prxy5608's picture
Training in progress, step 50, checkpoint
84baf9d verified
raw
history blame
9.75 kB
{
"best_metric": 1.0066642761230469,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.09090909090909091,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0018181818181818182,
"grad_norm": 138.68397521972656,
"learning_rate": 5e-06,
"loss": 14.5689,
"step": 1
},
{
"epoch": 0.0018181818181818182,
"eval_loss": 4.257202625274658,
"eval_runtime": 15.5048,
"eval_samples_per_second": 59.788,
"eval_steps_per_second": 29.926,
"step": 1
},
{
"epoch": 0.0036363636363636364,
"grad_norm": 122.03857421875,
"learning_rate": 1e-05,
"loss": 15.5416,
"step": 2
},
{
"epoch": 0.005454545454545455,
"grad_norm": 139.68202209472656,
"learning_rate": 1.5e-05,
"loss": 16.1754,
"step": 3
},
{
"epoch": 0.007272727272727273,
"grad_norm": 154.2438507080078,
"learning_rate": 2e-05,
"loss": 15.2385,
"step": 4
},
{
"epoch": 0.00909090909090909,
"grad_norm": 146.93878173828125,
"learning_rate": 2.5e-05,
"loss": 15.5613,
"step": 5
},
{
"epoch": 0.01090909090909091,
"grad_norm": 120.0749282836914,
"learning_rate": 3e-05,
"loss": 14.4842,
"step": 6
},
{
"epoch": 0.012727272727272728,
"grad_norm": 126.85943603515625,
"learning_rate": 3.5e-05,
"loss": 13.4979,
"step": 7
},
{
"epoch": 0.014545454545454545,
"grad_norm": 175.2422637939453,
"learning_rate": 4e-05,
"loss": 12.2678,
"step": 8
},
{
"epoch": 0.016363636363636365,
"grad_norm": 129.5550537109375,
"learning_rate": 4.5e-05,
"loss": 11.7683,
"step": 9
},
{
"epoch": 0.01818181818181818,
"grad_norm": 114.66398620605469,
"learning_rate": 5e-05,
"loss": 10.7645,
"step": 10
},
{
"epoch": 0.02,
"grad_norm": 109.88460540771484,
"learning_rate": 5.500000000000001e-05,
"loss": 9.8579,
"step": 11
},
{
"epoch": 0.02181818181818182,
"grad_norm": 122.863037109375,
"learning_rate": 6e-05,
"loss": 9.304,
"step": 12
},
{
"epoch": 0.023636363636363636,
"grad_norm": 123.73020935058594,
"learning_rate": 6.500000000000001e-05,
"loss": 8.3192,
"step": 13
},
{
"epoch": 0.025454545454545455,
"grad_norm": 147.00076293945312,
"learning_rate": 7e-05,
"loss": 7.907,
"step": 14
},
{
"epoch": 0.02727272727272727,
"grad_norm": 338.5273132324219,
"learning_rate": 7.500000000000001e-05,
"loss": 8.9278,
"step": 15
},
{
"epoch": 0.02909090909090909,
"grad_norm": 143.44017028808594,
"learning_rate": 8e-05,
"loss": 7.7997,
"step": 16
},
{
"epoch": 0.03090909090909091,
"grad_norm": 175.75901794433594,
"learning_rate": 8.5e-05,
"loss": 7.0567,
"step": 17
},
{
"epoch": 0.03272727272727273,
"grad_norm": 161.01739501953125,
"learning_rate": 9e-05,
"loss": 7.9452,
"step": 18
},
{
"epoch": 0.034545454545454546,
"grad_norm": 217.87303161621094,
"learning_rate": 9.5e-05,
"loss": 8.277,
"step": 19
},
{
"epoch": 0.03636363636363636,
"grad_norm": 193.74627685546875,
"learning_rate": 0.0001,
"loss": 7.6536,
"step": 20
},
{
"epoch": 0.038181818181818185,
"grad_norm": 253.91064453125,
"learning_rate": 9.999238475781957e-05,
"loss": 6.6774,
"step": 21
},
{
"epoch": 0.04,
"grad_norm": 213.30625915527344,
"learning_rate": 9.99695413509548e-05,
"loss": 6.5032,
"step": 22
},
{
"epoch": 0.04181818181818182,
"grad_norm": 161.59420776367188,
"learning_rate": 9.99314767377287e-05,
"loss": 6.4562,
"step": 23
},
{
"epoch": 0.04363636363636364,
"grad_norm": 163.30369567871094,
"learning_rate": 9.987820251299122e-05,
"loss": 6.051,
"step": 24
},
{
"epoch": 0.045454545454545456,
"grad_norm": 164.57496643066406,
"learning_rate": 9.980973490458728e-05,
"loss": 5.5738,
"step": 25
},
{
"epoch": 0.04727272727272727,
"grad_norm": 137.8650360107422,
"learning_rate": 9.972609476841367e-05,
"loss": 5.9991,
"step": 26
},
{
"epoch": 0.04909090909090909,
"grad_norm": 147.88990783691406,
"learning_rate": 9.962730758206611e-05,
"loss": 5.2916,
"step": 27
},
{
"epoch": 0.05090909090909091,
"grad_norm": 175.40298461914062,
"learning_rate": 9.951340343707852e-05,
"loss": 5.123,
"step": 28
},
{
"epoch": 0.05272727272727273,
"grad_norm": 143.73516845703125,
"learning_rate": 9.938441702975689e-05,
"loss": 4.696,
"step": 29
},
{
"epoch": 0.05454545454545454,
"grad_norm": 162.42837524414062,
"learning_rate": 9.924038765061042e-05,
"loss": 4.4559,
"step": 30
},
{
"epoch": 0.056363636363636366,
"grad_norm": 138.40577697753906,
"learning_rate": 9.908135917238321e-05,
"loss": 5.1119,
"step": 31
},
{
"epoch": 0.05818181818181818,
"grad_norm": 152.168212890625,
"learning_rate": 9.890738003669029e-05,
"loss": 4.7344,
"step": 32
},
{
"epoch": 0.06,
"grad_norm": 221.61441040039062,
"learning_rate": 9.871850323926177e-05,
"loss": 4.8725,
"step": 33
},
{
"epoch": 0.06181818181818182,
"grad_norm": 134.0053253173828,
"learning_rate": 9.851478631379982e-05,
"loss": 4.1396,
"step": 34
},
{
"epoch": 0.06363636363636363,
"grad_norm": 169.15768432617188,
"learning_rate": 9.829629131445342e-05,
"loss": 4.7024,
"step": 35
},
{
"epoch": 0.06545454545454546,
"grad_norm": 295.5130310058594,
"learning_rate": 9.806308479691595e-05,
"loss": 4.3401,
"step": 36
},
{
"epoch": 0.06727272727272728,
"grad_norm": 170.70733642578125,
"learning_rate": 9.781523779815179e-05,
"loss": 5.3419,
"step": 37
},
{
"epoch": 0.06909090909090909,
"grad_norm": 150.62545776367188,
"learning_rate": 9.755282581475769e-05,
"loss": 4.5806,
"step": 38
},
{
"epoch": 0.07090909090909091,
"grad_norm": 159.96763610839844,
"learning_rate": 9.727592877996585e-05,
"loss": 4.1185,
"step": 39
},
{
"epoch": 0.07272727272727272,
"grad_norm": 145.9441680908203,
"learning_rate": 9.698463103929542e-05,
"loss": 4.1673,
"step": 40
},
{
"epoch": 0.07454545454545454,
"grad_norm": 107.2767333984375,
"learning_rate": 9.667902132486009e-05,
"loss": 4.7757,
"step": 41
},
{
"epoch": 0.07636363636363637,
"grad_norm": 204.49026489257812,
"learning_rate": 9.635919272833938e-05,
"loss": 4.7596,
"step": 42
},
{
"epoch": 0.07818181818181819,
"grad_norm": 115.9788818359375,
"learning_rate": 9.602524267262203e-05,
"loss": 5.3676,
"step": 43
},
{
"epoch": 0.08,
"grad_norm": 70.77046966552734,
"learning_rate": 9.567727288213005e-05,
"loss": 3.8195,
"step": 44
},
{
"epoch": 0.08181818181818182,
"grad_norm": 74.69246673583984,
"learning_rate": 9.53153893518325e-05,
"loss": 4.8097,
"step": 45
},
{
"epoch": 0.08363636363636363,
"grad_norm": 90.72003173828125,
"learning_rate": 9.493970231495835e-05,
"loss": 5.028,
"step": 46
},
{
"epoch": 0.08545454545454545,
"grad_norm": 85.53260803222656,
"learning_rate": 9.45503262094184e-05,
"loss": 4.1861,
"step": 47
},
{
"epoch": 0.08727272727272728,
"grad_norm": 90.01811981201172,
"learning_rate": 9.414737964294636e-05,
"loss": 4.2923,
"step": 48
},
{
"epoch": 0.0890909090909091,
"grad_norm": 103.90205383300781,
"learning_rate": 9.373098535696979e-05,
"loss": 4.0331,
"step": 49
},
{
"epoch": 0.09090909090909091,
"grad_norm": 54.6790657043457,
"learning_rate": 9.330127018922194e-05,
"loss": 5.0269,
"step": 50
},
{
"epoch": 0.09090909090909091,
"eval_loss": 1.0066642761230469,
"eval_runtime": 15.4751,
"eval_samples_per_second": 59.903,
"eval_steps_per_second": 29.984,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3725608982937600.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}