| { | |
| "best_metric": 0.4772830307483673, | |
| "best_model_checkpoint": "Phi-3.5-mini-instruct_text_to_sql\\checkpoint-500", | |
| "epoch": 0.7451564828614009, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07451564828614009, | |
| "grad_norm": 0.05202275142073631, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07451564828614009, | |
| "eval_loss": 0.5696993470191956, | |
| "eval_runtime": 27.4333, | |
| "eval_samples_per_second": 4.593, | |
| "eval_steps_per_second": 0.583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.038158852607011795, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 0.5364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "eval_loss": 0.5185158848762512, | |
| "eval_runtime": 26.2689, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.609, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "grad_norm": 0.12953701615333557, | |
| "learning_rate": 0.00019872208493487546, | |
| "loss": 0.5099, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22354694485842028, | |
| "eval_loss": 0.5075405240058899, | |
| "eval_runtime": 26.9551, | |
| "eval_samples_per_second": 4.674, | |
| "eval_steps_per_second": 0.594, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.036496683955192566, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 0.5012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "eval_loss": 0.49924516677856445, | |
| "eval_runtime": 26.2588, | |
| "eval_samples_per_second": 4.798, | |
| "eval_steps_per_second": 0.609, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "grad_norm": 0.047366924583911896, | |
| "learning_rate": 0.0001949210010777752, | |
| "loss": 0.4915, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37257824143070045, | |
| "eval_loss": 0.49416425824165344, | |
| "eval_runtime": 26.2568, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.609, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.035322971642017365, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.4908, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "eval_loss": 0.48849040269851685, | |
| "eval_runtime": 26.2674, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 0.609, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "grad_norm": 0.04145614430308342, | |
| "learning_rate": 0.0001886938976751951, | |
| "loss": 0.486, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5216095380029806, | |
| "eval_loss": 0.48535990715026855, | |
| "eval_runtime": 26.2577, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.609, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.04975809529423714, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.4867, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "eval_loss": 0.4834245443344116, | |
| "eval_runtime": 26.1969, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.611, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "grad_norm": 0.05116498842835426, | |
| "learning_rate": 0.00018019992891214008, | |
| "loss": 0.4792, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6706408345752608, | |
| "eval_loss": 0.4825398325920105, | |
| "eval_runtime": 26.1757, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 0.611, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.039921361953020096, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.4781, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "eval_loss": 0.4772830307483673, | |
| "eval_runtime": 26.1948, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 0.611, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2013, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90386203000832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |