Upload 5 files
Browse files- checkpoint-1275/config.json +459 -0
- checkpoint-1275/rng_state.pth +3 -0
- checkpoint-1275/scheduler.pt +3 -0
- checkpoint-1275/trainer_state.json +1766 -0
- checkpoint-1275/training_args.bin +3 -0
checkpoint-1275/config.json
ADDED
|
@@ -0,0 +1,459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "XinWenMonash/swin_transformer",
|
| 3 |
+
"_num_labels": 200,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"SwinForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"depths": [
|
| 9 |
+
2,
|
| 10 |
+
2,
|
| 11 |
+
18,
|
| 12 |
+
2
|
| 13 |
+
],
|
| 14 |
+
"drop_path_rate": 0.1,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embed_dim": 128,
|
| 17 |
+
"encoder_stride": 32,
|
| 18 |
+
"hidden_act": "gelu",
|
| 19 |
+
"hidden_dropout_prob": 0.0,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"id2label": {
|
| 22 |
+
"0": "acadian_flycatcher",
|
| 23 |
+
"1": "american_crow",
|
| 24 |
+
"2": "american_goldfinch",
|
| 25 |
+
"3": "american_pipit",
|
| 26 |
+
"4": "american_redstart",
|
| 27 |
+
"5": "american_three_toed_woodpecker",
|
| 28 |
+
"6": "anna_hummingbird",
|
| 29 |
+
"7": "artic_tern",
|
| 30 |
+
"8": "baird_sparrow",
|
| 31 |
+
"9": "baltimore_oriole",
|
| 32 |
+
"10": "bank_swallow",
|
| 33 |
+
"11": "barn_swallow",
|
| 34 |
+
"12": "bay_breasted_warbler",
|
| 35 |
+
"13": "belted_kingfisher",
|
| 36 |
+
"14": "bewick_wren",
|
| 37 |
+
"15": "black_and_white_warbler",
|
| 38 |
+
"16": "black_billed_cuckoo",
|
| 39 |
+
"17": "black_capped_vireo",
|
| 40 |
+
"18": "black_footed_albatross",
|
| 41 |
+
"19": "black_tern",
|
| 42 |
+
"20": "black_throated_blue_warbler",
|
| 43 |
+
"21": "black_throated_sparrow",
|
| 44 |
+
"22": "blue_grosbeak",
|
| 45 |
+
"23": "blue_headed_vireo",
|
| 46 |
+
"24": "blue_jay",
|
| 47 |
+
"25": "blue_winged_warbler",
|
| 48 |
+
"26": "boat_tailed_grackle",
|
| 49 |
+
"27": "bobolink",
|
| 50 |
+
"28": "bohemian_waxwing",
|
| 51 |
+
"29": "brandt_cormorant",
|
| 52 |
+
"30": "brewer_blackbird",
|
| 53 |
+
"31": "brewer_sparrow",
|
| 54 |
+
"32": "bronzed_cowbird",
|
| 55 |
+
"33": "brown_creeper",
|
| 56 |
+
"34": "brown_pelican",
|
| 57 |
+
"35": "brown_thrasher",
|
| 58 |
+
"36": "cactus_wren",
|
| 59 |
+
"37": "california_gull",
|
| 60 |
+
"38": "canada_warbler",
|
| 61 |
+
"39": "cape_glossy_starling",
|
| 62 |
+
"40": "cape_may_warbler",
|
| 63 |
+
"41": "cardinal",
|
| 64 |
+
"42": "carolina_wren",
|
| 65 |
+
"43": "caspian_tern",
|
| 66 |
+
"44": "cedar_waxwing",
|
| 67 |
+
"45": "cerulean_warbler",
|
| 68 |
+
"46": "chestnut_sided_warbler",
|
| 69 |
+
"47": "chipping_sparrow",
|
| 70 |
+
"48": "chuck_will_widow",
|
| 71 |
+
"49": "clark_nutcracker",
|
| 72 |
+
"50": "clay_colored_sparrow",
|
| 73 |
+
"51": "cliff_swallow",
|
| 74 |
+
"52": "common_raven",
|
| 75 |
+
"53": "common_tern",
|
| 76 |
+
"54": "common_yellowthroat",
|
| 77 |
+
"55": "crested_auklet",
|
| 78 |
+
"56": "dark_eyed_junco",
|
| 79 |
+
"57": "downy_woodpecker",
|
| 80 |
+
"58": "eared_grebe",
|
| 81 |
+
"59": "eastern_towhee",
|
| 82 |
+
"60": "elegant_tern",
|
| 83 |
+
"61": "european_goldfinch",
|
| 84 |
+
"62": "evening_grosbeak",
|
| 85 |
+
"63": "field_sparrow",
|
| 86 |
+
"64": "fish_crow",
|
| 87 |
+
"65": "florida_jay",
|
| 88 |
+
"66": "forsters_tern",
|
| 89 |
+
"67": "fox_sparrow",
|
| 90 |
+
"68": "frigatebird",
|
| 91 |
+
"69": "gadwall",
|
| 92 |
+
"70": "geococcyx",
|
| 93 |
+
"71": "glaucous_winged_gull",
|
| 94 |
+
"72": "golden_winged_warbler",
|
| 95 |
+
"73": "grasshopper_sparrow",
|
| 96 |
+
"74": "gray_catbird",
|
| 97 |
+
"75": "gray_crowned_rosy_finch",
|
| 98 |
+
"76": "gray_kingbird",
|
| 99 |
+
"77": "great_crested_flycatcher",
|
| 100 |
+
"78": "great_grey_shrike",
|
| 101 |
+
"79": "green_jay",
|
| 102 |
+
"80": "green_kingfisher",
|
| 103 |
+
"81": "green_tailed_towhee",
|
| 104 |
+
"82": "green_violetear",
|
| 105 |
+
"83": "groove_billed_ani",
|
| 106 |
+
"84": "harris_sparrow",
|
| 107 |
+
"85": "heermann_gull",
|
| 108 |
+
"86": "henslow_sparrow",
|
| 109 |
+
"87": "herring_gull",
|
| 110 |
+
"88": "hooded_merganser",
|
| 111 |
+
"89": "hooded_oriole",
|
| 112 |
+
"90": "hooded_warbler",
|
| 113 |
+
"91": "horned_grebe",
|
| 114 |
+
"92": "horned_lark",
|
| 115 |
+
"93": "horned_puffin",
|
| 116 |
+
"94": "house_sparrow",
|
| 117 |
+
"95": "house_wren",
|
| 118 |
+
"96": "indigo_bunting",
|
| 119 |
+
"97": "ivory_gull",
|
| 120 |
+
"98": "kentucky_warbler",
|
| 121 |
+
"99": "laysan_albatross",
|
| 122 |
+
"100": "lazuli_bunting",
|
| 123 |
+
"101": "le_conte_sparrow",
|
| 124 |
+
"102": "least_auklet",
|
| 125 |
+
"103": "least_flycatcher",
|
| 126 |
+
"104": "least_tern",
|
| 127 |
+
"105": "lincoln_sparrow",
|
| 128 |
+
"106": "loggerhead_shrike",
|
| 129 |
+
"107": "long_tailed_jaeger",
|
| 130 |
+
"108": "louisiana_waterthrush",
|
| 131 |
+
"109": "magnolia_warbler",
|
| 132 |
+
"110": "mallard",
|
| 133 |
+
"111": "mangrove_cuckoo",
|
| 134 |
+
"112": "marsh_wren",
|
| 135 |
+
"113": "mockingbird",
|
| 136 |
+
"114": "mourning_warbler",
|
| 137 |
+
"115": "myrtle_warbler",
|
| 138 |
+
"116": "nashville_warbler",
|
| 139 |
+
"117": "nelson_sharp_tailed_sparrow",
|
| 140 |
+
"118": "nighthawk",
|
| 141 |
+
"119": "northern_flicker",
|
| 142 |
+
"120": "northern_fulmar",
|
| 143 |
+
"121": "northern_waterthrush",
|
| 144 |
+
"122": "olive_sided_flycatcher",
|
| 145 |
+
"123": "orange_crowned_warbler",
|
| 146 |
+
"124": "orchard_oriole",
|
| 147 |
+
"125": "ovenbird",
|
| 148 |
+
"126": "pacific_loon",
|
| 149 |
+
"127": "painted_bunting",
|
| 150 |
+
"128": "palm_warbler",
|
| 151 |
+
"129": "parakeet_auklet",
|
| 152 |
+
"130": "pelagic_cormorant",
|
| 153 |
+
"131": "philadelphia_vireo",
|
| 154 |
+
"132": "pied_billed_grebe",
|
| 155 |
+
"133": "pied_kingfisher",
|
| 156 |
+
"134": "pigeon_guillemot",
|
| 157 |
+
"135": "pileated_woodpecker",
|
| 158 |
+
"136": "pine_grosbeak",
|
| 159 |
+
"137": "pine_warbler",
|
| 160 |
+
"138": "pomarine_jaeger",
|
| 161 |
+
"139": "prairie_warbler",
|
| 162 |
+
"140": "prothonotary_warbler",
|
| 163 |
+
"141": "purple_finch",
|
| 164 |
+
"142": "red_bellied_woodpecker",
|
| 165 |
+
"143": "red_breasted_merganser",
|
| 166 |
+
"144": "red_cockaded_woodpecker",
|
| 167 |
+
"145": "red_eyed_vireo",
|
| 168 |
+
"146": "red_faced_cormorant",
|
| 169 |
+
"147": "red_headed_woodpecker",
|
| 170 |
+
"148": "red_legged_kittiwake",
|
| 171 |
+
"149": "red_winged_blackbird",
|
| 172 |
+
"150": "rhinoceros_auklet",
|
| 173 |
+
"151": "ring_billed_gull",
|
| 174 |
+
"152": "ringed_kingfisher",
|
| 175 |
+
"153": "rock_wren",
|
| 176 |
+
"154": "rose_breasted_grosbeak",
|
| 177 |
+
"155": "ruby_throated_hummingbird",
|
| 178 |
+
"156": "rufous_hummingbird",
|
| 179 |
+
"157": "rusty_blackbird",
|
| 180 |
+
"158": "sage_thrasher",
|
| 181 |
+
"159": "savannah_sparrow",
|
| 182 |
+
"160": "sayornis",
|
| 183 |
+
"161": "scarlet_tanager",
|
| 184 |
+
"162": "scissor_tailed_flycatcher",
|
| 185 |
+
"163": "scott_oriole",
|
| 186 |
+
"164": "seaside_sparrow",
|
| 187 |
+
"165": "shiny_cowbird",
|
| 188 |
+
"166": "slaty_backed_gull",
|
| 189 |
+
"167": "song_sparrow",
|
| 190 |
+
"168": "sooty_albatross",
|
| 191 |
+
"169": "spotted_catbird",
|
| 192 |
+
"170": "summer_tanager",
|
| 193 |
+
"171": "swainson_warbler",
|
| 194 |
+
"172": "tennessee_warbler",
|
| 195 |
+
"173": "tree_sparrow",
|
| 196 |
+
"174": "tree_swallow",
|
| 197 |
+
"175": "tropical_kingbird",
|
| 198 |
+
"176": "vermilion_flycatcher",
|
| 199 |
+
"177": "vesper_sparrow",
|
| 200 |
+
"178": "warbling_vireo",
|
| 201 |
+
"179": "western_grebe",
|
| 202 |
+
"180": "western_gull",
|
| 203 |
+
"181": "western_meadowlark",
|
| 204 |
+
"182": "western_wood_pewee",
|
| 205 |
+
"183": "whip_poor_will",
|
| 206 |
+
"184": "white_breasted_kingfisher",
|
| 207 |
+
"185": "white_breasted_nuthatch",
|
| 208 |
+
"186": "white_crowned_sparrow",
|
| 209 |
+
"187": "white_eyed_vireo",
|
| 210 |
+
"188": "white_necked_raven",
|
| 211 |
+
"189": "white_pelican",
|
| 212 |
+
"190": "white_throated_sparrow",
|
| 213 |
+
"191": "wilson_warbler",
|
| 214 |
+
"192": "winter_wren",
|
| 215 |
+
"193": "worm_eating_warbler",
|
| 216 |
+
"194": "yellow_bellied_flycatcher",
|
| 217 |
+
"195": "yellow_billed_cuckoo",
|
| 218 |
+
"196": "yellow_breasted_chat",
|
| 219 |
+
"197": "yellow_headed_blackbird",
|
| 220 |
+
"198": "yellow_throated_vireo",
|
| 221 |
+
"199": "yellow_warbler"
|
| 222 |
+
},
|
| 223 |
+
"image_size": 224,
|
| 224 |
+
"initializer_range": 0.02,
|
| 225 |
+
"label2id": {
|
| 226 |
+
"acadian_flycatcher": 0,
|
| 227 |
+
"american_crow": 1,
|
| 228 |
+
"american_goldfinch": 2,
|
| 229 |
+
"american_pipit": 3,
|
| 230 |
+
"american_redstart": 4,
|
| 231 |
+
"american_three_toed_woodpecker": 5,
|
| 232 |
+
"anna_hummingbird": 6,
|
| 233 |
+
"artic_tern": 7,
|
| 234 |
+
"baird_sparrow": 8,
|
| 235 |
+
"baltimore_oriole": 9,
|
| 236 |
+
"bank_swallow": 10,
|
| 237 |
+
"barn_swallow": 11,
|
| 238 |
+
"bay_breasted_warbler": 12,
|
| 239 |
+
"belted_kingfisher": 13,
|
| 240 |
+
"bewick_wren": 14,
|
| 241 |
+
"black_and_white_warbler": 15,
|
| 242 |
+
"black_billed_cuckoo": 16,
|
| 243 |
+
"black_capped_vireo": 17,
|
| 244 |
+
"black_footed_albatross": 18,
|
| 245 |
+
"black_tern": 19,
|
| 246 |
+
"black_throated_blue_warbler": 20,
|
| 247 |
+
"black_throated_sparrow": 21,
|
| 248 |
+
"blue_grosbeak": 22,
|
| 249 |
+
"blue_headed_vireo": 23,
|
| 250 |
+
"blue_jay": 24,
|
| 251 |
+
"blue_winged_warbler": 25,
|
| 252 |
+
"boat_tailed_grackle": 26,
|
| 253 |
+
"bobolink": 27,
|
| 254 |
+
"bohemian_waxwing": 28,
|
| 255 |
+
"brandt_cormorant": 29,
|
| 256 |
+
"brewer_blackbird": 30,
|
| 257 |
+
"brewer_sparrow": 31,
|
| 258 |
+
"bronzed_cowbird": 32,
|
| 259 |
+
"brown_creeper": 33,
|
| 260 |
+
"brown_pelican": 34,
|
| 261 |
+
"brown_thrasher": 35,
|
| 262 |
+
"cactus_wren": 36,
|
| 263 |
+
"california_gull": 37,
|
| 264 |
+
"canada_warbler": 38,
|
| 265 |
+
"cape_glossy_starling": 39,
|
| 266 |
+
"cape_may_warbler": 40,
|
| 267 |
+
"cardinal": 41,
|
| 268 |
+
"carolina_wren": 42,
|
| 269 |
+
"caspian_tern": 43,
|
| 270 |
+
"cedar_waxwing": 44,
|
| 271 |
+
"cerulean_warbler": 45,
|
| 272 |
+
"chestnut_sided_warbler": 46,
|
| 273 |
+
"chipping_sparrow": 47,
|
| 274 |
+
"chuck_will_widow": 48,
|
| 275 |
+
"clark_nutcracker": 49,
|
| 276 |
+
"clay_colored_sparrow": 50,
|
| 277 |
+
"cliff_swallow": 51,
|
| 278 |
+
"common_raven": 52,
|
| 279 |
+
"common_tern": 53,
|
| 280 |
+
"common_yellowthroat": 54,
|
| 281 |
+
"crested_auklet": 55,
|
| 282 |
+
"dark_eyed_junco": 56,
|
| 283 |
+
"downy_woodpecker": 57,
|
| 284 |
+
"eared_grebe": 58,
|
| 285 |
+
"eastern_towhee": 59,
|
| 286 |
+
"elegant_tern": 60,
|
| 287 |
+
"european_goldfinch": 61,
|
| 288 |
+
"evening_grosbeak": 62,
|
| 289 |
+
"field_sparrow": 63,
|
| 290 |
+
"fish_crow": 64,
|
| 291 |
+
"florida_jay": 65,
|
| 292 |
+
"forsters_tern": 66,
|
| 293 |
+
"fox_sparrow": 67,
|
| 294 |
+
"frigatebird": 68,
|
| 295 |
+
"gadwall": 69,
|
| 296 |
+
"geococcyx": 70,
|
| 297 |
+
"glaucous_winged_gull": 71,
|
| 298 |
+
"golden_winged_warbler": 72,
|
| 299 |
+
"grasshopper_sparrow": 73,
|
| 300 |
+
"gray_catbird": 74,
|
| 301 |
+
"gray_crowned_rosy_finch": 75,
|
| 302 |
+
"gray_kingbird": 76,
|
| 303 |
+
"great_crested_flycatcher": 77,
|
| 304 |
+
"great_grey_shrike": 78,
|
| 305 |
+
"green_jay": 79,
|
| 306 |
+
"green_kingfisher": 80,
|
| 307 |
+
"green_tailed_towhee": 81,
|
| 308 |
+
"green_violetear": 82,
|
| 309 |
+
"groove_billed_ani": 83,
|
| 310 |
+
"harris_sparrow": 84,
|
| 311 |
+
"heermann_gull": 85,
|
| 312 |
+
"henslow_sparrow": 86,
|
| 313 |
+
"herring_gull": 87,
|
| 314 |
+
"hooded_merganser": 88,
|
| 315 |
+
"hooded_oriole": 89,
|
| 316 |
+
"hooded_warbler": 90,
|
| 317 |
+
"horned_grebe": 91,
|
| 318 |
+
"horned_lark": 92,
|
| 319 |
+
"horned_puffin": 93,
|
| 320 |
+
"house_sparrow": 94,
|
| 321 |
+
"house_wren": 95,
|
| 322 |
+
"indigo_bunting": 96,
|
| 323 |
+
"ivory_gull": 97,
|
| 324 |
+
"kentucky_warbler": 98,
|
| 325 |
+
"laysan_albatross": 99,
|
| 326 |
+
"lazuli_bunting": 100,
|
| 327 |
+
"le_conte_sparrow": 101,
|
| 328 |
+
"least_auklet": 102,
|
| 329 |
+
"least_flycatcher": 103,
|
| 330 |
+
"least_tern": 104,
|
| 331 |
+
"lincoln_sparrow": 105,
|
| 332 |
+
"loggerhead_shrike": 106,
|
| 333 |
+
"long_tailed_jaeger": 107,
|
| 334 |
+
"louisiana_waterthrush": 108,
|
| 335 |
+
"magnolia_warbler": 109,
|
| 336 |
+
"mallard": 110,
|
| 337 |
+
"mangrove_cuckoo": 111,
|
| 338 |
+
"marsh_wren": 112,
|
| 339 |
+
"mockingbird": 113,
|
| 340 |
+
"mourning_warbler": 114,
|
| 341 |
+
"myrtle_warbler": 115,
|
| 342 |
+
"nashville_warbler": 116,
|
| 343 |
+
"nelson_sharp_tailed_sparrow": 117,
|
| 344 |
+
"nighthawk": 118,
|
| 345 |
+
"northern_flicker": 119,
|
| 346 |
+
"northern_fulmar": 120,
|
| 347 |
+
"northern_waterthrush": 121,
|
| 348 |
+
"olive_sided_flycatcher": 122,
|
| 349 |
+
"orange_crowned_warbler": 123,
|
| 350 |
+
"orchard_oriole": 124,
|
| 351 |
+
"ovenbird": 125,
|
| 352 |
+
"pacific_loon": 126,
|
| 353 |
+
"painted_bunting": 127,
|
| 354 |
+
"palm_warbler": 128,
|
| 355 |
+
"parakeet_auklet": 129,
|
| 356 |
+
"pelagic_cormorant": 130,
|
| 357 |
+
"philadelphia_vireo": 131,
|
| 358 |
+
"pied_billed_grebe": 132,
|
| 359 |
+
"pied_kingfisher": 133,
|
| 360 |
+
"pigeon_guillemot": 134,
|
| 361 |
+
"pileated_woodpecker": 135,
|
| 362 |
+
"pine_grosbeak": 136,
|
| 363 |
+
"pine_warbler": 137,
|
| 364 |
+
"pomarine_jaeger": 138,
|
| 365 |
+
"prairie_warbler": 139,
|
| 366 |
+
"prothonotary_warbler": 140,
|
| 367 |
+
"purple_finch": 141,
|
| 368 |
+
"red_bellied_woodpecker": 142,
|
| 369 |
+
"red_breasted_merganser": 143,
|
| 370 |
+
"red_cockaded_woodpecker": 144,
|
| 371 |
+
"red_eyed_vireo": 145,
|
| 372 |
+
"red_faced_cormorant": 146,
|
| 373 |
+
"red_headed_woodpecker": 147,
|
| 374 |
+
"red_legged_kittiwake": 148,
|
| 375 |
+
"red_winged_blackbird": 149,
|
| 376 |
+
"rhinoceros_auklet": 150,
|
| 377 |
+
"ring_billed_gull": 151,
|
| 378 |
+
"ringed_kingfisher": 152,
|
| 379 |
+
"rock_wren": 153,
|
| 380 |
+
"rose_breasted_grosbeak": 154,
|
| 381 |
+
"ruby_throated_hummingbird": 155,
|
| 382 |
+
"rufous_hummingbird": 156,
|
| 383 |
+
"rusty_blackbird": 157,
|
| 384 |
+
"sage_thrasher": 158,
|
| 385 |
+
"savannah_sparrow": 159,
|
| 386 |
+
"sayornis": 160,
|
| 387 |
+
"scarlet_tanager": 161,
|
| 388 |
+
"scissor_tailed_flycatcher": 162,
|
| 389 |
+
"scott_oriole": 163,
|
| 390 |
+
"seaside_sparrow": 164,
|
| 391 |
+
"shiny_cowbird": 165,
|
| 392 |
+
"slaty_backed_gull": 166,
|
| 393 |
+
"song_sparrow": 167,
|
| 394 |
+
"sooty_albatross": 168,
|
| 395 |
+
"spotted_catbird": 169,
|
| 396 |
+
"summer_tanager": 170,
|
| 397 |
+
"swainson_warbler": 171,
|
| 398 |
+
"tennessee_warbler": 172,
|
| 399 |
+
"tree_sparrow": 173,
|
| 400 |
+
"tree_swallow": 174,
|
| 401 |
+
"tropical_kingbird": 175,
|
| 402 |
+
"vermilion_flycatcher": 176,
|
| 403 |
+
"vesper_sparrow": 177,
|
| 404 |
+
"warbling_vireo": 178,
|
| 405 |
+
"western_grebe": 179,
|
| 406 |
+
"western_gull": 180,
|
| 407 |
+
"western_meadowlark": 181,
|
| 408 |
+
"western_wood_pewee": 182,
|
| 409 |
+
"whip_poor_will": 183,
|
| 410 |
+
"white_breasted_kingfisher": 184,
|
| 411 |
+
"white_breasted_nuthatch": 185,
|
| 412 |
+
"white_crowned_sparrow": 186,
|
| 413 |
+
"white_eyed_vireo": 187,
|
| 414 |
+
"white_necked_raven": 188,
|
| 415 |
+
"white_pelican": 189,
|
| 416 |
+
"white_throated_sparrow": 190,
|
| 417 |
+
"wilson_warbler": 191,
|
| 418 |
+
"winter_wren": 192,
|
| 419 |
+
"worm_eating_warbler": 193,
|
| 420 |
+
"yellow_bellied_flycatcher": 194,
|
| 421 |
+
"yellow_billed_cuckoo": 195,
|
| 422 |
+
"yellow_breasted_chat": 196,
|
| 423 |
+
"yellow_headed_blackbird": 197,
|
| 424 |
+
"yellow_throated_vireo": 198,
|
| 425 |
+
"yellow_warbler": 199
|
| 426 |
+
},
|
| 427 |
+
"layer_norm_eps": 1e-05,
|
| 428 |
+
"mlp_ratio": 4.0,
|
| 429 |
+
"model_type": "swin",
|
| 430 |
+
"num_channels": 3,
|
| 431 |
+
"num_heads": [
|
| 432 |
+
4,
|
| 433 |
+
8,
|
| 434 |
+
16,
|
| 435 |
+
32
|
| 436 |
+
],
|
| 437 |
+
"num_layers": 4,
|
| 438 |
+
"out_features": [
|
| 439 |
+
"stage4"
|
| 440 |
+
],
|
| 441 |
+
"out_indices": [
|
| 442 |
+
4
|
| 443 |
+
],
|
| 444 |
+
"patch_size": 4,
|
| 445 |
+
"path_norm": true,
|
| 446 |
+
"problem_type": "single_label_classification",
|
| 447 |
+
"qkv_bias": true,
|
| 448 |
+
"stage_names": [
|
| 449 |
+
"stem",
|
| 450 |
+
"stage1",
|
| 451 |
+
"stage2",
|
| 452 |
+
"stage3",
|
| 453 |
+
"stage4"
|
| 454 |
+
],
|
| 455 |
+
"torch_dtype": "float32",
|
| 456 |
+
"transformers_version": "4.48.0",
|
| 457 |
+
"use_absolute_embeddings": false,
|
| 458 |
+
"window_size": 7
|
| 459 |
+
}
|
checkpoint-1275/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:145e6aaae71e94de31b985ff1f2edcf9ca2d96f63bd4758700b5bfe07bceb9b5
|
| 3 |
+
size 14244
|
checkpoint-1275/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abfb41d8963e26d42b1b2b5d933e991567e940c3a7bfa1df8fa6831c0d990e47
|
| 3 |
+
size 1064
|
checkpoint-1275/trainer_state.json
ADDED
|
@@ -0,0 +1,1766 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3975684940814972,
|
| 3 |
+
"best_model_checkpoint": "Model-Swin-Transformer-\\checkpoint-1275",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 7,
|
| 6 |
+
"global_step": 1275,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1390728476821192,
|
| 13 |
+
"grad_norm": 3.756645917892456,
|
| 14 |
+
"learning_rate": 7.000000000000001e-07,
|
| 15 |
+
"loss": 5.3644,
|
| 16 |
+
"step": 7
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2781456953642384,
|
| 20 |
+
"grad_norm": 3.558716297149658,
|
| 21 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 22 |
+
"loss": 5.3658,
|
| 23 |
+
"step": 14
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.41721854304635764,
|
| 27 |
+
"grad_norm": 3.7727837562561035,
|
| 28 |
+
"learning_rate": 2.1000000000000002e-06,
|
| 29 |
+
"loss": 5.3463,
|
| 30 |
+
"step": 21
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5562913907284768,
|
| 34 |
+
"grad_norm": 3.529733896255493,
|
| 35 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 36 |
+
"loss": 5.3343,
|
| 37 |
+
"step": 28
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.695364238410596,
|
| 41 |
+
"grad_norm": 4.100412368774414,
|
| 42 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 43 |
+
"loss": 5.3713,
|
| 44 |
+
"step": 35
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8344370860927153,
|
| 48 |
+
"grad_norm": 4.024387836456299,
|
| 49 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 50 |
+
"loss": 5.3528,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9735099337748344,
|
| 55 |
+
"grad_norm": 3.3524274826049805,
|
| 56 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 57 |
+
"loss": 5.3086,
|
| 58 |
+
"step": 49
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_accuracy": 0.00819672131147541,
|
| 63 |
+
"eval_f1_macro": 0.004708259390712807,
|
| 64 |
+
"eval_f1_micro": 0.00819672131147541,
|
| 65 |
+
"eval_f1_weighted": 0.005191171978413603,
|
| 66 |
+
"eval_loss": 5.3028178215026855,
|
| 67 |
+
"eval_precision_macro": 0.004008928571428571,
|
| 68 |
+
"eval_precision_micro": 0.00819672131147541,
|
| 69 |
+
"eval_precision_weighted": 0.004471604215456675,
|
| 70 |
+
"eval_recall_macro": 0.007458333333333333,
|
| 71 |
+
"eval_recall_micro": 0.00819672131147541,
|
| 72 |
+
"eval_recall_weighted": 0.00819672131147541,
|
| 73 |
+
"eval_runtime": 18.3225,
|
| 74 |
+
"eval_samples_per_second": 66.585,
|
| 75 |
+
"eval_steps_per_second": 1.092,
|
| 76 |
+
"step": 51
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.099337748344371,
|
| 80 |
+
"grad_norm": 3.333894729614258,
|
| 81 |
+
"learning_rate": 5.600000000000001e-06,
|
| 82 |
+
"loss": 4.7989,
|
| 83 |
+
"step": 56
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.23841059602649,
|
| 87 |
+
"grad_norm": 3.226445198059082,
|
| 88 |
+
"learning_rate": 6.300000000000001e-06,
|
| 89 |
+
"loss": 5.2748,
|
| 90 |
+
"step": 63
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.3774834437086092,
|
| 94 |
+
"grad_norm": 2.960792303085327,
|
| 95 |
+
"learning_rate": 7.000000000000001e-06,
|
| 96 |
+
"loss": 5.2799,
|
| 97 |
+
"step": 70
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.5165562913907285,
|
| 101 |
+
"grad_norm": 2.967210054397583,
|
| 102 |
+
"learning_rate": 7.7e-06,
|
| 103 |
+
"loss": 5.2765,
|
| 104 |
+
"step": 77
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.6556291390728477,
|
| 108 |
+
"grad_norm": 2.8297080993652344,
|
| 109 |
+
"learning_rate": 8.400000000000001e-06,
|
| 110 |
+
"loss": 5.2309,
|
| 111 |
+
"step": 84
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.794701986754967,
|
| 115 |
+
"grad_norm": 3.001478433609009,
|
| 116 |
+
"learning_rate": 9.100000000000001e-06,
|
| 117 |
+
"loss": 5.2076,
|
| 118 |
+
"step": 91
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.9337748344370862,
|
| 122 |
+
"grad_norm": 3.130455493927002,
|
| 123 |
+
"learning_rate": 9.800000000000001e-06,
|
| 124 |
+
"loss": 5.1799,
|
| 125 |
+
"step": 98
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0,
|
| 129 |
+
"eval_accuracy": 0.031967213114754096,
|
| 130 |
+
"eval_f1_macro": 0.02138895151975647,
|
| 131 |
+
"eval_f1_micro": 0.031967213114754096,
|
| 132 |
+
"eval_f1_weighted": 0.022752398833071827,
|
| 133 |
+
"eval_loss": 5.114638805389404,
|
| 134 |
+
"eval_precision_macro": 0.02439267581077926,
|
| 135 |
+
"eval_precision_micro": 0.031967213114754096,
|
| 136 |
+
"eval_precision_weighted": 0.026138166290088277,
|
| 137 |
+
"eval_recall_macro": 0.030029761904761903,
|
| 138 |
+
"eval_recall_micro": 0.031967213114754096,
|
| 139 |
+
"eval_recall_weighted": 0.031967213114754096,
|
| 140 |
+
"eval_runtime": 19.7575,
|
| 141 |
+
"eval_samples_per_second": 61.749,
|
| 142 |
+
"eval_steps_per_second": 1.012,
|
| 143 |
+
"step": 102
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.0596026490066226,
|
| 147 |
+
"grad_norm": 3.9784674644470215,
|
| 148 |
+
"learning_rate": 1.05e-05,
|
| 149 |
+
"loss": 4.6593,
|
| 150 |
+
"step": 105
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.198675496688742,
|
| 154 |
+
"grad_norm": 4.487362861633301,
|
| 155 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 156 |
+
"loss": 5.1011,
|
| 157 |
+
"step": 112
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.337748344370861,
|
| 161 |
+
"grad_norm": 3.840144157409668,
|
| 162 |
+
"learning_rate": 1.19e-05,
|
| 163 |
+
"loss": 5.0346,
|
| 164 |
+
"step": 119
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.47682119205298,
|
| 168 |
+
"grad_norm": 4.5351409912109375,
|
| 169 |
+
"learning_rate": 1.2600000000000001e-05,
|
| 170 |
+
"loss": 4.993,
|
| 171 |
+
"step": 126
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.6158940397350996,
|
| 175 |
+
"grad_norm": 5.248815059661865,
|
| 176 |
+
"learning_rate": 1.3300000000000001e-05,
|
| 177 |
+
"loss": 4.9318,
|
| 178 |
+
"step": 133
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.7549668874172184,
|
| 182 |
+
"grad_norm": 5.679067611694336,
|
| 183 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 184 |
+
"loss": 4.8848,
|
| 185 |
+
"step": 140
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.8940397350993377,
|
| 189 |
+
"grad_norm": 5.753520488739014,
|
| 190 |
+
"learning_rate": 1.47e-05,
|
| 191 |
+
"loss": 4.7788,
|
| 192 |
+
"step": 147
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.0,
|
| 196 |
+
"eval_accuracy": 0.20163934426229507,
|
| 197 |
+
"eval_f1_macro": 0.15865115752245537,
|
| 198 |
+
"eval_f1_micro": 0.20163934426229507,
|
| 199 |
+
"eval_f1_weighted": 0.16819957965187343,
|
| 200 |
+
"eval_loss": 4.359624862670898,
|
| 201 |
+
"eval_precision_macro": 0.2004175752293943,
|
| 202 |
+
"eval_precision_micro": 0.20163934426229507,
|
| 203 |
+
"eval_precision_weighted": 0.21056413625270873,
|
| 204 |
+
"eval_recall_macro": 0.18860714285714286,
|
| 205 |
+
"eval_recall_micro": 0.20163934426229507,
|
| 206 |
+
"eval_recall_weighted": 0.20163934426229507,
|
| 207 |
+
"eval_runtime": 16.799,
|
| 208 |
+
"eval_samples_per_second": 72.623,
|
| 209 |
+
"eval_steps_per_second": 1.191,
|
| 210 |
+
"step": 153
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.019867549668874,
|
| 214 |
+
"grad_norm": 7.467461585998535,
|
| 215 |
+
"learning_rate": 1.54e-05,
|
| 216 |
+
"loss": 4.1979,
|
| 217 |
+
"step": 154
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.1589403973509933,
|
| 221 |
+
"grad_norm": 8.049297332763672,
|
| 222 |
+
"learning_rate": 1.6100000000000002e-05,
|
| 223 |
+
"loss": 4.3989,
|
| 224 |
+
"step": 161
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.2980132450331126,
|
| 228 |
+
"grad_norm": 15.375213623046875,
|
| 229 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 230 |
+
"loss": 4.2083,
|
| 231 |
+
"step": 168
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.437086092715232,
|
| 235 |
+
"grad_norm": 9.002079963684082,
|
| 236 |
+
"learning_rate": 1.75e-05,
|
| 237 |
+
"loss": 4.0218,
|
| 238 |
+
"step": 175
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.576158940397351,
|
| 242 |
+
"grad_norm": 9.430607795715332,
|
| 243 |
+
"learning_rate": 1.8200000000000002e-05,
|
| 244 |
+
"loss": 3.8887,
|
| 245 |
+
"step": 182
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.7152317880794703,
|
| 249 |
+
"grad_norm": 8.839299201965332,
|
| 250 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 251 |
+
"loss": 3.6825,
|
| 252 |
+
"step": 189
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.8543046357615895,
|
| 256 |
+
"grad_norm": 10.325126647949219,
|
| 257 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 258 |
+
"loss": 3.5607,
|
| 259 |
+
"step": 196
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 3.993377483443709,
|
| 263 |
+
"grad_norm": 10.668830871582031,
|
| 264 |
+
"learning_rate": 2.0300000000000002e-05,
|
| 265 |
+
"loss": 3.3596,
|
| 266 |
+
"step": 203
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.0,
|
| 270 |
+
"eval_accuracy": 0.4819672131147541,
|
| 271 |
+
"eval_f1_macro": 0.4183671558365781,
|
| 272 |
+
"eval_f1_micro": 0.4819672131147541,
|
| 273 |
+
"eval_f1_weighted": 0.4325206736160847,
|
| 274 |
+
"eval_loss": 2.7524967193603516,
|
| 275 |
+
"eval_precision_macro": 0.4532485780774093,
|
| 276 |
+
"eval_precision_micro": 0.4819672131147541,
|
| 277 |
+
"eval_precision_weighted": 0.4607049565114263,
|
| 278 |
+
"eval_recall_macro": 0.4596547619047619,
|
| 279 |
+
"eval_recall_micro": 0.4819672131147541,
|
| 280 |
+
"eval_recall_weighted": 0.4819672131147541,
|
| 281 |
+
"eval_runtime": 21.0215,
|
| 282 |
+
"eval_samples_per_second": 58.036,
|
| 283 |
+
"eval_steps_per_second": 0.951,
|
| 284 |
+
"step": 204
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.119205298013245,
|
| 288 |
+
"grad_norm": 14.15578842163086,
|
| 289 |
+
"learning_rate": 2.1e-05,
|
| 290 |
+
"loss": 2.792,
|
| 291 |
+
"step": 210
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.258278145695364,
|
| 295 |
+
"grad_norm": 13.17058277130127,
|
| 296 |
+
"learning_rate": 2.1700000000000002e-05,
|
| 297 |
+
"loss": 2.9187,
|
| 298 |
+
"step": 217
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.397350993377484,
|
| 302 |
+
"grad_norm": 17.613101959228516,
|
| 303 |
+
"learning_rate": 2.2400000000000002e-05,
|
| 304 |
+
"loss": 2.8103,
|
| 305 |
+
"step": 224
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.5364238410596025,
|
| 309 |
+
"grad_norm": 10.50324821472168,
|
| 310 |
+
"learning_rate": 2.3100000000000002e-05,
|
| 311 |
+
"loss": 2.6919,
|
| 312 |
+
"step": 231
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.675496688741722,
|
| 316 |
+
"grad_norm": 9.514472007751465,
|
| 317 |
+
"learning_rate": 2.38e-05,
|
| 318 |
+
"loss": 2.4714,
|
| 319 |
+
"step": 238
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.814569536423841,
|
| 323 |
+
"grad_norm": 9.27059268951416,
|
| 324 |
+
"learning_rate": 2.45e-05,
|
| 325 |
+
"loss": 2.4165,
|
| 326 |
+
"step": 245
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.95364238410596,
|
| 330 |
+
"grad_norm": 14.103813171386719,
|
| 331 |
+
"learning_rate": 2.5200000000000003e-05,
|
| 332 |
+
"loss": 2.2583,
|
| 333 |
+
"step": 252
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 5.0,
|
| 337 |
+
"eval_accuracy": 0.6754098360655738,
|
| 338 |
+
"eval_f1_macro": 0.6554426723087714,
|
| 339 |
+
"eval_f1_micro": 0.6754098360655738,
|
| 340 |
+
"eval_f1_weighted": 0.661180283037551,
|
| 341 |
+
"eval_loss": 1.6013199090957642,
|
| 342 |
+
"eval_precision_macro": 0.7148540158456954,
|
| 343 |
+
"eval_precision_micro": 0.6754098360655738,
|
| 344 |
+
"eval_precision_weighted": 0.7134497831635958,
|
| 345 |
+
"eval_recall_macro": 0.6648869047619047,
|
| 346 |
+
"eval_recall_micro": 0.6754098360655738,
|
| 347 |
+
"eval_recall_weighted": 0.6754098360655738,
|
| 348 |
+
"eval_runtime": 17.8695,
|
| 349 |
+
"eval_samples_per_second": 68.273,
|
| 350 |
+
"eval_steps_per_second": 1.119,
|
| 351 |
+
"step": 255
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.079470198675497,
|
| 355 |
+
"grad_norm": 10.124486923217773,
|
| 356 |
+
"learning_rate": 2.5900000000000003e-05,
|
| 357 |
+
"loss": 1.7994,
|
| 358 |
+
"step": 259
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.218543046357616,
|
| 362 |
+
"grad_norm": 9.2846040725708,
|
| 363 |
+
"learning_rate": 2.6600000000000003e-05,
|
| 364 |
+
"loss": 1.8769,
|
| 365 |
+
"step": 266
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.357615894039735,
|
| 369 |
+
"grad_norm": 9.681060791015625,
|
| 370 |
+
"learning_rate": 2.7300000000000003e-05,
|
| 371 |
+
"loss": 1.8592,
|
| 372 |
+
"step": 273
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.496688741721854,
|
| 376 |
+
"grad_norm": 10.057909965515137,
|
| 377 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 378 |
+
"loss": 1.7236,
|
| 379 |
+
"step": 280
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 5.635761589403973,
|
| 383 |
+
"grad_norm": 11.661372184753418,
|
| 384 |
+
"learning_rate": 2.87e-05,
|
| 385 |
+
"loss": 1.7951,
|
| 386 |
+
"step": 287
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.774834437086093,
|
| 390 |
+
"grad_norm": 9.344789505004883,
|
| 391 |
+
"learning_rate": 2.94e-05,
|
| 392 |
+
"loss": 1.6862,
|
| 393 |
+
"step": 294
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 5.913907284768212,
|
| 397 |
+
"grad_norm": 9.517767906188965,
|
| 398 |
+
"learning_rate": 3.01e-05,
|
| 399 |
+
"loss": 1.5559,
|
| 400 |
+
"step": 301
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 6.0,
|
| 404 |
+
"eval_accuracy": 0.7745901639344263,
|
| 405 |
+
"eval_f1_macro": 0.7566554592638184,
|
| 406 |
+
"eval_f1_micro": 0.7745901639344263,
|
| 407 |
+
"eval_f1_weighted": 0.7613547559463157,
|
| 408 |
+
"eval_loss": 1.02675461769104,
|
| 409 |
+
"eval_precision_macro": 0.799015755078255,
|
| 410 |
+
"eval_precision_micro": 0.7745901639344263,
|
| 411 |
+
"eval_precision_weighted": 0.802561029589718,
|
| 412 |
+
"eval_recall_macro": 0.767904761904762,
|
| 413 |
+
"eval_recall_micro": 0.7745901639344263,
|
| 414 |
+
"eval_recall_weighted": 0.7745901639344263,
|
| 415 |
+
"eval_runtime": 20.701,
|
| 416 |
+
"eval_samples_per_second": 58.934,
|
| 417 |
+
"eval_steps_per_second": 0.966,
|
| 418 |
+
"step": 306
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 6.039735099337748,
|
| 422 |
+
"grad_norm": 8.714813232421875,
|
| 423 |
+
"learning_rate": 3.08e-05,
|
| 424 |
+
"loss": 1.3741,
|
| 425 |
+
"step": 308
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 6.178807947019868,
|
| 429 |
+
"grad_norm": 8.35527515411377,
|
| 430 |
+
"learning_rate": 3.15e-05,
|
| 431 |
+
"loss": 1.355,
|
| 432 |
+
"step": 315
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 6.317880794701987,
|
| 436 |
+
"grad_norm": 10.128329277038574,
|
| 437 |
+
"learning_rate": 3.2200000000000003e-05,
|
| 438 |
+
"loss": 1.31,
|
| 439 |
+
"step": 322
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 6.456953642384106,
|
| 443 |
+
"grad_norm": 8.156630516052246,
|
| 444 |
+
"learning_rate": 3.29e-05,
|
| 445 |
+
"loss": 1.2743,
|
| 446 |
+
"step": 329
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.596026490066225,
|
| 450 |
+
"grad_norm": 8.779105186462402,
|
| 451 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 452 |
+
"loss": 1.3193,
|
| 453 |
+
"step": 336
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.735099337748345,
|
| 457 |
+
"grad_norm": 11.118610382080078,
|
| 458 |
+
"learning_rate": 3.430000000000001e-05,
|
| 459 |
+
"loss": 1.2748,
|
| 460 |
+
"step": 343
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 6.874172185430464,
|
| 464 |
+
"grad_norm": 8.063292503356934,
|
| 465 |
+
"learning_rate": 3.5e-05,
|
| 466 |
+
"loss": 1.2319,
|
| 467 |
+
"step": 350
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 7.0,
|
| 471 |
+
"grad_norm": 7.127477169036865,
|
| 472 |
+
"learning_rate": 3.57e-05,
|
| 473 |
+
"loss": 1.0089,
|
| 474 |
+
"step": 357
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 7.0,
|
| 478 |
+
"eval_accuracy": 0.8016393442622951,
|
| 479 |
+
"eval_f1_macro": 0.7894899096002038,
|
| 480 |
+
"eval_f1_micro": 0.8016393442622951,
|
| 481 |
+
"eval_f1_weighted": 0.7904804760759438,
|
| 482 |
+
"eval_loss": 0.7927541136741638,
|
| 483 |
+
"eval_precision_macro": 0.8299506911217438,
|
| 484 |
+
"eval_precision_micro": 0.8016393442622951,
|
| 485 |
+
"eval_precision_weighted": 0.8283684745893546,
|
| 486 |
+
"eval_recall_macro": 0.7991785714285714,
|
| 487 |
+
"eval_recall_micro": 0.8016393442622951,
|
| 488 |
+
"eval_recall_weighted": 0.8016393442622951,
|
| 489 |
+
"eval_runtime": 19.3393,
|
| 490 |
+
"eval_samples_per_second": 63.084,
|
| 491 |
+
"eval_steps_per_second": 1.034,
|
| 492 |
+
"step": 357
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.139072847682119,
|
| 496 |
+
"grad_norm": 9.581562995910645,
|
| 497 |
+
"learning_rate": 3.6400000000000004e-05,
|
| 498 |
+
"loss": 1.0836,
|
| 499 |
+
"step": 364
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.2781456953642385,
|
| 503 |
+
"grad_norm": 11.660162925720215,
|
| 504 |
+
"learning_rate": 3.71e-05,
|
| 505 |
+
"loss": 0.9816,
|
| 506 |
+
"step": 371
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.417218543046357,
|
| 510 |
+
"grad_norm": 10.361519813537598,
|
| 511 |
+
"learning_rate": 3.7800000000000004e-05,
|
| 512 |
+
"loss": 1.1386,
|
| 513 |
+
"step": 378
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.556291390728477,
|
| 517 |
+
"grad_norm": 8.699442863464355,
|
| 518 |
+
"learning_rate": 3.85e-05,
|
| 519 |
+
"loss": 0.9964,
|
| 520 |
+
"step": 385
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.695364238410596,
|
| 524 |
+
"grad_norm": 9.233181953430176,
|
| 525 |
+
"learning_rate": 3.9200000000000004e-05,
|
| 526 |
+
"loss": 1.077,
|
| 527 |
+
"step": 392
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.8344370860927155,
|
| 531 |
+
"grad_norm": 10.234973907470703,
|
| 532 |
+
"learning_rate": 3.99e-05,
|
| 533 |
+
"loss": 0.9844,
|
| 534 |
+
"step": 399
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.973509933774834,
|
| 538 |
+
"grad_norm": 9.366828918457031,
|
| 539 |
+
"learning_rate": 4.0600000000000004e-05,
|
| 540 |
+
"loss": 1.0463,
|
| 541 |
+
"step": 406
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.0,
|
| 545 |
+
"eval_accuracy": 0.8311475409836065,
|
| 546 |
+
"eval_f1_macro": 0.8222988632697376,
|
| 547 |
+
"eval_f1_micro": 0.8311475409836065,
|
| 548 |
+
"eval_f1_weighted": 0.8253316645805044,
|
| 549 |
+
"eval_loss": 0.6437082886695862,
|
| 550 |
+
"eval_precision_macro": 0.8575361999111999,
|
| 551 |
+
"eval_precision_micro": 0.8311475409836065,
|
| 552 |
+
"eval_precision_weighted": 0.8598102466750007,
|
| 553 |
+
"eval_recall_macro": 0.8266071428571429,
|
| 554 |
+
"eval_recall_micro": 0.8311475409836065,
|
| 555 |
+
"eval_recall_weighted": 0.8311475409836065,
|
| 556 |
+
"eval_runtime": 16.6963,
|
| 557 |
+
"eval_samples_per_second": 73.07,
|
| 558 |
+
"eval_steps_per_second": 1.198,
|
| 559 |
+
"step": 408
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 8.099337748344372,
|
| 563 |
+
"grad_norm": 8.740901947021484,
|
| 564 |
+
"learning_rate": 4.13e-05,
|
| 565 |
+
"loss": 0.8633,
|
| 566 |
+
"step": 413
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 8.23841059602649,
|
| 570 |
+
"grad_norm": 9.237879753112793,
|
| 571 |
+
"learning_rate": 4.2e-05,
|
| 572 |
+
"loss": 0.978,
|
| 573 |
+
"step": 420
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 8.37748344370861,
|
| 577 |
+
"grad_norm": 9.53095817565918,
|
| 578 |
+
"learning_rate": 4.27e-05,
|
| 579 |
+
"loss": 0.9132,
|
| 580 |
+
"step": 427
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 8.516556291390728,
|
| 584 |
+
"grad_norm": 9.277670860290527,
|
| 585 |
+
"learning_rate": 4.3400000000000005e-05,
|
| 586 |
+
"loss": 0.8908,
|
| 587 |
+
"step": 434
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 8.655629139072847,
|
| 591 |
+
"grad_norm": 7.736002445220947,
|
| 592 |
+
"learning_rate": 4.41e-05,
|
| 593 |
+
"loss": 0.9602,
|
| 594 |
+
"step": 441
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 8.794701986754967,
|
| 598 |
+
"grad_norm": 9.285863876342773,
|
| 599 |
+
"learning_rate": 4.4800000000000005e-05,
|
| 600 |
+
"loss": 0.8773,
|
| 601 |
+
"step": 448
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 8.933774834437086,
|
| 605 |
+
"grad_norm": 6.872951507568359,
|
| 606 |
+
"learning_rate": 4.55e-05,
|
| 607 |
+
"loss": 0.8551,
|
| 608 |
+
"step": 455
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 9.0,
|
| 612 |
+
"eval_accuracy": 0.8467213114754099,
|
| 613 |
+
"eval_f1_macro": 0.8380145271395273,
|
| 614 |
+
"eval_f1_micro": 0.8467213114754099,
|
| 615 |
+
"eval_f1_weighted": 0.8412076976650266,
|
| 616 |
+
"eval_loss": 0.5831084847450256,
|
| 617 |
+
"eval_precision_macro": 0.8702838485044367,
|
| 618 |
+
"eval_precision_micro": 0.8467213114754099,
|
| 619 |
+
"eval_precision_weighted": 0.8695735086995936,
|
| 620 |
+
"eval_recall_macro": 0.8410952380952381,
|
| 621 |
+
"eval_recall_micro": 0.8467213114754099,
|
| 622 |
+
"eval_recall_weighted": 0.8467213114754099,
|
| 623 |
+
"eval_runtime": 17.1069,
|
| 624 |
+
"eval_samples_per_second": 71.316,
|
| 625 |
+
"eval_steps_per_second": 1.169,
|
| 626 |
+
"step": 459
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 9.059602649006623,
|
| 630 |
+
"grad_norm": 9.55445671081543,
|
| 631 |
+
"learning_rate": 4.6200000000000005e-05,
|
| 632 |
+
"loss": 0.7727,
|
| 633 |
+
"step": 462
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 9.198675496688741,
|
| 637 |
+
"grad_norm": 10.598060607910156,
|
| 638 |
+
"learning_rate": 4.69e-05,
|
| 639 |
+
"loss": 0.7759,
|
| 640 |
+
"step": 469
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 9.33774834437086,
|
| 644 |
+
"grad_norm": 9.53549861907959,
|
| 645 |
+
"learning_rate": 4.76e-05,
|
| 646 |
+
"loss": 0.8016,
|
| 647 |
+
"step": 476
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 9.47682119205298,
|
| 651 |
+
"grad_norm": 8.146626472473145,
|
| 652 |
+
"learning_rate": 4.83e-05,
|
| 653 |
+
"loss": 0.779,
|
| 654 |
+
"step": 483
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 9.6158940397351,
|
| 658 |
+
"grad_norm": 6.373037815093994,
|
| 659 |
+
"learning_rate": 4.9e-05,
|
| 660 |
+
"loss": 0.6726,
|
| 661 |
+
"step": 490
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 9.754966887417218,
|
| 665 |
+
"grad_norm": 9.011489868164062,
|
| 666 |
+
"learning_rate": 4.97e-05,
|
| 667 |
+
"loss": 0.835,
|
| 668 |
+
"step": 497
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 9.894039735099337,
|
| 672 |
+
"grad_norm": 8.79944133758545,
|
| 673 |
+
"learning_rate": 4.995555555555556e-05,
|
| 674 |
+
"loss": 0.7234,
|
| 675 |
+
"step": 504
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 10.0,
|
| 679 |
+
"eval_accuracy": 0.8672131147540983,
|
| 680 |
+
"eval_f1_macro": 0.8578000912486207,
|
| 681 |
+
"eval_f1_micro": 0.8672131147540983,
|
| 682 |
+
"eval_f1_weighted": 0.8622077336035869,
|
| 683 |
+
"eval_loss": 0.5154255628585815,
|
| 684 |
+
"eval_precision_macro": 0.8773138528138529,
|
| 685 |
+
"eval_precision_micro": 0.8672131147540983,
|
| 686 |
+
"eval_precision_weighted": 0.8793111737988787,
|
| 687 |
+
"eval_recall_macro": 0.8614821428571429,
|
| 688 |
+
"eval_recall_micro": 0.8672131147540983,
|
| 689 |
+
"eval_recall_weighted": 0.8672131147540983,
|
| 690 |
+
"eval_runtime": 18.8743,
|
| 691 |
+
"eval_samples_per_second": 64.638,
|
| 692 |
+
"eval_steps_per_second": 1.06,
|
| 693 |
+
"step": 510
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 10.019867549668874,
|
| 697 |
+
"grad_norm": 12.6382474899292,
|
| 698 |
+
"learning_rate": 4.987777777777778e-05,
|
| 699 |
+
"loss": 0.6376,
|
| 700 |
+
"step": 511
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 10.158940397350994,
|
| 704 |
+
"grad_norm": 7.875304222106934,
|
| 705 |
+
"learning_rate": 4.9800000000000004e-05,
|
| 706 |
+
"loss": 0.608,
|
| 707 |
+
"step": 518
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 10.298013245033113,
|
| 711 |
+
"grad_norm": 8.565564155578613,
|
| 712 |
+
"learning_rate": 4.972222222222223e-05,
|
| 713 |
+
"loss": 0.7333,
|
| 714 |
+
"step": 525
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 10.437086092715232,
|
| 718 |
+
"grad_norm": 8.355602264404297,
|
| 719 |
+
"learning_rate": 4.964444444444445e-05,
|
| 720 |
+
"loss": 0.6883,
|
| 721 |
+
"step": 532
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 10.57615894039735,
|
| 725 |
+
"grad_norm": 8.657296180725098,
|
| 726 |
+
"learning_rate": 4.956666666666667e-05,
|
| 727 |
+
"loss": 0.7567,
|
| 728 |
+
"step": 539
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 10.71523178807947,
|
| 732 |
+
"grad_norm": 7.550002098083496,
|
| 733 |
+
"learning_rate": 4.948888888888889e-05,
|
| 734 |
+
"loss": 0.7422,
|
| 735 |
+
"step": 546
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 10.85430463576159,
|
| 739 |
+
"grad_norm": 7.08698844909668,
|
| 740 |
+
"learning_rate": 4.9411111111111114e-05,
|
| 741 |
+
"loss": 0.7045,
|
| 742 |
+
"step": 553
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 10.993377483443709,
|
| 746 |
+
"grad_norm": 8.84117317199707,
|
| 747 |
+
"learning_rate": 4.933333333333334e-05,
|
| 748 |
+
"loss": 0.7177,
|
| 749 |
+
"step": 560
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 11.0,
|
| 753 |
+
"eval_accuracy": 0.8745901639344262,
|
| 754 |
+
"eval_f1_macro": 0.8674472995614636,
|
| 755 |
+
"eval_f1_micro": 0.8745901639344262,
|
| 756 |
+
"eval_f1_weighted": 0.869469718145237,
|
| 757 |
+
"eval_loss": 0.4802148938179016,
|
| 758 |
+
"eval_precision_macro": 0.8951194083694085,
|
| 759 |
+
"eval_precision_micro": 0.8745901639344262,
|
| 760 |
+
"eval_precision_weighted": 0.8939981489366735,
|
| 761 |
+
"eval_recall_macro": 0.8713035714285715,
|
| 762 |
+
"eval_recall_micro": 0.8745901639344262,
|
| 763 |
+
"eval_recall_weighted": 0.8745901639344262,
|
| 764 |
+
"eval_runtime": 17.7202,
|
| 765 |
+
"eval_samples_per_second": 68.848,
|
| 766 |
+
"eval_steps_per_second": 1.129,
|
| 767 |
+
"step": 561
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 11.119205298013245,
|
| 771 |
+
"grad_norm": 9.191046714782715,
|
| 772 |
+
"learning_rate": 4.925555555555556e-05,
|
| 773 |
+
"loss": 0.5652,
|
| 774 |
+
"step": 567
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 11.258278145695364,
|
| 778 |
+
"grad_norm": 6.099012851715088,
|
| 779 |
+
"learning_rate": 4.917777777777778e-05,
|
| 780 |
+
"loss": 0.6823,
|
| 781 |
+
"step": 574
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 11.397350993377483,
|
| 785 |
+
"grad_norm": 7.644286632537842,
|
| 786 |
+
"learning_rate": 4.91e-05,
|
| 787 |
+
"loss": 0.5704,
|
| 788 |
+
"step": 581
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 11.536423841059603,
|
| 792 |
+
"grad_norm": 7.208959579467773,
|
| 793 |
+
"learning_rate": 4.9022222222222224e-05,
|
| 794 |
+
"loss": 0.5889,
|
| 795 |
+
"step": 588
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 11.675496688741722,
|
| 799 |
+
"grad_norm": 8.255132675170898,
|
| 800 |
+
"learning_rate": 4.894444444444445e-05,
|
| 801 |
+
"loss": 0.7361,
|
| 802 |
+
"step": 595
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 11.814569536423841,
|
| 806 |
+
"grad_norm": 8.378829002380371,
|
| 807 |
+
"learning_rate": 4.886666666666667e-05,
|
| 808 |
+
"loss": 0.6723,
|
| 809 |
+
"step": 602
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 11.95364238410596,
|
| 813 |
+
"grad_norm": 11.726705551147461,
|
| 814 |
+
"learning_rate": 4.878888888888889e-05,
|
| 815 |
+
"loss": 0.711,
|
| 816 |
+
"step": 609
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 12.0,
|
| 820 |
+
"eval_accuracy": 0.8565573770491803,
|
| 821 |
+
"eval_f1_macro": 0.8515204682228676,
|
| 822 |
+
"eval_f1_micro": 0.8565573770491803,
|
| 823 |
+
"eval_f1_weighted": 0.8536645233724359,
|
| 824 |
+
"eval_loss": 0.4757900536060333,
|
| 825 |
+
"eval_precision_macro": 0.8826355588855589,
|
| 826 |
+
"eval_precision_micro": 0.8565573770491803,
|
| 827 |
+
"eval_precision_weighted": 0.8834410489328521,
|
| 828 |
+
"eval_recall_macro": 0.8537678571428572,
|
| 829 |
+
"eval_recall_micro": 0.8565573770491803,
|
| 830 |
+
"eval_recall_weighted": 0.8565573770491803,
|
| 831 |
+
"eval_runtime": 18.3018,
|
| 832 |
+
"eval_samples_per_second": 66.66,
|
| 833 |
+
"eval_steps_per_second": 1.093,
|
| 834 |
+
"step": 612
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 12.079470198675496,
|
| 838 |
+
"grad_norm": 7.42709493637085,
|
| 839 |
+
"learning_rate": 4.871111111111111e-05,
|
| 840 |
+
"loss": 0.5113,
|
| 841 |
+
"step": 616
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 12.218543046357617,
|
| 845 |
+
"grad_norm": 9.922298431396484,
|
| 846 |
+
"learning_rate": 4.8633333333333334e-05,
|
| 847 |
+
"loss": 0.6113,
|
| 848 |
+
"step": 623
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 12.357615894039736,
|
| 852 |
+
"grad_norm": 5.806549072265625,
|
| 853 |
+
"learning_rate": 4.855555555555556e-05,
|
| 854 |
+
"loss": 0.592,
|
| 855 |
+
"step": 630
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 12.496688741721854,
|
| 859 |
+
"grad_norm": 8.837335586547852,
|
| 860 |
+
"learning_rate": 4.847777777777778e-05,
|
| 861 |
+
"loss": 0.604,
|
| 862 |
+
"step": 637
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 12.635761589403973,
|
| 866 |
+
"grad_norm": 7.156353950500488,
|
| 867 |
+
"learning_rate": 4.8400000000000004e-05,
|
| 868 |
+
"loss": 0.5203,
|
| 869 |
+
"step": 644
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 12.774834437086092,
|
| 873 |
+
"grad_norm": 8.29881477355957,
|
| 874 |
+
"learning_rate": 4.832222222222223e-05,
|
| 875 |
+
"loss": 0.6528,
|
| 876 |
+
"step": 651
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 12.913907284768213,
|
| 880 |
+
"grad_norm": 7.490756511688232,
|
| 881 |
+
"learning_rate": 4.824444444444445e-05,
|
| 882 |
+
"loss": 0.5318,
|
| 883 |
+
"step": 658
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 13.0,
|
| 887 |
+
"eval_accuracy": 0.8672131147540983,
|
| 888 |
+
"eval_f1_macro": 0.8627146097366685,
|
| 889 |
+
"eval_f1_micro": 0.8672131147540983,
|
| 890 |
+
"eval_f1_weighted": 0.8659745527428748,
|
| 891 |
+
"eval_loss": 0.4569399952888489,
|
| 892 |
+
"eval_precision_macro": 0.8866749639249639,
|
| 893 |
+
"eval_precision_micro": 0.8672131147540983,
|
| 894 |
+
"eval_precision_weighted": 0.888172740283396,
|
| 895 |
+
"eval_recall_macro": 0.8630297619047619,
|
| 896 |
+
"eval_recall_micro": 0.8672131147540983,
|
| 897 |
+
"eval_recall_weighted": 0.8672131147540983,
|
| 898 |
+
"eval_runtime": 17.7039,
|
| 899 |
+
"eval_samples_per_second": 68.911,
|
| 900 |
+
"eval_steps_per_second": 1.13,
|
| 901 |
+
"step": 663
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 13.039735099337749,
|
| 905 |
+
"grad_norm": 8.017422676086426,
|
| 906 |
+
"learning_rate": 4.8166666666666674e-05,
|
| 907 |
+
"loss": 0.4727,
|
| 908 |
+
"step": 665
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 13.178807947019868,
|
| 912 |
+
"grad_norm": 7.218966007232666,
|
| 913 |
+
"learning_rate": 4.808888888888889e-05,
|
| 914 |
+
"loss": 0.5897,
|
| 915 |
+
"step": 672
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 13.317880794701987,
|
| 919 |
+
"grad_norm": 10.478813171386719,
|
| 920 |
+
"learning_rate": 4.8011111111111114e-05,
|
| 921 |
+
"loss": 0.5473,
|
| 922 |
+
"step": 679
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 13.456953642384105,
|
| 926 |
+
"grad_norm": 6.682877540588379,
|
| 927 |
+
"learning_rate": 4.793333333333334e-05,
|
| 928 |
+
"loss": 0.5479,
|
| 929 |
+
"step": 686
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 13.596026490066226,
|
| 933 |
+
"grad_norm": 12.535813331604004,
|
| 934 |
+
"learning_rate": 4.785555555555556e-05,
|
| 935 |
+
"loss": 0.5458,
|
| 936 |
+
"step": 693
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 13.735099337748345,
|
| 940 |
+
"grad_norm": 7.044444561004639,
|
| 941 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 942 |
+
"loss": 0.5401,
|
| 943 |
+
"step": 700
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 13.874172185430464,
|
| 947 |
+
"grad_norm": 7.247359752655029,
|
| 948 |
+
"learning_rate": 4.77e-05,
|
| 949 |
+
"loss": 0.5912,
|
| 950 |
+
"step": 707
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 14.0,
|
| 954 |
+
"grad_norm": 6.261186122894287,
|
| 955 |
+
"learning_rate": 4.7622222222222224e-05,
|
| 956 |
+
"loss": 0.5383,
|
| 957 |
+
"step": 714
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 14.0,
|
| 961 |
+
"eval_accuracy": 0.8786885245901639,
|
| 962 |
+
"eval_f1_macro": 0.87375893714129,
|
| 963 |
+
"eval_f1_micro": 0.8786885245901639,
|
| 964 |
+
"eval_f1_weighted": 0.8755628520466998,
|
| 965 |
+
"eval_loss": 0.4514833092689514,
|
| 966 |
+
"eval_precision_macro": 0.8954447203123673,
|
| 967 |
+
"eval_precision_micro": 0.8786885245901639,
|
| 968 |
+
"eval_precision_weighted": 0.8948432423143127,
|
| 969 |
+
"eval_recall_macro": 0.8754642857142858,
|
| 970 |
+
"eval_recall_micro": 0.8786885245901639,
|
| 971 |
+
"eval_recall_weighted": 0.8786885245901639,
|
| 972 |
+
"eval_runtime": 18.849,
|
| 973 |
+
"eval_samples_per_second": 64.725,
|
| 974 |
+
"eval_steps_per_second": 1.061,
|
| 975 |
+
"step": 714
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 14.139072847682119,
|
| 979 |
+
"grad_norm": 8.038314819335938,
|
| 980 |
+
"learning_rate": 4.754444444444445e-05,
|
| 981 |
+
"loss": 0.4757,
|
| 982 |
+
"step": 721
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 14.278145695364238,
|
| 986 |
+
"grad_norm": 6.933023929595947,
|
| 987 |
+
"learning_rate": 4.746666666666667e-05,
|
| 988 |
+
"loss": 0.5422,
|
| 989 |
+
"step": 728
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 14.417218543046358,
|
| 993 |
+
"grad_norm": 5.427736282348633,
|
| 994 |
+
"learning_rate": 4.7388888888888894e-05,
|
| 995 |
+
"loss": 0.45,
|
| 996 |
+
"step": 735
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.556291390728477,
|
| 1000 |
+
"grad_norm": 7.140816688537598,
|
| 1001 |
+
"learning_rate": 4.731111111111111e-05,
|
| 1002 |
+
"loss": 0.4801,
|
| 1003 |
+
"step": 742
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.695364238410596,
|
| 1007 |
+
"grad_norm": 14.195199966430664,
|
| 1008 |
+
"learning_rate": 4.7233333333333334e-05,
|
| 1009 |
+
"loss": 0.4627,
|
| 1010 |
+
"step": 749
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.834437086092715,
|
| 1014 |
+
"grad_norm": 6.867580413818359,
|
| 1015 |
+
"learning_rate": 4.715555555555556e-05,
|
| 1016 |
+
"loss": 0.4988,
|
| 1017 |
+
"step": 756
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.973509933774835,
|
| 1021 |
+
"grad_norm": 6.6102519035339355,
|
| 1022 |
+
"learning_rate": 4.707777777777778e-05,
|
| 1023 |
+
"loss": 0.4884,
|
| 1024 |
+
"step": 763
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 15.0,
|
| 1028 |
+
"eval_accuracy": 0.8762295081967213,
|
| 1029 |
+
"eval_f1_macro": 0.8721245222748117,
|
| 1030 |
+
"eval_f1_micro": 0.8762295081967213,
|
| 1031 |
+
"eval_f1_weighted": 0.8740396988842932,
|
| 1032 |
+
"eval_loss": 0.4364243745803833,
|
| 1033 |
+
"eval_precision_macro": 0.8978099123099124,
|
| 1034 |
+
"eval_precision_micro": 0.8762295081967213,
|
| 1035 |
+
"eval_precision_weighted": 0.899852774729824,
|
| 1036 |
+
"eval_recall_macro": 0.8744226190476191,
|
| 1037 |
+
"eval_recall_micro": 0.8762295081967213,
|
| 1038 |
+
"eval_recall_weighted": 0.8762295081967213,
|
| 1039 |
+
"eval_runtime": 18.6981,
|
| 1040 |
+
"eval_samples_per_second": 65.247,
|
| 1041 |
+
"eval_steps_per_second": 1.07,
|
| 1042 |
+
"step": 765
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 15.099337748344372,
|
| 1046 |
+
"grad_norm": 6.755874156951904,
|
| 1047 |
+
"learning_rate": 4.7e-05,
|
| 1048 |
+
"loss": 0.4067,
|
| 1049 |
+
"step": 770
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 15.23841059602649,
|
| 1053 |
+
"grad_norm": 7.634614944458008,
|
| 1054 |
+
"learning_rate": 4.692222222222222e-05,
|
| 1055 |
+
"loss": 0.5742,
|
| 1056 |
+
"step": 777
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 15.37748344370861,
|
| 1060 |
+
"grad_norm": 4.661431789398193,
|
| 1061 |
+
"learning_rate": 4.6844444444444444e-05,
|
| 1062 |
+
"loss": 0.4345,
|
| 1063 |
+
"step": 784
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 15.516556291390728,
|
| 1067 |
+
"grad_norm": 18.19213104248047,
|
| 1068 |
+
"learning_rate": 4.676666666666667e-05,
|
| 1069 |
+
"loss": 0.3906,
|
| 1070 |
+
"step": 791
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 15.655629139072847,
|
| 1074 |
+
"grad_norm": 9.202508926391602,
|
| 1075 |
+
"learning_rate": 4.668888888888889e-05,
|
| 1076 |
+
"loss": 0.4467,
|
| 1077 |
+
"step": 798
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 15.794701986754967,
|
| 1081 |
+
"grad_norm": 5.7517619132995605,
|
| 1082 |
+
"learning_rate": 4.6611111111111114e-05,
|
| 1083 |
+
"loss": 0.4794,
|
| 1084 |
+
"step": 805
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 15.933774834437086,
|
| 1088 |
+
"grad_norm": 7.352263927459717,
|
| 1089 |
+
"learning_rate": 4.653333333333334e-05,
|
| 1090 |
+
"loss": 0.5808,
|
| 1091 |
+
"step": 812
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 16.0,
|
| 1095 |
+
"eval_accuracy": 0.8844262295081967,
|
| 1096 |
+
"eval_f1_macro": 0.8804055188447603,
|
| 1097 |
+
"eval_f1_micro": 0.8844262295081967,
|
| 1098 |
+
"eval_f1_weighted": 0.8828176785374927,
|
| 1099 |
+
"eval_loss": 0.42853277921676636,
|
| 1100 |
+
"eval_precision_macro": 0.9033134920634922,
|
| 1101 |
+
"eval_precision_micro": 0.8844262295081967,
|
| 1102 |
+
"eval_precision_weighted": 0.9039139344262296,
|
| 1103 |
+
"eval_recall_macro": 0.8815000000000001,
|
| 1104 |
+
"eval_recall_micro": 0.8844262295081967,
|
| 1105 |
+
"eval_recall_weighted": 0.8844262295081967,
|
| 1106 |
+
"eval_runtime": 16.8381,
|
| 1107 |
+
"eval_samples_per_second": 72.455,
|
| 1108 |
+
"eval_steps_per_second": 1.188,
|
| 1109 |
+
"step": 816
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 16.05960264900662,
|
| 1113 |
+
"grad_norm": 7.281948089599609,
|
| 1114 |
+
"learning_rate": 4.645555555555556e-05,
|
| 1115 |
+
"loss": 0.4086,
|
| 1116 |
+
"step": 819
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 16.198675496688743,
|
| 1120 |
+
"grad_norm": 6.114387512207031,
|
| 1121 |
+
"learning_rate": 4.6377777777777784e-05,
|
| 1122 |
+
"loss": 0.4764,
|
| 1123 |
+
"step": 826
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 16.337748344370862,
|
| 1127 |
+
"grad_norm": 6.659070014953613,
|
| 1128 |
+
"learning_rate": 4.630000000000001e-05,
|
| 1129 |
+
"loss": 0.3795,
|
| 1130 |
+
"step": 833
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 16.47682119205298,
|
| 1134 |
+
"grad_norm": 4.916147708892822,
|
| 1135 |
+
"learning_rate": 4.6222222222222224e-05,
|
| 1136 |
+
"loss": 0.4566,
|
| 1137 |
+
"step": 840
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 16.6158940397351,
|
| 1141 |
+
"grad_norm": 4.47711706161499,
|
| 1142 |
+
"learning_rate": 4.614444444444445e-05,
|
| 1143 |
+
"loss": 0.4853,
|
| 1144 |
+
"step": 847
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 16.75496688741722,
|
| 1148 |
+
"grad_norm": 3.844993829727173,
|
| 1149 |
+
"learning_rate": 4.606666666666667e-05,
|
| 1150 |
+
"loss": 0.4298,
|
| 1151 |
+
"step": 854
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 16.894039735099337,
|
| 1155 |
+
"grad_norm": 6.387825012207031,
|
| 1156 |
+
"learning_rate": 4.5988888888888894e-05,
|
| 1157 |
+
"loss": 0.5004,
|
| 1158 |
+
"step": 861
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 17.0,
|
| 1162 |
+
"eval_accuracy": 0.8762295081967213,
|
| 1163 |
+
"eval_f1_macro": 0.8698742597272009,
|
| 1164 |
+
"eval_f1_micro": 0.8762295081967213,
|
| 1165 |
+
"eval_f1_weighted": 0.8724110373447403,
|
| 1166 |
+
"eval_loss": 0.4314015805721283,
|
| 1167 |
+
"eval_precision_macro": 0.8928979076479078,
|
| 1168 |
+
"eval_precision_micro": 0.8762295081967213,
|
| 1169 |
+
"eval_precision_weighted": 0.8934799694840678,
|
| 1170 |
+
"eval_recall_macro": 0.8727380952380953,
|
| 1171 |
+
"eval_recall_micro": 0.8762295081967213,
|
| 1172 |
+
"eval_recall_weighted": 0.8762295081967213,
|
| 1173 |
+
"eval_runtime": 16.836,
|
| 1174 |
+
"eval_samples_per_second": 72.464,
|
| 1175 |
+
"eval_steps_per_second": 1.188,
|
| 1176 |
+
"step": 867
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 17.019867549668874,
|
| 1180 |
+
"grad_norm": 27.180448532104492,
|
| 1181 |
+
"learning_rate": 4.591111111111112e-05,
|
| 1182 |
+
"loss": 0.3922,
|
| 1183 |
+
"step": 868
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 17.158940397350992,
|
| 1187 |
+
"grad_norm": 7.212271690368652,
|
| 1188 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 1189 |
+
"loss": 0.4964,
|
| 1190 |
+
"step": 875
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 17.29801324503311,
|
| 1194 |
+
"grad_norm": 6.941275119781494,
|
| 1195 |
+
"learning_rate": 4.575555555555556e-05,
|
| 1196 |
+
"loss": 0.4749,
|
| 1197 |
+
"step": 882
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 17.437086092715234,
|
| 1201 |
+
"grad_norm": 5.599315166473389,
|
| 1202 |
+
"learning_rate": 4.567777777777778e-05,
|
| 1203 |
+
"loss": 0.4885,
|
| 1204 |
+
"step": 889
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 17.576158940397352,
|
| 1208 |
+
"grad_norm": 5.130136489868164,
|
| 1209 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 1210 |
+
"loss": 0.5264,
|
| 1211 |
+
"step": 896
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 17.71523178807947,
|
| 1215 |
+
"grad_norm": 6.701182842254639,
|
| 1216 |
+
"learning_rate": 4.552222222222222e-05,
|
| 1217 |
+
"loss": 0.4466,
|
| 1218 |
+
"step": 903
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 17.85430463576159,
|
| 1222 |
+
"grad_norm": 6.988078594207764,
|
| 1223 |
+
"learning_rate": 4.5444444444444444e-05,
|
| 1224 |
+
"loss": 0.3975,
|
| 1225 |
+
"step": 910
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 17.99337748344371,
|
| 1229 |
+
"grad_norm": 21.04884910583496,
|
| 1230 |
+
"learning_rate": 4.536666666666667e-05,
|
| 1231 |
+
"loss": 0.3537,
|
| 1232 |
+
"step": 917
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 18.0,
|
| 1236 |
+
"eval_accuracy": 0.8827868852459017,
|
| 1237 |
+
"eval_f1_macro": 0.8796409929939343,
|
| 1238 |
+
"eval_f1_micro": 0.8827868852459017,
|
| 1239 |
+
"eval_f1_weighted": 0.8807563045280018,
|
| 1240 |
+
"eval_loss": 0.43711456656455994,
|
| 1241 |
+
"eval_precision_macro": 0.8961841630591632,
|
| 1242 |
+
"eval_precision_micro": 0.8827868852459017,
|
| 1243 |
+
"eval_precision_weighted": 0.8967877250254299,
|
| 1244 |
+
"eval_recall_macro": 0.8815892857142857,
|
| 1245 |
+
"eval_recall_micro": 0.8827868852459017,
|
| 1246 |
+
"eval_recall_weighted": 0.8827868852459017,
|
| 1247 |
+
"eval_runtime": 16.5565,
|
| 1248 |
+
"eval_samples_per_second": 73.687,
|
| 1249 |
+
"eval_steps_per_second": 1.208,
|
| 1250 |
+
"step": 918
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 18.119205298013245,
|
| 1254 |
+
"grad_norm": 7.078250408172607,
|
| 1255 |
+
"learning_rate": 4.528888888888889e-05,
|
| 1256 |
+
"loss": 0.406,
|
| 1257 |
+
"step": 924
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 18.258278145695364,
|
| 1261 |
+
"grad_norm": 5.898381233215332,
|
| 1262 |
+
"learning_rate": 4.5211111111111114e-05,
|
| 1263 |
+
"loss": 0.3619,
|
| 1264 |
+
"step": 931
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 18.397350993377483,
|
| 1268 |
+
"grad_norm": 7.024068355560303,
|
| 1269 |
+
"learning_rate": 4.513333333333333e-05,
|
| 1270 |
+
"loss": 0.4441,
|
| 1271 |
+
"step": 938
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 18.5364238410596,
|
| 1275 |
+
"grad_norm": 6.673207759857178,
|
| 1276 |
+
"learning_rate": 4.5055555555555554e-05,
|
| 1277 |
+
"loss": 0.3495,
|
| 1278 |
+
"step": 945
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 18.67549668874172,
|
| 1282 |
+
"grad_norm": 7.188521385192871,
|
| 1283 |
+
"learning_rate": 4.497777777777778e-05,
|
| 1284 |
+
"loss": 0.424,
|
| 1285 |
+
"step": 952
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 18.814569536423843,
|
| 1289 |
+
"grad_norm": 13.439776420593262,
|
| 1290 |
+
"learning_rate": 4.49e-05,
|
| 1291 |
+
"loss": 0.3988,
|
| 1292 |
+
"step": 959
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 18.95364238410596,
|
| 1296 |
+
"grad_norm": 6.0843305587768555,
|
| 1297 |
+
"learning_rate": 4.4822222222222224e-05,
|
| 1298 |
+
"loss": 0.4362,
|
| 1299 |
+
"step": 966
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 19.0,
|
| 1303 |
+
"eval_accuracy": 0.8827868852459017,
|
| 1304 |
+
"eval_f1_macro": 0.8795757517766032,
|
| 1305 |
+
"eval_f1_micro": 0.8827868852459017,
|
| 1306 |
+
"eval_f1_weighted": 0.8811126749814384,
|
| 1307 |
+
"eval_loss": 0.41565409302711487,
|
| 1308 |
+
"eval_precision_macro": 0.9002148268398268,
|
| 1309 |
+
"eval_precision_micro": 0.8827868852459017,
|
| 1310 |
+
"eval_precision_weighted": 0.9000307820594705,
|
| 1311 |
+
"eval_recall_macro": 0.8807797619047619,
|
| 1312 |
+
"eval_recall_micro": 0.8827868852459017,
|
| 1313 |
+
"eval_recall_weighted": 0.8827868852459017,
|
| 1314 |
+
"eval_runtime": 20.7708,
|
| 1315 |
+
"eval_samples_per_second": 58.736,
|
| 1316 |
+
"eval_steps_per_second": 0.963,
|
| 1317 |
+
"step": 969
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 19.079470198675498,
|
| 1321 |
+
"grad_norm": 5.036433696746826,
|
| 1322 |
+
"learning_rate": 4.474444444444445e-05,
|
| 1323 |
+
"loss": 0.3053,
|
| 1324 |
+
"step": 973
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 19.218543046357617,
|
| 1328 |
+
"grad_norm": 6.565299034118652,
|
| 1329 |
+
"learning_rate": 4.466666666666667e-05,
|
| 1330 |
+
"loss": 0.3934,
|
| 1331 |
+
"step": 980
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 19.357615894039736,
|
| 1335 |
+
"grad_norm": 8.689690589904785,
|
| 1336 |
+
"learning_rate": 4.4588888888888894e-05,
|
| 1337 |
+
"loss": 0.4622,
|
| 1338 |
+
"step": 987
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 19.496688741721854,
|
| 1342 |
+
"grad_norm": 6.253081321716309,
|
| 1343 |
+
"learning_rate": 4.451111111111112e-05,
|
| 1344 |
+
"loss": 0.4095,
|
| 1345 |
+
"step": 994
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 19.635761589403973,
|
| 1349 |
+
"grad_norm": 5.1961846351623535,
|
| 1350 |
+
"learning_rate": 4.443333333333334e-05,
|
| 1351 |
+
"loss": 0.3806,
|
| 1352 |
+
"step": 1001
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 19.774834437086092,
|
| 1356 |
+
"grad_norm": 7.494758129119873,
|
| 1357 |
+
"learning_rate": 4.435555555555556e-05,
|
| 1358 |
+
"loss": 0.4382,
|
| 1359 |
+
"step": 1008
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 19.91390728476821,
|
| 1363 |
+
"grad_norm": 4.928430557250977,
|
| 1364 |
+
"learning_rate": 4.427777777777778e-05,
|
| 1365 |
+
"loss": 0.3672,
|
| 1366 |
+
"step": 1015
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 20.0,
|
| 1370 |
+
"eval_accuracy": 0.8885245901639345,
|
| 1371 |
+
"eval_f1_macro": 0.8857740416618127,
|
| 1372 |
+
"eval_f1_micro": 0.8885245901639345,
|
| 1373 |
+
"eval_f1_weighted": 0.8862372325718009,
|
| 1374 |
+
"eval_loss": 0.404880166053772,
|
| 1375 |
+
"eval_precision_macro": 0.9038582528582529,
|
| 1376 |
+
"eval_precision_micro": 0.8885245901639345,
|
| 1377 |
+
"eval_precision_weighted": 0.9033163921688513,
|
| 1378 |
+
"eval_recall_macro": 0.887125,
|
| 1379 |
+
"eval_recall_micro": 0.8885245901639345,
|
| 1380 |
+
"eval_recall_weighted": 0.8885245901639345,
|
| 1381 |
+
"eval_runtime": 31.922,
|
| 1382 |
+
"eval_samples_per_second": 38.218,
|
| 1383 |
+
"eval_steps_per_second": 0.627,
|
| 1384 |
+
"step": 1020
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 20.039735099337747,
|
| 1388 |
+
"grad_norm": 4.6109299659729,
|
| 1389 |
+
"learning_rate": 4.4200000000000004e-05,
|
| 1390 |
+
"loss": 0.3098,
|
| 1391 |
+
"step": 1022
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 20.178807947019866,
|
| 1395 |
+
"grad_norm": 9.729621887207031,
|
| 1396 |
+
"learning_rate": 4.412222222222223e-05,
|
| 1397 |
+
"loss": 0.3719,
|
| 1398 |
+
"step": 1029
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 20.31788079470199,
|
| 1402 |
+
"grad_norm": 5.514610767364502,
|
| 1403 |
+
"learning_rate": 4.404444444444445e-05,
|
| 1404 |
+
"loss": 0.3623,
|
| 1405 |
+
"step": 1036
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 20.456953642384107,
|
| 1409 |
+
"grad_norm": 4.57627534866333,
|
| 1410 |
+
"learning_rate": 4.396666666666667e-05,
|
| 1411 |
+
"loss": 0.3866,
|
| 1412 |
+
"step": 1043
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 20.596026490066226,
|
| 1416 |
+
"grad_norm": 5.22489595413208,
|
| 1417 |
+
"learning_rate": 4.388888888888889e-05,
|
| 1418 |
+
"loss": 0.3288,
|
| 1419 |
+
"step": 1050
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 20.735099337748345,
|
| 1423 |
+
"grad_norm": 5.026643753051758,
|
| 1424 |
+
"learning_rate": 4.3811111111111114e-05,
|
| 1425 |
+
"loss": 0.3729,
|
| 1426 |
+
"step": 1057
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 20.874172185430464,
|
| 1430 |
+
"grad_norm": 5.927851676940918,
|
| 1431 |
+
"learning_rate": 4.373333333333334e-05,
|
| 1432 |
+
"loss": 0.3909,
|
| 1433 |
+
"step": 1064
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 21.0,
|
| 1437 |
+
"grad_norm": 2.4257664680480957,
|
| 1438 |
+
"learning_rate": 4.3655555555555554e-05,
|
| 1439 |
+
"loss": 0.3431,
|
| 1440 |
+
"step": 1071
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 21.0,
|
| 1444 |
+
"eval_accuracy": 0.8885245901639345,
|
| 1445 |
+
"eval_f1_macro": 0.8852515238029943,
|
| 1446 |
+
"eval_f1_micro": 0.8885245901639345,
|
| 1447 |
+
"eval_f1_weighted": 0.8881485842454984,
|
| 1448 |
+
"eval_loss": 0.4021802544593811,
|
| 1449 |
+
"eval_precision_macro": 0.9078284354534355,
|
| 1450 |
+
"eval_precision_micro": 0.8885245901639345,
|
| 1451 |
+
"eval_precision_weighted": 0.9098325740743773,
|
| 1452 |
+
"eval_recall_macro": 0.885482142857143,
|
| 1453 |
+
"eval_recall_micro": 0.8885245901639345,
|
| 1454 |
+
"eval_recall_weighted": 0.8885245901639345,
|
| 1455 |
+
"eval_runtime": 19.889,
|
| 1456 |
+
"eval_samples_per_second": 61.341,
|
| 1457 |
+
"eval_steps_per_second": 1.006,
|
| 1458 |
+
"step": 1071
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 21.13907284768212,
|
| 1462 |
+
"grad_norm": 4.817611217498779,
|
| 1463 |
+
"learning_rate": 4.357777777777778e-05,
|
| 1464 |
+
"loss": 0.3287,
|
| 1465 |
+
"step": 1078
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 21.278145695364238,
|
| 1469 |
+
"grad_norm": 5.901778697967529,
|
| 1470 |
+
"learning_rate": 4.35e-05,
|
| 1471 |
+
"loss": 0.3539,
|
| 1472 |
+
"step": 1085
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 21.417218543046356,
|
| 1476 |
+
"grad_norm": 6.392418384552002,
|
| 1477 |
+
"learning_rate": 4.3422222222222224e-05,
|
| 1478 |
+
"loss": 0.3926,
|
| 1479 |
+
"step": 1092
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 21.556291390728475,
|
| 1483 |
+
"grad_norm": 14.076611518859863,
|
| 1484 |
+
"learning_rate": 4.334444444444445e-05,
|
| 1485 |
+
"loss": 0.3784,
|
| 1486 |
+
"step": 1099
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 21.695364238410598,
|
| 1490 |
+
"grad_norm": 8.352983474731445,
|
| 1491 |
+
"learning_rate": 4.3266666666666664e-05,
|
| 1492 |
+
"loss": 0.3291,
|
| 1493 |
+
"step": 1106
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 21.834437086092716,
|
| 1497 |
+
"grad_norm": 8.554953575134277,
|
| 1498 |
+
"learning_rate": 4.318888888888889e-05,
|
| 1499 |
+
"loss": 0.3553,
|
| 1500 |
+
"step": 1113
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 21.973509933774835,
|
| 1504 |
+
"grad_norm": 5.422201633453369,
|
| 1505 |
+
"learning_rate": 4.311111111111111e-05,
|
| 1506 |
+
"loss": 0.3301,
|
| 1507 |
+
"step": 1120
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 22.0,
|
| 1511 |
+
"eval_accuracy": 0.8868852459016393,
|
| 1512 |
+
"eval_f1_macro": 0.8844045750001632,
|
| 1513 |
+
"eval_f1_micro": 0.8868852459016393,
|
| 1514 |
+
"eval_f1_weighted": 0.8863481245798025,
|
| 1515 |
+
"eval_loss": 0.43187016248703003,
|
| 1516 |
+
"eval_precision_macro": 0.905546176046176,
|
| 1517 |
+
"eval_precision_micro": 0.8868852459016393,
|
| 1518 |
+
"eval_precision_weighted": 0.9069275010053698,
|
| 1519 |
+
"eval_recall_macro": 0.884922619047619,
|
| 1520 |
+
"eval_recall_micro": 0.8868852459016393,
|
| 1521 |
+
"eval_recall_weighted": 0.8868852459016393,
|
| 1522 |
+
"eval_runtime": 16.9877,
|
| 1523 |
+
"eval_samples_per_second": 71.817,
|
| 1524 |
+
"eval_steps_per_second": 1.177,
|
| 1525 |
+
"step": 1122
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 22.09933774834437,
|
| 1529 |
+
"grad_norm": 4.536903381347656,
|
| 1530 |
+
"learning_rate": 4.3033333333333334e-05,
|
| 1531 |
+
"loss": 0.3081,
|
| 1532 |
+
"step": 1127
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 22.23841059602649,
|
| 1536 |
+
"grad_norm": 5.818119525909424,
|
| 1537 |
+
"learning_rate": 4.295555555555556e-05,
|
| 1538 |
+
"loss": 0.4447,
|
| 1539 |
+
"step": 1134
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 22.37748344370861,
|
| 1543 |
+
"grad_norm": 6.355660438537598,
|
| 1544 |
+
"learning_rate": 4.287777777777778e-05,
|
| 1545 |
+
"loss": 0.2905,
|
| 1546 |
+
"step": 1141
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 22.516556291390728,
|
| 1550 |
+
"grad_norm": 3.7836861610412598,
|
| 1551 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 1552 |
+
"loss": 0.3363,
|
| 1553 |
+
"step": 1148
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 22.655629139072847,
|
| 1557 |
+
"grad_norm": 7.677190780639648,
|
| 1558 |
+
"learning_rate": 4.272222222222223e-05,
|
| 1559 |
+
"loss": 0.335,
|
| 1560 |
+
"step": 1155
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 22.794701986754966,
|
| 1564 |
+
"grad_norm": 9.610170364379883,
|
| 1565 |
+
"learning_rate": 4.264444444444445e-05,
|
| 1566 |
+
"loss": 0.3224,
|
| 1567 |
+
"step": 1162
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 22.933774834437084,
|
| 1571 |
+
"grad_norm": 4.4913458824157715,
|
| 1572 |
+
"learning_rate": 4.2566666666666674e-05,
|
| 1573 |
+
"loss": 0.3594,
|
| 1574 |
+
"step": 1169
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 23.0,
|
| 1578 |
+
"eval_accuracy": 0.8909836065573771,
|
| 1579 |
+
"eval_f1_macro": 0.8853569522153114,
|
| 1580 |
+
"eval_f1_micro": 0.8909836065573771,
|
| 1581 |
+
"eval_f1_weighted": 0.8877271844125241,
|
| 1582 |
+
"eval_loss": 0.415208101272583,
|
| 1583 |
+
"eval_precision_macro": 0.9054862637362637,
|
| 1584 |
+
"eval_precision_micro": 0.8909836065573771,
|
| 1585 |
+
"eval_precision_weighted": 0.9061880492003442,
|
| 1586 |
+
"eval_recall_macro": 0.8882023809523809,
|
| 1587 |
+
"eval_recall_micro": 0.8909836065573771,
|
| 1588 |
+
"eval_recall_weighted": 0.8909836065573771,
|
| 1589 |
+
"eval_runtime": 21.468,
|
| 1590 |
+
"eval_samples_per_second": 56.829,
|
| 1591 |
+
"eval_steps_per_second": 0.932,
|
| 1592 |
+
"step": 1173
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 23.05960264900662,
|
| 1596 |
+
"grad_norm": 6.537961959838867,
|
| 1597 |
+
"learning_rate": 4.248888888888889e-05,
|
| 1598 |
+
"loss": 0.3416,
|
| 1599 |
+
"step": 1176
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 23.198675496688743,
|
| 1603 |
+
"grad_norm": 4.195661544799805,
|
| 1604 |
+
"learning_rate": 4.2411111111111114e-05,
|
| 1605 |
+
"loss": 0.3493,
|
| 1606 |
+
"step": 1183
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 23.337748344370862,
|
| 1610 |
+
"grad_norm": 6.090582370758057,
|
| 1611 |
+
"learning_rate": 4.233333333333334e-05,
|
| 1612 |
+
"loss": 0.2816,
|
| 1613 |
+
"step": 1190
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 23.47682119205298,
|
| 1617 |
+
"grad_norm": 4.269461154937744,
|
| 1618 |
+
"learning_rate": 4.225555555555556e-05,
|
| 1619 |
+
"loss": 0.3461,
|
| 1620 |
+
"step": 1197
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 23.6158940397351,
|
| 1624 |
+
"grad_norm": 5.240416049957275,
|
| 1625 |
+
"learning_rate": 4.217777777777778e-05,
|
| 1626 |
+
"loss": 0.3688,
|
| 1627 |
+
"step": 1204
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 23.75496688741722,
|
| 1631 |
+
"grad_norm": 3.2008297443389893,
|
| 1632 |
+
"learning_rate": 4.21e-05,
|
| 1633 |
+
"loss": 0.2945,
|
| 1634 |
+
"step": 1211
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 23.894039735099337,
|
| 1638 |
+
"grad_norm": 5.42747163772583,
|
| 1639 |
+
"learning_rate": 4.2022222222222223e-05,
|
| 1640 |
+
"loss": 0.365,
|
| 1641 |
+
"step": 1218
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 24.0,
|
| 1645 |
+
"eval_accuracy": 0.8868852459016393,
|
| 1646 |
+
"eval_f1_macro": 0.8826740438354216,
|
| 1647 |
+
"eval_f1_micro": 0.8868852459016393,
|
| 1648 |
+
"eval_f1_weighted": 0.885225590303497,
|
| 1649 |
+
"eval_loss": 0.41284599900245667,
|
| 1650 |
+
"eval_precision_macro": 0.8989790764790766,
|
| 1651 |
+
"eval_precision_micro": 0.8868852459016393,
|
| 1652 |
+
"eval_precision_weighted": 0.90095879757765,
|
| 1653 |
+
"eval_recall_macro": 0.8842916666666667,
|
| 1654 |
+
"eval_recall_micro": 0.8868852459016393,
|
| 1655 |
+
"eval_recall_weighted": 0.8868852459016393,
|
| 1656 |
+
"eval_runtime": 18.0644,
|
| 1657 |
+
"eval_samples_per_second": 67.536,
|
| 1658 |
+
"eval_steps_per_second": 1.107,
|
| 1659 |
+
"step": 1224
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 24.019867549668874,
|
| 1663 |
+
"grad_norm": 4.910553455352783,
|
| 1664 |
+
"learning_rate": 4.194444444444445e-05,
|
| 1665 |
+
"loss": 0.27,
|
| 1666 |
+
"step": 1225
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 24.158940397350992,
|
| 1670 |
+
"grad_norm": 4.917506694793701,
|
| 1671 |
+
"learning_rate": 4.186666666666667e-05,
|
| 1672 |
+
"loss": 0.2662,
|
| 1673 |
+
"step": 1232
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 24.29801324503311,
|
| 1677 |
+
"grad_norm": 6.041675090789795,
|
| 1678 |
+
"learning_rate": 4.178888888888889e-05,
|
| 1679 |
+
"loss": 0.3693,
|
| 1680 |
+
"step": 1239
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 24.437086092715234,
|
| 1684 |
+
"grad_norm": 6.5168776512146,
|
| 1685 |
+
"learning_rate": 4.171111111111111e-05,
|
| 1686 |
+
"loss": 0.2868,
|
| 1687 |
+
"step": 1246
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 24.576158940397352,
|
| 1691 |
+
"grad_norm": 3.36521315574646,
|
| 1692 |
+
"learning_rate": 4.1633333333333333e-05,
|
| 1693 |
+
"loss": 0.4133,
|
| 1694 |
+
"step": 1253
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 24.71523178807947,
|
| 1698 |
+
"grad_norm": 4.277838230133057,
|
| 1699 |
+
"learning_rate": 4.155555555555556e-05,
|
| 1700 |
+
"loss": 0.2291,
|
| 1701 |
+
"step": 1260
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 24.85430463576159,
|
| 1705 |
+
"grad_norm": 5.821409225463867,
|
| 1706 |
+
"learning_rate": 4.147777777777778e-05,
|
| 1707 |
+
"loss": 0.2927,
|
| 1708 |
+
"step": 1267
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 24.99337748344371,
|
| 1712 |
+
"grad_norm": 6.532901763916016,
|
| 1713 |
+
"learning_rate": 4.14e-05,
|
| 1714 |
+
"loss": 0.3711,
|
| 1715 |
+
"step": 1274
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 25.0,
|
| 1719 |
+
"eval_accuracy": 0.8885245901639345,
|
| 1720 |
+
"eval_f1_macro": 0.8860624318491966,
|
| 1721 |
+
"eval_f1_micro": 0.8885245901639345,
|
| 1722 |
+
"eval_f1_weighted": 0.8860652284338398,
|
| 1723 |
+
"eval_loss": 0.3975684940814972,
|
| 1724 |
+
"eval_precision_macro": 0.9022628066378067,
|
| 1725 |
+
"eval_precision_micro": 0.8885245901639345,
|
| 1726 |
+
"eval_precision_weighted": 0.901722671681688,
|
| 1727 |
+
"eval_recall_macro": 0.8880000000000001,
|
| 1728 |
+
"eval_recall_micro": 0.8885245901639345,
|
| 1729 |
+
"eval_recall_weighted": 0.8885245901639345,
|
| 1730 |
+
"eval_runtime": 19.8974,
|
| 1731 |
+
"eval_samples_per_second": 61.315,
|
| 1732 |
+
"eval_steps_per_second": 1.005,
|
| 1733 |
+
"step": 1275
|
| 1734 |
+
}
|
| 1735 |
+
],
|
| 1736 |
+
"logging_steps": 7,
|
| 1737 |
+
"max_steps": 5000,
|
| 1738 |
+
"num_input_tokens_seen": 0,
|
| 1739 |
+
"num_train_epochs": 100,
|
| 1740 |
+
"save_steps": 7,
|
| 1741 |
+
"stateful_callbacks": {
|
| 1742 |
+
"EarlyStoppingCallback": {
|
| 1743 |
+
"args": {
|
| 1744 |
+
"early_stopping_patience": 5,
|
| 1745 |
+
"early_stopping_threshold": 0.01
|
| 1746 |
+
},
|
| 1747 |
+
"attributes": {
|
| 1748 |
+
"early_stopping_patience_counter": 5
|
| 1749 |
+
}
|
| 1750 |
+
},
|
| 1751 |
+
"TrainerControl": {
|
| 1752 |
+
"args": {
|
| 1753 |
+
"should_epoch_stop": false,
|
| 1754 |
+
"should_evaluate": false,
|
| 1755 |
+
"should_log": false,
|
| 1756 |
+
"should_save": true,
|
| 1757 |
+
"should_training_stop": true
|
| 1758 |
+
},
|
| 1759 |
+
"attributes": {}
|
| 1760 |
+
}
|
| 1761 |
+
},
|
| 1762 |
+
"total_flos": 9.44898430624727e+18,
|
| 1763 |
+
"train_batch_size": 32,
|
| 1764 |
+
"trial_name": null,
|
| 1765 |
+
"trial_params": null
|
| 1766 |
+
}
|
checkpoint-1275/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e36d308132a8108aca1f8f9de8ab7c5f8ba3dca8073c7913d5cd428b151f1cc
|
| 3 |
+
size 5368
|