| { |
| "best_global_step": 150, |
| "best_metric": 1.1094907522201538, |
| "best_model_checkpoint": "mistral-7b-frlegal-lora/checkpoint-100", |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 255, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11834319526627218, |
| "grad_norm": 3.7848479747772217, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 2.8047, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.23668639053254437, |
| "grad_norm": 3.650196075439453, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 1.8139, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.35502958579881655, |
| "grad_norm": 4.603827476501465, |
| "learning_rate": 0.00019912663755458515, |
| "loss": 1.5624, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.47337278106508873, |
| "grad_norm": 3.440032482147217, |
| "learning_rate": 0.0001903930131004367, |
| "loss": 1.3397, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.591715976331361, |
| "grad_norm": 4.5781025886535645, |
| "learning_rate": 0.00018165938864628822, |
| "loss": 1.2809, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.591715976331361, |
| "eval_loss": 1.2312296628952026, |
| "eval_runtime": 60.6234, |
| "eval_samples_per_second": 2.788, |
| "eval_steps_per_second": 1.402, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7100591715976331, |
| "grad_norm": 3.0015316009521484, |
| "learning_rate": 0.00017292576419213976, |
| "loss": 1.1795, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.8284023668639053, |
| "grad_norm": 2.660057544708252, |
| "learning_rate": 0.00016419213973799127, |
| "loss": 1.0804, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.9467455621301775, |
| "grad_norm": 2.6601247787475586, |
| "learning_rate": 0.0001554585152838428, |
| "loss": 1.1704, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0591715976331362, |
| "grad_norm": 2.8257343769073486, |
| "learning_rate": 0.00014672489082969434, |
| "loss": 0.9553, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.1775147928994083, |
| "grad_norm": 2.2877657413482666, |
| "learning_rate": 0.00013799126637554588, |
| "loss": 0.8022, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.1775147928994083, |
| "eval_loss": 1.1341192722320557, |
| "eval_runtime": 60.7323, |
| "eval_samples_per_second": 2.783, |
| "eval_steps_per_second": 1.4, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.2958579881656804, |
| "grad_norm": 2.4518744945526123, |
| "learning_rate": 0.00012925764192139738, |
| "loss": 0.7463, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.4142011834319526, |
| "grad_norm": 2.634495735168457, |
| "learning_rate": 0.0001205240174672489, |
| "loss": 0.7574, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.532544378698225, |
| "grad_norm": 2.428051710128784, |
| "learning_rate": 0.00011179039301310044, |
| "loss": 0.7658, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.650887573964497, |
| "grad_norm": 2.903827667236328, |
| "learning_rate": 0.00010305676855895196, |
| "loss": 0.7334, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.7692307692307692, |
| "grad_norm": 2.4579429626464844, |
| "learning_rate": 9.43231441048035e-05, |
| "loss": 0.7041, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7692307692307692, |
| "eval_loss": 1.1094907522201538, |
| "eval_runtime": 60.6543, |
| "eval_samples_per_second": 2.786, |
| "eval_steps_per_second": 1.401, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.8875739644970415, |
| "grad_norm": 2.4557547569274902, |
| "learning_rate": 8.558951965065502e-05, |
| "loss": 0.7263, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.915830135345459, |
| "learning_rate": 7.685589519650656e-05, |
| "loss": 0.784, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.1183431952662723, |
| "grad_norm": 3.7625837326049805, |
| "learning_rate": 6.812227074235808e-05, |
| "loss": 0.4613, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.2366863905325443, |
| "grad_norm": 2.049013376235962, |
| "learning_rate": 5.9388646288209616e-05, |
| "loss": 0.4533, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.3550295857988166, |
| "grad_norm": 1.8300621509552002, |
| "learning_rate": 5.065502183406113e-05, |
| "loss": 0.456, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.3550295857988166, |
| "eval_loss": 1.1557873487472534, |
| "eval_runtime": 60.6355, |
| "eval_samples_per_second": 2.787, |
| "eval_steps_per_second": 1.402, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.4733727810650885, |
| "grad_norm": 1.6030356884002686, |
| "learning_rate": 4.192139737991266e-05, |
| "loss": 0.4833, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.591715976331361, |
| "grad_norm": 2.6860575675964355, |
| "learning_rate": 3.3187772925764197e-05, |
| "loss": 0.5044, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.710059171597633, |
| "grad_norm": 2.007375955581665, |
| "learning_rate": 2.445414847161572e-05, |
| "loss": 0.4456, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.828402366863905, |
| "grad_norm": 1.3755784034729004, |
| "learning_rate": 1.572052401746725e-05, |
| "loss": 0.4325, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.9467455621301775, |
| "grad_norm": 2.183783769607544, |
| "learning_rate": 6.986899563318778e-06, |
| "loss": 0.4677, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.9467455621301775, |
| "eval_loss": 1.1586920022964478, |
| "eval_runtime": 60.6003, |
| "eval_samples_per_second": 2.789, |
| "eval_steps_per_second": 1.403, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 255, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8132308222967808.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
