| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03250344220481683, | |
| "eval_steps": 8, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036114935783129813, | |
| "eval_loss": 2.6933271884918213, | |
| "eval_runtime": 996.8086, | |
| "eval_samples_per_second": 9.357, | |
| "eval_steps_per_second": 4.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010834480734938942, | |
| "grad_norm": 0.606799304485321, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5701, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021668961469877884, | |
| "grad_norm": 0.6125881671905518, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002889194862650385, | |
| "eval_loss": 2.4693448543548584, | |
| "eval_runtime": 995.3823, | |
| "eval_samples_per_second": 9.37, | |
| "eval_steps_per_second": 4.686, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003250344220481683, | |
| "grad_norm": 0.5005409121513367, | |
| "learning_rate": 9e-05, | |
| "loss": 2.455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004333792293975577, | |
| "grad_norm": 0.5685995817184448, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3321, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005417240367469472, | |
| "grad_norm": 0.3448821008205414, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.2488, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00577838972530077, | |
| "eval_loss": 2.2601964473724365, | |
| "eval_runtime": 995.6768, | |
| "eval_samples_per_second": 9.367, | |
| "eval_steps_per_second": 4.684, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006500688440963366, | |
| "grad_norm": 0.3276103436946869, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2062, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007584136514457261, | |
| "grad_norm": 0.33101603388786316, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 2.2203, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008667584587951154, | |
| "grad_norm": 0.29219868779182434, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 2.1191, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008667584587951154, | |
| "eval_loss": 2.177788496017456, | |
| "eval_runtime": 996.3567, | |
| "eval_samples_per_second": 9.361, | |
| "eval_steps_per_second": 4.681, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00975103266144505, | |
| "grad_norm": 0.2517762780189514, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1499, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010834480734938944, | |
| "grad_norm": 0.3143475651741028, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 2.1606, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01155677945060154, | |
| "eval_loss": 2.130772590637207, | |
| "eval_runtime": 996.0058, | |
| "eval_samples_per_second": 9.364, | |
| "eval_steps_per_second": 4.683, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011917928808432838, | |
| "grad_norm": 0.28296035528182983, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 2.0661, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013001376881926732, | |
| "grad_norm": 0.293642520904541, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 2.1699, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014084824955420626, | |
| "grad_norm": 0.27195706963539124, | |
| "learning_rate": 0.00016579387259397127, | |
| "loss": 2.0588, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014445974313251925, | |
| "eval_loss": 2.096694231033325, | |
| "eval_runtime": 995.8729, | |
| "eval_samples_per_second": 9.366, | |
| "eval_steps_per_second": 4.683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015168273028914521, | |
| "grad_norm": 0.2799226641654968, | |
| "learning_rate": 0.00015508969814521025, | |
| "loss": 2.0406, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016251721102408415, | |
| "grad_norm": 0.29726603627204895, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 2.1195, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017335169175902308, | |
| "grad_norm": 0.278397798538208, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0464, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017335169175902308, | |
| "eval_loss": 2.0712993144989014, | |
| "eval_runtime": 996.1713, | |
| "eval_samples_per_second": 9.363, | |
| "eval_steps_per_second": 4.682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018418617249396203, | |
| "grad_norm": 0.2522198557853699, | |
| "learning_rate": 0.00011785568947986367, | |
| "loss": 2.0516, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0195020653228901, | |
| "grad_norm": 0.2991744875907898, | |
| "learning_rate": 0.00010448648303505151, | |
| "loss": 2.0324, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020224364038552694, | |
| "eval_loss": 2.0532875061035156, | |
| "eval_runtime": 996.415, | |
| "eval_samples_per_second": 9.361, | |
| "eval_steps_per_second": 4.681, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02058551339638399, | |
| "grad_norm": 0.27935004234313965, | |
| "learning_rate": 9.103606910965666e-05, | |
| "loss": 2.0368, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.021668961469877887, | |
| "grad_norm": 0.29219961166381836, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 2.0315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02275240954337178, | |
| "grad_norm": 0.2893526554107666, | |
| "learning_rate": 6.486251759186572e-05, | |
| "loss": 2.0128, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02311355890120308, | |
| "eval_loss": 2.0402984619140625, | |
| "eval_runtime": 995.4422, | |
| "eval_samples_per_second": 9.37, | |
| "eval_steps_per_second": 4.685, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.023835857616865675, | |
| "grad_norm": 0.3017539978027344, | |
| "learning_rate": 5.261313375270014e-05, | |
| "loss": 2.0256, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02491930569035957, | |
| "grad_norm": 0.31945106387138367, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.0501, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.026002753763853463, | |
| "grad_norm": 0.2786339819431305, | |
| "learning_rate": 3.089373510131354e-05, | |
| "loss": 2.064, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.026002753763853463, | |
| "eval_loss": 2.03191876411438, | |
| "eval_runtime": 996.4736, | |
| "eval_samples_per_second": 9.36, | |
| "eval_steps_per_second": 4.681, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02708620183734736, | |
| "grad_norm": 0.2601235508918762, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 2.0599, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02816964991084125, | |
| "grad_norm": 0.2593807578086853, | |
| "learning_rate": 1.415512063981339e-05, | |
| "loss": 2.0068, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02889194862650385, | |
| "eval_loss": 2.0276479721069336, | |
| "eval_runtime": 997.0668, | |
| "eval_samples_per_second": 9.354, | |
| "eval_steps_per_second": 4.678, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.029253097984335147, | |
| "grad_norm": 0.27310940623283386, | |
| "learning_rate": 8.047222744854943e-06, | |
| "loss": 1.9976, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030336546057829043, | |
| "grad_norm": 0.2755163013935089, | |
| "learning_rate": 3.6037139304146762e-06, | |
| "loss": 2.0511, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03141999413132294, | |
| "grad_norm": 0.28938886523246765, | |
| "learning_rate": 9.0502382320653e-07, | |
| "loss": 2.0863, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.031781143489154236, | |
| "eval_loss": 2.0262272357940674, | |
| "eval_runtime": 996.6015, | |
| "eval_samples_per_second": 9.359, | |
| "eval_steps_per_second": 4.68, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.03250344220481683, | |
| "grad_norm": 0.26352646946907043, | |
| "learning_rate": 0.0, | |
| "loss": 1.9889, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.788172886114304e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |