| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.46403712296983757, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02320185614849188, | |
| "grad_norm": 26.745355095184312, | |
| "learning_rate": 5e-07, | |
| "loss": 1.6569, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04640371229698376, | |
| "grad_norm": 13.080188660738868, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5099, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06960556844547564, | |
| "grad_norm": 7.775505635686351, | |
| "learning_rate": 9.998470286265414e-07, | |
| "loss": 1.2782, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09280742459396751, | |
| "grad_norm": 6.492859712313467, | |
| "learning_rate": 9.993882081071305e-07, | |
| "loss": 1.2359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11600928074245939, | |
| "grad_norm": 5.355551984540261, | |
| "learning_rate": 9.986238191873872e-07, | |
| "loss": 1.204, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13921113689095127, | |
| "grad_norm": 5.125393165293572, | |
| "learning_rate": 9.975543295858033e-07, | |
| "loss": 1.1627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16241299303944315, | |
| "grad_norm": 4.710071299991241, | |
| "learning_rate": 9.961803937075514e-07, | |
| "loss": 1.1463, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18561484918793503, | |
| "grad_norm": 5.029376799191572, | |
| "learning_rate": 9.945028522440653e-07, | |
| "loss": 1.1394, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2088167053364269, | |
| "grad_norm": 4.763291242870039, | |
| "learning_rate": 9.925227316586314e-07, | |
| "loss": 1.1371, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23201856148491878, | |
| "grad_norm": 4.903033982523367, | |
| "learning_rate": 9.902412435583125e-07, | |
| "loss": 1.1181, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23201856148491878, | |
| "eval_loss": 1.1214605569839478, | |
| "eval_runtime": 105.8329, | |
| "eval_samples_per_second": 57.912, | |
| "eval_steps_per_second": 0.907, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2552204176334107, | |
| "grad_norm": 4.785575700738186, | |
| "learning_rate": 9.876597839525813e-07, | |
| "loss": 1.1163, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.27842227378190254, | |
| "grad_norm": 4.600727000401806, | |
| "learning_rate": 9.847799323991233e-07, | |
| "loss": 1.1232, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.30162412993039445, | |
| "grad_norm": 4.8200416840356315, | |
| "learning_rate": 9.816034510373285e-07, | |
| "loss": 1.125, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3248259860788863, | |
| "grad_norm": 4.958997518359378, | |
| "learning_rate": 9.781322835100637e-07, | |
| "loss": 1.108, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3480278422273782, | |
| "grad_norm": 4.883541365508776, | |
| "learning_rate": 9.743685537743856e-07, | |
| "loss": 1.106, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.37122969837587005, | |
| "grad_norm": 4.973507458353338, | |
| "learning_rate": 9.70314564801922e-07, | |
| "loss": 1.0973, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.39443155452436196, | |
| "grad_norm": 4.704415990191669, | |
| "learning_rate": 9.659727971697173e-07, | |
| "loss": 1.0964, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4176334106728538, | |
| "grad_norm": 4.759885977268913, | |
| "learning_rate": 9.613459075424033e-07, | |
| "loss": 1.0956, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4408352668213457, | |
| "grad_norm": 4.868535908803129, | |
| "learning_rate": 9.564367270466245e-07, | |
| "loss": 1.0787, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.46403712296983757, | |
| "grad_norm": 5.180286116736628, | |
| "learning_rate": 9.51248259538713e-07, | |
| "loss": 1.0765, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46403712296983757, | |
| "eval_loss": 1.0775035619735718, | |
| "eval_runtime": 105.5293, | |
| "eval_samples_per_second": 58.079, | |
| "eval_steps_per_second": 0.91, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 645, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 589411381149696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |