| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3220035778175313, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007155635062611807, | |
| "eval_loss": 8.003866195678711, | |
| "eval_runtime": 21.074, | |
| "eval_samples_per_second": 11.199, | |
| "eval_steps_per_second": 1.424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02146690518783542, | |
| "grad_norm": 36.30503845214844, | |
| "learning_rate": 3e-05, | |
| "loss": 29.32, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03577817531305903, | |
| "eval_loss": 6.45150899887085, | |
| "eval_runtime": 21.281, | |
| "eval_samples_per_second": 11.09, | |
| "eval_steps_per_second": 1.41, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04293381037567084, | |
| "grad_norm": 59.01460647583008, | |
| "learning_rate": 6e-05, | |
| "loss": 29.5122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06440071556350627, | |
| "grad_norm": 31.912750244140625, | |
| "learning_rate": 9e-05, | |
| "loss": 15.7048, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07155635062611806, | |
| "eval_loss": 1.4119746685028076, | |
| "eval_runtime": 21.3324, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 1.406, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08586762075134168, | |
| "grad_norm": 12.302176475524902, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 5.5122, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1073345259391771, | |
| "grad_norm": 7.404484272003174, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4541, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1073345259391771, | |
| "eval_loss": 0.1575503647327423, | |
| "eval_runtime": 21.3407, | |
| "eval_samples_per_second": 11.059, | |
| "eval_steps_per_second": 1.406, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12880143112701253, | |
| "grad_norm": 6.458031177520752, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.5215, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14311270125223613, | |
| "eval_loss": 0.0960574522614479, | |
| "eval_runtime": 21.3479, | |
| "eval_samples_per_second": 11.055, | |
| "eval_steps_per_second": 1.405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15026833631484796, | |
| "grad_norm": 21.97161293029785, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.3563, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17173524150268335, | |
| "grad_norm": 2.182478666305542, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.2626, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17889087656529518, | |
| "eval_loss": 0.041570138186216354, | |
| "eval_runtime": 21.352, | |
| "eval_samples_per_second": 11.053, | |
| "eval_steps_per_second": 1.405, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19320214669051877, | |
| "grad_norm": 1.8692655563354492, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.1014, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2146690518783542, | |
| "grad_norm": 10.44522762298584, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4899, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2146690518783542, | |
| "eval_loss": 0.021523064002394676, | |
| "eval_runtime": 21.3288, | |
| "eval_samples_per_second": 11.065, | |
| "eval_steps_per_second": 1.407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23613595706618962, | |
| "grad_norm": 1.440638780593872, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0295, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2504472271914132, | |
| "eval_loss": 0.017327968031167984, | |
| "eval_runtime": 21.3349, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 1.406, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25760286225402507, | |
| "grad_norm": 0.0844140574336052, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0055, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "grad_norm": 0.12384696304798126, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0257, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.28622540250447226, | |
| "eval_loss": 0.014691304415464401, | |
| "eval_runtime": 21.3348, | |
| "eval_samples_per_second": 11.062, | |
| "eval_steps_per_second": 1.406, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3005366726296959, | |
| "grad_norm": 13.742753982543945, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3220035778175313, | |
| "grad_norm": 3.5590667724609375, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3220035778175313, | |
| "eval_loss": 0.015118077397346497, | |
| "eval_runtime": 21.333, | |
| "eval_samples_per_second": 11.063, | |
| "eval_steps_per_second": 1.406, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.987288966234112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |