| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 144, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.070298769771529, |
| "grad_norm": 0.041015625, |
| "learning_rate": 4.972222222222223e-05, |
| "loss": 0.6872987270355224, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.140597539543058, |
| "grad_norm": 0.036376953125, |
| "learning_rate": 4.937500000000001e-05, |
| "loss": 0.6830456733703614, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.210896309314587, |
| "grad_norm": 0.038330078125, |
| "learning_rate": 4.902777777777778e-05, |
| "loss": 0.7479233264923095, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.281195079086116, |
| "grad_norm": 0.0380859375, |
| "learning_rate": 4.8680555555555554e-05, |
| "loss": 0.7160741329193115, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.351493848857645, |
| "grad_norm": 0.03955078125, |
| "learning_rate": 4.8333333333333334e-05, |
| "loss": 0.6858582973480225, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.421792618629174, |
| "grad_norm": 0.038818359375, |
| "learning_rate": 4.7986111111111113e-05, |
| "loss": 0.6775042533874511, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.492091388400703, |
| "grad_norm": 0.03271484375, |
| "learning_rate": 4.7638888888888887e-05, |
| "loss": 0.6517538070678711, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.562390158172232, |
| "grad_norm": 0.039306640625, |
| "learning_rate": 4.7291666666666666e-05, |
| "loss": 0.7560918807983399, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.632688927943761, |
| "grad_norm": 0.037109375, |
| "learning_rate": 4.6944444444444446e-05, |
| "loss": 0.7019021511077881, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.70298769771529, |
| "grad_norm": 0.03369140625, |
| "learning_rate": 4.6597222222222226e-05, |
| "loss": 0.6687473297119141, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.773286467486819, |
| "grad_norm": 0.03369140625, |
| "learning_rate": 4.6250000000000006e-05, |
| "loss": 0.6842537879943847, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.843585237258348, |
| "grad_norm": 0.03173828125, |
| "learning_rate": 4.590277777777778e-05, |
| "loss": 0.6241245269775391, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9138840070298769, |
| "grad_norm": 0.038818359375, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 0.6967287063598633, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.984182776801406, |
| "grad_norm": 0.036376953125, |
| "learning_rate": 4.520833333333334e-05, |
| "loss": 0.6635632038116455, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0421792618629173, |
| "grad_norm": 0.032958984375, |
| "learning_rate": 4.486111111111111e-05, |
| "loss": 0.6175796985626221, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.1124780316344465, |
| "grad_norm": 0.033203125, |
| "learning_rate": 4.4513888888888885e-05, |
| "loss": 0.5492826938629151, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.1827768014059754, |
| "grad_norm": 0.047119140625, |
| "learning_rate": 4.4166666666666665e-05, |
| "loss": 0.5715642452239991, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.2530755711775043, |
| "grad_norm": 0.03857421875, |
| "learning_rate": 4.3819444444444445e-05, |
| "loss": 0.6231389522552491, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3233743409490333, |
| "grad_norm": 0.040283203125, |
| "learning_rate": 4.3472222222222225e-05, |
| "loss": 0.5583981513977051, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.3936731107205624, |
| "grad_norm": 0.04736328125, |
| "learning_rate": 4.3125000000000005e-05, |
| "loss": 0.5893191814422607, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4639718804920914, |
| "grad_norm": 0.041015625, |
| "learning_rate": 4.277777777777778e-05, |
| "loss": 0.5815530776977539, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.5342706502636205, |
| "grad_norm": 0.0361328125, |
| "learning_rate": 4.243055555555556e-05, |
| "loss": 0.5973546504974365, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6045694200351495, |
| "grad_norm": 0.041259765625, |
| "learning_rate": 4.208333333333334e-05, |
| "loss": 0.5985394954681397, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.6748681898066784, |
| "grad_norm": 0.0311279296875, |
| "learning_rate": 4.173611111111112e-05, |
| "loss": 0.5578798294067383, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7451669595782073, |
| "grad_norm": 0.036376953125, |
| "learning_rate": 4.138888888888889e-05, |
| "loss": 0.5978553295135498, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.8154657293497363, |
| "grad_norm": 0.041748046875, |
| "learning_rate": 4.104166666666667e-05, |
| "loss": 0.6134780406951904, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8857644991212654, |
| "grad_norm": 0.041748046875, |
| "learning_rate": 4.0694444444444444e-05, |
| "loss": 0.5452652454376221, |
| "step": 135 |
| }, |
| { |
| "epoch": 1.9560632688927944, |
| "grad_norm": 0.03759765625, |
| "learning_rate": 4.0347222222222223e-05, |
| "loss": 0.5957761287689209, |
| "step": 140 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 720, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 7.15883274043392e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
