| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 35.73957158962796, | |
| "global_step": 39600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002388, | |
| "loss": 5.1061, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 3.2615509033203125, | |
| "eval_runtime": 209.4571, | |
| "eval_samples_per_second": 18.892, | |
| "eval_steps_per_second": 2.363, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002990989719814553, | |
| "loss": 1.8298, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.5897451639175415, | |
| "eval_runtime": 208.9676, | |
| "eval_samples_per_second": 18.936, | |
| "eval_steps_per_second": 2.369, | |
| "eval_wer": 0.7382658232272045, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002978895383995162, | |
| "loss": 0.7312, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.38931864500045776, | |
| "eval_runtime": 205.7748, | |
| "eval_samples_per_second": 19.23, | |
| "eval_steps_per_second": 2.406, | |
| "eval_wer": 0.5565651976374375, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002966801048175771, | |
| "loss": 0.5859, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.3028641939163208, | |
| "eval_runtime": 210.4962, | |
| "eval_samples_per_second": 18.798, | |
| "eval_steps_per_second": 2.352, | |
| "eval_wer": 0.43102785447174363, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00029547067123563797, | |
| "loss": 0.5272, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.2646712362766266, | |
| "eval_runtime": 208.1951, | |
| "eval_samples_per_second": 19.006, | |
| "eval_steps_per_second": 2.378, | |
| "eval_wer": 0.3874462656834306, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00029426123765369884, | |
| "loss": 0.4691, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.25143691897392273, | |
| "eval_runtime": 208.3951, | |
| "eval_samples_per_second": 18.988, | |
| "eval_steps_per_second": 2.375, | |
| "eval_wer": 0.3728025722573655, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002930518040717597, | |
| "loss": 0.4313, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.23935846984386444, | |
| "eval_runtime": 208.5439, | |
| "eval_samples_per_second": 18.974, | |
| "eval_steps_per_second": 2.374, | |
| "eval_wer": 0.33872715199384895, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002918423704898206, | |
| "loss": 0.4157, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.22154289484024048, | |
| "eval_runtime": 207.5705, | |
| "eval_samples_per_second": 19.063, | |
| "eval_steps_per_second": 2.385, | |
| "eval_wer": 0.3165344423863279, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00029063293690788144, | |
| "loss": 0.382, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_loss": 0.22716625034809113, | |
| "eval_runtime": 208.4179, | |
| "eval_samples_per_second": 18.986, | |
| "eval_steps_per_second": 2.375, | |
| "eval_wer": 0.310103798972495, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.0002894235033259423, | |
| "loss": 0.3636, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 0.21131443977355957, | |
| "eval_runtime": 206.1846, | |
| "eval_samples_per_second": 19.192, | |
| "eval_steps_per_second": 2.401, | |
| "eval_wer": 0.30538566385908505, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.00028821406974400323, | |
| "loss": 0.3665, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.21285590529441833, | |
| "eval_runtime": 205.9986, | |
| "eval_samples_per_second": 19.209, | |
| "eval_steps_per_second": 2.403, | |
| "eval_wer": 0.2907769195820082, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.00028700463616206405, | |
| "loss": 0.333, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_loss": 0.2077477127313614, | |
| "eval_runtime": 208.1768, | |
| "eval_samples_per_second": 19.008, | |
| "eval_steps_per_second": 2.378, | |
| "eval_wer": 0.2788243106280362, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.00028579520258012497, | |
| "loss": 0.3313, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 0.18993255496025085, | |
| "eval_runtime": 205.0681, | |
| "eval_samples_per_second": 19.296, | |
| "eval_steps_per_second": 2.414, | |
| "eval_wer": 0.2659979729493587, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00028458576899818584, | |
| "loss": 0.3222, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 0.19064170122146606, | |
| "eval_runtime": 205.7167, | |
| "eval_samples_per_second": 19.235, | |
| "eval_steps_per_second": 2.406, | |
| "eval_wer": 0.2542201097403278, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.0002833763354162467, | |
| "loss": 0.3003, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.1921728551387787, | |
| "eval_runtime": 204.1327, | |
| "eval_samples_per_second": 19.384, | |
| "eval_steps_per_second": 2.425, | |
| "eval_wer": 0.2612099395379722, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.00028216690183430757, | |
| "loss": 0.3057, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "eval_loss": 0.19207137823104858, | |
| "eval_runtime": 205.293, | |
| "eval_samples_per_second": 19.275, | |
| "eval_steps_per_second": 2.411, | |
| "eval_wer": 0.2560724146367036, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.0002809604918363233, | |
| "loss": 0.297, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_loss": 0.1768147200345993, | |
| "eval_runtime": 204.3464, | |
| "eval_samples_per_second": 19.364, | |
| "eval_steps_per_second": 2.422, | |
| "eval_wer": 0.24146367035962674, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 0.0002797510582543842, | |
| "loss": 0.2834, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 0.18651635944843292, | |
| "eval_runtime": 205.3683, | |
| "eval_samples_per_second": 19.268, | |
| "eval_steps_per_second": 2.41, | |
| "eval_wer": 0.24894278824310628, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 0.00027854162467244505, | |
| "loss": 0.2787, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_loss": 0.18522889912128448, | |
| "eval_runtime": 204.2237, | |
| "eval_samples_per_second": 19.376, | |
| "eval_steps_per_second": 2.424, | |
| "eval_wer": 0.24726522909167162, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 0.0002773321910905059, | |
| "loss": 0.2678, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "eval_loss": 0.1824478805065155, | |
| "eval_runtime": 203.4819, | |
| "eval_samples_per_second": 19.446, | |
| "eval_steps_per_second": 2.433, | |
| "eval_wer": 0.23087407821619543, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.0002761227575085668, | |
| "loss": 0.2665, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_loss": 0.17768050730228424, | |
| "eval_runtime": 203.7918, | |
| "eval_samples_per_second": 19.417, | |
| "eval_steps_per_second": 2.429, | |
| "eval_wer": 0.2309789256631601, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 0.00027491332392662766, | |
| "loss": 0.2722, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_loss": 0.17655304074287415, | |
| "eval_runtime": 203.4054, | |
| "eval_samples_per_second": 19.454, | |
| "eval_steps_per_second": 2.434, | |
| "eval_wer": 0.23216719672875966, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 0.0002737038903446885, | |
| "loss": 0.2549, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "eval_loss": 0.18208913505077362, | |
| "eval_runtime": 203.5406, | |
| "eval_samples_per_second": 19.441, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.23590675567049943, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00027249748034670427, | |
| "loss": 0.2535, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "eval_loss": 0.17272169888019562, | |
| "eval_runtime": 204.5912, | |
| "eval_samples_per_second": 19.341, | |
| "eval_steps_per_second": 2.419, | |
| "eval_wer": 0.22619089225177366, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.00027128804676476514, | |
| "loss": 0.2508, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 0.17887552082538605, | |
| "eval_runtime": 202.6986, | |
| "eval_samples_per_second": 19.522, | |
| "eval_steps_per_second": 2.442, | |
| "eval_wer": 0.22301051969384544, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 0.000270078613182826, | |
| "loss": 0.2354, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "eval_loss": 0.17052198946475983, | |
| "eval_runtime": 202.2989, | |
| "eval_samples_per_second": 19.56, | |
| "eval_steps_per_second": 2.447, | |
| "eval_wer": 0.2227658756509279, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.0002688691796008869, | |
| "loss": 0.2449, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "eval_loss": 0.17250895500183105, | |
| "eval_runtime": 202.4538, | |
| "eval_samples_per_second": 19.545, | |
| "eval_steps_per_second": 2.445, | |
| "eval_wer": 0.2203893335197288, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.0002676597460189478, | |
| "loss": 0.2461, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "eval_loss": 0.18136142194271088, | |
| "eval_runtime": 202.9746, | |
| "eval_samples_per_second": 19.495, | |
| "eval_steps_per_second": 2.439, | |
| "eval_wer": 0.23083912906720722, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 0.0002664533360209635, | |
| "loss": 0.2354, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "eval_loss": 0.17660640180110931, | |
| "eval_runtime": 202.5754, | |
| "eval_samples_per_second": 19.533, | |
| "eval_steps_per_second": 2.444, | |
| "eval_wer": 0.21902631670918812, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 0.00026524390243902435, | |
| "loss": 0.2271, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "eval_loss": 0.16712866723537445, | |
| "eval_runtime": 204.6252, | |
| "eval_samples_per_second": 19.338, | |
| "eval_steps_per_second": 2.419, | |
| "eval_wer": 0.22643553629469124, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.0002640344688570853, | |
| "loss": 0.2262, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "eval_loss": 0.16640537977218628, | |
| "eval_runtime": 205.9457, | |
| "eval_samples_per_second": 19.214, | |
| "eval_steps_per_second": 2.404, | |
| "eval_wer": 0.2237444518225981, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 0.0002628250352751461, | |
| "loss": 0.222, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "eval_loss": 0.16319511830806732, | |
| "eval_runtime": 203.9378, | |
| "eval_samples_per_second": 19.403, | |
| "eval_steps_per_second": 2.427, | |
| "eval_wer": 0.20773774158599237, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 0.000261615601693207, | |
| "loss": 0.2254, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "eval_loss": 0.16412602365016937, | |
| "eval_runtime": 203.9337, | |
| "eval_samples_per_second": 19.403, | |
| "eval_steps_per_second": 2.427, | |
| "eval_wer": 0.21906126585817634, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 0.0002604061681112679, | |
| "loss": 0.2198, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "eval_loss": 0.16197219491004944, | |
| "eval_runtime": 202.2546, | |
| "eval_samples_per_second": 19.564, | |
| "eval_steps_per_second": 2.447, | |
| "eval_wer": 0.2122112326564848, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 0.00025919673452932875, | |
| "loss": 0.2167, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "eval_loss": 0.15757694840431213, | |
| "eval_runtime": 202.2278, | |
| "eval_samples_per_second": 19.567, | |
| "eval_steps_per_second": 2.448, | |
| "eval_wer": 0.2082270296718275, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 0.0002579903245313445, | |
| "loss": 0.2138, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.16401419043540955, | |
| "eval_runtime": 202.7059, | |
| "eval_samples_per_second": 19.521, | |
| "eval_steps_per_second": 2.442, | |
| "eval_wer": 0.2156711984063188, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 0.0002567808909494053, | |
| "loss": 0.2112, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "eval_loss": 0.17054887115955353, | |
| "eval_runtime": 203.4699, | |
| "eval_samples_per_second": 19.448, | |
| "eval_steps_per_second": 2.433, | |
| "eval_wer": 0.21696431691888302, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 0.00025557145736746623, | |
| "loss": 0.2038, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "eval_loss": 0.1620979905128479, | |
| "eval_runtime": 203.3439, | |
| "eval_samples_per_second": 19.46, | |
| "eval_steps_per_second": 2.434, | |
| "eval_wer": 0.2075979449900395, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 0.0002543620237855271, | |
| "loss": 0.2101, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "eval_loss": 0.16726231575012207, | |
| "eval_runtime": 203.5727, | |
| "eval_samples_per_second": 19.438, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.19962953902072483, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 0.00025315259020358797, | |
| "loss": 0.2013, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "eval_loss": 0.16415779292583466, | |
| "eval_runtime": 202.8281, | |
| "eval_samples_per_second": 19.509, | |
| "eval_steps_per_second": 2.44, | |
| "eval_wer": 0.20885611435361548, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 0.00025194315662164883, | |
| "loss": 0.21, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "eval_loss": 0.1616578996181488, | |
| "eval_runtime": 203.1464, | |
| "eval_samples_per_second": 19.479, | |
| "eval_steps_per_second": 2.437, | |
| "eval_wer": 0.2186768252193059, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 0.0002507337230397097, | |
| "loss": 0.2002, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "eval_loss": 0.1627209484577179, | |
| "eval_runtime": 202.7336, | |
| "eval_samples_per_second": 19.518, | |
| "eval_steps_per_second": 2.442, | |
| "eval_wer": 0.21839723202740013, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 0.00024952428945777057, | |
| "loss": 0.2007, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "eval_loss": 0.1601659506559372, | |
| "eval_runtime": 202.199, | |
| "eval_samples_per_second": 19.57, | |
| "eval_steps_per_second": 2.448, | |
| "eval_wer": 0.20924055499248592, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 0.0002483178794597863, | |
| "loss": 0.2042, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "eval_loss": 0.15520912408828735, | |
| "eval_runtime": 202.5397, | |
| "eval_samples_per_second": 19.537, | |
| "eval_steps_per_second": 2.444, | |
| "eval_wer": 0.1952958445461853, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 0.0002471084458778472, | |
| "loss": 0.187, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "eval_loss": 0.16360661387443542, | |
| "eval_runtime": 202.7459, | |
| "eval_samples_per_second": 19.517, | |
| "eval_steps_per_second": 2.441, | |
| "eval_wer": 0.19442211582147975, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 0.00024589901229590805, | |
| "loss": 0.1931, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "eval_loss": 0.1533084213733673, | |
| "eval_runtime": 203.0495, | |
| "eval_samples_per_second": 19.488, | |
| "eval_steps_per_second": 2.438, | |
| "eval_wer": 0.1916960822003984, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "learning_rate": 0.000244689578713969, | |
| "loss": 0.1891, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 16.97, | |
| "eval_loss": 0.16208086907863617, | |
| "eval_runtime": 202.8946, | |
| "eval_samples_per_second": 19.503, | |
| "eval_steps_per_second": 2.44, | |
| "eval_wer": 0.1907175060287282, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 0.00024348014513202981, | |
| "loss": 0.1863, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "eval_loss": 0.15993733704090118, | |
| "eval_runtime": 202.8467, | |
| "eval_samples_per_second": 19.507, | |
| "eval_steps_per_second": 2.44, | |
| "eval_wer": 0.1905777094327753, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 0.00024227071155009068, | |
| "loss": 0.1863, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "eval_loss": 0.15354220569133759, | |
| "eval_runtime": 202.9873, | |
| "eval_samples_per_second": 19.494, | |
| "eval_steps_per_second": 2.439, | |
| "eval_wer": 0.1911718449655751, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 0.00024106127796815155, | |
| "loss": 0.1827, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "eval_loss": 0.1616511195898056, | |
| "eval_runtime": 204.4003, | |
| "eval_samples_per_second": 19.359, | |
| "eval_steps_per_second": 2.422, | |
| "eval_wer": 0.1880264215566351, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 0.00023985184438621244, | |
| "loss": 0.1822, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "eval_loss": 0.1649104207754135, | |
| "eval_runtime": 206.8059, | |
| "eval_samples_per_second": 19.134, | |
| "eval_steps_per_second": 2.394, | |
| "eval_wer": 0.18806137070562332, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "learning_rate": 0.0002386424108042733, | |
| "loss": 0.1841, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "eval_loss": 0.16039612889289856, | |
| "eval_runtime": 204.0742, | |
| "eval_samples_per_second": 19.39, | |
| "eval_steps_per_second": 2.426, | |
| "eval_wer": 0.18942438751616397, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 0.00023743297722233418, | |
| "loss": 0.1817, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "eval_loss": 0.157293900847435, | |
| "eval_runtime": 202.3143, | |
| "eval_samples_per_second": 19.559, | |
| "eval_steps_per_second": 2.447, | |
| "eval_wer": 0.1810715409079789, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 0.00023622959080830475, | |
| "loss": 0.1756, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "eval_loss": 0.16328036785125732, | |
| "eval_runtime": 204.2348, | |
| "eval_samples_per_second": 19.375, | |
| "eval_steps_per_second": 2.424, | |
| "eval_wer": 0.18809631985461153, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 0.00023502015722636564, | |
| "loss": 0.1804, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "eval_loss": 0.1585751324892044, | |
| "eval_runtime": 204.9615, | |
| "eval_samples_per_second": 19.306, | |
| "eval_steps_per_second": 2.415, | |
| "eval_wer": 0.18823611645056443, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 0.0002338107236444265, | |
| "loss": 0.1736, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "eval_loss": 0.15415678918361664, | |
| "eval_runtime": 202.4017, | |
| "eval_samples_per_second": 19.55, | |
| "eval_steps_per_second": 2.446, | |
| "eval_wer": 0.19033306538985775, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 20.58, | |
| "learning_rate": 0.00023260129006248738, | |
| "loss": 0.1704, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 20.58, | |
| "eval_loss": 0.1622617095708847, | |
| "eval_runtime": 206.2682, | |
| "eval_samples_per_second": 19.184, | |
| "eval_steps_per_second": 2.4, | |
| "eval_wer": 0.1983014713591724, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "learning_rate": 0.00023139185648054828, | |
| "loss": 0.1741, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 20.94, | |
| "eval_loss": 0.15422095358371735, | |
| "eval_runtime": 208.5273, | |
| "eval_samples_per_second": 18.976, | |
| "eval_steps_per_second": 2.374, | |
| "eval_wer": 0.19568028518505573, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "learning_rate": 0.00023018242289860912, | |
| "loss": 0.1642, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 21.3, | |
| "eval_loss": 0.155488982796669, | |
| "eval_runtime": 206.3858, | |
| "eval_samples_per_second": 19.173, | |
| "eval_steps_per_second": 2.398, | |
| "eval_wer": 0.19704330199559641, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 0.00022897601290062486, | |
| "loss": 0.1707, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "eval_loss": 0.15275663137435913, | |
| "eval_runtime": 206.6413, | |
| "eval_samples_per_second": 19.149, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 0.18442665921084822, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 0.00022776657931868573, | |
| "loss": 0.1673, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_loss": 0.15888585150241852, | |
| "eval_runtime": 208.9307, | |
| "eval_samples_per_second": 18.939, | |
| "eval_steps_per_second": 2.369, | |
| "eval_wer": 0.1858246251703771, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 0.0002265571457367466, | |
| "loss": 0.1593, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "eval_loss": 0.15319041907787323, | |
| "eval_runtime": 206.6808, | |
| "eval_samples_per_second": 19.145, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 0.17750672771118023, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 22.74, | |
| "learning_rate": 0.0002253477121548075, | |
| "loss": 0.1595, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 22.74, | |
| "eval_loss": 0.15495522320270538, | |
| "eval_runtime": 211.5152, | |
| "eval_samples_per_second": 18.708, | |
| "eval_steps_per_second": 2.34, | |
| "eval_wer": 0.1755495753678398, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "learning_rate": 0.00022413827857286836, | |
| "loss": 0.1598, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 23.1, | |
| "eval_loss": 0.16047397255897522, | |
| "eval_runtime": 213.237, | |
| "eval_samples_per_second": 18.557, | |
| "eval_steps_per_second": 2.321, | |
| "eval_wer": 0.18624401495823575, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 0.00022293186857488405, | |
| "loss": 0.1573, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "eval_loss": 0.15952068567276, | |
| "eval_runtime": 205.0554, | |
| "eval_samples_per_second": 19.297, | |
| "eval_steps_per_second": 2.414, | |
| "eval_wer": 0.17796106664802713, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 0.00022172243499294495, | |
| "loss": 0.1596, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "eval_loss": 0.15038904547691345, | |
| "eval_runtime": 203.7621, | |
| "eval_samples_per_second": 19.42, | |
| "eval_steps_per_second": 2.429, | |
| "eval_wer": 0.17879984622374445, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 0.00022051300141100584, | |
| "loss": 0.1589, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "eval_loss": 0.15989159047603607, | |
| "eval_runtime": 202.8293, | |
| "eval_samples_per_second": 19.509, | |
| "eval_steps_per_second": 2.44, | |
| "eval_wer": 0.17677279558242756, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 0.00021930356782906668, | |
| "loss": 0.1551, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "eval_loss": 0.15309767425060272, | |
| "eval_runtime": 203.5071, | |
| "eval_samples_per_second": 19.444, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.1685946947191836, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 0.00021809413424712758, | |
| "loss": 0.1593, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "eval_loss": 0.1611892282962799, | |
| "eval_runtime": 203.404, | |
| "eval_samples_per_second": 19.454, | |
| "eval_steps_per_second": 2.434, | |
| "eval_wer": 0.181560828993814, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 0.00021688470066518845, | |
| "loss": 0.1519, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "eval_loss": 0.16373491287231445, | |
| "eval_runtime": 203.251, | |
| "eval_samples_per_second": 19.469, | |
| "eval_steps_per_second": 2.435, | |
| "eval_wer": 0.17638835494355712, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 25.63, | |
| "learning_rate": 0.0002156752670832493, | |
| "loss": 0.1509, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 25.63, | |
| "eval_loss": 0.15399527549743652, | |
| "eval_runtime": 203.0998, | |
| "eval_samples_per_second": 19.483, | |
| "eval_steps_per_second": 2.437, | |
| "eval_wer": 0.17093628770139446, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "learning_rate": 0.0002144658335013102, | |
| "loss": 0.1524, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "eval_loss": 0.1519121676683426, | |
| "eval_runtime": 203.5041, | |
| "eval_samples_per_second": 19.444, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.18072204941809666, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 26.35, | |
| "learning_rate": 0.00021325639991937108, | |
| "loss": 0.1452, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 26.35, | |
| "eval_loss": 0.15314562618732452, | |
| "eval_runtime": 203.4098, | |
| "eval_samples_per_second": 19.453, | |
| "eval_steps_per_second": 2.434, | |
| "eval_wer": 0.17310313493866425, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "learning_rate": 0.0002120499899213868, | |
| "loss": 0.1485, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 26.71, | |
| "eval_loss": 0.14827923476696014, | |
| "eval_runtime": 203.2718, | |
| "eval_samples_per_second": 19.467, | |
| "eval_steps_per_second": 2.435, | |
| "eval_wer": 0.16136022087862162, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "learning_rate": 0.0002108405563394477, | |
| "loss": 0.1513, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "eval_loss": 0.15502476692199707, | |
| "eval_runtime": 203.5744, | |
| "eval_samples_per_second": 19.438, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.16579876280012582, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 27.44, | |
| "learning_rate": 0.00020963112275750853, | |
| "loss": 0.1437, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 27.44, | |
| "eval_loss": 0.15631796419620514, | |
| "eval_runtime": 204.0627, | |
| "eval_samples_per_second": 19.391, | |
| "eval_steps_per_second": 2.426, | |
| "eval_wer": 0.16614825429000804, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 0.00020842168917556943, | |
| "loss": 0.1445, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "eval_loss": 0.15840862691402435, | |
| "eval_runtime": 204.5713, | |
| "eval_samples_per_second": 19.343, | |
| "eval_steps_per_second": 2.42, | |
| "eval_wer": 0.17086638940341803, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 0.0002072122555936303, | |
| "loss": 0.1438, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "eval_loss": 0.15680429339408875, | |
| "eval_runtime": 204.0022, | |
| "eval_samples_per_second": 19.397, | |
| "eval_steps_per_second": 2.426, | |
| "eval_wer": 0.1630727291790445, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 0.00020600282201169116, | |
| "loss": 0.1423, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 0.15523846447467804, | |
| "eval_runtime": 203.5692, | |
| "eval_samples_per_second": 19.438, | |
| "eval_steps_per_second": 2.432, | |
| "eval_wer": 0.16090588194177471, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 28.88, | |
| "learning_rate": 0.00020479338842975206, | |
| "loss": 0.1451, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 28.88, | |
| "eval_loss": 0.1542510688304901, | |
| "eval_runtime": 203.7413, | |
| "eval_samples_per_second": 19.422, | |
| "eval_steps_per_second": 2.43, | |
| "eval_wer": 0.16314262747702094, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "learning_rate": 0.00020358395484781292, | |
| "loss": 0.1396, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "eval_loss": 0.15091465413570404, | |
| "eval_runtime": 203.6781, | |
| "eval_samples_per_second": 19.428, | |
| "eval_steps_per_second": 2.43, | |
| "eval_wer": 0.16317757662600915, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 0.0002023745212658738, | |
| "loss": 0.142, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "eval_loss": 0.15581683814525604, | |
| "eval_runtime": 203.4725, | |
| "eval_samples_per_second": 19.447, | |
| "eval_steps_per_second": 2.433, | |
| "eval_wer": 0.1635620172648796, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 29.96, | |
| "learning_rate": 0.0002011650876839347, | |
| "loss": 0.1385, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 29.96, | |
| "eval_loss": 0.145892933011055, | |
| "eval_runtime": 203.8769, | |
| "eval_samples_per_second": 19.409, | |
| "eval_steps_per_second": 2.428, | |
| "eval_wer": 0.17338272813057, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "learning_rate": 0.00019995565410199556, | |
| "loss": 0.1376, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 30.32, | |
| "eval_loss": 0.15049244463443756, | |
| "eval_runtime": 203.9232, | |
| "eval_samples_per_second": 19.404, | |
| "eval_steps_per_second": 2.427, | |
| "eval_wer": 0.17236920280991158, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 0.00019874924410401127, | |
| "loss": 0.1399, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "eval_loss": 0.14067970216274261, | |
| "eval_runtime": 203.8686, | |
| "eval_samples_per_second": 19.41, | |
| "eval_steps_per_second": 2.428, | |
| "eval_wer": 0.1610107293887394, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 31.05, | |
| "learning_rate": 0.00019753981052207217, | |
| "loss": 0.1377, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 31.05, | |
| "eval_loss": 0.1523168534040451, | |
| "eval_runtime": 203.6263, | |
| "eval_samples_per_second": 19.433, | |
| "eval_steps_per_second": 2.431, | |
| "eval_wer": 0.17292838919372314, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 31.41, | |
| "learning_rate": 0.000196330376940133, | |
| "loss": 0.1331, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 31.41, | |
| "eval_loss": 0.14309507608413696, | |
| "eval_runtime": 204.8423, | |
| "eval_samples_per_second": 19.317, | |
| "eval_steps_per_second": 2.416, | |
| "eval_wer": 0.1706566945094887, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 31.77, | |
| "learning_rate": 0.0001951209433581939, | |
| "loss": 0.1356, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 31.77, | |
| "eval_loss": 0.1558520793914795, | |
| "eval_runtime": 204.495, | |
| "eval_samples_per_second": 19.35, | |
| "eval_steps_per_second": 2.421, | |
| "eval_wer": 0.16391150875476182, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 0.00019391150977625477, | |
| "loss": 0.1381, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "eval_loss": 0.14920052886009216, | |
| "eval_runtime": 204.3124, | |
| "eval_samples_per_second": 19.367, | |
| "eval_steps_per_second": 2.423, | |
| "eval_wer": 0.1660783559920316, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "learning_rate": 0.00019270207619431564, | |
| "loss": 0.1332, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "eval_loss": 0.15177668631076813, | |
| "eval_runtime": 204.8291, | |
| "eval_samples_per_second": 19.319, | |
| "eval_steps_per_second": 2.417, | |
| "eval_wer": 0.16139517002760984, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "learning_rate": 0.00019149264261237654, | |
| "loss": 0.1345, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 32.85, | |
| "eval_loss": 0.14764094352722168, | |
| "eval_runtime": 204.5031, | |
| "eval_samples_per_second": 19.349, | |
| "eval_steps_per_second": 2.421, | |
| "eval_wer": 0.1562925942753294, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 33.21, | |
| "learning_rate": 0.00019028320903043738, | |
| "loss": 0.1307, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 33.21, | |
| "eval_loss": 0.1433647871017456, | |
| "eval_runtime": 205.0597, | |
| "eval_samples_per_second": 19.297, | |
| "eval_steps_per_second": 2.414, | |
| "eval_wer": 0.15922832279034005, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 0.00018907679903245312, | |
| "loss": 0.1309, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "eval_loss": 0.1497233361005783, | |
| "eval_runtime": 204.4523, | |
| "eval_samples_per_second": 19.354, | |
| "eval_steps_per_second": 2.421, | |
| "eval_wer": 0.17090133855240625, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 0.00018786736545051402, | |
| "loss": 0.1319, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "eval_loss": 0.15207722783088684, | |
| "eval_runtime": 204.6556, | |
| "eval_samples_per_second": 19.335, | |
| "eval_steps_per_second": 2.419, | |
| "eval_wer": 0.1708314402544298, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 0.00018665793186857486, | |
| "loss": 0.1279, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "eval_loss": 0.14533580839633942, | |
| "eval_runtime": 205.2587, | |
| "eval_samples_per_second": 19.278, | |
| "eval_steps_per_second": 2.412, | |
| "eval_wer": 0.1569566281061056, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "learning_rate": 0.00018544849828663575, | |
| "loss": 0.1268, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "eval_loss": 0.14409175515174866, | |
| "eval_runtime": 204.8962, | |
| "eval_samples_per_second": 19.312, | |
| "eval_steps_per_second": 2.416, | |
| "eval_wer": 0.1608709327927865, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 0.0001842390647046966, | |
| "loss": 0.1301, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_loss": 0.1421143114566803, | |
| "eval_runtime": 205.2147, | |
| "eval_samples_per_second": 19.282, | |
| "eval_steps_per_second": 2.412, | |
| "eval_wer": 0.1567818823611645, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.0001830296311227575, | |
| "loss": 0.1248, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "eval_loss": 0.14348700642585754, | |
| "eval_runtime": 209.2746, | |
| "eval_samples_per_second": 18.908, | |
| "eval_steps_per_second": 2.365, | |
| "eval_wer": 0.15727117044699962, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "learning_rate": 0.00018182322112477323, | |
| "loss": 0.1256, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 35.74, | |
| "eval_loss": 0.14100748300552368, | |
| "eval_runtime": 214.9156, | |
| "eval_samples_per_second": 18.412, | |
| "eval_steps_per_second": 2.303, | |
| "eval_wer": 0.1528326285254954, | |
| "step": 39600 | |
| } | |
| ], | |
| "max_steps": 99720, | |
| "num_train_epochs": 90, | |
| "total_flos": 1.728945548938538e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |