| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03088803088803089, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010296010296010295, | |
| "eval_loss": 8.052192687988281, | |
| "eval_runtime": 50.6652, | |
| "eval_samples_per_second": 8.073, | |
| "eval_steps_per_second": 4.046, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003088803088803089, | |
| "grad_norm": 2.3171470165252686, | |
| "learning_rate": 6e-05, | |
| "loss": 8.1366, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006177606177606178, | |
| "grad_norm": 2.199993848800659, | |
| "learning_rate": 0.00012, | |
| "loss": 7.8185, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008236808236808236, | |
| "eval_loss": 6.953918933868408, | |
| "eval_runtime": 50.3163, | |
| "eval_samples_per_second": 8.129, | |
| "eval_steps_per_second": 4.074, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009266409266409266, | |
| "grad_norm": 1.46760892868042, | |
| "learning_rate": 0.00018, | |
| "loss": 7.3099, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012355212355212355, | |
| "grad_norm": 1.9026381969451904, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.4483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015444015444015444, | |
| "grad_norm": 2.2243525981903076, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.2288, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016473616473616472, | |
| "eval_loss": 5.587409496307373, | |
| "eval_runtime": 50.485, | |
| "eval_samples_per_second": 8.101, | |
| "eval_steps_per_second": 4.061, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018532818532818532, | |
| "grad_norm": 1.6756141185760498, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.5012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 1.8792874813079834, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.9086, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02471042471042471, | |
| "grad_norm": 1.52913236618042, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 4.9885, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02471042471042471, | |
| "eval_loss": 4.979452133178711, | |
| "eval_runtime": 50.4983, | |
| "eval_samples_per_second": 8.099, | |
| "eval_steps_per_second": 4.06, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027799227799227798, | |
| "grad_norm": 1.5601953268051147, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.1317, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03088803088803089, | |
| "grad_norm": 1.4515669345855713, | |
| "learning_rate": 0.0, | |
| "loss": 4.9942, | |
| "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": 1.0747719909900288e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |