| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1303780964797914, | |
| "eval_steps": 3, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005215123859191656, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005215123859191656, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9745, | |
| "eval_samples_per_second": 32.566, | |
| "eval_steps_per_second": 8.242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010430247718383311, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01564537157757497, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01564537157757497, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.955, | |
| "eval_samples_per_second": 32.694, | |
| "eval_steps_per_second": 8.275, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020860495436766623, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02607561929595828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03129074315514994, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03129074315514994, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9604, | |
| "eval_samples_per_second": 32.659, | |
| "eval_steps_per_second": 8.266, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03650586701434159, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.041720990873533245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0469361147327249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0469361147327249, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.961, | |
| "eval_samples_per_second": 32.655, | |
| "eval_steps_per_second": 8.264, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05215123859191656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05736636245110821, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06258148631029987, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06258148631029987, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9578, | |
| "eval_samples_per_second": 32.676, | |
| "eval_steps_per_second": 8.27, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07301173402868318, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07822685788787484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07822685788787484, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9593, | |
| "eval_samples_per_second": 32.666, | |
| "eval_steps_per_second": 8.267, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08344198174706649, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08865710560625815, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0938722294654498, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0938722294654498, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9569, | |
| "eval_samples_per_second": 32.682, | |
| "eval_steps_per_second": 8.271, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09908735332464146, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10430247718383312, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10951760104302477, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10951760104302477, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9625, | |
| "eval_samples_per_second": 32.645, | |
| "eval_steps_per_second": 8.262, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11473272490221642, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11994784876140809, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12516297262059975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12516297262059975, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9616, | |
| "eval_samples_per_second": 32.65, | |
| "eval_steps_per_second": 8.263, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1303780964797914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.69912849629184e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |