| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.056121971751940884, |
| "eval_steps": 200, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0023384154896642037, |
| "grad_norm": 1.9981695413589478, |
| "learning_rate": 4.4859813084112145e-06, |
| "loss": 0.47716766357421875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.004676830979328407, |
| "grad_norm": 1.9483280181884766, |
| "learning_rate": 9.158878504672897e-06, |
| "loss": 0.4592530059814453, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0070152464689926105, |
| "grad_norm": 2.1290855407714844, |
| "learning_rate": 1.3831775700934579e-05, |
| "loss": 0.394501838684082, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.009353661958656815, |
| "grad_norm": 2.8394205570220947, |
| "learning_rate": 1.8504672897196264e-05, |
| "loss": 0.3752219009399414, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.011692077448321018, |
| "grad_norm": 2.5833706855773926, |
| "learning_rate": 2.3177570093457944e-05, |
| "loss": 0.40475303649902344, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.014030492937985221, |
| "grad_norm": 2.622011661529541, |
| "learning_rate": 2.7850467289719627e-05, |
| "loss": 0.45625301361083986, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.016368908427649424, |
| "grad_norm": 2.9406535625457764, |
| "learning_rate": 3.2523364485981314e-05, |
| "loss": 0.34918937683105467, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "grad_norm": 3.8391785621643066, |
| "learning_rate": 3.7196261682242994e-05, |
| "loss": 0.41711517333984377, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "eval_pairs_with_negatives_loss": 0.3914637565612793, |
| "eval_pairs_with_negatives_runtime": 44.0353, |
| "eval_pairs_with_negatives_samples_per_second": 28.523, |
| "eval_pairs_with_negatives_steps_per_second": 3.565, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "eval_positives_loss": 0.1480681300163269, |
| "eval_positives_runtime": 51.7193, |
| "eval_positives_samples_per_second": 42.537, |
| "eval_positives_steps_per_second": 5.317, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.02104573940697783, |
| "grad_norm": 2.3628170490264893, |
| "learning_rate": 4.186915887850468e-05, |
| "loss": 0.4296648406982422, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.023384154896642036, |
| "grad_norm": 2.698835611343384, |
| "learning_rate": 4.6542056074766354e-05, |
| "loss": 0.43652393341064455, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.02572257038630624, |
| "grad_norm": 4.1166558265686035, |
| "learning_rate": 5.121495327102804e-05, |
| "loss": 0.4344004440307617, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.028060985875970442, |
| "grad_norm": 4.551556587219238, |
| "learning_rate": 5.588785046728973e-05, |
| "loss": 0.41842262268066405, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.030399401365634647, |
| "grad_norm": 2.3925657272338867, |
| "learning_rate": 6.056074766355141e-05, |
| "loss": 0.4197782897949219, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.03273781685529885, |
| "grad_norm": 3.1023190021514893, |
| "learning_rate": 6.52336448598131e-05, |
| "loss": 0.4292975616455078, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.03507623234496305, |
| "grad_norm": 4.1481032371521, |
| "learning_rate": 6.990654205607478e-05, |
| "loss": 0.4758753204345703, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.03741464783462726, |
| "grad_norm": 3.8799962997436523, |
| "learning_rate": 7.457943925233644e-05, |
| "loss": 0.3311753845214844, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.03741464783462726, |
| "eval_pairs_with_negatives_loss": 0.3694910407066345, |
| "eval_pairs_with_negatives_runtime": 44.2166, |
| "eval_pairs_with_negatives_samples_per_second": 28.406, |
| "eval_pairs_with_negatives_steps_per_second": 3.551, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.03741464783462726, |
| "eval_positives_loss": 0.11797073483467102, |
| "eval_positives_runtime": 51.3355, |
| "eval_positives_samples_per_second": 42.855, |
| "eval_positives_steps_per_second": 5.357, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.03975306332429146, |
| "grad_norm": 3.7068564891815186, |
| "learning_rate": 7.925233644859813e-05, |
| "loss": 0.388726806640625, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.04209147881395566, |
| "grad_norm": 2.3407328128814697, |
| "learning_rate": 8.392523364485981e-05, |
| "loss": 0.4401784133911133, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.04442989430361987, |
| "grad_norm": 3.0923948287963867, |
| "learning_rate": 8.85981308411215e-05, |
| "loss": 0.41050430297851564, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.04676830979328407, |
| "grad_norm": 2.626753568649292, |
| "learning_rate": 9.327102803738317e-05, |
| "loss": 0.3923164749145508, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.04910672528294827, |
| "grad_norm": 2.729557991027832, |
| "learning_rate": 9.794392523364486e-05, |
| "loss": 0.3163204765319824, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.05144514077261248, |
| "grad_norm": 3.1612608432769775, |
| "learning_rate": 9.986215045293424e-05, |
| "loss": 0.35652976989746094, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.05378355626227668, |
| "grad_norm": 2.224350690841675, |
| "learning_rate": 9.961599054745964e-05, |
| "loss": 0.37072269439697264, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.056121971751940884, |
| "grad_norm": 3.207382917404175, |
| "learning_rate": 9.936983064198503e-05, |
| "loss": 0.3007513427734375, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.056121971751940884, |
| "eval_pairs_with_negatives_loss": 0.3388254940509796, |
| "eval_pairs_with_negatives_runtime": 43.9558, |
| "eval_pairs_with_negatives_samples_per_second": 28.574, |
| "eval_pairs_with_negatives_steps_per_second": 3.572, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.056121971751940884, |
| "eval_positives_loss": 0.10862970352172852, |
| "eval_positives_runtime": 51.7355, |
| "eval_positives_samples_per_second": 42.524, |
| "eval_positives_steps_per_second": 5.315, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 10691, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
