| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014035481697731866, | |
| "eval_steps": 63, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.614192679092747e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 202.2991, | |
| "eval_samples_per_second": 18.537, | |
| "eval_steps_per_second": 9.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005614192679092747, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 0.0783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011228385358185494, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 0.0586, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016842578037278239, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 0.1994, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022456770716370988, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002807096339546373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0033685156074556477, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0035369413878284304, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.4736, | |
| "eval_samples_per_second": 18.613, | |
| "eval_steps_per_second": 9.306, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003929934875364922, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001672300890261317, | |
| "loss": 0.139, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0044913541432741975, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015721166601221698, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005052773411183472, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014625382902408356, | |
| "loss": 0.1583, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005614192679092746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013453650544213076, | |
| "loss": 1.9159, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006175611947002021, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.265, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0067370312149112955, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010960230259076818, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007073882775656861, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.5026, | |
| "eval_samples_per_second": 18.61, | |
| "eval_steps_per_second": 9.305, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.007298450482820571, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.679484224283449e-05, | |
| "loss": 0.4924, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.007859869750729845, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.404001049666211e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.00842128901863912, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.154724133689677e-05, | |
| "loss": 0.0956, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008982708286548395, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.952166568776062e-05, | |
| "loss": 0.042, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.009544127554457668, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8160743168947496e-05, | |
| "loss": 0.6566, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.010105546822366944, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.010610824163485291, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.5094, | |
| "eval_samples_per_second": 18.61, | |
| "eval_steps_per_second": 9.305, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.010666966090276219, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8165064990227252e-05, | |
| "loss": 0.0509, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.011228385358185492, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.985863781320435e-05, | |
| "loss": 0.0291, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.011789804626094767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.286812958766106e-05, | |
| "loss": 0.0899, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.012351223894004042, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.308324265397836e-06, | |
| "loss": 0.0206, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.012912643161913318, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.270513696097055e-06, | |
| "loss": 0.0575, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.013474062429822591, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.209986176753948e-07, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.014035481697731866, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.1379, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 63, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.814564604097331e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |