| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01531745423910546, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "grad_norm": 17.287343978881836, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.7338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006126981695642184, | |
| "eval_loss": 7.338890075683594, | |
| "eval_runtime": 102.2997, | |
| "eval_samples_per_second": 13.441, | |
| "eval_steps_per_second": 6.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012253963391284368, | |
| "grad_norm": 19.69684600830078, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 6.6071, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018380945086926552, | |
| "grad_norm": 15.072196960449219, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4661, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024507926782568737, | |
| "grad_norm": 13.428487777709961, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 4.7479, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030634908478210923, | |
| "grad_norm": 11.567410469055176, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 3.0655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036761890173853105, | |
| "grad_norm": 9.213797569274902, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.3632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004288887186949529, | |
| "grad_norm": 7.1370110511779785, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 2.0916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004901585356513747, | |
| "grad_norm": 6.3253607749938965, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 2.1295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005514283526077966, | |
| "grad_norm": 7.013556957244873, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.4501, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006126981695642185, | |
| "grad_norm": 5.644176483154297, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 1.9675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006739679865206402, | |
| "grad_norm": 5.919342994689941, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.3086, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007352378034770621, | |
| "grad_norm": 5.985039234161377, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.0753, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007965076204334839, | |
| "grad_norm": 4.99806022644043, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 2.3884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008577774373899057, | |
| "grad_norm": 4.707241535186768, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.3303, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009190472543463276, | |
| "grad_norm": 5.004825592041016, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.8894, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009803170713027495, | |
| "grad_norm": 4.547674179077148, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 1.8635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010415868882591713, | |
| "grad_norm": 3.931337833404541, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 1.7631, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011028567052155932, | |
| "grad_norm": 4.3983025550842285, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.5144, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01164126522172015, | |
| "grad_norm": 4.176623821258545, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.6272, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01225396339128437, | |
| "grad_norm": 4.463096618652344, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 1.778, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012866661560848588, | |
| "grad_norm": 3.474909543991089, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1662, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013479359730412805, | |
| "grad_norm": 5.438625812530518, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 2.1278, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014092057899977023, | |
| "grad_norm": 3.6824615001678467, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 1.9374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014704756069541242, | |
| "grad_norm": 3.76320481300354, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.3381, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "grad_norm": 4.320566177368164, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 1.987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01531745423910546, | |
| "eval_loss": 1.7541515827178955, | |
| "eval_runtime": 103.2143, | |
| "eval_samples_per_second": 13.322, | |
| "eval_steps_per_second": 6.666, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9837753453772800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |