| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021200664287481007, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.066888095827003e-05, | |
| "eval_loss": 2.3646445274353027, | |
| "eval_runtime": 1157.98, | |
| "eval_samples_per_second": 7.719, | |
| "eval_steps_per_second": 3.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021200664287481007, | |
| "grad_norm": 0.6784875988960266, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2903, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00042401328574962014, | |
| "grad_norm": 0.7525308728218079, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2873, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005653510476661603, | |
| "eval_loss": 2.24292254447937, | |
| "eval_runtime": 1162.2913, | |
| "eval_samples_per_second": 7.69, | |
| "eval_steps_per_second": 3.845, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006360199286244302, | |
| "grad_norm": 0.5270115733146667, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2784, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008480265714992403, | |
| "grad_norm": 0.521692156791687, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1963, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010600332143740504, | |
| "grad_norm": 0.604248583316803, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.2337, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011307020953323205, | |
| "eval_loss": 2.1639838218688965, | |
| "eval_runtime": 1163.4509, | |
| "eval_samples_per_second": 7.682, | |
| "eval_steps_per_second": 3.841, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012720398572488604, | |
| "grad_norm": 0.38564443588256836, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1148, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014840465001236705, | |
| "grad_norm": 0.3931140899658203, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.2127, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016960531429984806, | |
| "grad_norm": 0.3743416965007782, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.1533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016960531429984806, | |
| "eval_loss": 2.149599313735962, | |
| "eval_runtime": 1162.5415, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 3.844, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019080597858732906, | |
| "grad_norm": 0.3767165541648865, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.1056, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0021200664287481007, | |
| "grad_norm": 0.3632538914680481, | |
| "learning_rate": 0.0, | |
| "loss": 2.1531, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6785199790555136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |