{"train/decoder_grad_norm": 0.18293321132659912, "train/decoder_param_norm": 1063.0654296875, "train/encoder_grad_norm": 0.148331880569458, "train/encoder_param_norm": 2323.336669921875, "train/grad_norm": 0.23551413416862488, "layer_grad_norm/": {"decoder": {"model": {"decoder": {"embed_positions": {"embedding": 0.008046639151871204}, "embed_tokens": {"embedding": 0.060666970908641815}, "layernorm_embedding": {"bias": 0.003096886444836855, "scale": 0.0024350089952349663}, "layers": {"FlaxBartDecoderLayers": {"encoder_attn": {"k_proj": {"bias": 5.256703389022732e-06, "kernel": 0.011271456256508827}, "out_proj": {"bias": 0.007880721241235733, "kernel": 0.03872065246105194}, "q_proj": {"bias": 0.0004976371419616044, "kernel": 0.01105893962085247}, "v_proj": {"bias": 0.015226359479129314, "kernel": 0.030586158856749535}}, "encoder_attn_layer_norm": {"bias": 0.01159473042935133, "scale": 0.012393548153340816}, "fc1": {"bias": 0.004439335782080889, "kernel": 0.10113218426704407}, "fc2": {"bias": 0.011387723498046398, "kernel": 0.09879624843597412}, "final_layer_norm": {"bias": 0.026725012809038162, "scale": 0.026244478300213814}, "self_attn": {"k_proj": {"bias": 1.8891130366682773e-06, "kernel": 0.010783703066408634}, "out_proj": {"bias": 0.016153542324900627, "kernel": 0.039619628340005875}, "q_proj": {"bias": 0.0008692306582815945, "kernel": 0.01054653525352478}, "v_proj": {"bias": 0.01716933213174343, "kernel": 0.04919762164354324}}, "self_attn_layer_norm": {"bias": 0.007215098012238741, "scale": 0.008393414318561554}}}}}}, "encoder": {"adapter": {"layers": {"0": {"conv": {"bias": 0.022141050547361374, "kernel": 0.049536462873220444}}, "1": {"conv": {"bias": 0.017486272379755974, "kernel": 0.03386249393224716}}, "2": {"conv": {"bias": 0.020221581682562828, "kernel": 0.05212334543466568}}}}, "encoder": {"layer_norm": {"bias": 0.07752241939306259, "scale": 0.03339512273669243}, "layers": {"FlaxWav2Vec2EncoderLayers": {"attention": {"k_proj": {"bias": 1.787670839803468e-06, "kernel": 0.016130739822983742}, "out_proj": {"bias": 0.001517767203040421, "kernel": 0.0303343553096056}, "q_proj": {"bias": 0.002082030288875103, "kernel": 0.01582256518304348}, "v_proj": {"bias": 0.00666964752599597, "kernel": 0.027823949232697487}}, "feed_forward": {"intermediate_dense": {"bias": 0.002947209170088172, "kernel": 0.03786110132932663}, "output_dense": {"bias": 0.0014471356989815831, "kernel": 0.03480111435055733}}, "final_layer_norm": {"bias": 0.014765393920242786, "scale": 0.01634989120066166}, "layer_norm": {"bias": 0.03281298279762268, "scale": 0.024696579203009605}}}, "pos_conv_embed": {"conv": {"bias": 0.0003536914009600878, "weight_g": 0.0017076540971174836, "weight_v": 0.0059150331653654575}}}, "feature_extractor": {"conv_layers": {"0": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "1": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "2": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "3": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "4": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "5": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}, "6": {"conv": {"bias": 0.0, "kernel": 0.0}, "layer_norm": {"bias": 0.0, "scale": 0.0}}}}, "feature_projection": {"layer_norm": {"bias": 0.00199363986030221, "scale": 0.0019663891289383173}, "projection": {"bias": 0.000548368610907346, "kernel": 0.015020000748336315}}, "masked_spec_embed": 0.0}}, "layer_param_norm/": {"decoder": {"model": {"decoder": {"embed_positions": {"embedding": 58.655296325683594}, "embed_tokens": {"embedding": 628.4320678710938}, "layernorm_embedding": {"bias": 2.423579692840576, "scale": 13.864307403564453}, "layers": {"FlaxBartDecoderLayers": {"encoder_attn": {"k_proj": {"bias": 47.95212173461914, "kernel": 331.52020263671875}, "out_proj": {"bias": 6.132379531860352, "kernel": 227.88941955566406}, "q_proj": {"bias": 20.880966186523438, "kernel": 338.4452819824219}, "v_proj": {"bias": 3.570829391479492, "kernel": 232.0838623046875}}, "encoder_attn_layer_norm": {"bias": 11.024534225463867, "scale": 57.68368148803711}, "fc1": {"bias": 26.054283142089844, "kernel": 346.79296875}, "fc2": {"bias": 7.841187953948975, "kernel": 248.94561767578125}, "final_layer_norm": {"bias": 3.914222002029419, "scale": 63.57343673706055}, "self_attn": {"k_proj": {"bias": 59.552547454833984, "kernel": 280.0233459472656}, "out_proj": {"bias": 3.7681872844696045, "kernel": 132.86544799804688}, "q_proj": {"bias": 32.200714111328125, "kernel": 283.1105651855469}, "v_proj": {"bias": 2.561887741088867, "kernel": 141.2297821044922}}, "self_attn_layer_norm": {"bias": 8.89633846282959, "scale": 84.71704864501953}}}}}}, "encoder": {"adapter": {"layers": {"0": {"conv": {"bias": 1.1991273164749146, "kernel": 62.47041320800781}}, "1": {"conv": {"bias": 1.3806315660476685, "kernel": 60.54581069946289}}, "2": {"conv": {"bias": 1.5864932537078857, "kernel": 60.361602783203125}}}}, "encoder": {"layer_norm": {"bias": 0.2923617959022522, "scale": 4.219600677490234}, "layers": {"FlaxWav2Vec2EncoderLayers": {"attention": {"k_proj": {"bias": 19.385311126708984, "kernel": 553.5303955078125}, "out_proj": {"bias": 16.84536361694336, "kernel": 705.300537109375}, "q_proj": {"bias": 40.93048858642578, "kernel": 546.0474243164062}, "v_proj": {"bias": 15.559945106506348, "kernel": 696.8070068359375}}, "feed_forward": {"intermediate_dense": {"bias": 24.44249725341797, "kernel": 1377.5845947265625}, "output_dense": {"bias": 20.795345306396484, "kernel": 1303.997314453125}}, "final_layer_norm": {"bias": 32.52366256713867, "scale": 142.01145935058594}, "layer_norm": {"bias": 7.272017478942871, "scale": 45.770084381103516}}}, "pos_conv_embed": {"conv": {"bias": 15.211658477783203, "weight_g": 21.0489501953125, "weight_v": 214.11346435546875}}}, "feature_extractor": {"conv_layers": {"0": {"conv": {"bias": 0.5982058644294739, "kernel": 8.08896541595459}, "layer_norm": {"bias": 10.069783210754395, "scale": 10.451257705688477}}, "1": {"conv": {"bias": 4.74075174331665, "kernel": 90.8435287475586}, "layer_norm": {"bias": 6.922820091247559, "scale": 19.5467586517334}}, "2": {"conv": {"bias": 6.7732415199279785, "kernel": 146.13897705078125}, "layer_norm": {"bias": 9.044225692749023, "scale": 19.424888610839844}}, "3": {"conv": {"bias": 5.224758148193359, "kernel": 159.10508728027344}, "layer_norm": {"bias": 8.319666862487793, "scale": 17.64743423461914}}, "4": {"conv": {"bias": 4.434978008270264, "kernel": 157.35813903808594}, "layer_norm": {"bias": 9.193974494934082, "scale": 15.562357902526855}}, "5": {"conv": {"bias": 5.297643661499023, "kernel": 131.1835174560547}, "layer_norm": {"bias": 10.735219955444336, "scale": 13.812533378601074}}, "6": {"conv": {"bias": 5.615579128265381, "kernel": 136.41822814941406}, "layer_norm": {"bias": 12.515308380126953, "scale": 11.152680397033691}}}}, "feature_projection": {"layer_norm": {"bias": 9.234997749328613, "scale": 27.593135833740234}, "projection": {"bias": 4.323590278625488, "kernel": 88.11954498291016}}, "masked_spec_embed": 26.247730255126953}}, "train/learning_rate": 2.0254545233910903e-05, "train/loss": 0.008378183469176292, "train/param_norm": 2554.995361328125, "_timestamp": 1661871981, "_runtime": 195214, "_step": 39975, "eval/loss": 0.9876799583435059, "eval/wer": 0.04759016212639241, "eval/cer": 0.035079873533571844, "eval/step_10k": {"_type": "table-file", "sha256": "8b44e8a00a036a18ffdf81b4d076c8bf849ea6649001c69e94fa439b14f110ee", "size": 26434, "artifact_path": "wandb-client-artifact://18m0dj4hts3yiat04x5pvmncavkjapd5wb8bznb37vw8c0lqna3m2yjd1wtdrfstuoo7ejt2sphvjo0zuw1e5ne5d3qbkd7c1fylclfggig6us5tsmsj2uum5pchx48n:latest/eval/step_10k.table.json", "_latest_artifact_path": "wandb-client-artifact://18m0dj4hts3yiat04x5pvmncavkjapd5wb8bznb37vw8c0lqna3m2yjd1wtdrfstuoo7ejt2sphvjo0zuw1e5ne5d3qbkd7c1fylclfggig6us5tsmsj2uum5pchx48n:latest/eval/step_10k.table.json", "path": "media/table/eval/step_10k_10000_8b44e8a00a036a18ffdf.table.json", "ncols": 7, "nrows": 50}, "eval/step_20k": {"_type": "table-file", "sha256": "a0a50c5d8793ca99e4646f70c3624f8742c5285825bc1c59ab4083ac4de9d6e3", "size": 26657, "artifact_path": "wandb-client-artifact://13ri9hnxp93kf7dsdol2hs1j0v7bpkwwvujpi27awdck0fjm6vfog0dun9k9toif5xrt3cijlotddakikiw0bnbo3go679b4d2spq9c0w865vq0k9auiszkkbvev62fc:latest/eval/step_20k.table.json", "_latest_artifact_path": "wandb-client-artifact://13ri9hnxp93kf7dsdol2hs1j0v7bpkwwvujpi27awdck0fjm6vfog0dun9k9toif5xrt3cijlotddakikiw0bnbo3go679b4d2spq9c0w865vq0k9auiszkkbvev62fc:latest/eval/step_20k.table.json", "path": "media/table/eval/step_20k_20000_a0a50c5d8793ca99e464.table.json", "ncols": 7, "nrows": 50}, "eval/step_30k": {"_type": "table-file", "sha256": "509ad8614e16ae2800f100e82fd40356d3559e0425cf50e8e19c3155dc6c604e", "size": 26610, "artifact_path": "wandb-client-artifact://1v7mr89p2ldfoyyvrj6x6g0s8qpvgnioclm4puk5i0wphipeujkyna0xf7y63nt4a5qivkdzytt4lzhwuraoe53a5683ln1yzntyw9kh7vhcxz7oci70rpw62o1tz6ho:latest/eval/step_30k.table.json", "_latest_artifact_path": "wandb-client-artifact://1v7mr89p2ldfoyyvrj6x6g0s8qpvgnioclm4puk5i0wphipeujkyna0xf7y63nt4a5qivkdzytt4lzhwuraoe53a5683ln1yzntyw9kh7vhcxz7oci70rpw62o1tz6ho:latest/eval/step_30k.table.json", "path": "media/table/eval/step_30k_30000_509ad8614e16ae2800f1.table.json", "ncols": 7, "nrows": 50}}