| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001110814893806096, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.443259575224385e-05, | |
| "grad_norm": 74.77045440673828, | |
| "learning_rate": 1e-05, | |
| "loss": 12.5149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.443259575224385e-05, | |
| "eval_loss": 12.948126792907715, | |
| "eval_runtime": 2085.2718, | |
| "eval_samples_per_second": 9.089, | |
| "eval_steps_per_second": 1.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.88651915044877e-05, | |
| "grad_norm": 73.22039031982422, | |
| "learning_rate": 2e-05, | |
| "loss": 13.3496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013329778725673153, | |
| "grad_norm": 72.73692321777344, | |
| "learning_rate": 3e-05, | |
| "loss": 12.6915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001777303830089754, | |
| "grad_norm": 72.64486694335938, | |
| "learning_rate": 4e-05, | |
| "loss": 12.016, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00022216297876121924, | |
| "grad_norm": 76.35221862792969, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00026659557451346307, | |
| "grad_norm": 61.80672836303711, | |
| "learning_rate": 6e-05, | |
| "loss": 7.6542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00031102817026570695, | |
| "grad_norm": 40.792171478271484, | |
| "learning_rate": 7e-05, | |
| "loss": 4.2684, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003554607660179508, | |
| "grad_norm": 17.3669490814209, | |
| "learning_rate": 8e-05, | |
| "loss": 3.3804, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003998933617701946, | |
| "grad_norm": 21.140520095825195, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5972, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003998933617701946, | |
| "eval_loss": 1.9437395334243774, | |
| "eval_runtime": 2088.5806, | |
| "eval_samples_per_second": 9.075, | |
| "eval_steps_per_second": 1.135, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004443259575224385, | |
| "grad_norm": 18.79267692565918, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2143, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004887585532746823, | |
| "grad_norm": 8.969635963439941, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.6568, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005331911490269261, | |
| "grad_norm": 8.22108268737793, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.6399, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00057762374477917, | |
| "grad_norm": 6.7568230628967285, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.3787, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006220563405314139, | |
| "grad_norm": 22.37034034729004, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.3557, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006664889362836577, | |
| "grad_norm": 6.20902156829834, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.5788, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007109215320359015, | |
| "grad_norm": 5.11328649520874, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.319, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007553541277881454, | |
| "grad_norm": 7.359101295471191, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.0957, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007997867235403892, | |
| "grad_norm": 4.124218940734863, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.1526, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007997867235403892, | |
| "eval_loss": 1.082924246788025, | |
| "eval_runtime": 2088.8216, | |
| "eval_samples_per_second": 9.074, | |
| "eval_steps_per_second": 1.135, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000844219319292633, | |
| "grad_norm": 4.501346588134766, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.922, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.000888651915044877, | |
| "grad_norm": 5.430482387542725, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.8881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009330845107971208, | |
| "grad_norm": 2.8988702297210693, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.9686, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009775171065493646, | |
| "grad_norm": 2.7791342735290527, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7266, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0010219497023016084, | |
| "grad_norm": 4.415706157684326, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.4575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010663822980538523, | |
| "grad_norm": 3.8715085983276367, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.239, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001110814893806096, | |
| "grad_norm": 4.328126430511475, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2685, | |
| "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": 1.85471820890112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |