{
"best_metric": 2.588986396789551,
"best_model_checkpoint": "output/radiohead/checkpoint-240",
"epoch": 8.0,
"global_step": 240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.17,
"learning_rate": 0.0001280093426996125,
"loss": 3.2073,
"step": 5
},
{
"epoch": 0.33,
"learning_rate": 0.00010290000000000001,
"loss": 2.9899,
"step": 10
},
{
"epoch": 0.5,
"learning_rate": 6.86e-05,
"loss": 2.8292,
"step": 15
},
{
"epoch": 0.67,
"learning_rate": 3.4300000000000014e-05,
"loss": 2.8291,
"step": 20
},
{
"epoch": 0.83,
"learning_rate": 9.190657300387505e-06,
"loss": 2.8479,
"step": 25
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 2.9261,
"step": 30
},
{
"epoch": 1.0,
"eval_loss": 2.8060529232025146,
"eval_runtime": 2.0848,
"eval_samples_per_second": 22.545,
"eval_steps_per_second": 2.878,
"step": 30
},
{
"epoch": 1.17,
"learning_rate": 9.190657300387513e-06,
"loss": 2.6517,
"step": 35
},
{
"epoch": 1.33,
"learning_rate": 3.429999999999997e-05,
"loss": 2.7329,
"step": 40
},
{
"epoch": 1.5,
"learning_rate": 6.859999999999999e-05,
"loss": 2.7524,
"step": 45
},
{
"epoch": 1.67,
"learning_rate": 0.00010290000000000001,
"loss": 2.5591,
"step": 50
},
{
"epoch": 1.83,
"learning_rate": 0.00012800934269961248,
"loss": 2.6201,
"step": 55
},
{
"epoch": 2.0,
"learning_rate": 0.0001372,
"loss": 2.5207,
"step": 60
},
{
"epoch": 2.0,
"eval_loss": 2.7088782787323,
"eval_runtime": 2.1182,
"eval_samples_per_second": 22.189,
"eval_steps_per_second": 2.833,
"step": 60
},
{
"epoch": 2.17,
"learning_rate": 0.00012800934269961253,
"loss": 2.3985,
"step": 65
},
{
"epoch": 2.33,
"learning_rate": 0.00010289999999999998,
"loss": 2.3027,
"step": 70
},
{
"epoch": 2.5,
"learning_rate": 6.860000000000001e-05,
"loss": 2.1903,
"step": 75
},
{
"epoch": 2.67,
"learning_rate": 3.4300000000000054e-05,
"loss": 2.2458,
"step": 80
},
{
"epoch": 2.83,
"learning_rate": 9.190657300387498e-06,
"loss": 2.2898,
"step": 85
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 2.2945,
"step": 90
},
{
"epoch": 3.0,
"eval_loss": 2.6637511253356934,
"eval_runtime": 2.1338,
"eval_samples_per_second": 22.027,
"eval_steps_per_second": 2.812,
"step": 90
},
{
"epoch": 3.17,
"learning_rate": 9.190657300387474e-06,
"loss": 2.1611,
"step": 95
},
{
"epoch": 3.33,
"learning_rate": 3.4300000000000014e-05,
"loss": 2.0392,
"step": 100
},
{
"epoch": 3.5,
"learning_rate": 6.859999999999997e-05,
"loss": 2.3157,
"step": 105
},
{
"epoch": 3.67,
"learning_rate": 0.00010289999999999994,
"loss": 2.1789,
"step": 110
},
{
"epoch": 3.83,
"learning_rate": 0.0001280093426996125,
"loss": 2.1359,
"step": 115
},
{
"epoch": 4.0,
"learning_rate": 0.0001372,
"loss": 2.0964,
"step": 120
},
{
"epoch": 4.0,
"eval_loss": 2.617748737335205,
"eval_runtime": 2.1438,
"eval_samples_per_second": 21.924,
"eval_steps_per_second": 2.799,
"step": 120
},
{
"epoch": 4.17,
"learning_rate": 0.00012800934269961248,
"loss": 1.8717,
"step": 125
},
{
"epoch": 4.33,
"learning_rate": 0.00010290000000000009,
"loss": 1.9838,
"step": 130
},
{
"epoch": 4.5,
"learning_rate": 6.860000000000003e-05,
"loss": 2.0446,
"step": 135
},
{
"epoch": 4.67,
"learning_rate": 3.429999999999996e-05,
"loss": 1.8428,
"step": 140
},
{
"epoch": 4.83,
"learning_rate": 9.190657300387574e-06,
"loss": 1.9594,
"step": 145
},
{
"epoch": 5.0,
"learning_rate": 0.0,
"loss": 2.0192,
"step": 150
},
{
"epoch": 5.0,
"eval_loss": 2.6335015296936035,
"eval_runtime": 2.1534,
"eval_samples_per_second": 21.826,
"eval_steps_per_second": 2.786,
"step": 150
},
{
"epoch": 5.17,
"learning_rate": 9.190657300387467e-06,
"loss": 1.7401,
"step": 155
},
{
"epoch": 5.33,
"learning_rate": 3.429999999999989e-05,
"loss": 1.8589,
"step": 160
},
{
"epoch": 5.5,
"learning_rate": 6.859999999999984e-05,
"loss": 1.7454,
"step": 165
},
{
"epoch": 5.67,
"learning_rate": 0.00010290000000000003,
"loss": 1.8506,
"step": 170
},
{
"epoch": 5.83,
"learning_rate": 0.00012800934269961248,
"loss": 1.7711,
"step": 175
},
{
"epoch": 6.0,
"learning_rate": 0.0001372,
"loss": 1.6952,
"step": 180
},
{
"epoch": 6.0,
"eval_loss": 2.604886293411255,
"eval_runtime": 2.1277,
"eval_samples_per_second": 22.09,
"eval_steps_per_second": 2.82,
"step": 180
},
{
"epoch": 6.17,
"learning_rate": 0.00012800934269961253,
"loss": 1.7717,
"step": 185
},
{
"epoch": 6.33,
"learning_rate": 0.00010290000000000012,
"loss": 1.577,
"step": 190
},
{
"epoch": 6.5,
"learning_rate": 6.859999999999993e-05,
"loss": 1.5197,
"step": 195
},
{
"epoch": 6.67,
"learning_rate": 3.429999999999998e-05,
"loss": 1.6176,
"step": 200
},
{
"epoch": 6.83,
"learning_rate": 9.19065730038752e-06,
"loss": 1.562,
"step": 205
},
{
"epoch": 7.0,
"learning_rate": 0.0,
"loss": 1.6157,
"step": 210
},
{
"epoch": 7.0,
"eval_loss": 2.6068503856658936,
"eval_runtime": 2.1309,
"eval_samples_per_second": 22.056,
"eval_steps_per_second": 2.816,
"step": 210
},
{
"epoch": 7.17,
"learning_rate": 9.190657300387459e-06,
"loss": 1.5445,
"step": 215
},
{
"epoch": 7.33,
"learning_rate": 3.429999999999988e-05,
"loss": 1.5187,
"step": 220
},
{
"epoch": 7.5,
"learning_rate": 6.859999999999982e-05,
"loss": 1.4775,
"step": 225
},
{
"epoch": 7.67,
"learning_rate": 0.00010290000000000002,
"loss": 1.3245,
"step": 230
},
{
"epoch": 7.83,
"learning_rate": 0.00012800934269961248,
"loss": 1.6077,
"step": 235
},
{
"epoch": 8.0,
"learning_rate": 0.0001372,
"loss": 1.5085,
"step": 240
},
{
"epoch": 8.0,
"eval_loss": 2.588986396789551,
"eval_runtime": 2.1323,
"eval_samples_per_second": 22.042,
"eval_steps_per_second": 2.814,
"step": 240
}
],
"max_steps": 300,
"num_train_epochs": 10,
"total_flos": 243524173824000.0,
"trial_name": null,
"trial_params": null
}