| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15015015015015015, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006006006006006006, | |
| "grad_norm": 0.4190921187400818, | |
| "learning_rate": 1e-05, | |
| "loss": 2.8248, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006006006006006006, | |
| "eval_loss": 1.4474337100982666, | |
| "eval_runtime": 20.7102, | |
| "eval_samples_per_second": 6.76, | |
| "eval_steps_per_second": 0.869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012012012012012012, | |
| "grad_norm": 0.4117864668369293, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8999, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 0.47476091980934143, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024024024024024024, | |
| "grad_norm": 0.5182833671569824, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0016, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03003003003003003, | |
| "grad_norm": 0.5595167279243469, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9978, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 0.4953429400920868, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9403, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.042042042042042045, | |
| "grad_norm": 0.5607187747955322, | |
| "learning_rate": 7e-05, | |
| "loss": 2.8352, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 0.5155525803565979, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8618, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 0.5875859260559082, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "eval_loss": 1.3532243967056274, | |
| "eval_runtime": 20.8925, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 0.862, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06006006006006006, | |
| "grad_norm": 0.5471853613853455, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7472, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06606606606606606, | |
| "grad_norm": 0.6831285953521729, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.7426, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 0.5598995089530945, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.4549, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07807807807807808, | |
| "grad_norm": 0.6646794080734253, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.4884, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08408408408408409, | |
| "grad_norm": 0.8190558552742004, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.5538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09009009009009009, | |
| "grad_norm": 0.6523075699806213, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.6107, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 0.6743414402008057, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.4982, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1021021021021021, | |
| "grad_norm": 0.6463999152183533, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.3463, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 0.6486225724220276, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.4509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "eval_loss": 1.1851264238357544, | |
| "eval_runtime": 20.8737, | |
| "eval_samples_per_second": 6.707, | |
| "eval_steps_per_second": 0.862, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11411411411411411, | |
| "grad_norm": 0.6646873354911804, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.5231, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12012012012012012, | |
| "grad_norm": 0.6953087449073792, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.3943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12612612612612611, | |
| "grad_norm": 0.6595270037651062, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.3606, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13213213213213212, | |
| "grad_norm": 0.64484703540802, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.3778, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13813813813813813, | |
| "grad_norm": 0.8236026763916016, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.2202, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 0.6265228986740112, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.2827, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15015015015015015, | |
| "grad_norm": 0.6501413583755493, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3664, | |
| "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": 6.347789697024e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |