| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.983050847457627, | |
| "eval_steps": 1000, | |
| "global_step": 132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 7.197507381439209, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.1191, | |
| "num_input_tokens_seen": 43904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 6.066619873046875, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6537, | |
| "num_input_tokens_seen": 91264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 2.8696072101593018, | |
| "learning_rate": 4.9793066853402536e-05, | |
| "loss": 2.3123, | |
| "num_input_tokens_seen": 141184, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 1.9488307237625122, | |
| "learning_rate": 4.9175693119783013e-05, | |
| "loss": 1.7347, | |
| "num_input_tokens_seen": 186944, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5649717514124294, | |
| "grad_norm": 2.07496976852417, | |
| "learning_rate": 4.815809920628738e-05, | |
| "loss": 1.6167, | |
| "num_input_tokens_seen": 234496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.4913270473480225, | |
| "learning_rate": 4.6757131025753886e-05, | |
| "loss": 1.6705, | |
| "num_input_tokens_seen": 282432, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7909604519774012, | |
| "grad_norm": 1.5118441581726074, | |
| "learning_rate": 4.499598111849299e-05, | |
| "loss": 1.5204, | |
| "num_input_tokens_seen": 331648, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 1.1554917097091675, | |
| "learning_rate": 4.2903804707859835e-05, | |
| "loss": 1.4231, | |
| "num_input_tokens_seen": 377024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 1.4432414770126343, | |
| "learning_rate": 4.051523704568557e-05, | |
| "loss": 1.42, | |
| "num_input_tokens_seen": 424576, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "grad_norm": 1.4247018098831177, | |
| "learning_rate": 3.7869820037745776e-05, | |
| "loss": 1.451, | |
| "num_input_tokens_seen": 474816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2429378531073447, | |
| "grad_norm": 1.644587755203247, | |
| "learning_rate": 3.501134764128167e-05, | |
| "loss": 1.2046, | |
| "num_input_tokens_seen": 523392, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 1.6693050861358643, | |
| "learning_rate": 3.1987140871290236e-05, | |
| "loss": 1.3315, | |
| "num_input_tokens_seen": 567680, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4689265536723164, | |
| "grad_norm": 1.8458465337753296, | |
| "learning_rate": 2.884726441760155e-05, | |
| "loss": 1.2132, | |
| "num_input_tokens_seen": 610816, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.5819209039548023, | |
| "grad_norm": 1.5384082794189453, | |
| "learning_rate": 2.564369784137472e-05, | |
| "loss": 1.1863, | |
| "num_input_tokens_seen": 656640, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 1.7151033878326416, | |
| "learning_rate": 2.2429475071565987e-05, | |
| "loss": 1.2067, | |
| "num_input_tokens_seen": 705792, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.807909604519774, | |
| "grad_norm": 1.9599609375, | |
| "learning_rate": 1.9257806446705116e-05, | |
| "loss": 1.1691, | |
| "num_input_tokens_seen": 751232, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.92090395480226, | |
| "grad_norm": 1.5244255065917969, | |
| "learning_rate": 1.618119783627263e-05, | |
| "loss": 1.2593, | |
| "num_input_tokens_seen": 799552, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 1.6506624221801758, | |
| "learning_rate": 1.325058142431701e-05, | |
| "loss": 1.2249, | |
| "num_input_tokens_seen": 849408, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.146892655367232, | |
| "grad_norm": 1.7030749320983887, | |
| "learning_rate": 1.051447254488591e-05, | |
| "loss": 1.0921, | |
| "num_input_tokens_seen": 897024, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "grad_norm": 1.9787169694900513, | |
| "learning_rate": 8.018166527567672e-06, | |
| "loss": 1.1254, | |
| "num_input_tokens_seen": 943232, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": 2.088651418685913, | |
| "learning_rate": 5.8029888490850005e-06, | |
| "loss": 1.1332, | |
| "num_input_tokens_seen": 989824, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.4858757062146895, | |
| "grad_norm": 2.087944746017456, | |
| "learning_rate": 3.90561100442036e-06, | |
| "loss": 1.0718, | |
| "num_input_tokens_seen": 1036224, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.598870056497175, | |
| "grad_norm": 1.599670648574829, | |
| "learning_rate": 2.3574434229882145e-06, | |
| "loss": 1.2027, | |
| "num_input_tokens_seen": 1082368, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 1.867066740989685, | |
| "learning_rate": 1.1841154799154374e-06, | |
| "loss": 1.1742, | |
| "num_input_tokens_seen": 1131264, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.824858757062147, | |
| "grad_norm": 1.7015374898910522, | |
| "learning_rate": 4.050512106620913e-07, | |
| "loss": 1.1628, | |
| "num_input_tokens_seen": 1177472, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.937853107344633, | |
| "grad_norm": 1.7900928258895874, | |
| "learning_rate": 3.314775287923677e-08, | |
| "loss": 1.0574, | |
| "num_input_tokens_seen": 1224000, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "num_input_tokens_seen": 1245248, | |
| "step": 132, | |
| "total_flos": 7355069552918528.0, | |
| "train_loss": 1.5248766162178733, | |
| "train_runtime": 164.4609, | |
| "train_samples_per_second": 51.641, | |
| "train_steps_per_second": 0.803 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 132, | |
| "num_input_tokens_seen": 1245248, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7355069552918528.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |