| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016586921850079744, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 0.2786005139350891, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8579, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 0.9026059508323669, | |
| "eval_runtime": 91.1092, | |
| "eval_samples_per_second": 10.866, | |
| "eval_steps_per_second": 5.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": 0.2709323465824127, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8977, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 0.2819572687149048, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.7939, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": 0.29136133193969727, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9395, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 0.26331567764282227, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9607, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 0.2830480933189392, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8113, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": 0.26591408252716064, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.8025, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": 0.26501235365867615, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7995, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 0.3157069683074951, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.8294, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 0.2955096960067749, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 0.34986257553100586, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.9643, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 0.323536217212677, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.8256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005528973950026581, | |
| "grad_norm": 0.3692857623100281, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.8779, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005528973950026581, | |
| "eval_loss": 0.8817930221557617, | |
| "eval_runtime": 89.8917, | |
| "eval_samples_per_second": 11.013, | |
| "eval_steps_per_second": 5.507, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005954279638490165, | |
| "grad_norm": 0.4119487404823303, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.9006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 0.3977135419845581, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.9069, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "grad_norm": 0.45003339648246765, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.9576, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007230196703880914, | |
| "grad_norm": 0.40881747007369995, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.7697, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 0.5239385962486267, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.8861, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00808080808080808, | |
| "grad_norm": 0.4427054822444916, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.8403, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": 0.4336467683315277, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.8088, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 0.46326103806495667, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.7963, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 0.4596688449382782, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.7968, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009782030834662414, | |
| "grad_norm": 0.4667969346046448, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.8305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 0.3937626779079437, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.7507, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 0.41750970482826233, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.785, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011057947900053162, | |
| "grad_norm": 0.415423721075058, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.8375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011057947900053162, | |
| "eval_loss": 0.7622473239898682, | |
| "eval_runtime": 89.8141, | |
| "eval_samples_per_second": 11.023, | |
| "eval_steps_per_second": 5.511, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011483253588516746, | |
| "grad_norm": 0.3313671350479126, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.7642, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01190855927698033, | |
| "grad_norm": 0.37808409333229065, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.7655, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012333864965443912, | |
| "grad_norm": 0.3844619691371918, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.8025, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 0.37186184525489807, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.8364, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01318447634237108, | |
| "grad_norm": 0.310320645570755, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.6388, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013609782030834662, | |
| "grad_norm": 0.3105718493461609, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.7279, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 0.3364258110523224, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.7568, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014460393407761828, | |
| "grad_norm": 0.34743359684944153, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.7706, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014885699096225412, | |
| "grad_norm": 0.29443031549453735, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.7154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015311004784688996, | |
| "grad_norm": 0.3357723653316498, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.752, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01573631047315258, | |
| "grad_norm": 0.2919500470161438, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.7965, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01616161616161616, | |
| "grad_norm": 0.27403074502944946, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.7265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016586921850079744, | |
| "grad_norm": 0.27928847074508667, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.6562, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016586921850079744, | |
| "eval_loss": 0.7195438146591187, | |
| "eval_runtime": 90.1408, | |
| "eval_samples_per_second": 10.983, | |
| "eval_steps_per_second": 5.491, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.366738559664128e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |