 |
+
"SC2086": 0.65,
|
| 5 |
+
"DL3003": 0.35,
|
| 6 |
+
"DL3015": 0.3,
|
| 7 |
+
"DL3047": 0.25,
|
| 8 |
+
"DL3009": 0.55,
|
| 9 |
+
"DL3004": 0.45,
|
| 10 |
+
"DL4001": 0.3,
|
| 11 |
+
"DL4000": 0.1,
|
| 12 |
+
"DL3059": 0.8,
|
| 13 |
+
"DL3018": 0.2,
|
| 14 |
+
"SC2016": 0.2,
|
| 15 |
+
"SC2046": 0.7,
|
| 16 |
+
"DL3006": 0.2,
|
| 17 |
+
"SC2028": 0.25,
|
| 18 |
+
"DL3027": 0.35,
|
| 19 |
+
"DL3020": 0.5,
|
| 20 |
+
"DL3025": 0.4,
|
| 21 |
+
"DL3042": 0.75,
|
| 22 |
+
"DL3013": 0.35,
|
| 23 |
+
"DL3007": 0.2,
|
| 24 |
+
"DL3033": 0.05,
|
| 25 |
+
"SC2043": 0.4,
|
| 26 |
+
"DL3019": 0.3,
|
| 27 |
+
"DL3005": 0.25,
|
| 28 |
+
"DL3002": 0.2,
|
| 29 |
+
"DL3048": 0.25,
|
| 30 |
+
"DL3045": 0.15,
|
| 31 |
+
"DL3032": 0.1
|
| 32 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 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": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b754ba202e4af27dfb0573df1d80680d823091d6ef53d0ec0851c302120f2965
|
| 3 |
+
size 4856
|
training_log.json
ADDED
|
@@ -0,0 +1,2675 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 0.4904,
|
| 4 |
+
"grad_norm": 0.5958866477012634,
|
| 5 |
+
"learning_rate": 1.9944444444444447e-05,
|
| 6 |
+
"epoch": 0.03,
|
| 7 |
+
"step": 50
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"loss": 0.3657,
|
| 11 |
+
"grad_norm": 0.4602122902870178,
|
| 12 |
+
"learning_rate": 1.988888888888889e-05,
|
| 13 |
+
"epoch": 0.07,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"loss": 0.3182,
|
| 18 |
+
"grad_norm": 0.6156640648841858,
|
| 19 |
+
"learning_rate": 1.9833333333333335e-05,
|
| 20 |
+
"epoch": 0.1,
|
| 21 |
+
"step": 150
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"loss": 0.275,
|
| 25 |
+
"grad_norm": 0.4630753695964813,
|
| 26 |
+
"learning_rate": 1.977777777777778e-05,
|
| 27 |
+
"epoch": 0.13,
|
| 28 |
+
"step": 200
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"loss": 0.252,
|
| 32 |
+
"grad_norm": 0.6395113468170166,
|
| 33 |
+
"learning_rate": 1.9722222222222224e-05,
|
| 34 |
+
"epoch": 0.17,
|
| 35 |
+
"step": 250
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"loss": 0.2434,
|
| 39 |
+
"grad_norm": 0.4501757025718689,
|
| 40 |
+
"learning_rate": 1.9666666666666666e-05,
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"step": 300
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 0.2208,
|
| 46 |
+
"grad_norm": 0.6610535383224487,
|
| 47 |
+
"learning_rate": 1.961111111111111e-05,
|
| 48 |
+
"epoch": 0.23,
|
| 49 |
+
"step": 350
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"loss": 0.2192,
|
| 53 |
+
"grad_norm": 0.40222012996673584,
|
| 54 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 55 |
+
"epoch": 0.27,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"loss": 0.2138,
|
| 60 |
+
"grad_norm": 0.7299392223358154,
|
| 61 |
+
"learning_rate": 1.95e-05,
|
| 62 |
+
"epoch": 0.3,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"loss": 0.2066,
|
| 67 |
+
"grad_norm": 0.5643211007118225,
|
| 68 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 69 |
+
"epoch": 0.33,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 0.2021,
|
| 74 |
+
"grad_norm": 1.0369503498077393,
|
| 75 |
+
"learning_rate": 1.938888888888889e-05,
|
| 76 |
+
"epoch": 0.37,
|
| 77 |
+
"step": 550
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"loss": 0.1908,
|
| 81 |
+
"grad_norm": 0.37896671891212463,
|
| 82 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"step": 600
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 0.1831,
|
| 88 |
+
"grad_norm": 0.3660513162612915,
|
| 89 |
+
"learning_rate": 1.927777777777778e-05,
|
| 90 |
+
"epoch": 0.43,
|
| 91 |
+
"step": 650
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"loss": 0.1808,
|
| 95 |
+
"grad_norm": 0.5333911776542664,
|
| 96 |
+
"learning_rate": 1.9222222222222225e-05,
|
| 97 |
+
"epoch": 0.47,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"loss": 0.1609,
|
| 102 |
+
"grad_norm": 0.54070645570755,
|
| 103 |
+
"learning_rate": 1.916666666666667e-05,
|
| 104 |
+
"epoch": 0.5,
|
| 105 |
+
"step": 750
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"loss": 0.1637,
|
| 109 |
+
"grad_norm": 0.41102516651153564,
|
| 110 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 111 |
+
"epoch": 0.53,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"loss": 0.1614,
|
| 116 |
+
"grad_norm": 0.4941543936729431,
|
| 117 |
+
"learning_rate": 1.9055555555555555e-05,
|
| 118 |
+
"epoch": 0.57,
|
| 119 |
+
"step": 850
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"loss": 0.1503,
|
| 123 |
+
"grad_norm": 0.5441026091575623,
|
| 124 |
+
"learning_rate": 1.9e-05,
|
| 125 |
+
"epoch": 0.6,
|
| 126 |
+
"step": 900
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"loss": 0.153,
|
| 130 |
+
"grad_norm": 0.5017764568328857,
|
| 131 |
+
"learning_rate": 1.8944444444444447e-05,
|
| 132 |
+
"epoch": 0.63,
|
| 133 |
+
"step": 950
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"loss": 0.1619,
|
| 137 |
+
"grad_norm": 1.039005994796753,
|
| 138 |
+
"learning_rate": 1.888888888888889e-05,
|
| 139 |
+
"epoch": 0.67,
|
| 140 |
+
"step": 1000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"loss": 0.1571,
|
| 144 |
+
"grad_norm": 0.401298463344574,
|
| 145 |
+
"learning_rate": 1.8833333333333335e-05,
|
| 146 |
+
"epoch": 0.7,
|
| 147 |
+
"step": 1050
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"loss": 0.1549,
|
| 151 |
+
"grad_norm": 0.5666447877883911,
|
| 152 |
+
"learning_rate": 1.877777777777778e-05,
|
| 153 |
+
"epoch": 0.73,
|
| 154 |
+
"step": 1100
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"loss": 0.1458,
|
| 158 |
+
"grad_norm": 0.6719347834587097,
|
| 159 |
+
"learning_rate": 1.8722222222222223e-05,
|
| 160 |
+
"epoch": 0.77,
|
| 161 |
+
"step": 1150
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"loss": 0.1442,
|
| 165 |
+
"grad_norm": 0.6617727875709534,
|
| 166 |
+
"learning_rate": 1.866666666666667e-05,
|
| 167 |
+
"epoch": 0.8,
|
| 168 |
+
"step": 1200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"loss": 0.1522,
|
| 172 |
+
"grad_norm": 0.6959300637245178,
|
| 173 |
+
"learning_rate": 1.8611111111111114e-05,
|
| 174 |
+
"epoch": 0.83,
|
| 175 |
+
"step": 1250
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"loss": 0.126,
|
| 179 |
+
"grad_norm": 0.3736123740673065,
|
| 180 |
+
"learning_rate": 1.8555555555555557e-05,
|
| 181 |
+
"epoch": 0.87,
|
| 182 |
+
"step": 1300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"loss": 0.1373,
|
| 186 |
+
"grad_norm": 0.20589721202850342,
|
| 187 |
+
"learning_rate": 1.8500000000000002e-05,
|
| 188 |
+
"epoch": 0.9,
|
| 189 |
+
"step": 1350
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"loss": 0.138,
|
| 193 |
+
"grad_norm": 0.9768441319465637,
|
| 194 |
+
"learning_rate": 1.8444444444444448e-05,
|
| 195 |
+
"epoch": 0.93,
|
| 196 |
+
"step": 1400
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"loss": 0.1324,
|
| 200 |
+
"grad_norm": 0.27331632375717163,
|
| 201 |
+
"learning_rate": 1.838888888888889e-05,
|
| 202 |
+
"epoch": 0.97,
|
| 203 |
+
"step": 1450
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"loss": 0.1324,
|
| 207 |
+
"grad_norm": 0.7121672034263611,
|
| 208 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"eval_loss": 0.12290950864553452,
|
| 214 |
+
"eval_accuracy": 0.43533333333333335,
|
| 215 |
+
"eval_f1": 0.8652792990142387,
|
| 216 |
+
"eval_precision": 0.9544356230583362,
|
| 217 |
+
"eval_recall": 0.7913566113337149,
|
| 218 |
+
"eval_runtime": 403.441,
|
| 219 |
+
"eval_samples_per_second": 3.718,
|
| 220 |
+
"eval_steps_per_second": 0.466,
|
| 221 |
+
"epoch": 1.0,
|
| 222 |
+
"step": 1500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"loss": 0.1187,
|
| 226 |
+
"grad_norm": 0.5251692533493042,
|
| 227 |
+
"learning_rate": 1.827777777777778e-05,
|
| 228 |
+
"epoch": 1.03,
|
| 229 |
+
"step": 1550
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"loss": 0.1219,
|
| 233 |
+
"grad_norm": 0.7017450332641602,
|
| 234 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 235 |
+
"epoch": 1.07,
|
| 236 |
+
"step": 1600
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"loss": 0.1116,
|
| 240 |
+
"grad_norm": 0.248159259557724,
|
| 241 |
+
"learning_rate": 1.8166666666666667e-05,
|
| 242 |
+
"epoch": 1.1,
|
| 243 |
+
"step": 1650
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"loss": 0.127,
|
| 247 |
+
"grad_norm": 0.9016281366348267,
|
| 248 |
+
"learning_rate": 1.8111111111111112e-05,
|
| 249 |
+
"epoch": 1.13,
|
| 250 |
+
"step": 1700
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"loss": 0.1203,
|
| 254 |
+
"grad_norm": 0.7193984389305115,
|
| 255 |
+
"learning_rate": 1.8055555555555558e-05,
|
| 256 |
+
"epoch": 1.17,
|
| 257 |
+
"step": 1750
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"loss": 0.1195,
|
| 261 |
+
"grad_norm": 0.7280067205429077,
|
| 262 |
+
"learning_rate": 1.8e-05,
|
| 263 |
+
"epoch": 1.2,
|
| 264 |
+
"step": 1800
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"loss": 0.1094,
|
| 268 |
+
"grad_norm": 0.906154453754425,
|
| 269 |
+
"learning_rate": 1.7944444444444446e-05,
|
| 270 |
+
"epoch": 1.23,
|
| 271 |
+
"step": 1850
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"loss": 0.1155,
|
| 275 |
+
"grad_norm": 0.4714917838573456,
|
| 276 |
+
"learning_rate": 1.7888888888888892e-05,
|
| 277 |
+
"epoch": 1.27,
|
| 278 |
+
"step": 1900
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"loss": 0.1106,
|
| 282 |
+
"grad_norm": 0.7589433789253235,
|
| 283 |
+
"learning_rate": 1.7833333333333334e-05,
|
| 284 |
+
"epoch": 1.3,
|
| 285 |
+
"step": 1950
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"loss": 0.1052,
|
| 289 |
+
"grad_norm": 0.5668336153030396,
|
| 290 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 291 |
+
"epoch": 1.33,
|
| 292 |
+
"step": 2000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"loss": 0.1084,
|
| 296 |
+
"grad_norm": 1.1015430688858032,
|
| 297 |
+
"learning_rate": 1.7722222222222222e-05,
|
| 298 |
+
"epoch": 1.37,
|
| 299 |
+
"step": 2050
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"loss": 0.1017,
|
| 303 |
+
"grad_norm": 0.23899418115615845,
|
| 304 |
+
"learning_rate": 1.7666666666666668e-05,
|
| 305 |
+
"epoch": 1.4,
|
| 306 |
+
"step": 2100
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"loss": 0.1042,
|
| 310 |
+
"grad_norm": 0.6596136689186096,
|
| 311 |
+
"learning_rate": 1.7611111111111114e-05,
|
| 312 |
+
"epoch": 1.43,
|
| 313 |
+
"step": 2150
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"loss": 0.1054,
|
| 317 |
+
"grad_norm": 0.5246695280075073,
|
| 318 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 319 |
+
"epoch": 1.47,
|
| 320 |
+
"step": 2200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"loss": 0.103,
|
| 324 |
+
"grad_norm": 0.7709386348724365,
|
| 325 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 326 |
+
"epoch": 1.5,
|
| 327 |
+
"step": 2250
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"loss": 0.0977,
|
| 331 |
+
"grad_norm": 0.6520675420761108,
|
| 332 |
+
"learning_rate": 1.7444444444444448e-05,
|
| 333 |
+
"epoch": 1.53,
|
| 334 |
+
"step": 2300
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"loss": 0.0931,
|
| 338 |
+
"grad_norm": 0.44711801409721375,
|
| 339 |
+
"learning_rate": 1.738888888888889e-05,
|
| 340 |
+
"epoch": 1.57,
|
| 341 |
+
"step": 2350
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"loss": 0.0937,
|
| 345 |
+
"grad_norm": 0.7022482752799988,
|
| 346 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 347 |
+
"epoch": 1.6,
|
| 348 |
+
"step": 2400
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"loss": 0.0961,
|
| 352 |
+
"grad_norm": 0.9846331477165222,
|
| 353 |
+
"learning_rate": 1.727777777777778e-05,
|
| 354 |
+
"epoch": 1.63,
|
| 355 |
+
"step": 2450
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"loss": 0.0974,
|
| 359 |
+
"grad_norm": 0.5135018229484558,
|
| 360 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 361 |
+
"epoch": 1.67,
|
| 362 |
+
"step": 2500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"loss": 0.0822,
|
| 366 |
+
"grad_norm": 0.47495317459106445,
|
| 367 |
+
"learning_rate": 1.7166666666666666e-05,
|
| 368 |
+
"epoch": 1.7,
|
| 369 |
+
"step": 2550
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"loss": 0.0883,
|
| 373 |
+
"grad_norm": 0.6149684190750122,
|
| 374 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 375 |
+
"epoch": 1.73,
|
| 376 |
+
"step": 2600
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"loss": 0.0932,
|
| 380 |
+
"grad_norm": 0.85074782371521,
|
| 381 |
+
"learning_rate": 1.7055555555555558e-05,
|
| 382 |
+
"epoch": 1.77,
|
| 383 |
+
"step": 2650
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"loss": 0.083,
|
| 387 |
+
"grad_norm": 0.5721635222434998,
|
| 388 |
+
"learning_rate": 1.7e-05,
|
| 389 |
+
"epoch": 1.8,
|
| 390 |
+
"step": 2700
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"loss": 0.0829,
|
| 394 |
+
"grad_norm": 0.31835615634918213,
|
| 395 |
+
"learning_rate": 1.6944444444444446e-05,
|
| 396 |
+
"epoch": 1.83,
|
| 397 |
+
"step": 2750
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"loss": 0.079,
|
| 401 |
+
"grad_norm": 0.616396963596344,
|
| 402 |
+
"learning_rate": 1.688888888888889e-05,
|
| 403 |
+
"epoch": 1.87,
|
| 404 |
+
"step": 2800
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"loss": 0.0855,
|
| 408 |
+
"grad_norm": 0.711447536945343,
|
| 409 |
+
"learning_rate": 1.6833333333333334e-05,
|
| 410 |
+
"epoch": 1.9,
|
| 411 |
+
"step": 2850
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"loss": 0.0895,
|
| 415 |
+
"grad_norm": 0.48665234446525574,
|
| 416 |
+
"learning_rate": 1.677777777777778e-05,
|
| 417 |
+
"epoch": 1.93,
|
| 418 |
+
"step": 2900
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"loss": 0.0874,
|
| 422 |
+
"grad_norm": 0.7903698086738586,
|
| 423 |
+
"learning_rate": 1.6722222222222225e-05,
|
| 424 |
+
"epoch": 1.97,
|
| 425 |
+
"step": 2950
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"loss": 0.0838,
|
| 429 |
+
"grad_norm": 0.3140181005001068,
|
| 430 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 431 |
+
"epoch": 2.0,
|
| 432 |
+
"step": 3000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"eval_loss": 0.07791818678379059,
|
| 436 |
+
"eval_accuracy": 0.604,
|
| 437 |
+
"eval_f1": 0.925355272999252,
|
| 438 |
+
"eval_precision": 0.9692886242557192,
|
| 439 |
+
"eval_recall": 0.885231825987407,
|
| 440 |
+
"eval_runtime": 404.0361,
|
| 441 |
+
"eval_samples_per_second": 3.713,
|
| 442 |
+
"eval_steps_per_second": 0.465,
|
| 443 |
+
"epoch": 2.0,
|
| 444 |
+
"step": 3000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"loss": 0.0793,
|
| 448 |
+
"grad_norm": 0.4299638271331787,
|
| 449 |
+
"learning_rate": 1.6611111111111113e-05,
|
| 450 |
+
"epoch": 2.03,
|
| 451 |
+
"step": 3050
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"loss": 0.0719,
|
| 455 |
+
"grad_norm": 0.5105370283126831,
|
| 456 |
+
"learning_rate": 1.6555555555555556e-05,
|
| 457 |
+
"epoch": 2.07,
|
| 458 |
+
"step": 3100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"loss": 0.0675,
|
| 462 |
+
"grad_norm": 0.8778389096260071,
|
| 463 |
+
"learning_rate": 1.65e-05,
|
| 464 |
+
"epoch": 2.1,
|
| 465 |
+
"step": 3150
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"loss": 0.071,
|
| 469 |
+
"grad_norm": 0.4817022681236267,
|
| 470 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 471 |
+
"epoch": 2.13,
|
| 472 |
+
"step": 3200
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"loss": 0.0744,
|
| 476 |
+
"grad_norm": 0.5327057242393494,
|
| 477 |
+
"learning_rate": 1.638888888888889e-05,
|
| 478 |
+
"epoch": 2.17,
|
| 479 |
+
"step": 3250
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"loss": 0.0761,
|
| 483 |
+
"grad_norm": 0.3640955090522766,
|
| 484 |
+
"learning_rate": 1.6333333333333335e-05,
|
| 485 |
+
"epoch": 2.2,
|
| 486 |
+
"step": 3300
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"loss": 0.0788,
|
| 490 |
+
"grad_norm": 0.3881916105747223,
|
| 491 |
+
"learning_rate": 1.6277777777777777e-05,
|
| 492 |
+
"epoch": 2.23,
|
| 493 |
+
"step": 3350
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"loss": 0.0701,
|
| 497 |
+
"grad_norm": 0.30048519372940063,
|
| 498 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 499 |
+
"epoch": 2.27,
|
| 500 |
+
"step": 3400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"loss": 0.0716,
|
| 504 |
+
"grad_norm": 0.6386255621910095,
|
| 505 |
+
"learning_rate": 1.616666666666667e-05,
|
| 506 |
+
"epoch": 2.3,
|
| 507 |
+
"step": 3450
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"loss": 0.0665,
|
| 511 |
+
"grad_norm": 0.950891375541687,
|
| 512 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 513 |
+
"epoch": 2.33,
|
| 514 |
+
"step": 3500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"loss": 0.0659,
|
| 518 |
+
"grad_norm": 0.5039156675338745,
|
| 519 |
+
"learning_rate": 1.6055555555555557e-05,
|
| 520 |
+
"epoch": 2.37,
|
| 521 |
+
"step": 3550
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"loss": 0.0706,
|
| 525 |
+
"grad_norm": 0.20529164373874664,
|
| 526 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 527 |
+
"epoch": 2.4,
|
| 528 |
+
"step": 3600
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"loss": 0.0653,
|
| 532 |
+
"grad_norm": 0.4774051010608673,
|
| 533 |
+
"learning_rate": 1.594444444444445e-05,
|
| 534 |
+
"epoch": 2.43,
|
| 535 |
+
"step": 3650
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"loss": 0.0674,
|
| 539 |
+
"grad_norm": 0.4316297471523285,
|
| 540 |
+
"learning_rate": 1.588888888888889e-05,
|
| 541 |
+
"epoch": 2.47,
|
| 542 |
+
"step": 3700
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"loss": 0.073,
|
| 546 |
+
"grad_norm": 1.2835804224014282,
|
| 547 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 548 |
+
"epoch": 2.5,
|
| 549 |
+
"step": 3750
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"loss": 0.064,
|
| 553 |
+
"grad_norm": 0.27332884073257446,
|
| 554 |
+
"learning_rate": 1.577777777777778e-05,
|
| 555 |
+
"epoch": 2.53,
|
| 556 |
+
"step": 3800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"loss": 0.0695,
|
| 560 |
+
"grad_norm": 3.6316583156585693,
|
| 561 |
+
"learning_rate": 1.5722222222222225e-05,
|
| 562 |
+
"epoch": 2.57,
|
| 563 |
+
"step": 3850
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"loss": 0.0626,
|
| 567 |
+
"grad_norm": 0.5828558206558228,
|
| 568 |
+
"learning_rate": 1.5666666666666667e-05,
|
| 569 |
+
"epoch": 2.6,
|
| 570 |
+
"step": 3900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"loss": 0.0703,
|
| 574 |
+
"grad_norm": 0.4646282494068146,
|
| 575 |
+
"learning_rate": 1.5611111111111113e-05,
|
| 576 |
+
"epoch": 2.63,
|
| 577 |
+
"step": 3950
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"loss": 0.0654,
|
| 581 |
+
"grad_norm": 0.7953578233718872,
|
| 582 |
+
"learning_rate": 1.555555555555556e-05,
|
| 583 |
+
"epoch": 2.67,
|
| 584 |
+
"step": 4000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"loss": 0.0647,
|
| 588 |
+
"grad_norm": 1.1880340576171875,
|
| 589 |
+
"learning_rate": 1.55e-05,
|
| 590 |
+
"epoch": 2.7,
|
| 591 |
+
"step": 4050
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"loss": 0.0637,
|
| 595 |
+
"grad_norm": 0.5192042589187622,
|
| 596 |
+
"learning_rate": 1.5444444444444446e-05,
|
| 597 |
+
"epoch": 2.73,
|
| 598 |
+
"step": 4100
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"loss": 0.0648,
|
| 602 |
+
"grad_norm": 0.5041971802711487,
|
| 603 |
+
"learning_rate": 1.5388888888888892e-05,
|
| 604 |
+
"epoch": 2.77,
|
| 605 |
+
"step": 4150
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"loss": 0.0651,
|
| 609 |
+
"grad_norm": 0.5176190733909607,
|
| 610 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 611 |
+
"epoch": 2.8,
|
| 612 |
+
"step": 4200
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"loss": 0.0591,
|
| 616 |
+
"grad_norm": 0.6175917983055115,
|
| 617 |
+
"learning_rate": 1.5277777777777777e-05,
|
| 618 |
+
"epoch": 2.83,
|
| 619 |
+
"step": 4250
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"loss": 0.0681,
|
| 623 |
+
"grad_norm": 0.9707493185997009,
|
| 624 |
+
"learning_rate": 1.5222222222222223e-05,
|
| 625 |
+
"epoch": 2.87,
|
| 626 |
+
"step": 4300
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"loss": 0.0624,
|
| 630 |
+
"grad_norm": 0.5937142372131348,
|
| 631 |
+
"learning_rate": 1.5166666666666667e-05,
|
| 632 |
+
"epoch": 2.9,
|
| 633 |
+
"step": 4350
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"loss": 0.0632,
|
| 637 |
+
"grad_norm": 0.45223355293273926,
|
| 638 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 639 |
+
"epoch": 2.93,
|
| 640 |
+
"step": 4400
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"loss": 0.0623,
|
| 644 |
+
"grad_norm": 0.6646191477775574,
|
| 645 |
+
"learning_rate": 1.5055555555555556e-05,
|
| 646 |
+
"epoch": 2.97,
|
| 647 |
+
"step": 4450
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"loss": 0.0589,
|
| 651 |
+
"grad_norm": 0.29040953516960144,
|
| 652 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 653 |
+
"epoch": 3.0,
|
| 654 |
+
"step": 4500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"eval_loss": 0.059341732412576675,
|
| 658 |
+
"eval_accuracy": 0.7013333333333334,
|
| 659 |
+
"eval_f1": 0.9475547687541491,
|
| 660 |
+
"eval_precision": 0.9777743948850662,
|
| 661 |
+
"eval_recall": 0.9191471093302804,
|
| 662 |
+
"eval_runtime": 373.05,
|
| 663 |
+
"eval_samples_per_second": 4.021,
|
| 664 |
+
"eval_steps_per_second": 0.504,
|
| 665 |
+
"epoch": 3.0,
|
| 666 |
+
"step": 4500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"loss": 0.0614,
|
| 670 |
+
"grad_norm": 0.9815644025802612,
|
| 671 |
+
"learning_rate": 1.4944444444444446e-05,
|
| 672 |
+
"epoch": 3.03,
|
| 673 |
+
"step": 4550
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"loss": 0.054,
|
| 677 |
+
"grad_norm": 0.6002834439277649,
|
| 678 |
+
"learning_rate": 1.488888888888889e-05,
|
| 679 |
+
"epoch": 3.07,
|
| 680 |
+
"step": 4600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"loss": 0.0519,
|
| 684 |
+
"grad_norm": 0.658513069152832,
|
| 685 |
+
"learning_rate": 1.4833333333333336e-05,
|
| 686 |
+
"epoch": 3.1,
|
| 687 |
+
"step": 4650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"loss": 0.0536,
|
| 691 |
+
"grad_norm": 0.48609504103660583,
|
| 692 |
+
"learning_rate": 1.477777777777778e-05,
|
| 693 |
+
"epoch": 3.13,
|
| 694 |
+
"step": 4700
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"loss": 0.0525,
|
| 698 |
+
"grad_norm": 0.21742594242095947,
|
| 699 |
+
"learning_rate": 1.4722222222222224e-05,
|
| 700 |
+
"epoch": 3.17,
|
| 701 |
+
"step": 4750
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"loss": 0.0584,
|
| 705 |
+
"grad_norm": 0.845954418182373,
|
| 706 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 707 |
+
"epoch": 3.2,
|
| 708 |
+
"step": 4800
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"loss": 0.0494,
|
| 712 |
+
"grad_norm": 0.9900146126747131,
|
| 713 |
+
"learning_rate": 1.4611111111111112e-05,
|
| 714 |
+
"epoch": 3.23,
|
| 715 |
+
"step": 4850
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"loss": 0.0555,
|
| 719 |
+
"grad_norm": 0.1688126176595688,
|
| 720 |
+
"learning_rate": 1.4555555555555556e-05,
|
| 721 |
+
"epoch": 3.27,
|
| 722 |
+
"step": 4900
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"loss": 0.0518,
|
| 726 |
+
"grad_norm": 0.2642045319080353,
|
| 727 |
+
"learning_rate": 1.45e-05,
|
| 728 |
+
"epoch": 3.3,
|
| 729 |
+
"step": 4950
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"loss": 0.0436,
|
| 733 |
+
"grad_norm": 0.3140838146209717,
|
| 734 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 735 |
+
"epoch": 3.33,
|
| 736 |
+
"step": 5000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"loss": 0.0532,
|
| 740 |
+
"grad_norm": 0.8053641319274902,
|
| 741 |
+
"learning_rate": 1.438888888888889e-05,
|
| 742 |
+
"epoch": 3.37,
|
| 743 |
+
"step": 5050
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"loss": 0.0556,
|
| 747 |
+
"grad_norm": 1.414271354675293,
|
| 748 |
+
"learning_rate": 1.4333333333333334e-05,
|
| 749 |
+
"epoch": 3.4,
|
| 750 |
+
"step": 5100
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"loss": 0.0571,
|
| 754 |
+
"grad_norm": 0.5971333384513855,
|
| 755 |
+
"learning_rate": 1.427777777777778e-05,
|
| 756 |
+
"epoch": 3.43,
|
| 757 |
+
"step": 5150
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"loss": 0.053,
|
| 761 |
+
"grad_norm": 0.4587002694606781,
|
| 762 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 763 |
+
"epoch": 3.47,
|
| 764 |
+
"step": 5200
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"loss": 0.0504,
|
| 768 |
+
"grad_norm": 0.6501361131668091,
|
| 769 |
+
"learning_rate": 1.416666666666667e-05,
|
| 770 |
+
"epoch": 3.5,
|
| 771 |
+
"step": 5250
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"loss": 0.0533,
|
| 775 |
+
"grad_norm": 1.1308332681655884,
|
| 776 |
+
"learning_rate": 1.4111111111111113e-05,
|
| 777 |
+
"epoch": 3.53,
|
| 778 |
+
"step": 5300
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"loss": 0.0508,
|
| 782 |
+
"grad_norm": 1.671701192855835,
|
| 783 |
+
"learning_rate": 1.4055555555555556e-05,
|
| 784 |
+
"epoch": 3.57,
|
| 785 |
+
"step": 5350
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"loss": 0.0526,
|
| 789 |
+
"grad_norm": 0.7493703961372375,
|
| 790 |
+
"learning_rate": 1.4e-05,
|
| 791 |
+
"epoch": 3.6,
|
| 792 |
+
"step": 5400
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"loss": 0.0523,
|
| 796 |
+
"grad_norm": 0.1724095195531845,
|
| 797 |
+
"learning_rate": 1.3944444444444446e-05,
|
| 798 |
+
"epoch": 3.63,
|
| 799 |
+
"step": 5450
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"loss": 0.0471,
|
| 803 |
+
"grad_norm": 0.28638821840286255,
|
| 804 |
+
"learning_rate": 1.388888888888889e-05,
|
| 805 |
+
"epoch": 3.67,
|
| 806 |
+
"step": 5500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"loss": 0.0539,
|
| 810 |
+
"grad_norm": 1.1178017854690552,
|
| 811 |
+
"learning_rate": 1.3833333333333334e-05,
|
| 812 |
+
"epoch": 3.7,
|
| 813 |
+
"step": 5550
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"loss": 0.0454,
|
| 817 |
+
"grad_norm": 0.3396628499031067,
|
| 818 |
+
"learning_rate": 1.377777777777778e-05,
|
| 819 |
+
"epoch": 3.73,
|
| 820 |
+
"step": 5600
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"loss": 0.0458,
|
| 824 |
+
"grad_norm": 0.6596197485923767,
|
| 825 |
+
"learning_rate": 1.3722222222222223e-05,
|
| 826 |
+
"epoch": 3.77,
|
| 827 |
+
"step": 5650
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"loss": 0.0491,
|
| 831 |
+
"grad_norm": 0.6554704308509827,
|
| 832 |
+
"learning_rate": 1.3666666666666667e-05,
|
| 833 |
+
"epoch": 3.8,
|
| 834 |
+
"step": 5700
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"loss": 0.042,
|
| 838 |
+
"grad_norm": 0.16569265723228455,
|
| 839 |
+
"learning_rate": 1.3611111111111113e-05,
|
| 840 |
+
"epoch": 3.83,
|
| 841 |
+
"step": 5750
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"loss": 0.0489,
|
| 845 |
+
"grad_norm": 0.4453265964984894,
|
| 846 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 847 |
+
"epoch": 3.87,
|
| 848 |
+
"step": 5800
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"loss": 0.0479,
|
| 852 |
+
"grad_norm": 0.917383074760437,
|
| 853 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 854 |
+
"epoch": 3.9,
|
| 855 |
+
"step": 5850
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"loss": 0.0502,
|
| 859 |
+
"grad_norm": 0.8061167597770691,
|
| 860 |
+
"learning_rate": 1.3444444444444447e-05,
|
| 861 |
+
"epoch": 3.93,
|
| 862 |
+
"step": 5900
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"loss": 0.045,
|
| 866 |
+
"grad_norm": 0.14958856999874115,
|
| 867 |
+
"learning_rate": 1.338888888888889e-05,
|
| 868 |
+
"epoch": 3.97,
|
| 869 |
+
"step": 5950
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"loss": 0.0486,
|
| 873 |
+
"grad_norm": 0.5399668216705322,
|
| 874 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 875 |
+
"epoch": 4.0,
|
| 876 |
+
"step": 6000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"eval_loss": 0.05016530305147171,
|
| 880 |
+
"eval_accuracy": 0.7253333333333334,
|
| 881 |
+
"eval_f1": 0.952742677671463,
|
| 882 |
+
"eval_precision": 0.9729971654483067,
|
| 883 |
+
"eval_recall": 0.9333142530051517,
|
| 884 |
+
"eval_runtime": 401.4594,
|
| 885 |
+
"eval_samples_per_second": 3.736,
|
| 886 |
+
"eval_steps_per_second": 0.468,
|
| 887 |
+
"epoch": 4.0,
|
| 888 |
+
"step": 6000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"loss": 0.0403,
|
| 892 |
+
"grad_norm": 1.0464340448379517,
|
| 893 |
+
"learning_rate": 1.3277777777777779e-05,
|
| 894 |
+
"epoch": 4.03,
|
| 895 |
+
"step": 6050
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"loss": 0.0398,
|
| 899 |
+
"grad_norm": 0.4619244635105133,
|
| 900 |
+
"learning_rate": 1.3222222222222223e-05,
|
| 901 |
+
"epoch": 4.07,
|
| 902 |
+
"step": 6100
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"loss": 0.0446,
|
| 906 |
+
"grad_norm": 0.8172645568847656,
|
| 907 |
+
"learning_rate": 1.3166666666666667e-05,
|
| 908 |
+
"epoch": 4.1,
|
| 909 |
+
"step": 6150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"loss": 0.0423,
|
| 913 |
+
"grad_norm": 0.7000390291213989,
|
| 914 |
+
"learning_rate": 1.3111111111111113e-05,
|
| 915 |
+
"epoch": 4.13,
|
| 916 |
+
"step": 6200
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"loss": 0.0373,
|
| 920 |
+
"grad_norm": 1.2198138236999512,
|
| 921 |
+
"learning_rate": 1.3055555555555557e-05,
|
| 922 |
+
"epoch": 4.17,
|
| 923 |
+
"step": 6250
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"loss": 0.0434,
|
| 927 |
+
"grad_norm": 0.25625166296958923,
|
| 928 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 929 |
+
"epoch": 4.2,
|
| 930 |
+
"step": 6300
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"loss": 0.0434,
|
| 934 |
+
"grad_norm": 0.8375250697135925,
|
| 935 |
+
"learning_rate": 1.2944444444444447e-05,
|
| 936 |
+
"epoch": 4.23,
|
| 937 |
+
"step": 6350
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"loss": 0.0419,
|
| 941 |
+
"grad_norm": 1.2568154335021973,
|
| 942 |
+
"learning_rate": 1.288888888888889e-05,
|
| 943 |
+
"epoch": 4.27,
|
| 944 |
+
"step": 6400
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"loss": 0.04,
|
| 948 |
+
"grad_norm": 0.08529137074947357,
|
| 949 |
+
"learning_rate": 1.2833333333333335e-05,
|
| 950 |
+
"epoch": 4.3,
|
| 951 |
+
"step": 6450
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"loss": 0.0408,
|
| 955 |
+
"grad_norm": 0.8144034147262573,
|
| 956 |
+
"learning_rate": 1.2777777777777777e-05,
|
| 957 |
+
"epoch": 4.33,
|
| 958 |
+
"step": 6500
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"loss": 0.0421,
|
| 962 |
+
"grad_norm": 0.41111770272254944,
|
| 963 |
+
"learning_rate": 1.2722222222222223e-05,
|
| 964 |
+
"epoch": 4.37,
|
| 965 |
+
"step": 6550
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"loss": 0.0433,
|
| 969 |
+
"grad_norm": 0.40817421674728394,
|
| 970 |
+
"learning_rate": 1.2666666666666667e-05,
|
| 971 |
+
"epoch": 4.4,
|
| 972 |
+
"step": 6600
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"loss": 0.0393,
|
| 976 |
+
"grad_norm": 0.6191626787185669,
|
| 977 |
+
"learning_rate": 1.2611111111111113e-05,
|
| 978 |
+
"epoch": 4.43,
|
| 979 |
+
"step": 6650
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"loss": 0.0339,
|
| 983 |
+
"grad_norm": 0.46081477403640747,
|
| 984 |
+
"learning_rate": 1.2555555555555557e-05,
|
| 985 |
+
"epoch": 4.47,
|
| 986 |
+
"step": 6700
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"loss": 0.0422,
|
| 990 |
+
"grad_norm": 0.453768789768219,
|
| 991 |
+
"learning_rate": 1.25e-05,
|
| 992 |
+
"epoch": 4.5,
|
| 993 |
+
"step": 6750
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"loss": 0.0382,
|
| 997 |
+
"grad_norm": 0.3311583399772644,
|
| 998 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 999 |
+
"epoch": 4.53,
|
| 1000 |
+
"step": 6800
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"loss": 0.04,
|
| 1004 |
+
"grad_norm": 0.5008330345153809,
|
| 1005 |
+
"learning_rate": 1.238888888888889e-05,
|
| 1006 |
+
"epoch": 4.57,
|
| 1007 |
+
"step": 6850
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"loss": 0.0389,
|
| 1011 |
+
"grad_norm": 0.9684385061264038,
|
| 1012 |
+
"learning_rate": 1.2333333333333334e-05,
|
| 1013 |
+
"epoch": 4.6,
|
| 1014 |
+
"step": 6900
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"loss": 0.0393,
|
| 1018 |
+
"grad_norm": 0.38716915249824524,
|
| 1019 |
+
"learning_rate": 1.227777777777778e-05,
|
| 1020 |
+
"epoch": 4.63,
|
| 1021 |
+
"step": 6950
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"loss": 0.0428,
|
| 1025 |
+
"grad_norm": 0.7534592151641846,
|
| 1026 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 1027 |
+
"epoch": 4.67,
|
| 1028 |
+
"step": 7000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"loss": 0.0416,
|
| 1032 |
+
"grad_norm": 0.6481875777244568,
|
| 1033 |
+
"learning_rate": 1.2166666666666667e-05,
|
| 1034 |
+
"epoch": 4.7,
|
| 1035 |
+
"step": 7050
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"loss": 0.0377,
|
| 1039 |
+
"grad_norm": 0.93485027551651,
|
| 1040 |
+
"learning_rate": 1.211111111111111e-05,
|
| 1041 |
+
"epoch": 4.73,
|
| 1042 |
+
"step": 7100
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"loss": 0.0397,
|
| 1046 |
+
"grad_norm": 0.3216228485107422,
|
| 1047 |
+
"learning_rate": 1.2055555555555556e-05,
|
| 1048 |
+
"epoch": 4.77,
|
| 1049 |
+
"step": 7150
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"loss": 0.0382,
|
| 1053 |
+
"grad_norm": 0.6930127143859863,
|
| 1054 |
+
"learning_rate": 1.2e-05,
|
| 1055 |
+
"epoch": 4.8,
|
| 1056 |
+
"step": 7200
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"loss": 0.0378,
|
| 1060 |
+
"grad_norm": 0.2020283341407776,
|
| 1061 |
+
"learning_rate": 1.1944444444444444e-05,
|
| 1062 |
+
"epoch": 4.83,
|
| 1063 |
+
"step": 7250
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"loss": 0.0384,
|
| 1067 |
+
"grad_norm": 0.35124385356903076,
|
| 1068 |
+
"learning_rate": 1.188888888888889e-05,
|
| 1069 |
+
"epoch": 4.87,
|
| 1070 |
+
"step": 7300
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"loss": 0.038,
|
| 1074 |
+
"grad_norm": 0.5830740928649902,
|
| 1075 |
+
"learning_rate": 1.1833333333333334e-05,
|
| 1076 |
+
"epoch": 4.9,
|
| 1077 |
+
"step": 7350
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"loss": 0.04,
|
| 1081 |
+
"grad_norm": 0.8609558343887329,
|
| 1082 |
+
"learning_rate": 1.177777777777778e-05,
|
| 1083 |
+
"epoch": 4.93,
|
| 1084 |
+
"step": 7400
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"loss": 0.0446,
|
| 1088 |
+
"grad_norm": 0.8603160977363586,
|
| 1089 |
+
"learning_rate": 1.1722222222222224e-05,
|
| 1090 |
+
"epoch": 4.97,
|
| 1091 |
+
"step": 7450
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"loss": 0.0405,
|
| 1095 |
+
"grad_norm": 0.3362710475921631,
|
| 1096 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 1097 |
+
"epoch": 5.0,
|
| 1098 |
+
"step": 7500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"eval_loss": 0.04217784106731415,
|
| 1102 |
+
"eval_accuracy": 0.7713333333333333,
|
| 1103 |
+
"eval_f1": 0.9617064647641235,
|
| 1104 |
+
"eval_precision": 0.9788085358624777,
|
| 1105 |
+
"eval_recall": 0.9451917572982256,
|
| 1106 |
+
"eval_runtime": 421.9356,
|
| 1107 |
+
"eval_samples_per_second": 3.555,
|
| 1108 |
+
"eval_steps_per_second": 0.446,
|
| 1109 |
+
"epoch": 5.0,
|
| 1110 |
+
"step": 7500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"loss": 0.031,
|
| 1114 |
+
"grad_norm": 0.6572943925857544,
|
| 1115 |
+
"learning_rate": 1.1611111111111114e-05,
|
| 1116 |
+
"epoch": 5.03,
|
| 1117 |
+
"step": 7550
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"loss": 0.0351,
|
| 1121 |
+
"grad_norm": 0.6608228087425232,
|
| 1122 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 1123 |
+
"epoch": 5.07,
|
| 1124 |
+
"step": 7600
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"loss": 0.0335,
|
| 1128 |
+
"grad_norm": 0.34060031175613403,
|
| 1129 |
+
"learning_rate": 1.15e-05,
|
| 1130 |
+
"epoch": 5.1,
|
| 1131 |
+
"step": 7650
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"loss": 0.0358,
|
| 1135 |
+
"grad_norm": 0.8972667455673218,
|
| 1136 |
+
"learning_rate": 1.1444444444444444e-05,
|
| 1137 |
+
"epoch": 5.13,
|
| 1138 |
+
"step": 7700
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"loss": 0.0337,
|
| 1142 |
+
"grad_norm": 0.42261555790901184,
|
| 1143 |
+
"learning_rate": 1.138888888888889e-05,
|
| 1144 |
+
"epoch": 5.17,
|
| 1145 |
+
"step": 7750
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"loss": 0.0329,
|
| 1149 |
+
"grad_norm": 0.5377686619758606,
|
| 1150 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 1151 |
+
"epoch": 5.2,
|
| 1152 |
+
"step": 7800
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"loss": 0.0359,
|
| 1156 |
+
"grad_norm": 0.5514285564422607,
|
| 1157 |
+
"learning_rate": 1.1277777777777778e-05,
|
| 1158 |
+
"epoch": 5.23,
|
| 1159 |
+
"step": 7850
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"loss": 0.035,
|
| 1163 |
+
"grad_norm": 0.3760692775249481,
|
| 1164 |
+
"learning_rate": 1.1222222222222224e-05,
|
| 1165 |
+
"epoch": 5.27,
|
| 1166 |
+
"step": 7900
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"loss": 0.0358,
|
| 1170 |
+
"grad_norm": 0.11783821135759354,
|
| 1171 |
+
"learning_rate": 1.1166666666666668e-05,
|
| 1172 |
+
"epoch": 5.3,
|
| 1173 |
+
"step": 7950
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"loss": 0.0351,
|
| 1177 |
+
"grad_norm": 1.0664758682250977,
|
| 1178 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 1179 |
+
"epoch": 5.33,
|
| 1180 |
+
"step": 8000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"loss": 0.0312,
|
| 1184 |
+
"grad_norm": 0.8289102911949158,
|
| 1185 |
+
"learning_rate": 1.1055555555555557e-05,
|
| 1186 |
+
"epoch": 5.37,
|
| 1187 |
+
"step": 8050
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"loss": 0.0325,
|
| 1191 |
+
"grad_norm": 0.4296257197856903,
|
| 1192 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 1193 |
+
"epoch": 5.4,
|
| 1194 |
+
"step": 8100
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"loss": 0.0329,
|
| 1198 |
+
"grad_norm": 0.43858158588409424,
|
| 1199 |
+
"learning_rate": 1.0944444444444447e-05,
|
| 1200 |
+
"epoch": 5.43,
|
| 1201 |
+
"step": 8150
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"loss": 0.0313,
|
| 1205 |
+
"grad_norm": 0.7341222763061523,
|
| 1206 |
+
"learning_rate": 1.088888888888889e-05,
|
| 1207 |
+
"epoch": 5.47,
|
| 1208 |
+
"step": 8200
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"loss": 0.0318,
|
| 1212 |
+
"grad_norm": 0.0853128656744957,
|
| 1213 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 1214 |
+
"epoch": 5.5,
|
| 1215 |
+
"step": 8250
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"loss": 0.0305,
|
| 1219 |
+
"grad_norm": 0.3742698132991791,
|
| 1220 |
+
"learning_rate": 1.0777777777777778e-05,
|
| 1221 |
+
"epoch": 5.53,
|
| 1222 |
+
"step": 8300
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"loss": 0.0347,
|
| 1226 |
+
"grad_norm": 1.1857047080993652,
|
| 1227 |
+
"learning_rate": 1.0722222222222223e-05,
|
| 1228 |
+
"epoch": 5.57,
|
| 1229 |
+
"step": 8350
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"loss": 0.0376,
|
| 1233 |
+
"grad_norm": 0.6907274127006531,
|
| 1234 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 1235 |
+
"epoch": 5.6,
|
| 1236 |
+
"step": 8400
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"loss": 0.0362,
|
| 1240 |
+
"grad_norm": 1.3683446645736694,
|
| 1241 |
+
"learning_rate": 1.0611111111111111e-05,
|
| 1242 |
+
"epoch": 5.63,
|
| 1243 |
+
"step": 8450
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"loss": 0.028,
|
| 1247 |
+
"grad_norm": 0.4153459966182709,
|
| 1248 |
+
"learning_rate": 1.0555555555555557e-05,
|
| 1249 |
+
"epoch": 5.67,
|
| 1250 |
+
"step": 8500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"loss": 0.029,
|
| 1254 |
+
"grad_norm": 0.3362661600112915,
|
| 1255 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 1256 |
+
"epoch": 5.7,
|
| 1257 |
+
"step": 8550
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"loss": 0.0336,
|
| 1261 |
+
"grad_norm": 0.6201055645942688,
|
| 1262 |
+
"learning_rate": 1.0444444444444445e-05,
|
| 1263 |
+
"epoch": 5.73,
|
| 1264 |
+
"step": 8600
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"loss": 0.0299,
|
| 1268 |
+
"grad_norm": 0.4934876263141632,
|
| 1269 |
+
"learning_rate": 1.0388888888888891e-05,
|
| 1270 |
+
"epoch": 5.77,
|
| 1271 |
+
"step": 8650
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"loss": 0.0311,
|
| 1275 |
+
"grad_norm": 0.7425228953361511,
|
| 1276 |
+
"learning_rate": 1.0333333333333335e-05,
|
| 1277 |
+
"epoch": 5.8,
|
| 1278 |
+
"step": 8700
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"loss": 0.033,
|
| 1282 |
+
"grad_norm": 0.9107281565666199,
|
| 1283 |
+
"learning_rate": 1.0277777777777777e-05,
|
| 1284 |
+
"epoch": 5.83,
|
| 1285 |
+
"step": 8750
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"loss": 0.0284,
|
| 1289 |
+
"grad_norm": 0.7918747663497925,
|
| 1290 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 1291 |
+
"epoch": 5.87,
|
| 1292 |
+
"step": 8800
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"loss": 0.0311,
|
| 1296 |
+
"grad_norm": 0.8067458868026733,
|
| 1297 |
+
"learning_rate": 1.0166666666666667e-05,
|
| 1298 |
+
"epoch": 5.9,
|
| 1299 |
+
"step": 8850
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"loss": 0.029,
|
| 1303 |
+
"grad_norm": 0.8999997973442078,
|
| 1304 |
+
"learning_rate": 1.0111111111111111e-05,
|
| 1305 |
+
"epoch": 5.93,
|
| 1306 |
+
"step": 8900
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"loss": 0.0288,
|
| 1310 |
+
"grad_norm": 0.5887193083763123,
|
| 1311 |
+
"learning_rate": 1.0055555555555557e-05,
|
| 1312 |
+
"epoch": 5.97,
|
| 1313 |
+
"step": 8950
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"loss": 0.029,
|
| 1317 |
+
"grad_norm": 0.12278777360916138,
|
| 1318 |
+
"learning_rate": 1e-05,
|
| 1319 |
+
"epoch": 6.0,
|
| 1320 |
+
"step": 9000
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"eval_loss": 0.038735076785087585,
|
| 1324 |
+
"eval_accuracy": 0.79,
|
| 1325 |
+
"eval_f1": 0.963403145155446,
|
| 1326 |
+
"eval_precision": 0.9759213037733079,
|
| 1327 |
+
"eval_recall": 0.9512020606754437,
|
| 1328 |
+
"eval_runtime": 420.923,
|
| 1329 |
+
"eval_samples_per_second": 3.564,
|
| 1330 |
+
"eval_steps_per_second": 0.447,
|
| 1331 |
+
"epoch": 6.0,
|
| 1332 |
+
"step": 9000
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"loss": 0.0311,
|
| 1336 |
+
"grad_norm": 0.15732979774475098,
|
| 1337 |
+
"learning_rate": 9.944444444444445e-06,
|
| 1338 |
+
"epoch": 6.03,
|
| 1339 |
+
"step": 9050
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"loss": 0.027,
|
| 1343 |
+
"grad_norm": 0.3718239367008209,
|
| 1344 |
+
"learning_rate": 9.88888888888889e-06,
|
| 1345 |
+
"epoch": 6.07,
|
| 1346 |
+
"step": 9100
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"loss": 0.0248,
|
| 1350 |
+
"grad_norm": 0.4709440767765045,
|
| 1351 |
+
"learning_rate": 9.833333333333333e-06,
|
| 1352 |
+
"epoch": 6.1,
|
| 1353 |
+
"step": 9150
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"loss": 0.0277,
|
| 1357 |
+
"grad_norm": 0.1499980241060257,
|
| 1358 |
+
"learning_rate": 9.777777777777779e-06,
|
| 1359 |
+
"epoch": 6.13,
|
| 1360 |
+
"step": 9200
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"loss": 0.0244,
|
| 1364 |
+
"grad_norm": 0.4170394837856293,
|
| 1365 |
+
"learning_rate": 9.722222222222223e-06,
|
| 1366 |
+
"epoch": 6.17,
|
| 1367 |
+
"step": 9250
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"loss": 0.0238,
|
| 1371 |
+
"grad_norm": 0.2653655409812927,
|
| 1372 |
+
"learning_rate": 9.666666666666667e-06,
|
| 1373 |
+
"epoch": 6.2,
|
| 1374 |
+
"step": 9300
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"loss": 0.0285,
|
| 1378 |
+
"grad_norm": 0.7988731265068054,
|
| 1379 |
+
"learning_rate": 9.611111111111112e-06,
|
| 1380 |
+
"epoch": 6.23,
|
| 1381 |
+
"step": 9350
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"loss": 0.0299,
|
| 1385 |
+
"grad_norm": 0.8069539666175842,
|
| 1386 |
+
"learning_rate": 9.555555555555556e-06,
|
| 1387 |
+
"epoch": 6.27,
|
| 1388 |
+
"step": 9400
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"loss": 0.0262,
|
| 1392 |
+
"grad_norm": 0.5015062093734741,
|
| 1393 |
+
"learning_rate": 9.5e-06,
|
| 1394 |
+
"epoch": 6.3,
|
| 1395 |
+
"step": 9450
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"loss": 0.0279,
|
| 1399 |
+
"grad_norm": 0.8432004451751709,
|
| 1400 |
+
"learning_rate": 9.444444444444445e-06,
|
| 1401 |
+
"epoch": 6.33,
|
| 1402 |
+
"step": 9500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"loss": 0.0216,
|
| 1406 |
+
"grad_norm": 0.6179779171943665,
|
| 1407 |
+
"learning_rate": 9.38888888888889e-06,
|
| 1408 |
+
"epoch": 6.37,
|
| 1409 |
+
"step": 9550
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"loss": 0.0233,
|
| 1413 |
+
"grad_norm": 0.21573516726493835,
|
| 1414 |
+
"learning_rate": 9.333333333333334e-06,
|
| 1415 |
+
"epoch": 6.4,
|
| 1416 |
+
"step": 9600
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"loss": 0.026,
|
| 1420 |
+
"grad_norm": 0.1759645938873291,
|
| 1421 |
+
"learning_rate": 9.277777777777778e-06,
|
| 1422 |
+
"epoch": 6.43,
|
| 1423 |
+
"step": 9650
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"loss": 0.0274,
|
| 1427 |
+
"grad_norm": 0.6740387082099915,
|
| 1428 |
+
"learning_rate": 9.222222222222224e-06,
|
| 1429 |
+
"epoch": 6.47,
|
| 1430 |
+
"step": 9700
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"loss": 0.0323,
|
| 1434 |
+
"grad_norm": 0.7693589925765991,
|
| 1435 |
+
"learning_rate": 9.166666666666666e-06,
|
| 1436 |
+
"epoch": 6.5,
|
| 1437 |
+
"step": 9750
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"loss": 0.0278,
|
| 1441 |
+
"grad_norm": 0.5023288726806641,
|
| 1442 |
+
"learning_rate": 9.111111111111112e-06,
|
| 1443 |
+
"epoch": 6.53,
|
| 1444 |
+
"step": 9800
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"loss": 0.028,
|
| 1448 |
+
"grad_norm": 0.5492318272590637,
|
| 1449 |
+
"learning_rate": 9.055555555555556e-06,
|
| 1450 |
+
"epoch": 6.57,
|
| 1451 |
+
"step": 9850
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"loss": 0.0242,
|
| 1455 |
+
"grad_norm": 0.2837912440299988,
|
| 1456 |
+
"learning_rate": 9e-06,
|
| 1457 |
+
"epoch": 6.6,
|
| 1458 |
+
"step": 9900
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"loss": 0.0272,
|
| 1462 |
+
"grad_norm": 0.680008053779602,
|
| 1463 |
+
"learning_rate": 8.944444444444446e-06,
|
| 1464 |
+
"epoch": 6.63,
|
| 1465 |
+
"step": 9950
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"loss": 0.0289,
|
| 1469 |
+
"grad_norm": 1.9726448059082031,
|
| 1470 |
+
"learning_rate": 8.888888888888888e-06,
|
| 1471 |
+
"epoch": 6.67,
|
| 1472 |
+
"step": 10000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"loss": 0.0271,
|
| 1476 |
+
"grad_norm": 1.6224364042282104,
|
| 1477 |
+
"learning_rate": 8.833333333333334e-06,
|
| 1478 |
+
"epoch": 6.7,
|
| 1479 |
+
"step": 10050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"loss": 0.0275,
|
| 1483 |
+
"grad_norm": 0.19931891560554504,
|
| 1484 |
+
"learning_rate": 8.777777777777778e-06,
|
| 1485 |
+
"epoch": 6.73,
|
| 1486 |
+
"step": 10100
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"loss": 0.0281,
|
| 1490 |
+
"grad_norm": 0.5207138657569885,
|
| 1491 |
+
"learning_rate": 8.722222222222224e-06,
|
| 1492 |
+
"epoch": 6.77,
|
| 1493 |
+
"step": 10150
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"loss": 0.0265,
|
| 1497 |
+
"grad_norm": 0.29777082800865173,
|
| 1498 |
+
"learning_rate": 8.666666666666668e-06,
|
| 1499 |
+
"epoch": 6.8,
|
| 1500 |
+
"step": 10200
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"loss": 0.0292,
|
| 1504 |
+
"grad_norm": 0.8728300929069519,
|
| 1505 |
+
"learning_rate": 8.611111111111112e-06,
|
| 1506 |
+
"epoch": 6.83,
|
| 1507 |
+
"step": 10250
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"loss": 0.0226,
|
| 1511 |
+
"grad_norm": 0.7866277694702148,
|
| 1512 |
+
"learning_rate": 8.555555555555556e-06,
|
| 1513 |
+
"epoch": 6.87,
|
| 1514 |
+
"step": 10300
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"loss": 0.0273,
|
| 1518 |
+
"grad_norm": 0.3908791244029999,
|
| 1519 |
+
"learning_rate": 8.5e-06,
|
| 1520 |
+
"epoch": 6.9,
|
| 1521 |
+
"step": 10350
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"loss": 0.0253,
|
| 1525 |
+
"grad_norm": 0.9716600775718689,
|
| 1526 |
+
"learning_rate": 8.444444444444446e-06,
|
| 1527 |
+
"epoch": 6.93,
|
| 1528 |
+
"step": 10400
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"loss": 0.0272,
|
| 1532 |
+
"grad_norm": 0.49167874455451965,
|
| 1533 |
+
"learning_rate": 8.38888888888889e-06,
|
| 1534 |
+
"epoch": 6.97,
|
| 1535 |
+
"step": 10450
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"loss": 0.0264,
|
| 1539 |
+
"grad_norm": 0.7925304174423218,
|
| 1540 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1541 |
+
"epoch": 7.0,
|
| 1542 |
+
"step": 10500
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"eval_loss": 0.036279063671827316,
|
| 1546 |
+
"eval_accuracy": 0.7973333333333333,
|
| 1547 |
+
"eval_f1": 0.965166908563135,
|
| 1548 |
+
"eval_precision": 0.9790930506478209,
|
| 1549 |
+
"eval_recall": 0.9516313680595306,
|
| 1550 |
+
"eval_runtime": 520.5295,
|
| 1551 |
+
"eval_samples_per_second": 2.882,
|
| 1552 |
+
"eval_steps_per_second": 0.361,
|
| 1553 |
+
"epoch": 7.0,
|
| 1554 |
+
"step": 10500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"loss": 0.0222,
|
| 1558 |
+
"grad_norm": 0.8314028978347778,
|
| 1559 |
+
"learning_rate": 8.277777777777778e-06,
|
| 1560 |
+
"epoch": 7.03,
|
| 1561 |
+
"step": 10550
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"loss": 0.0246,
|
| 1565 |
+
"grad_norm": 0.16064128279685974,
|
| 1566 |
+
"learning_rate": 8.222222222222222e-06,
|
| 1567 |
+
"epoch": 7.07,
|
| 1568 |
+
"step": 10600
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"loss": 0.0236,
|
| 1572 |
+
"grad_norm": 0.6914618611335754,
|
| 1573 |
+
"learning_rate": 8.166666666666668e-06,
|
| 1574 |
+
"epoch": 7.1,
|
| 1575 |
+
"step": 10650
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"loss": 0.0197,
|
| 1579 |
+
"grad_norm": 0.2741406559944153,
|
| 1580 |
+
"learning_rate": 8.111111111111112e-06,
|
| 1581 |
+
"epoch": 7.13,
|
| 1582 |
+
"step": 10700
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"loss": 0.022,
|
| 1586 |
+
"grad_norm": 0.48848968744277954,
|
| 1587 |
+
"learning_rate": 8.055555555555557e-06,
|
| 1588 |
+
"epoch": 7.17,
|
| 1589 |
+
"step": 10750
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"loss": 0.0224,
|
| 1593 |
+
"grad_norm": 0.22712096571922302,
|
| 1594 |
+
"learning_rate": 8.000000000000001e-06,
|
| 1595 |
+
"epoch": 7.2,
|
| 1596 |
+
"step": 10800
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"loss": 0.021,
|
| 1600 |
+
"grad_norm": 0.4689682722091675,
|
| 1601 |
+
"learning_rate": 7.944444444444445e-06,
|
| 1602 |
+
"epoch": 7.23,
|
| 1603 |
+
"step": 10850
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"loss": 0.0224,
|
| 1607 |
+
"grad_norm": 0.8227229118347168,
|
| 1608 |
+
"learning_rate": 7.88888888888889e-06,
|
| 1609 |
+
"epoch": 7.27,
|
| 1610 |
+
"step": 10900
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"loss": 0.0225,
|
| 1614 |
+
"grad_norm": 0.08071909844875336,
|
| 1615 |
+
"learning_rate": 7.833333333333333e-06,
|
| 1616 |
+
"epoch": 7.3,
|
| 1617 |
+
"step": 10950
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"loss": 0.0251,
|
| 1621 |
+
"grad_norm": 0.674135684967041,
|
| 1622 |
+
"learning_rate": 7.77777777777778e-06,
|
| 1623 |
+
"epoch": 7.33,
|
| 1624 |
+
"step": 11000
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"loss": 0.024,
|
| 1628 |
+
"grad_norm": 0.5259861946105957,
|
| 1629 |
+
"learning_rate": 7.722222222222223e-06,
|
| 1630 |
+
"epoch": 7.37,
|
| 1631 |
+
"step": 11050
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"loss": 0.0228,
|
| 1635 |
+
"grad_norm": 0.3898846209049225,
|
| 1636 |
+
"learning_rate": 7.666666666666667e-06,
|
| 1637 |
+
"epoch": 7.4,
|
| 1638 |
+
"step": 11100
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"loss": 0.0232,
|
| 1642 |
+
"grad_norm": 0.6550074815750122,
|
| 1643 |
+
"learning_rate": 7.611111111111111e-06,
|
| 1644 |
+
"epoch": 7.43,
|
| 1645 |
+
"step": 11150
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"loss": 0.0221,
|
| 1649 |
+
"grad_norm": 0.41366636753082275,
|
| 1650 |
+
"learning_rate": 7.555555555555556e-06,
|
| 1651 |
+
"epoch": 7.47,
|
| 1652 |
+
"step": 11200
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"loss": 0.0237,
|
| 1656 |
+
"grad_norm": 0.37380266189575195,
|
| 1657 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1658 |
+
"epoch": 7.5,
|
| 1659 |
+
"step": 11250
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"loss": 0.0235,
|
| 1663 |
+
"grad_norm": 0.4968361556529999,
|
| 1664 |
+
"learning_rate": 7.444444444444445e-06,
|
| 1665 |
+
"epoch": 7.53,
|
| 1666 |
+
"step": 11300
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"loss": 0.0198,
|
| 1670 |
+
"grad_norm": 0.8349938988685608,
|
| 1671 |
+
"learning_rate": 7.38888888888889e-06,
|
| 1672 |
+
"epoch": 7.57,
|
| 1673 |
+
"step": 11350
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"loss": 0.0242,
|
| 1677 |
+
"grad_norm": 0.8924107551574707,
|
| 1678 |
+
"learning_rate": 7.333333333333333e-06,
|
| 1679 |
+
"epoch": 7.6,
|
| 1680 |
+
"step": 11400
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"loss": 0.0218,
|
| 1684 |
+
"grad_norm": 1.0067102909088135,
|
| 1685 |
+
"learning_rate": 7.277777777777778e-06,
|
| 1686 |
+
"epoch": 7.63,
|
| 1687 |
+
"step": 11450
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"loss": 0.0224,
|
| 1691 |
+
"grad_norm": 1.5542269945144653,
|
| 1692 |
+
"learning_rate": 7.222222222222223e-06,
|
| 1693 |
+
"epoch": 7.67,
|
| 1694 |
+
"step": 11500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"loss": 0.023,
|
| 1698 |
+
"grad_norm": 0.7638463973999023,
|
| 1699 |
+
"learning_rate": 7.166666666666667e-06,
|
| 1700 |
+
"epoch": 7.7,
|
| 1701 |
+
"step": 11550
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"loss": 0.0211,
|
| 1705 |
+
"grad_norm": 0.43382686376571655,
|
| 1706 |
+
"learning_rate": 7.111111111111112e-06,
|
| 1707 |
+
"epoch": 7.73,
|
| 1708 |
+
"step": 11600
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"loss": 0.024,
|
| 1712 |
+
"grad_norm": 0.748521625995636,
|
| 1713 |
+
"learning_rate": 7.055555555555557e-06,
|
| 1714 |
+
"epoch": 7.77,
|
| 1715 |
+
"step": 11650
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"loss": 0.0223,
|
| 1719 |
+
"grad_norm": 0.3006242513656616,
|
| 1720 |
+
"learning_rate": 7e-06,
|
| 1721 |
+
"epoch": 7.8,
|
| 1722 |
+
"step": 11700
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"loss": 0.0233,
|
| 1726 |
+
"grad_norm": 0.5056409239768982,
|
| 1727 |
+
"learning_rate": 6.944444444444445e-06,
|
| 1728 |
+
"epoch": 7.83,
|
| 1729 |
+
"step": 11750
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"loss": 0.0204,
|
| 1733 |
+
"grad_norm": 0.2664984464645386,
|
| 1734 |
+
"learning_rate": 6.88888888888889e-06,
|
| 1735 |
+
"epoch": 7.87,
|
| 1736 |
+
"step": 11800
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"loss": 0.0218,
|
| 1740 |
+
"grad_norm": 0.18376298248767853,
|
| 1741 |
+
"learning_rate": 6.833333333333334e-06,
|
| 1742 |
+
"epoch": 7.9,
|
| 1743 |
+
"step": 11850
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"loss": 0.0244,
|
| 1747 |
+
"grad_norm": 0.9237328171730042,
|
| 1748 |
+
"learning_rate": 6.777777777777779e-06,
|
| 1749 |
+
"epoch": 7.93,
|
| 1750 |
+
"step": 11900
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"loss": 0.025,
|
| 1754 |
+
"grad_norm": 0.43559354543685913,
|
| 1755 |
+
"learning_rate": 6.7222222222222235e-06,
|
| 1756 |
+
"epoch": 7.97,
|
| 1757 |
+
"step": 11950
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"loss": 0.0239,
|
| 1761 |
+
"grad_norm": 0.6444123983383179,
|
| 1762 |
+
"learning_rate": 6.666666666666667e-06,
|
| 1763 |
+
"epoch": 8.0,
|
| 1764 |
+
"step": 12000
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"eval_loss": 0.03503166139125824,
|
| 1768 |
+
"eval_accuracy": 0.8213333333333334,
|
| 1769 |
+
"eval_f1": 0.9685324825986079,
|
| 1770 |
+
"eval_precision": 0.9816284538506761,
|
| 1771 |
+
"eval_recall": 0.9557813394390383,
|
| 1772 |
+
"eval_runtime": 487.6742,
|
| 1773 |
+
"eval_samples_per_second": 3.076,
|
| 1774 |
+
"eval_steps_per_second": 0.386,
|
| 1775 |
+
"epoch": 8.0,
|
| 1776 |
+
"step": 12000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"loss": 0.019,
|
| 1780 |
+
"grad_norm": 0.10045385360717773,
|
| 1781 |
+
"learning_rate": 6.6111111111111115e-06,
|
| 1782 |
+
"epoch": 8.03,
|
| 1783 |
+
"step": 12050
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"loss": 0.0214,
|
| 1787 |
+
"grad_norm": 0.6069362759590149,
|
| 1788 |
+
"learning_rate": 6.555555555555556e-06,
|
| 1789 |
+
"epoch": 8.07,
|
| 1790 |
+
"step": 12100
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"loss": 0.0197,
|
| 1794 |
+
"grad_norm": 0.37218862771987915,
|
| 1795 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 1796 |
+
"epoch": 8.1,
|
| 1797 |
+
"step": 12150
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"loss": 0.0203,
|
| 1801 |
+
"grad_norm": 0.2680938243865967,
|
| 1802 |
+
"learning_rate": 6.444444444444445e-06,
|
| 1803 |
+
"epoch": 8.13,
|
| 1804 |
+
"step": 12200
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"loss": 0.0202,
|
| 1808 |
+
"grad_norm": 0.6604072451591492,
|
| 1809 |
+
"learning_rate": 6.3888888888888885e-06,
|
| 1810 |
+
"epoch": 8.17,
|
| 1811 |
+
"step": 12250
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"loss": 0.0182,
|
| 1815 |
+
"grad_norm": 0.18383300304412842,
|
| 1816 |
+
"learning_rate": 6.333333333333333e-06,
|
| 1817 |
+
"epoch": 8.2,
|
| 1818 |
+
"step": 12300
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"loss": 0.02,
|
| 1822 |
+
"grad_norm": 0.6499873995780945,
|
| 1823 |
+
"learning_rate": 6.277777777777778e-06,
|
| 1824 |
+
"epoch": 8.23,
|
| 1825 |
+
"step": 12350
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"loss": 0.0191,
|
| 1829 |
+
"grad_norm": 0.6889489889144897,
|
| 1830 |
+
"learning_rate": 6.222222222222223e-06,
|
| 1831 |
+
"epoch": 8.27,
|
| 1832 |
+
"step": 12400
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"loss": 0.0202,
|
| 1836 |
+
"grad_norm": 0.33093497157096863,
|
| 1837 |
+
"learning_rate": 6.166666666666667e-06,
|
| 1838 |
+
"epoch": 8.3,
|
| 1839 |
+
"step": 12450
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"loss": 0.0212,
|
| 1843 |
+
"grad_norm": 0.531550407409668,
|
| 1844 |
+
"learning_rate": 6.111111111111112e-06,
|
| 1845 |
+
"epoch": 8.33,
|
| 1846 |
+
"step": 12500
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"loss": 0.0196,
|
| 1850 |
+
"grad_norm": 0.581438422203064,
|
| 1851 |
+
"learning_rate": 6.055555555555555e-06,
|
| 1852 |
+
"epoch": 8.37,
|
| 1853 |
+
"step": 12550
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"loss": 0.02,
|
| 1857 |
+
"grad_norm": 0.7175195217132568,
|
| 1858 |
+
"learning_rate": 6e-06,
|
| 1859 |
+
"epoch": 8.4,
|
| 1860 |
+
"step": 12600
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"loss": 0.02,
|
| 1864 |
+
"grad_norm": 0.354005366563797,
|
| 1865 |
+
"learning_rate": 5.944444444444445e-06,
|
| 1866 |
+
"epoch": 8.43,
|
| 1867 |
+
"step": 12650
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"loss": 0.0202,
|
| 1871 |
+
"grad_norm": 0.39726442098617554,
|
| 1872 |
+
"learning_rate": 5.88888888888889e-06,
|
| 1873 |
+
"epoch": 8.47,
|
| 1874 |
+
"step": 12700
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"loss": 0.0195,
|
| 1878 |
+
"grad_norm": 0.5678325891494751,
|
| 1879 |
+
"learning_rate": 5.833333333333334e-06,
|
| 1880 |
+
"epoch": 8.5,
|
| 1881 |
+
"step": 12750
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"loss": 0.0204,
|
| 1885 |
+
"grad_norm": 0.9092422723770142,
|
| 1886 |
+
"learning_rate": 5.777777777777778e-06,
|
| 1887 |
+
"epoch": 8.53,
|
| 1888 |
+
"step": 12800
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"loss": 0.0194,
|
| 1892 |
+
"grad_norm": 0.17264424264431,
|
| 1893 |
+
"learning_rate": 5.722222222222222e-06,
|
| 1894 |
+
"epoch": 8.57,
|
| 1895 |
+
"step": 12850
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"loss": 0.0185,
|
| 1899 |
+
"grad_norm": 0.5633407235145569,
|
| 1900 |
+
"learning_rate": 5.666666666666667e-06,
|
| 1901 |
+
"epoch": 8.6,
|
| 1902 |
+
"step": 12900
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"loss": 0.0163,
|
| 1906 |
+
"grad_norm": 0.38537177443504333,
|
| 1907 |
+
"learning_rate": 5.611111111111112e-06,
|
| 1908 |
+
"epoch": 8.63,
|
| 1909 |
+
"step": 12950
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"loss": 0.018,
|
| 1913 |
+
"grad_norm": 0.2082950472831726,
|
| 1914 |
+
"learning_rate": 5.555555555555557e-06,
|
| 1915 |
+
"epoch": 8.67,
|
| 1916 |
+
"step": 13000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"loss": 0.0212,
|
| 1920 |
+
"grad_norm": 0.24411733448505402,
|
| 1921 |
+
"learning_rate": 5.500000000000001e-06,
|
| 1922 |
+
"epoch": 8.7,
|
| 1923 |
+
"step": 13050
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"loss": 0.02,
|
| 1927 |
+
"grad_norm": 0.236025869846344,
|
| 1928 |
+
"learning_rate": 5.444444444444445e-06,
|
| 1929 |
+
"epoch": 8.73,
|
| 1930 |
+
"step": 13100
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"loss": 0.0178,
|
| 1934 |
+
"grad_norm": 0.5068910121917725,
|
| 1935 |
+
"learning_rate": 5.388888888888889e-06,
|
| 1936 |
+
"epoch": 8.77,
|
| 1937 |
+
"step": 13150
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"loss": 0.0189,
|
| 1941 |
+
"grad_norm": 0.3922387957572937,
|
| 1942 |
+
"learning_rate": 5.333333333333334e-06,
|
| 1943 |
+
"epoch": 8.8,
|
| 1944 |
+
"step": 13200
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"loss": 0.0208,
|
| 1948 |
+
"grad_norm": 0.9244905710220337,
|
| 1949 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 1950 |
+
"epoch": 8.83,
|
| 1951 |
+
"step": 13250
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"loss": 0.0199,
|
| 1955 |
+
"grad_norm": 0.8682542443275452,
|
| 1956 |
+
"learning_rate": 5.2222222222222226e-06,
|
| 1957 |
+
"epoch": 8.87,
|
| 1958 |
+
"step": 13300
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"loss": 0.019,
|
| 1962 |
+
"grad_norm": 1.3180102109909058,
|
| 1963 |
+
"learning_rate": 5.1666666666666675e-06,
|
| 1964 |
+
"epoch": 8.9,
|
| 1965 |
+
"step": 13350
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"loss": 0.021,
|
| 1969 |
+
"grad_norm": 0.4705464839935303,
|
| 1970 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 1971 |
+
"epoch": 8.93,
|
| 1972 |
+
"step": 13400
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"loss": 0.0184,
|
| 1976 |
+
"grad_norm": 0.4992372989654541,
|
| 1977 |
+
"learning_rate": 5.0555555555555555e-06,
|
| 1978 |
+
"epoch": 8.97,
|
| 1979 |
+
"step": 13450
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"loss": 0.0191,
|
| 1983 |
+
"grad_norm": 1.026501178741455,
|
| 1984 |
+
"learning_rate": 5e-06,
|
| 1985 |
+
"epoch": 9.0,
|
| 1986 |
+
"step": 13500
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"eval_loss": 0.033837590366601944,
|
| 1990 |
+
"eval_accuracy": 0.814,
|
| 1991 |
+
"eval_f1": 0.9678493845039826,
|
| 1992 |
+
"eval_precision": 0.9796247434769862,
|
| 1993 |
+
"eval_recall": 0.9563537492844877,
|
| 1994 |
+
"eval_runtime": 520.4183,
|
| 1995 |
+
"eval_samples_per_second": 2.882,
|
| 1996 |
+
"eval_steps_per_second": 0.361,
|
| 1997 |
+
"epoch": 9.0,
|
| 1998 |
+
"step": 13500
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"loss": 0.0182,
|
| 2002 |
+
"grad_norm": 0.34491831064224243,
|
| 2003 |
+
"learning_rate": 4.944444444444445e-06,
|
| 2004 |
+
"epoch": 9.03,
|
| 2005 |
+
"step": 13550
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"loss": 0.0152,
|
| 2009 |
+
"grad_norm": 0.1780650019645691,
|
| 2010 |
+
"learning_rate": 4.888888888888889e-06,
|
| 2011 |
+
"epoch": 9.07,
|
| 2012 |
+
"step": 13600
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"loss": 0.016,
|
| 2016 |
+
"grad_norm": 0.49815917015075684,
|
| 2017 |
+
"learning_rate": 4.833333333333333e-06,
|
| 2018 |
+
"epoch": 9.1,
|
| 2019 |
+
"step": 13650
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"loss": 0.0178,
|
| 2023 |
+
"grad_norm": 0.21634286642074585,
|
| 2024 |
+
"learning_rate": 4.777777777777778e-06,
|
| 2025 |
+
"epoch": 9.13,
|
| 2026 |
+
"step": 13700
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"loss": 0.0174,
|
| 2030 |
+
"grad_norm": 0.512596845626831,
|
| 2031 |
+
"learning_rate": 4.722222222222222e-06,
|
| 2032 |
+
"epoch": 9.17,
|
| 2033 |
+
"step": 13750
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"loss": 0.0169,
|
| 2037 |
+
"grad_norm": 0.480957567691803,
|
| 2038 |
+
"learning_rate": 4.666666666666667e-06,
|
| 2039 |
+
"epoch": 9.2,
|
| 2040 |
+
"step": 13800
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"loss": 0.0187,
|
| 2044 |
+
"grad_norm": 0.4561571180820465,
|
| 2045 |
+
"learning_rate": 4.611111111111112e-06,
|
| 2046 |
+
"epoch": 9.23,
|
| 2047 |
+
"step": 13850
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"loss": 0.0192,
|
| 2051 |
+
"grad_norm": 0.31520533561706543,
|
| 2052 |
+
"learning_rate": 4.555555555555556e-06,
|
| 2053 |
+
"epoch": 9.27,
|
| 2054 |
+
"step": 13900
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"loss": 0.0186,
|
| 2058 |
+
"grad_norm": 0.33180102705955505,
|
| 2059 |
+
"learning_rate": 4.5e-06,
|
| 2060 |
+
"epoch": 9.3,
|
| 2061 |
+
"step": 13950
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"loss": 0.0199,
|
| 2065 |
+
"grad_norm": 0.8074162006378174,
|
| 2066 |
+
"learning_rate": 4.444444444444444e-06,
|
| 2067 |
+
"epoch": 9.33,
|
| 2068 |
+
"step": 14000
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"loss": 0.0187,
|
| 2072 |
+
"grad_norm": 0.07085882127285004,
|
| 2073 |
+
"learning_rate": 4.388888888888889e-06,
|
| 2074 |
+
"epoch": 9.37,
|
| 2075 |
+
"step": 14050
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"loss": 0.0156,
|
| 2079 |
+
"grad_norm": 0.2821616232395172,
|
| 2080 |
+
"learning_rate": 4.333333333333334e-06,
|
| 2081 |
+
"epoch": 9.4,
|
| 2082 |
+
"step": 14100
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"loss": 0.0163,
|
| 2086 |
+
"grad_norm": 0.7558738589286804,
|
| 2087 |
+
"learning_rate": 4.277777777777778e-06,
|
| 2088 |
+
"epoch": 9.43,
|
| 2089 |
+
"step": 14150
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"loss": 0.0191,
|
| 2093 |
+
"grad_norm": 0.23577666282653809,
|
| 2094 |
+
"learning_rate": 4.222222222222223e-06,
|
| 2095 |
+
"epoch": 9.47,
|
| 2096 |
+
"step": 14200
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"loss": 0.0141,
|
| 2100 |
+
"grad_norm": 0.6420838832855225,
|
| 2101 |
+
"learning_rate": 4.166666666666667e-06,
|
| 2102 |
+
"epoch": 9.5,
|
| 2103 |
+
"step": 14250
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"loss": 0.0175,
|
| 2107 |
+
"grad_norm": 0.4799270033836365,
|
| 2108 |
+
"learning_rate": 4.111111111111111e-06,
|
| 2109 |
+
"epoch": 9.53,
|
| 2110 |
+
"step": 14300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"loss": 0.0176,
|
| 2114 |
+
"grad_norm": 0.15877492725849152,
|
| 2115 |
+
"learning_rate": 4.055555555555556e-06,
|
| 2116 |
+
"epoch": 9.57,
|
| 2117 |
+
"step": 14350
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"loss": 0.0174,
|
| 2121 |
+
"grad_norm": 0.2862108647823334,
|
| 2122 |
+
"learning_rate": 4.000000000000001e-06,
|
| 2123 |
+
"epoch": 9.6,
|
| 2124 |
+
"step": 14400
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"loss": 0.0181,
|
| 2128 |
+
"grad_norm": 0.6650111079216003,
|
| 2129 |
+
"learning_rate": 3.944444444444445e-06,
|
| 2130 |
+
"epoch": 9.63,
|
| 2131 |
+
"step": 14450
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"loss": 0.0164,
|
| 2135 |
+
"grad_norm": 0.170445516705513,
|
| 2136 |
+
"learning_rate": 3.88888888888889e-06,
|
| 2137 |
+
"epoch": 9.67,
|
| 2138 |
+
"step": 14500
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"loss": 0.0164,
|
| 2142 |
+
"grad_norm": 1.0318118333816528,
|
| 2143 |
+
"learning_rate": 3.833333333333334e-06,
|
| 2144 |
+
"epoch": 9.7,
|
| 2145 |
+
"step": 14550
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"loss": 0.0172,
|
| 2149 |
+
"grad_norm": 0.1030106320977211,
|
| 2150 |
+
"learning_rate": 3.777777777777778e-06,
|
| 2151 |
+
"epoch": 9.73,
|
| 2152 |
+
"step": 14600
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"loss": 0.0175,
|
| 2156 |
+
"grad_norm": 0.5192915797233582,
|
| 2157 |
+
"learning_rate": 3.7222222222222225e-06,
|
| 2158 |
+
"epoch": 9.77,
|
| 2159 |
+
"step": 14650
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"loss": 0.0192,
|
| 2163 |
+
"grad_norm": 0.5223665833473206,
|
| 2164 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 2165 |
+
"epoch": 9.8,
|
| 2166 |
+
"step": 14700
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"loss": 0.0173,
|
| 2170 |
+
"grad_norm": 0.21479204297065735,
|
| 2171 |
+
"learning_rate": 3.6111111111111115e-06,
|
| 2172 |
+
"epoch": 9.83,
|
| 2173 |
+
"step": 14750
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"loss": 0.0177,
|
| 2177 |
+
"grad_norm": 0.18222138285636902,
|
| 2178 |
+
"learning_rate": 3.555555555555556e-06,
|
| 2179 |
+
"epoch": 9.87,
|
| 2180 |
+
"step": 14800
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"loss": 0.0161,
|
| 2184 |
+
"grad_norm": 0.5151605010032654,
|
| 2185 |
+
"learning_rate": 3.5e-06,
|
| 2186 |
+
"epoch": 9.9,
|
| 2187 |
+
"step": 14850
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"loss": 0.0154,
|
| 2191 |
+
"grad_norm": 0.41523924469947815,
|
| 2192 |
+
"learning_rate": 3.444444444444445e-06,
|
| 2193 |
+
"epoch": 9.93,
|
| 2194 |
+
"step": 14900
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"loss": 0.0155,
|
| 2198 |
+
"grad_norm": 0.5363922715187073,
|
| 2199 |
+
"learning_rate": 3.3888888888888893e-06,
|
| 2200 |
+
"epoch": 9.97,
|
| 2201 |
+
"step": 14950
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"loss": 0.0172,
|
| 2205 |
+
"grad_norm": 0.5515249967575073,
|
| 2206 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 2207 |
+
"epoch": 10.0,
|
| 2208 |
+
"step": 15000
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"eval_loss": 0.03265129774808884,
|
| 2212 |
+
"eval_accuracy": 0.816,
|
| 2213 |
+
"eval_f1": 0.9686844579446011,
|
| 2214 |
+
"eval_precision": 0.9792367305161573,
|
| 2215 |
+
"eval_recall": 0.9583571837435604,
|
| 2216 |
+
"eval_runtime": 522.0948,
|
| 2217 |
+
"eval_samples_per_second": 2.873,
|
| 2218 |
+
"eval_steps_per_second": 0.36,
|
| 2219 |
+
"epoch": 10.0,
|
| 2220 |
+
"step": 15000
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"loss": 0.014,
|
| 2224 |
+
"grad_norm": 0.4168848693370819,
|
| 2225 |
+
"learning_rate": 3.277777777777778e-06,
|
| 2226 |
+
"epoch": 10.03,
|
| 2227 |
+
"step": 15050
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"loss": 0.0156,
|
| 2231 |
+
"grad_norm": 0.22728918492794037,
|
| 2232 |
+
"learning_rate": 3.2222222222222227e-06,
|
| 2233 |
+
"epoch": 10.07,
|
| 2234 |
+
"step": 15100
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"loss": 0.0164,
|
| 2238 |
+
"grad_norm": 0.11018675565719604,
|
| 2239 |
+
"learning_rate": 3.1666666666666667e-06,
|
| 2240 |
+
"epoch": 10.1,
|
| 2241 |
+
"step": 15150
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"loss": 0.0153,
|
| 2245 |
+
"grad_norm": 0.2938558757305145,
|
| 2246 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 2247 |
+
"epoch": 10.13,
|
| 2248 |
+
"step": 15200
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"loss": 0.0174,
|
| 2252 |
+
"grad_norm": 0.48106732964515686,
|
| 2253 |
+
"learning_rate": 3.055555555555556e-06,
|
| 2254 |
+
"epoch": 10.17,
|
| 2255 |
+
"step": 15250
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"loss": 0.0157,
|
| 2259 |
+
"grad_norm": 0.6213731169700623,
|
| 2260 |
+
"learning_rate": 3e-06,
|
| 2261 |
+
"epoch": 10.2,
|
| 2262 |
+
"step": 15300
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"loss": 0.0136,
|
| 2266 |
+
"grad_norm": 0.12498883903026581,
|
| 2267 |
+
"learning_rate": 2.944444444444445e-06,
|
| 2268 |
+
"epoch": 10.23,
|
| 2269 |
+
"step": 15350
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"loss": 0.0136,
|
| 2273 |
+
"grad_norm": 0.4984402656555176,
|
| 2274 |
+
"learning_rate": 2.888888888888889e-06,
|
| 2275 |
+
"epoch": 10.27,
|
| 2276 |
+
"step": 15400
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"loss": 0.0143,
|
| 2280 |
+
"grad_norm": 0.1306380331516266,
|
| 2281 |
+
"learning_rate": 2.8333333333333335e-06,
|
| 2282 |
+
"epoch": 10.3,
|
| 2283 |
+
"step": 15450
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"loss": 0.0177,
|
| 2287 |
+
"grad_norm": 0.33903223276138306,
|
| 2288 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 2289 |
+
"epoch": 10.33,
|
| 2290 |
+
"step": 15500
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"loss": 0.0168,
|
| 2294 |
+
"grad_norm": 0.4361119866371155,
|
| 2295 |
+
"learning_rate": 2.7222222222222224e-06,
|
| 2296 |
+
"epoch": 10.37,
|
| 2297 |
+
"step": 15550
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"loss": 0.0155,
|
| 2301 |
+
"grad_norm": 0.6033740043640137,
|
| 2302 |
+
"learning_rate": 2.666666666666667e-06,
|
| 2303 |
+
"epoch": 10.4,
|
| 2304 |
+
"step": 15600
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"loss": 0.0155,
|
| 2308 |
+
"grad_norm": 0.37458139657974243,
|
| 2309 |
+
"learning_rate": 2.6111111111111113e-06,
|
| 2310 |
+
"epoch": 10.43,
|
| 2311 |
+
"step": 15650
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"loss": 0.0191,
|
| 2315 |
+
"grad_norm": 0.6604194045066833,
|
| 2316 |
+
"learning_rate": 2.5555555555555557e-06,
|
| 2317 |
+
"epoch": 10.47,
|
| 2318 |
+
"step": 15700
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"loss": 0.0147,
|
| 2322 |
+
"grad_norm": 0.560930073261261,
|
| 2323 |
+
"learning_rate": 2.5e-06,
|
| 2324 |
+
"epoch": 10.5,
|
| 2325 |
+
"step": 15750
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"loss": 0.0196,
|
| 2329 |
+
"grad_norm": 0.24454829096794128,
|
| 2330 |
+
"learning_rate": 2.4444444444444447e-06,
|
| 2331 |
+
"epoch": 10.53,
|
| 2332 |
+
"step": 15800
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"loss": 0.0173,
|
| 2336 |
+
"grad_norm": 0.9778093099594116,
|
| 2337 |
+
"learning_rate": 2.388888888888889e-06,
|
| 2338 |
+
"epoch": 10.57,
|
| 2339 |
+
"step": 15850
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"loss": 0.0151,
|
| 2343 |
+
"grad_norm": 0.1762203425168991,
|
| 2344 |
+
"learning_rate": 2.3333333333333336e-06,
|
| 2345 |
+
"epoch": 10.6,
|
| 2346 |
+
"step": 15900
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"loss": 0.0152,
|
| 2350 |
+
"grad_norm": 0.49755942821502686,
|
| 2351 |
+
"learning_rate": 2.277777777777778e-06,
|
| 2352 |
+
"epoch": 10.63,
|
| 2353 |
+
"step": 15950
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"loss": 0.016,
|
| 2357 |
+
"grad_norm": 0.4183555245399475,
|
| 2358 |
+
"learning_rate": 2.222222222222222e-06,
|
| 2359 |
+
"epoch": 10.67,
|
| 2360 |
+
"step": 16000
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"loss": 0.0163,
|
| 2364 |
+
"grad_norm": 0.2946385145187378,
|
| 2365 |
+
"learning_rate": 2.166666666666667e-06,
|
| 2366 |
+
"epoch": 10.7,
|
| 2367 |
+
"step": 16050
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"loss": 0.0155,
|
| 2371 |
+
"grad_norm": 0.27264583110809326,
|
| 2372 |
+
"learning_rate": 2.1111111111111114e-06,
|
| 2373 |
+
"epoch": 10.73,
|
| 2374 |
+
"step": 16100
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"loss": 0.0137,
|
| 2378 |
+
"grad_norm": 0.4318552017211914,
|
| 2379 |
+
"learning_rate": 2.0555555555555555e-06,
|
| 2380 |
+
"epoch": 10.77,
|
| 2381 |
+
"step": 16150
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"loss": 0.0147,
|
| 2385 |
+
"grad_norm": 0.2526138722896576,
|
| 2386 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 2387 |
+
"epoch": 10.8,
|
| 2388 |
+
"step": 16200
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"loss": 0.0142,
|
| 2392 |
+
"grad_norm": 0.12450098246335983,
|
| 2393 |
+
"learning_rate": 1.944444444444445e-06,
|
| 2394 |
+
"epoch": 10.83,
|
| 2395 |
+
"step": 16250
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"loss": 0.015,
|
| 2399 |
+
"grad_norm": 0.5571430325508118,
|
| 2400 |
+
"learning_rate": 1.888888888888889e-06,
|
| 2401 |
+
"epoch": 10.87,
|
| 2402 |
+
"step": 16300
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"loss": 0.016,
|
| 2406 |
+
"grad_norm": 0.48039206862449646,
|
| 2407 |
+
"learning_rate": 1.8333333333333333e-06,
|
| 2408 |
+
"epoch": 10.9,
|
| 2409 |
+
"step": 16350
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"loss": 0.0175,
|
| 2413 |
+
"grad_norm": 0.13909302651882172,
|
| 2414 |
+
"learning_rate": 1.777777777777778e-06,
|
| 2415 |
+
"epoch": 10.93,
|
| 2416 |
+
"step": 16400
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"loss": 0.0142,
|
| 2420 |
+
"grad_norm": 0.754486083984375,
|
| 2421 |
+
"learning_rate": 1.7222222222222224e-06,
|
| 2422 |
+
"epoch": 10.97,
|
| 2423 |
+
"step": 16450
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"loss": 0.0147,
|
| 2427 |
+
"grad_norm": 0.6141240000724792,
|
| 2428 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 2429 |
+
"epoch": 11.0,
|
| 2430 |
+
"step": 16500
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"eval_loss": 0.03264497593045235,
|
| 2434 |
+
"eval_accuracy": 0.822,
|
| 2435 |
+
"eval_f1": 0.9696138578130639,
|
| 2436 |
+
"eval_precision": 0.9781564001747488,
|
| 2437 |
+
"eval_recall": 0.9612192329708071,
|
| 2438 |
+
"eval_runtime": 521.02,
|
| 2439 |
+
"eval_samples_per_second": 2.879,
|
| 2440 |
+
"eval_steps_per_second": 0.361,
|
| 2441 |
+
"epoch": 11.0,
|
| 2442 |
+
"step": 16500
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"loss": 0.0148,
|
| 2446 |
+
"grad_norm": 0.6877202391624451,
|
| 2447 |
+
"learning_rate": 1.6111111111111113e-06,
|
| 2448 |
+
"epoch": 11.03,
|
| 2449 |
+
"step": 16550
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"loss": 0.0155,
|
| 2453 |
+
"grad_norm": 0.5596755743026733,
|
| 2454 |
+
"learning_rate": 1.5555555555555558e-06,
|
| 2455 |
+
"epoch": 11.07,
|
| 2456 |
+
"step": 16600
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"loss": 0.0165,
|
| 2460 |
+
"grad_norm": 0.268638551235199,
|
| 2461 |
+
"learning_rate": 1.5e-06,
|
| 2462 |
+
"epoch": 11.1,
|
| 2463 |
+
"step": 16650
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"loss": 0.0146,
|
| 2467 |
+
"grad_norm": 0.09044534713029861,
|
| 2468 |
+
"learning_rate": 1.4444444444444445e-06,
|
| 2469 |
+
"epoch": 11.13,
|
| 2470 |
+
"step": 16700
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"loss": 0.0153,
|
| 2474 |
+
"grad_norm": 0.29204678535461426,
|
| 2475 |
+
"learning_rate": 1.3888888888888892e-06,
|
| 2476 |
+
"epoch": 11.17,
|
| 2477 |
+
"step": 16750
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"loss": 0.0152,
|
| 2481 |
+
"grad_norm": 0.3674470782279968,
|
| 2482 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 2483 |
+
"epoch": 11.2,
|
| 2484 |
+
"step": 16800
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"loss": 0.0148,
|
| 2488 |
+
"grad_norm": 0.07375849038362503,
|
| 2489 |
+
"learning_rate": 1.2777777777777779e-06,
|
| 2490 |
+
"epoch": 11.23,
|
| 2491 |
+
"step": 16850
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"loss": 0.014,
|
| 2495 |
+
"grad_norm": 0.23876281082630157,
|
| 2496 |
+
"learning_rate": 1.2222222222222223e-06,
|
| 2497 |
+
"epoch": 11.27,
|
| 2498 |
+
"step": 16900
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"loss": 0.0139,
|
| 2502 |
+
"grad_norm": 0.5587507486343384,
|
| 2503 |
+
"learning_rate": 1.1666666666666668e-06,
|
| 2504 |
+
"epoch": 11.3,
|
| 2505 |
+
"step": 16950
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"loss": 0.0153,
|
| 2509 |
+
"grad_norm": 0.19995635747909546,
|
| 2510 |
+
"learning_rate": 1.111111111111111e-06,
|
| 2511 |
+
"epoch": 11.33,
|
| 2512 |
+
"step": 17000
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"loss": 0.0142,
|
| 2516 |
+
"grad_norm": 0.1458493173122406,
|
| 2517 |
+
"learning_rate": 1.0555555555555557e-06,
|
| 2518 |
+
"epoch": 11.37,
|
| 2519 |
+
"step": 17050
|
| 2520 |
+
},
|
| 2521 |
+
{
|
| 2522 |
+
"loss": 0.0146,
|
| 2523 |
+
"grad_norm": 0.5687617063522339,
|
| 2524 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 2525 |
+
"epoch": 11.4,
|
| 2526 |
+
"step": 17100
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"loss": 0.0133,
|
| 2530 |
+
"grad_norm": 0.5970475077629089,
|
| 2531 |
+
"learning_rate": 9.444444444444445e-07,
|
| 2532 |
+
"epoch": 11.43,
|
| 2533 |
+
"step": 17150
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"loss": 0.0142,
|
| 2537 |
+
"grad_norm": 0.3932097852230072,
|
| 2538 |
+
"learning_rate": 8.88888888888889e-07,
|
| 2539 |
+
"epoch": 11.47,
|
| 2540 |
+
"step": 17200
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"loss": 0.0149,
|
| 2544 |
+
"grad_norm": 0.1657884120941162,
|
| 2545 |
+
"learning_rate": 8.333333333333333e-07,
|
| 2546 |
+
"epoch": 11.5,
|
| 2547 |
+
"step": 17250
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"loss": 0.0131,
|
| 2551 |
+
"grad_norm": 0.10400531440973282,
|
| 2552 |
+
"learning_rate": 7.777777777777779e-07,
|
| 2553 |
+
"epoch": 11.53,
|
| 2554 |
+
"step": 17300
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"loss": 0.0143,
|
| 2558 |
+
"grad_norm": 0.27298837900161743,
|
| 2559 |
+
"learning_rate": 7.222222222222222e-07,
|
| 2560 |
+
"epoch": 11.57,
|
| 2561 |
+
"step": 17350
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"loss": 0.0157,
|
| 2565 |
+
"grad_norm": 0.5544312596321106,
|
| 2566 |
+
"learning_rate": 6.666666666666667e-07,
|
| 2567 |
+
"epoch": 11.6,
|
| 2568 |
+
"step": 17400
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"loss": 0.0134,
|
| 2572 |
+
"grad_norm": 0.027582811191678047,
|
| 2573 |
+
"learning_rate": 6.111111111111112e-07,
|
| 2574 |
+
"epoch": 11.63,
|
| 2575 |
+
"step": 17450
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"loss": 0.0141,
|
| 2579 |
+
"grad_norm": 0.5370105504989624,
|
| 2580 |
+
"learning_rate": 5.555555555555555e-07,
|
| 2581 |
+
"epoch": 11.67,
|
| 2582 |
+
"step": 17500
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"loss": 0.0159,
|
| 2586 |
+
"grad_norm": 0.7681547999382019,
|
| 2587 |
+
"learning_rate": 5.000000000000001e-07,
|
| 2588 |
+
"epoch": 11.7,
|
| 2589 |
+
"step": 17550
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"loss": 0.0152,
|
| 2593 |
+
"grad_norm": 0.5727664232254028,
|
| 2594 |
+
"learning_rate": 4.444444444444445e-07,
|
| 2595 |
+
"epoch": 11.73,
|
| 2596 |
+
"step": 17600
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"loss": 0.0139,
|
| 2600 |
+
"grad_norm": 0.324990838766098,
|
| 2601 |
+
"learning_rate": 3.8888888888888895e-07,
|
| 2602 |
+
"epoch": 11.77,
|
| 2603 |
+
"step": 17650
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"loss": 0.0139,
|
| 2607 |
+
"grad_norm": 0.16624578833580017,
|
| 2608 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 2609 |
+
"epoch": 11.8,
|
| 2610 |
+
"step": 17700
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"loss": 0.0151,
|
| 2614 |
+
"grad_norm": 0.5462536215782166,
|
| 2615 |
+
"learning_rate": 2.7777777777777776e-07,
|
| 2616 |
+
"epoch": 11.83,
|
| 2617 |
+
"step": 17750
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"loss": 0.0157,
|
| 2621 |
+
"grad_norm": 0.3523215055465698,
|
| 2622 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 2623 |
+
"epoch": 11.87,
|
| 2624 |
+
"step": 17800
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"loss": 0.0135,
|
| 2628 |
+
"grad_norm": 0.5089453458786011,
|
| 2629 |
+
"learning_rate": 1.6666666666666668e-07,
|
| 2630 |
+
"epoch": 11.9,
|
| 2631 |
+
"step": 17850
|
| 2632 |
+
},
|
| 2633 |
+
{
|
| 2634 |
+
"loss": 0.0151,
|
| 2635 |
+
"grad_norm": 0.45039597153663635,
|
| 2636 |
+
"learning_rate": 1.1111111111111112e-07,
|
| 2637 |
+
"epoch": 11.93,
|
| 2638 |
+
"step": 17900
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"loss": 0.0154,
|
| 2642 |
+
"grad_norm": 0.5319696068763733,
|
| 2643 |
+
"learning_rate": 5.555555555555556e-08,
|
| 2644 |
+
"epoch": 11.97,
|
| 2645 |
+
"step": 17950
|
| 2646 |
+
},
|
| 2647 |
+
{
|
| 2648 |
+
"loss": 0.0146,
|
| 2649 |
+
"grad_norm": 0.4072882831096649,
|
| 2650 |
+
"learning_rate": 0.0,
|
| 2651 |
+
"epoch": 12.0,
|
| 2652 |
+
"step": 18000
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"eval_loss": 0.03210272639989853,
|
| 2656 |
+
"eval_accuracy": 0.8293333333333334,
|
| 2657 |
+
"eval_f1": 0.9706901530464915,
|
| 2658 |
+
"eval_precision": 0.979458041958042,
|
| 2659 |
+
"eval_recall": 0.9620778477389811,
|
| 2660 |
+
"eval_runtime": 365.9115,
|
| 2661 |
+
"eval_samples_per_second": 4.099,
|
| 2662 |
+
"eval_steps_per_second": 0.514,
|
| 2663 |
+
"epoch": 12.0,
|
| 2664 |
+
"step": 18000
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"train_runtime": 94832.1488,
|
| 2668 |
+
"train_samples_per_second": 1.518,
|
| 2669 |
+
"train_steps_per_second": 0.19,
|
| 2670 |
+
"total_flos": 3.7897517039616e+16,
|
| 2671 |
+
"train_loss": 0.05056379745403926,
|
| 2672 |
+
"epoch": 12.0,
|
| 2673 |
+
"step": 18000
|
| 2674 |
+
}
|
| 2675 |
+
]
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|