| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 230, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.043478260869565216, |
| "grad_norm": 2.125, |
| "learning_rate": 1.9768115942028986e-05, |
| "loss": 1.4752726554870605, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08695652173913043, |
| "grad_norm": 1.859375, |
| "learning_rate": 1.947826086956522e-05, |
| "loss": 1.246222686767578, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13043478260869565, |
| "grad_norm": 1.6875, |
| "learning_rate": 1.918840579710145e-05, |
| "loss": 1.1879362106323241, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.17391304347826086, |
| "grad_norm": 1.6171875, |
| "learning_rate": 1.8898550724637685e-05, |
| "loss": 1.1490286827087401, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 1.703125, |
| "learning_rate": 1.8608695652173912e-05, |
| "loss": 1.2483633041381836, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 1.640625, |
| "learning_rate": 1.8318840579710146e-05, |
| "loss": 1.2286408424377442, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30434782608695654, |
| "grad_norm": 1.78125, |
| "learning_rate": 1.802898550724638e-05, |
| "loss": 1.1528528213500977, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.34782608695652173, |
| "grad_norm": 1.5703125, |
| "learning_rate": 1.773913043478261e-05, |
| "loss": 1.1953392028808594, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.391304347826087, |
| "grad_norm": 1.5703125, |
| "learning_rate": 1.7449275362318842e-05, |
| "loss": 1.2230706214904785, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 1.6953125, |
| "learning_rate": 1.7159420289855073e-05, |
| "loss": 1.1725500106811524, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4782608695652174, |
| "grad_norm": 1.625, |
| "learning_rate": 1.6869565217391307e-05, |
| "loss": 1.1918975830078125, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 1.6171875, |
| "learning_rate": 1.6579710144927538e-05, |
| "loss": 1.1676328659057618, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5652173913043478, |
| "grad_norm": 1.515625, |
| "learning_rate": 1.628985507246377e-05, |
| "loss": 1.1679247856140136, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.6086956521739131, |
| "grad_norm": 1.53125, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.0870880126953124, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 1.6171875, |
| "learning_rate": 1.5710144927536233e-05, |
| "loss": 1.1582844734191895, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6956521739130435, |
| "grad_norm": 1.65625, |
| "learning_rate": 1.5420289855072464e-05, |
| "loss": 1.1640958786010742, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7391304347826086, |
| "grad_norm": 1.6484375, |
| "learning_rate": 1.5130434782608697e-05, |
| "loss": 1.1900686264038085, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 1.6796875, |
| "learning_rate": 1.484057971014493e-05, |
| "loss": 1.1477184295654297, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8260869565217391, |
| "grad_norm": 1.703125, |
| "learning_rate": 1.455072463768116e-05, |
| "loss": 1.1650050163269043, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 1.8046875, |
| "learning_rate": 1.4260869565217392e-05, |
| "loss": 1.1436158180236817, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9130434782608695, |
| "grad_norm": 1.7734375, |
| "learning_rate": 1.3971014492753625e-05, |
| "loss": 1.1357536315917969, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "grad_norm": 1.6015625, |
| "learning_rate": 1.3681159420289856e-05, |
| "loss": 1.0976995468139648, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.5546875, |
| "learning_rate": 1.3391304347826088e-05, |
| "loss": 1.116806697845459, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.0434782608695652, |
| "grad_norm": 1.6875, |
| "learning_rate": 1.3101449275362319e-05, |
| "loss": 1.0336241722106934, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0869565217391304, |
| "grad_norm": 1.484375, |
| "learning_rate": 1.2811594202898551e-05, |
| "loss": 0.9886100769042969, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.1304347826086956, |
| "grad_norm": 1.7578125, |
| "learning_rate": 1.2521739130434784e-05, |
| "loss": 1.0494616508483887, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.1739130434782608, |
| "grad_norm": 1.8046875, |
| "learning_rate": 1.2231884057971015e-05, |
| "loss": 1.0672290802001954, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.2173913043478262, |
| "grad_norm": 1.71875, |
| "learning_rate": 1.1942028985507247e-05, |
| "loss": 0.9973515510559082, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.2608695652173914, |
| "grad_norm": 1.8046875, |
| "learning_rate": 1.1652173913043478e-05, |
| "loss": 0.9700364112854004, |
| "step": 145 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 1.609375, |
| "learning_rate": 1.1362318840579712e-05, |
| "loss": 1.0071863174438476, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.3478260869565217, |
| "grad_norm": 1.75, |
| "learning_rate": 1.1072463768115941e-05, |
| "loss": 1.0539615631103516, |
| "step": 155 |
| }, |
| { |
| "epoch": 1.391304347826087, |
| "grad_norm": 1.796875, |
| "learning_rate": 1.0782608695652175e-05, |
| "loss": 0.9773560523986816, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.434782608695652, |
| "grad_norm": 1.7109375, |
| "learning_rate": 1.0492753623188408e-05, |
| "loss": 1.0021091461181642, |
| "step": 165 |
| }, |
| { |
| "epoch": 1.4782608695652173, |
| "grad_norm": 1.765625, |
| "learning_rate": 1.0202898550724639e-05, |
| "loss": 1.007963275909424, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.5217391304347827, |
| "grad_norm": 1.59375, |
| "learning_rate": 9.913043478260871e-06, |
| "loss": 0.9554825782775879, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.5652173913043477, |
| "grad_norm": 1.7890625, |
| "learning_rate": 9.623188405797102e-06, |
| "loss": 0.9842275619506836, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.608695652173913, |
| "grad_norm": 1.65625, |
| "learning_rate": 9.333333333333334e-06, |
| "loss": 0.9370105743408204, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.6521739130434783, |
| "grad_norm": 1.6875, |
| "learning_rate": 9.043478260869565e-06, |
| "loss": 1.0002208709716798, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.6956521739130435, |
| "grad_norm": 1.7109375, |
| "learning_rate": 8.753623188405798e-06, |
| "loss": 0.949674415588379, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 1.6171875, |
| "learning_rate": 8.46376811594203e-06, |
| "loss": 0.9775739669799804, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.7826086956521738, |
| "grad_norm": 1.8671875, |
| "learning_rate": 8.173913043478263e-06, |
| "loss": 0.9460740089416504, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.8260869565217392, |
| "grad_norm": 1.6171875, |
| "learning_rate": 7.884057971014493e-06, |
| "loss": 0.9785075187683105, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.8695652173913042, |
| "grad_norm": 1.7734375, |
| "learning_rate": 7.594202898550726e-06, |
| "loss": 0.9877285957336426, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.9130434782608696, |
| "grad_norm": 1.6171875, |
| "learning_rate": 7.304347826086957e-06, |
| "loss": 0.9701601028442383, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.9565217391304348, |
| "grad_norm": 1.78125, |
| "learning_rate": 7.014492753623189e-06, |
| "loss": 0.9813606262207031, |
| "step": 225 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.71875, |
| "learning_rate": 6.724637681159421e-06, |
| "loss": 0.9989594459533692, |
| "step": 230 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 345, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.163217090052096e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
