| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002523722996163941, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010094891984655764, | |
| "grad_norm": 0.944897472858429, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010094891984655764, | |
| "eval_loss": 2.663647413253784, | |
| "eval_runtime": 837.5363, | |
| "eval_samples_per_second": 9.96, | |
| "eval_steps_per_second": 1.245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002018978396931153, | |
| "grad_norm": 1.1168081760406494, | |
| "learning_rate": 2e-05, | |
| "loss": 2.614, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003028467595396729, | |
| "grad_norm": 0.8895403742790222, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5742, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004037956793862306, | |
| "grad_norm": 1.1057639122009277, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6082, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005047445992327882, | |
| "grad_norm": 1.2985063791275024, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6844, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006056935190793458, | |
| "grad_norm": 1.2740225791931152, | |
| "learning_rate": 6e-05, | |
| "loss": 2.684, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007066424389259035, | |
| "grad_norm": 1.1661525964736938, | |
| "learning_rate": 7e-05, | |
| "loss": 2.5458, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008075913587724611, | |
| "grad_norm": 0.7164007425308228, | |
| "learning_rate": 8e-05, | |
| "loss": 2.447, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009085402786190188, | |
| "grad_norm": 0.8726524710655212, | |
| "learning_rate": 9e-05, | |
| "loss": 2.4571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009085402786190188, | |
| "eval_loss": 2.368643283843994, | |
| "eval_runtime": 836.9961, | |
| "eval_samples_per_second": 9.967, | |
| "eval_steps_per_second": 1.246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010094891984655764, | |
| "grad_norm": 0.793461263179779, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4332, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001110438118312134, | |
| "grad_norm": 0.6365218162536621, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.3091, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0012113870381586917, | |
| "grad_norm": 0.49457401037216187, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.2431, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0013123359580052493, | |
| "grad_norm": 0.7975025773048401, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.239, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001413284877851807, | |
| "grad_norm": 0.48324573040008545, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.227, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0015142337976983646, | |
| "grad_norm": 0.3696288764476776, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.2318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016151827175449223, | |
| "grad_norm": 0.3048635423183441, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1899, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00171613163739148, | |
| "grad_norm": 0.3256937265396118, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.2085, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0018170805572380376, | |
| "grad_norm": 0.2600611448287964, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.1825, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0018170805572380376, | |
| "eval_loss": 2.201138734817505, | |
| "eval_runtime": 836.612, | |
| "eval_samples_per_second": 9.971, | |
| "eval_steps_per_second": 1.247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0019180294770845953, | |
| "grad_norm": 0.3889247179031372, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1976, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0020189783969311527, | |
| "grad_norm": 0.30169251561164856, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.2119, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0021199273167777106, | |
| "grad_norm": 0.24492594599723816, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.2028, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002220876236624268, | |
| "grad_norm": 0.2256334125995636, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.158, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002321825156470826, | |
| "grad_norm": 0.299275279045105, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.1862, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0024227740763173833, | |
| "grad_norm": 0.2614262104034424, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.1995, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002523722996163941, | |
| "grad_norm": 0.36414486169815063, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1961, | |
| "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": 3.561120808619213e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |