| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003724048040219719, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.448096080439437e-05, | |
| "eval_loss": 11.930380821228027, | |
| "eval_runtime": 49.5414, | |
| "eval_samples_per_second": 114.127, | |
| "eval_steps_per_second": 57.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003724048040219719, | |
| "grad_norm": 0.023313909769058228, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9262, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007448096080439438, | |
| "grad_norm": 0.024473126977682114, | |
| "learning_rate": 0.0001, | |
| "loss": 11.931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007448096080439438, | |
| "eval_loss": 11.930343627929688, | |
| "eval_runtime": 50.4719, | |
| "eval_samples_per_second": 112.023, | |
| "eval_steps_per_second": 56.011, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011172144120659157, | |
| "grad_norm": 0.03296150267124176, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014896192160878876, | |
| "grad_norm": 0.022446773946285248, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014896192160878876, | |
| "eval_loss": 11.930259704589844, | |
| "eval_runtime": 49.9116, | |
| "eval_samples_per_second": 113.28, | |
| "eval_steps_per_second": 56.64, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018620240201098594, | |
| "grad_norm": 0.020162925124168396, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022344288241318315, | |
| "grad_norm": 0.029531003907322884, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022344288241318315, | |
| "eval_loss": 11.930198669433594, | |
| "eval_runtime": 50.5107, | |
| "eval_samples_per_second": 111.937, | |
| "eval_steps_per_second": 55.968, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002606833628153803, | |
| "grad_norm": 0.019078467041254044, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9312, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002979238432175775, | |
| "grad_norm": 0.023682741448283195, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9328, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002979238432175775, | |
| "eval_loss": 11.93016242980957, | |
| "eval_runtime": 50.4237, | |
| "eval_samples_per_second": 112.13, | |
| "eval_steps_per_second": 56.065, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033516432361977468, | |
| "grad_norm": 0.04054044187068939, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9268, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003724048040219719, | |
| "grad_norm": 0.02140682004392147, | |
| "learning_rate": 0.0, | |
| "loss": 11.9285, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003724048040219719, | |
| "eval_loss": 11.930160522460938, | |
| "eval_runtime": 49.6627, | |
| "eval_samples_per_second": 113.848, | |
| "eval_steps_per_second": 56.924, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |