| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1440922190201729, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005763688760806916, | |
| "grad_norm": 2.4409587383270264, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5006, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005763688760806916, | |
| "eval_loss": 5.976919174194336, | |
| "eval_runtime": 0.8589, | |
| "eval_samples_per_second": 678.789, | |
| "eval_steps_per_second": 22.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011527377521613832, | |
| "grad_norm": 2.5246589183807373, | |
| "learning_rate": 2e-05, | |
| "loss": 5.7539, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01729106628242075, | |
| "grad_norm": 5.136504173278809, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7782, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023054755043227664, | |
| "grad_norm": 1.6736292839050293, | |
| "learning_rate": 4e-05, | |
| "loss": 5.7622, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02881844380403458, | |
| "grad_norm": 2.1508893966674805, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9264, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0345821325648415, | |
| "grad_norm": 2.719834089279175, | |
| "learning_rate": 6e-05, | |
| "loss": 5.6231, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.040345821325648415, | |
| "grad_norm": 1.862425684928894, | |
| "learning_rate": 7e-05, | |
| "loss": 5.7143, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04610951008645533, | |
| "grad_norm": 2.0583953857421875, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7937, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05187319884726225, | |
| "grad_norm": 3.5244977474212646, | |
| "learning_rate": 9e-05, | |
| "loss": 5.5759, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05187319884726225, | |
| "eval_loss": 5.762571334838867, | |
| "eval_runtime": 0.8404, | |
| "eval_samples_per_second": 693.698, | |
| "eval_steps_per_second": 22.608, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05763688760806916, | |
| "grad_norm": 2.2905080318450928, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06340057636887608, | |
| "grad_norm": 2.9346985816955566, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 5.5274, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.069164265129683, | |
| "grad_norm": 3.4477925300598145, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 5.4946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07492795389048991, | |
| "grad_norm": 2.5624496936798096, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 5.5983, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08069164265129683, | |
| "grad_norm": 2.30907940864563, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 4.965, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08645533141210375, | |
| "grad_norm": 3.060831308364868, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 5.0549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09221902017291066, | |
| "grad_norm": 1.7213447093963623, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.1858, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09798270893371758, | |
| "grad_norm": 1.8246761560440063, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 5.1216, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1037463976945245, | |
| "grad_norm": 1.6783112287521362, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 5.0034, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1037463976945245, | |
| "eval_loss": 4.902072429656982, | |
| "eval_runtime": 0.8459, | |
| "eval_samples_per_second": 689.167, | |
| "eval_steps_per_second": 22.46, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10951008645533142, | |
| "grad_norm": 1.777565836906433, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.9386, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11527377521613832, | |
| "grad_norm": 2.9292523860931396, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 4.5237, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12103746397694524, | |
| "grad_norm": 1.343632459640503, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 4.4949, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12680115273775217, | |
| "grad_norm": 1.9242039918899536, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 4.7291, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13256484149855907, | |
| "grad_norm": 1.7752628326416016, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 4.6048, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.138328530259366, | |
| "grad_norm": 1.608022689819336, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 4.3314, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1440922190201729, | |
| "grad_norm": 1.1817405223846436, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.163, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1388375860838400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |