| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007187350263536177, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011978917105893628, | |
| "grad_norm": 0.5244863033294678, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023957834211787255, | |
| "grad_norm": 0.48653438687324524, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003593675131768088, | |
| "grad_norm": 0.5601047277450562, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004791566842357451, | |
| "grad_norm": 0.44419175386428833, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7164, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005989458552946814, | |
| "grad_norm": 0.4116540849208832, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007187350263536176, | |
| "grad_norm": 0.4420616328716278, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 1.7818, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008385241974125539, | |
| "grad_norm": 0.32181981205940247, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.5868, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009583133684714902, | |
| "grad_norm": 0.42711836099624634, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 1.7927, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010781025395304265, | |
| "grad_norm": 0.38062113523483276, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 1.538, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011978917105893627, | |
| "grad_norm": 0.42514052987098694, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.7095, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001317680881648299, | |
| "grad_norm": 0.46944913268089294, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 1.5404, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0014374700527072352, | |
| "grad_norm": 0.38414081931114197, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 1.4967, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015572592237661715, | |
| "grad_norm": 0.3784991502761841, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 1.6268, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016770483948251077, | |
| "grad_norm": 0.4482596516609192, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 1.7873, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0017968375658840442, | |
| "grad_norm": 0.39585763216018677, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 1.4746, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0019166267369429804, | |
| "grad_norm": 0.3013208508491516, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0020364159080019165, | |
| "grad_norm": 0.3526206612586975, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 1.5365, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002156205079060853, | |
| "grad_norm": 0.3260374069213867, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 1.5285, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002275994250119789, | |
| "grad_norm": 0.3397838771343231, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 1.5258, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0023957834211787254, | |
| "grad_norm": 0.3514011800289154, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.5212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002515572592237662, | |
| "grad_norm": 0.2991046607494354, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 1.4937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002635361763296598, | |
| "grad_norm": 0.40670260787010193, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 1.5486, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0027551509343555344, | |
| "grad_norm": 0.44339653849601746, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 1.7084, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0028749401054144704, | |
| "grad_norm": 0.42197489738464355, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 1.6023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002994729276473407, | |
| "grad_norm": 0.2680957019329071, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 1.5387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003114518447532343, | |
| "grad_norm": 0.3399680554866791, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 1.4657, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0032343076185912794, | |
| "grad_norm": 0.3926292061805725, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4645, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0033540967896502154, | |
| "grad_norm": 0.35624024271965027, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 1.6289, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003473885960709152, | |
| "grad_norm": 0.3598816990852356, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 1.5246, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0035936751317680884, | |
| "grad_norm": 0.32090121507644653, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 1.5073, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037134643028270244, | |
| "grad_norm": 0.41118231415748596, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 1.658, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.003833253473885961, | |
| "grad_norm": 0.3706068694591522, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 1.5052, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003953042644944897, | |
| "grad_norm": 0.29132771492004395, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 1.4859, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004072831816003833, | |
| "grad_norm": 0.4085879921913147, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 1.7738, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004192620987062769, | |
| "grad_norm": 0.2954878509044647, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 1.3454, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004312410158121706, | |
| "grad_norm": 0.38627880811691284, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 1.5715, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004432199329180642, | |
| "grad_norm": 0.3559410274028778, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 1.5292, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004551988500239578, | |
| "grad_norm": 0.367080420255661, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5069, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004671777671298514, | |
| "grad_norm": 0.39985454082489014, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 1.6255, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004791566842357451, | |
| "grad_norm": 0.35325756669044495, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 1.4723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004911356013416387, | |
| "grad_norm": 0.40606868267059326, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 1.5223, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005031145184475324, | |
| "grad_norm": 0.3160095810890198, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 1.5648, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005150934355534259, | |
| "grad_norm": 0.32667338848114014, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 1.4576, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005270723526593196, | |
| "grad_norm": 0.36070936918258667, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 1.4395, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005390512697652132, | |
| "grad_norm": 0.31305474042892456, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 1.465, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005510301868711069, | |
| "grad_norm": 0.3811737298965454, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 1.4937, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005630091039770004, | |
| "grad_norm": 0.37481462955474854, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 1.4718, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005749880210828941, | |
| "grad_norm": 0.35345253348350525, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 1.4519, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005869669381887877, | |
| "grad_norm": 0.377297580242157, | |
| "learning_rate": 4e-05, | |
| "loss": 1.326, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.005989458552946814, | |
| "grad_norm": 0.32999831438064575, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 1.5174, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00610924772400575, | |
| "grad_norm": 0.39304623007774353, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 1.8864, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006229036895064686, | |
| "grad_norm": 0.3829090893268585, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 1.6814, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006348826066123622, | |
| "grad_norm": 0.408879816532135, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 1.5488, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006468615237182559, | |
| "grad_norm": 0.35209059715270996, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 1.5671, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006588404408241495, | |
| "grad_norm": 0.37863975763320923, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.5382, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.006708193579300431, | |
| "grad_norm": 0.3059345483779907, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 1.4568, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.006827982750359367, | |
| "grad_norm": 0.38418012857437134, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 1.5161, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.006947771921418304, | |
| "grad_norm": 0.3427809774875641, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 1.3619, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00706756109247724, | |
| "grad_norm": 0.3328557014465332, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 1.4661, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007187350263536177, | |
| "grad_norm": 0.3424610197544098, | |
| "learning_rate": 0.0, | |
| "loss": 1.3327, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8160664240988160.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |