| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006073581439135122, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.036790719567561e-05, | |
| "eval_loss": 0.8727558255195618, | |
| "eval_runtime": 1304.3872, | |
| "eval_samples_per_second": 10.63, | |
| "eval_steps_per_second": 5.315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003036790719567561, | |
| "grad_norm": 0.7052744626998901, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7843, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006073581439135122, | |
| "grad_norm": 0.42328405380249023, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6129, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009110372158702683, | |
| "grad_norm": 0.4494202435016632, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5938, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012147162878270244, | |
| "grad_norm": 0.5013023614883423, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0015183953597837805, | |
| "grad_norm": 0.473978728055954, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0015183953597837805, | |
| "eval_loss": 0.6444454193115234, | |
| "eval_runtime": 1304.5841, | |
| "eval_samples_per_second": 10.628, | |
| "eval_steps_per_second": 5.314, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0018220744317405367, | |
| "grad_norm": 0.6711248159408569, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7031, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002125753503697293, | |
| "grad_norm": 0.5438421964645386, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6367, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0024294325756540488, | |
| "grad_norm": 0.5609766840934753, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6457, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0027331116476108047, | |
| "grad_norm": 0.773842990398407, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6022, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.003036790719567561, | |
| "grad_norm": 0.4400677978992462, | |
| "learning_rate": 0.0002, | |
| "loss": 0.594, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.003036790719567561, | |
| "eval_loss": 0.6259578466415405, | |
| "eval_runtime": 1306.1326, | |
| "eval_samples_per_second": 10.615, | |
| "eval_steps_per_second": 5.308, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.003340469791524317, | |
| "grad_norm": 0.5265600681304932, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6202, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0036441488634810734, | |
| "grad_norm": 0.6035001277923584, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5943, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00394782793543783, | |
| "grad_norm": 0.5358197689056396, | |
| "learning_rate": 0.0002, | |
| "loss": 0.575, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.004251507007394586, | |
| "grad_norm": 0.7852948904037476, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6843, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.004555186079351342, | |
| "grad_norm": 0.5582488179206848, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6097, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.004555186079351342, | |
| "eval_loss": 0.6131629347801208, | |
| "eval_runtime": 1306.016, | |
| "eval_samples_per_second": 10.616, | |
| "eval_steps_per_second": 5.309, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0048588651513080975, | |
| "grad_norm": 0.6850274801254272, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5936, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0051625442232648535, | |
| "grad_norm": 0.7021895051002502, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6144, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.005466223295221609, | |
| "grad_norm": 0.575738251209259, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6461, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.005769902367178366, | |
| "grad_norm": 0.6139180064201355, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5935, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.006073581439135122, | |
| "grad_norm": 0.534476101398468, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6254, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.006073581439135122, | |
| "eval_loss": 0.6035110354423523, | |
| "eval_runtime": 1305.0507, | |
| "eval_samples_per_second": 10.624, | |
| "eval_steps_per_second": 5.312, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.20957446930432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |