| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012084105373398855, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.028035124466285e-05, | |
| "eval_loss": 2.3150148391723633, | |
| "eval_runtime": 184.1572, | |
| "eval_samples_per_second": 56.767, | |
| "eval_steps_per_second": 28.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012084105373398856, | |
| "grad_norm": 1.2494455575942993, | |
| "learning_rate": 6e-05, | |
| "loss": 2.205, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024168210746797713, | |
| "grad_norm": 1.2602262496948242, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2981, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003222428099573028, | |
| "eval_loss": 1.9345731735229492, | |
| "eval_runtime": 183.2746, | |
| "eval_samples_per_second": 57.04, | |
| "eval_steps_per_second": 28.52, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003625231612019657, | |
| "grad_norm": 1.2954614162445068, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0799, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00048336421493595425, | |
| "grad_norm": 1.2402883768081665, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8293, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006042052686699428, | |
| "grad_norm": 1.329088807106018, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.5671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006444856199146056, | |
| "eval_loss": 1.5357359647750854, | |
| "eval_runtime": 183.4873, | |
| "eval_samples_per_second": 56.974, | |
| "eval_steps_per_second": 28.487, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007250463224039314, | |
| "grad_norm": 1.2818197011947632, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4472, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008458873761379199, | |
| "grad_norm": 1.2412055730819702, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.4521, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009667284298719085, | |
| "grad_norm": 1.0540664196014404, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.5259, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009667284298719085, | |
| "eval_loss": 1.4515408277511597, | |
| "eval_runtime": 183.1921, | |
| "eval_samples_per_second": 57.066, | |
| "eval_steps_per_second": 28.533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010875694836058971, | |
| "grad_norm": 1.2278207540512085, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.4075, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "grad_norm": 1.1783462762832642, | |
| "learning_rate": 0.0, | |
| "loss": 1.4371, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1451583854346240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |