| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007707129094412331, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015414258188824664, | |
| "grad_norm": 0.6734272241592407, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015414258188824664, | |
| "eval_loss": 1.66375732421875, | |
| "eval_runtime": 3.2935, | |
| "eval_samples_per_second": 15.182, | |
| "eval_steps_per_second": 3.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003082851637764933, | |
| "grad_norm": 0.8541533350944519, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3495, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00046242774566473987, | |
| "grad_norm": 0.6524771451950073, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.315, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006165703275529866, | |
| "grad_norm": 0.5823439955711365, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.3871, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007707129094412332, | |
| "grad_norm": 0.49418699741363525, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009248554913294797, | |
| "grad_norm": 0.5664134621620178, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3952, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010789980732177264, | |
| "grad_norm": 0.4901440739631653, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5234, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012331406551059731, | |
| "grad_norm": 0.3769587576389313, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.4229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013872832369942196, | |
| "grad_norm": 0.4188389480113983, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5131, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015414258188824663, | |
| "grad_norm": 0.5015379190444946, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001695568400770713, | |
| "grad_norm": 0.5772421956062317, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.572, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0018497109826589595, | |
| "grad_norm": 0.6743692755699158, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.5605, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002003853564547206, | |
| "grad_norm": 0.2970338761806488, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.4014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002157996146435453, | |
| "grad_norm": 0.2780226469039917, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.155, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0023121387283236996, | |
| "grad_norm": 0.2958413362503052, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.273, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0024662813102119463, | |
| "grad_norm": 0.3193422853946686, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2629, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026204238921001925, | |
| "grad_norm": 0.339270681142807, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3673, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0027745664739884392, | |
| "grad_norm": 0.2887856066226959, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002928709055876686, | |
| "grad_norm": 0.3095043897628784, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.3631, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0030828516377649326, | |
| "grad_norm": 0.32946938276290894, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.4236, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032369942196531793, | |
| "grad_norm": 0.33055737614631653, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003391136801541426, | |
| "grad_norm": 0.3694823384284973, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4547, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0035452793834296723, | |
| "grad_norm": 0.4111591875553131, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5789, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003699421965317919, | |
| "grad_norm": 0.48207613825798035, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0038535645472061657, | |
| "grad_norm": 0.7138695120811462, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.3662, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038535645472061657, | |
| "eval_loss": 1.3446707725524902, | |
| "eval_runtime": 3.2927, | |
| "eval_samples_per_second": 15.185, | |
| "eval_steps_per_second": 3.948, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004007707129094412, | |
| "grad_norm": 0.2780517339706421, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1835, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004161849710982659, | |
| "grad_norm": 0.2748948931694031, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1004, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004315992292870906, | |
| "grad_norm": 0.3136284351348877, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.2712, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004470134874759152, | |
| "grad_norm": 0.2965591847896576, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2592, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004624277456647399, | |
| "grad_norm": 0.3082920014858246, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004778420038535645, | |
| "grad_norm": 0.3298587501049042, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.4209, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0049325626204238925, | |
| "grad_norm": 0.30679869651794434, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3488, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005086705202312139, | |
| "grad_norm": 0.3360414505004883, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.4167, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005240847784200385, | |
| "grad_norm": 0.34086665511131287, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5297, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005394990366088632, | |
| "grad_norm": 0.39216431975364685, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5874, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0055491329479768784, | |
| "grad_norm": 0.4349631667137146, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.6172, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005703275529865126, | |
| "grad_norm": 0.5350357294082642, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.496, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005857418111753372, | |
| "grad_norm": 0.2876313328742981, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.209, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006011560693641618, | |
| "grad_norm": 0.2404983937740326, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.2665, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006165703275529865, | |
| "grad_norm": 0.266658216714859, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0063198458574181115, | |
| "grad_norm": 0.29665255546569824, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2722, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006473988439306359, | |
| "grad_norm": 0.2774446904659271, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.2849, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006628131021194605, | |
| "grad_norm": 0.2746015191078186, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2507, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006782273603082852, | |
| "grad_norm": 0.29231736063957214, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2986, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006936416184971098, | |
| "grad_norm": 0.31806090474128723, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.4726, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0070905587668593445, | |
| "grad_norm": 0.3273776173591614, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.4034, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007244701348747592, | |
| "grad_norm": 0.3434179127216339, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4006, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007398843930635838, | |
| "grad_norm": 0.38592585921287537, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.487, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007552986512524085, | |
| "grad_norm": 0.4318895936012268, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4787, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007707129094412331, | |
| "grad_norm": 0.569764256477356, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4057, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007707129094412331, | |
| "eval_loss": 1.3222453594207764, | |
| "eval_runtime": 3.3045, | |
| "eval_samples_per_second": 15.131, | |
| "eval_steps_per_second": 3.934, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.971813667564421e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |