| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007142857142857143, | |
| "grad_norm": 106.10796356201172, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 27.4831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 46.88632583618164, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 26.3105, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 16.438461303710938, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 20.4923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 9.703349113464355, | |
| "learning_rate": 0.00019996891820008164, | |
| "loss": 16.0475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 3.3252718448638916, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 13.4483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 3.251009941101074, | |
| "learning_rate": 0.0001962624246950012, | |
| "loss": 12.6172, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 5.38721227645874, | |
| "learning_rate": 0.00019214762118704076, | |
| "loss": 11.9827, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 10.532784461975098, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 11.0145, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 14.15513801574707, | |
| "learning_rate": 0.00017971325072229226, | |
| "loss": 9.3353, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 21.529788970947266, | |
| "learning_rate": 0.00017158668492597186, | |
| "loss": 7.229, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 15.934834480285645, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 4.7381, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 5.8390045166015625, | |
| "learning_rate": 0.0001521435203379498, | |
| "loss": 2.8963, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 4.718578815460205, | |
| "learning_rate": 0.00014112871031306119, | |
| "loss": 2.4009, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 3.6623828411102295, | |
| "learning_rate": 0.00012947551744109043, | |
| "loss": 2.1721, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.086202383041382, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.0155, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 1.1254757642745972, | |
| "learning_rate": 0.00010498458856606972, | |
| "loss": 1.9116, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.9386184215545654, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 1.8129, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 1.5302088260650635, | |
| "learning_rate": 8.018538568006027e-05, | |
| "loss": 1.7831, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 1.059885859489441, | |
| "learning_rate": 6.815133497483157e-05, | |
| "loss": 1.7466, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 1.2457741498947144, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 1.7392, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.7660045623779297, | |
| "learning_rate": 4.574537361342407e-05, | |
| "loss": 1.6987, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.7355481386184692, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.6811, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.7224046587944031, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 1.7008, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 0.7918136715888977, | |
| "learning_rate": 1.880619942841435e-05, | |
| "loss": 1.6759, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.5361932516098022, | |
| "learning_rate": 1.2177842662977135e-05, | |
| "loss": 1.6748, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 1.0850142240524292, | |
| "learning_rate": 6.9126251355795864e-06, | |
| "loss": 1.6777, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.7962830662727356, | |
| "learning_rate": 3.092271377092215e-06, | |
| "loss": 1.6705, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 0.7234132885932922, | |
| "learning_rate": 7.760793399827937e-07, | |
| "loss": 1.6417, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7538830637931824, | |
| "learning_rate": 0.0, | |
| "loss": 1.6542, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6615785360336304, | |
| "eval_runtime": 3.8187, | |
| "eval_samples_per_second": 46.613, | |
| "eval_steps_per_second": 0.786, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 140, | |
| "total_flos": 4.268849030789857e+17, | |
| "train_loss": 5.964417205538068, | |
| "train_runtime": 1743.5737, | |
| "train_samples_per_second": 10.269, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.268849030789857e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |