25 lines
5.8 KiB
JSON
25 lines
5.8 KiB
JSON
{"loss": 0.94696367, "grad_norm": 10.80766191, "learning_rate": 2e-06, "epoch": 0.03375527, "global_step/max_steps": "1/90", "elapsed_time": "44s", "remaining_time": "1h 5m 10s", "memory(GiB)": 17.96, "train_speed(s/it)": 43.929015}
|
|
{"loss": 0.89637852, "grad_norm": 5.23729643, "learning_rate": 1e-05, "epoch": 0.16877637, "global_step/max_steps": "5/90", "elapsed_time": "3m 18s", "remaining_time": "56m 4s", "memory(GiB)": 21.81, "train_speed(s/it)": 39.574058}
|
|
{"loss": 0.66306291, "grad_norm": 1.78996602, "learning_rate": 9.91e-06, "epoch": 0.33755274, "global_step/max_steps": "10/90", "elapsed_time": "6m 31s", "remaining_time": "52m 11s", "memory(GiB)": 21.83, "train_speed(s/it)": 39.142172}
|
|
{"loss": 0.55667224, "grad_norm": 0.54444642, "learning_rate": 9.66e-06, "epoch": 0.50632911, "global_step/max_steps": "15/90", "elapsed_time": "9m 46s", "remaining_time": "48m 49s", "memory(GiB)": 21.83, "train_speed(s/it)": 39.046744}
|
|
{"loss": 0.51744814, "grad_norm": 0.38919769, "learning_rate": 9.25e-06, "epoch": 0.67510549, "global_step/max_steps": "20/90", "elapsed_time": "13m 1s", "remaining_time": "45m 32s", "memory(GiB)": 21.83, "train_speed(s/it)": 39.026535}
|
|
{"loss": 0.49224515, "grad_norm": 0.31310064, "learning_rate": 8.7e-06, "epoch": 0.84388186, "global_step/max_steps": "25/90", "elapsed_time": "16m 14s", "remaining_time": "42m 12s", "memory(GiB)": 21.83, "train_speed(s/it)": 38.955932}
|
|
{"loss": 0.46885357, "grad_norm": 0.30629433, "learning_rate": 8.01e-06, "epoch": 1.0, "global_step/max_steps": "30/90", "elapsed_time": "19m 11s", "remaining_time": "38m 22s", "memory(GiB)": 21.83, "train_speed(s/it)": 38.358525}
|
|
{"eval_loss": 0.46753064, "eval_runtime": 5.4529, "eval_samples_per_second": 3.301, "eval_steps_per_second": 0.55, "eval_token_acc": 0.8484247, "epoch": 1.0, "global_step/max_steps": "30/90", "elapsed_time": "19m 16s", "remaining_time": "38m 32s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.540582}
|
|
{"loss": 0.45065856, "grad_norm": 0.22479396, "learning_rate": 7.23e-06, "epoch": 1.16877637, "global_step/max_steps": "35/90", "elapsed_time": "22m 49s", "remaining_time": "35m 51s", "memory(GiB)": 55.62, "train_speed(s/it)": 39.100009}
|
|
{"loss": 0.43795571, "grad_norm": 0.20356846, "learning_rate": 6.37e-06, "epoch": 1.33755274, "global_step/max_steps": "40/90", "elapsed_time": "26m 0s", "remaining_time": "32m 30s", "memory(GiB)": 55.62, "train_speed(s/it)": 39.006631}
|
|
{"loss": 0.4316505, "grad_norm": 0.19121272, "learning_rate": 5.46e-06, "epoch": 1.50632911, "global_step/max_steps": "45/90", "elapsed_time": "29m 14s", "remaining_time": "29m 14s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.96686}
|
|
{"loss": 0.42470713, "grad_norm": 0.18818883, "learning_rate": 4.54e-06, "epoch": 1.67510549, "global_step/max_steps": "50/90", "elapsed_time": "32m 28s", "remaining_time": "25m 58s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.952706}
|
|
{"loss": 0.42790194, "grad_norm": 0.18066057, "learning_rate": 3.63e-06, "epoch": 1.84388186, "global_step/max_steps": "55/90", "elapsed_time": "35m 42s", "remaining_time": "22m 43s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.937328}
|
|
{"loss": 0.42041221, "grad_norm": 0.23693164, "learning_rate": 2.77e-06, "epoch": 2.0, "global_step/max_steps": "60/90", "elapsed_time": "38m 41s", "remaining_time": "19m 21s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.689141}
|
|
{"eval_loss": 0.42993364, "eval_runtime": 5.3207, "eval_samples_per_second": 3.383, "eval_steps_per_second": 0.564, "eval_token_acc": 0.85763245, "epoch": 2.0, "global_step/max_steps": "60/90", "elapsed_time": "38m 47s", "remaining_time": "19m 23s", "memory(GiB)": 55.62, "train_speed(s/it)": 38.777954}
|
|
{"loss": 0.40938077, "grad_norm": 0.17432324, "learning_rate": 1.99e-06, "epoch": 2.16877637, "global_step/max_steps": "65/90", "elapsed_time": "43m 43s", "remaining_time": "16m 49s", "memory(GiB)": 55.62, "train_speed(s/it)": 40.351087}
|
|
{"loss": 0.40886183, "grad_norm": 0.16575423, "learning_rate": 1.3e-06, "epoch": 2.33755274, "global_step/max_steps": "70/90", "elapsed_time": "46m 56s", "remaining_time": "13m 25s", "memory(GiB)": 55.62, "train_speed(s/it)": 40.233402}
|
|
{"loss": 0.40611558, "grad_norm": 0.16679633, "learning_rate": 7.5e-07, "epoch": 2.50632911, "global_step/max_steps": "75/90", "elapsed_time": "50m 11s", "remaining_time": "10m 2s", "memory(GiB)": 55.62, "train_speed(s/it)": 40.143103}
|
|
{"loss": 0.40422888, "grad_norm": 0.17272271, "learning_rate": 3.4e-07, "epoch": 2.67510549, "global_step/max_steps": "80/90", "elapsed_time": "53m 22s", "remaining_time": "6m 40s", "memory(GiB)": 55.62, "train_speed(s/it)": 40.031174}
|
|
{"loss": 0.40749974, "grad_norm": 0.15805759, "learning_rate": 9e-08, "epoch": 2.84388186, "global_step/max_steps": "85/90", "elapsed_time": "56m 37s", "remaining_time": "3m 20s", "memory(GiB)": 55.62, "train_speed(s/it)": 39.959604}
|
|
{"loss": 0.41116924, "grad_norm": 0.22612395, "learning_rate": 0.0, "epoch": 3.0, "global_step/max_steps": "90/90", "elapsed_time": "59m 34s", "remaining_time": "0s", "memory(GiB)": 55.62, "train_speed(s/it)": 39.70667}
|
|
{"eval_loss": 0.42552102, "eval_runtime": 5.3859, "eval_samples_per_second": 3.342, "eval_steps_per_second": 0.557, "eval_token_acc": 0.85888424, "epoch": 3.0, "global_step/max_steps": "90/90", "elapsed_time": "59m 39s", "remaining_time": "0s", "memory(GiB)": 55.62, "train_speed(s/it)": 39.766603}
|
|
{"eval_loss": 0.42552102, "eval_runtime": 5.9515, "eval_samples_per_second": 3.024, "eval_steps_per_second": 0.504, "eval_token_acc": 0.85888424, "epoch": 3.0, "global_step/max_steps": "90/90", "elapsed_time": "1h 1m 26s", "remaining_time": "0s", "memory(GiB)": 55.62, "train_speed(s/it)": 40.950729}
|
|
{"train_runtime": 3758.6222, "train_samples_per_second": 1.517, "train_steps_per_second": 0.024, "total_flos": 165454361657344.0, "train_loss": 0.48029553, "epoch": 3.0, "global_step/max_steps": "90/90", "elapsed_time": "1h 2m 36s", "remaining_time": "0s", "memory(GiB)": 55.62, "train_speed(s/it)": 41.738349}
|