| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004265984109209193, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.1329920546045965e-05, | |
| "eval_loss": 0.7577171921730042, | |
| "eval_runtime": 1244.4389, | |
| "eval_samples_per_second": 15.863, | |
| "eval_steps_per_second": 7.931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021329920546045967, | |
| "grad_norm": 1.3042656183242798, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 2.8787, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00042659841092091935, | |
| "grad_norm": 2.96354079246521, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.8084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006398976163813789, | |
| "grad_norm": 1.2139008045196533, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 1.6233, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008531968218418387, | |
| "grad_norm": 0.9353722333908081, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 1.3712, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "grad_norm": 1.0384025573730469, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 1.3663, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010664960273022983, | |
| "eval_loss": 0.32812321186065674, | |
| "eval_runtime": 1244.8537, | |
| "eval_samples_per_second": 15.857, | |
| "eval_steps_per_second": 7.929, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0012797952327627579, | |
| "grad_norm": 1.19833505153656, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 1.278, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0014930944382232176, | |
| "grad_norm": 1.2064980268478394, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2484, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0017063936436836774, | |
| "grad_norm": 1.0184420347213745, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 1.2899, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 1.238606572151184, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 1.1212, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "grad_norm": 1.2906690835952759, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 1.2625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0021329920546045967, | |
| "eval_loss": 0.29829952120780945, | |
| "eval_runtime": 1245.3367, | |
| "eval_samples_per_second": 15.851, | |
| "eval_steps_per_second": 7.926, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002346291260065056, | |
| "grad_norm": 1.1385165452957153, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 1.2694, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0025595904655255157, | |
| "grad_norm": 1.0836408138275146, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 1.152, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0027728896709859757, | |
| "grad_norm": 1.0004163980484009, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 1.1292, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0029861888764464353, | |
| "grad_norm": 1.029665231704712, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 1.0651, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "grad_norm": 1.2531042098999023, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 1.123, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003199488081906895, | |
| "eval_loss": 0.28591254353523254, | |
| "eval_runtime": 1245.4094, | |
| "eval_samples_per_second": 15.85, | |
| "eval_steps_per_second": 7.925, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0034127872873673548, | |
| "grad_norm": 1.30852210521698, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 1.0811, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0036260864928278143, | |
| "grad_norm": 1.3546735048294067, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 1.0946, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.003839385698288274, | |
| "grad_norm": 1.1535334587097168, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 1.0432, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004052684903748734, | |
| "grad_norm": 1.2503819465637207, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 1.1116, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "grad_norm": 1.1021947860717773, | |
| "learning_rate": 0.0, | |
| "loss": 1.1163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004265984109209193, | |
| "eval_loss": 0.28369656205177307, | |
| "eval_runtime": 1243.8222, | |
| "eval_samples_per_second": 15.87, | |
| "eval_steps_per_second": 7.935, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.3218937061376e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |