| { | |
| "best_metric": 2.3539514541625977, | |
| "best_model_checkpoint": "desarrolloasesoreslocales/legal-mistral/checkpoint-170", | |
| "epoch": 3.0, | |
| "eval_steps": 10, | |
| "global_step": 174, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.885057471264368e-05, | |
| "loss": 2.4243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.5809202194213867, | |
| "eval_runtime": 79.9298, | |
| "eval_samples_per_second": 11.623, | |
| "eval_steps_per_second": 1.464, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.770114942528736e-05, | |
| "loss": 2.32, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 2.5187058448791504, | |
| "eval_runtime": 79.9944, | |
| "eval_samples_per_second": 11.613, | |
| "eval_steps_per_second": 1.463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6551724137931037e-05, | |
| "loss": 2.2652, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 2.479558229446411, | |
| "eval_runtime": 79.9192, | |
| "eval_samples_per_second": 11.624, | |
| "eval_steps_per_second": 1.464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.540229885057471e-05, | |
| "loss": 2.2424, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 2.449814796447754, | |
| "eval_runtime": 80.3275, | |
| "eval_samples_per_second": 11.565, | |
| "eval_steps_per_second": 1.457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4252873563218392e-05, | |
| "loss": 2.1759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 2.430422782897949, | |
| "eval_runtime": 80.3296, | |
| "eval_samples_per_second": 11.565, | |
| "eval_steps_per_second": 1.456, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.310344827586207e-05, | |
| "loss": 2.1698, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 2.4160897731781006, | |
| "eval_runtime": 79.8167, | |
| "eval_samples_per_second": 11.639, | |
| "eval_steps_per_second": 1.466, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.1954022988505748e-05, | |
| "loss": 2.1337, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 2.40354585647583, | |
| "eval_runtime": 79.8387, | |
| "eval_samples_per_second": 11.636, | |
| "eval_steps_per_second": 1.465, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.0804597701149427e-05, | |
| "loss": 2.1193, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 2.3962202072143555, | |
| "eval_runtime": 79.8113, | |
| "eval_samples_per_second": 11.64, | |
| "eval_steps_per_second": 1.466, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.655172413793105e-06, | |
| "loss": 2.0928, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 2.3851864337921143, | |
| "eval_runtime": 79.8078, | |
| "eval_samples_per_second": 11.64, | |
| "eval_steps_per_second": 1.466, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.505747126436782e-06, | |
| "loss": 2.1072, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 2.376269817352295, | |
| "eval_runtime": 79.9299, | |
| "eval_samples_per_second": 11.623, | |
| "eval_steps_per_second": 1.464, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.35632183908046e-06, | |
| "loss": 2.0701, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 2.3708786964416504, | |
| "eval_runtime": 79.9941, | |
| "eval_samples_per_second": 11.613, | |
| "eval_steps_per_second": 1.463, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.206896551724138e-06, | |
| "loss": 2.0584, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 2.3670151233673096, | |
| "eval_runtime": 80.0335, | |
| "eval_samples_per_second": 11.608, | |
| "eval_steps_per_second": 1.462, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.057471264367817e-06, | |
| "loss": 2.0569, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 2.3638148307800293, | |
| "eval_runtime": 80.0359, | |
| "eval_samples_per_second": 11.607, | |
| "eval_steps_per_second": 1.462, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.908045977011495e-06, | |
| "loss": 2.0396, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 2.3619213104248047, | |
| "eval_runtime": 80.0238, | |
| "eval_samples_per_second": 11.609, | |
| "eval_steps_per_second": 1.462, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7586206896551725e-06, | |
| "loss": 2.0406, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 2.3583548069000244, | |
| "eval_runtime": 80.0658, | |
| "eval_samples_per_second": 11.603, | |
| "eval_steps_per_second": 1.461, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.6091954022988506e-06, | |
| "loss": 2.0259, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 2.3552348613739014, | |
| "eval_runtime": 80.0434, | |
| "eval_samples_per_second": 11.606, | |
| "eval_steps_per_second": 1.462, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 4.5977011494252875e-07, | |
| "loss": 2.0492, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 2.3539514541625977, | |
| "eval_runtime": 80.0092, | |
| "eval_samples_per_second": 11.611, | |
| "eval_steps_per_second": 1.462, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 174, | |
| "total_flos": 7.500749066993664e+16, | |
| "train_loss": 2.138888589267073, | |
| "train_runtime": 4525.1585, | |
| "train_samples_per_second": 3.032, | |
| "train_steps_per_second": 0.038 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.3539514541625977, | |
| "eval_runtime": 80.117, | |
| "eval_samples_per_second": 11.596, | |
| "eval_steps_per_second": 1.46, | |
| "step": 174 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 174, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "total_flos": 7.500749066993664e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |