File size: 3,158 Bytes
f92112c fa65238 f92112c dcd0792 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c fa65238 f92112c f5735e5 fa65238 f5735e5 fa65238 f5735e5 fa65238 f5735e5 fa65238 f5735e5 fa65238 f5735e5 fa65238 f5735e5 fa65238 f5735e5 4e027ff fa65238 4e027ff fa65238 4e027ff fa65238 4e027ff fa65238 4e027ff dcd0792 fa65238 dcd0792 f92112c dcd0792 f92112c fa65238 f92112c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05383580080753701,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005383580080753701,
"grad_norm": 1.332345962524414,
"learning_rate": 2e-05,
"loss": 0.7345,
"step": 1
},
{
"epoch": 0.005383580080753701,
"eval_loss": 0.7382340431213379,
"eval_runtime": 7.7076,
"eval_samples_per_second": 10.25,
"eval_steps_per_second": 5.19,
"step": 1
},
{
"epoch": 0.010767160161507403,
"grad_norm": 1.5144602060317993,
"learning_rate": 4e-05,
"loss": 0.7732,
"step": 2
},
{
"epoch": 0.016150740242261104,
"grad_norm": 1.4010770320892334,
"learning_rate": 6e-05,
"loss": 0.7996,
"step": 3
},
{
"epoch": 0.016150740242261104,
"eval_loss": 0.6860002279281616,
"eval_runtime": 7.8686,
"eval_samples_per_second": 10.04,
"eval_steps_per_second": 5.083,
"step": 3
},
{
"epoch": 0.021534320323014805,
"grad_norm": 1.2587902545928955,
"learning_rate": 8e-05,
"loss": 0.665,
"step": 4
},
{
"epoch": 0.026917900403768506,
"grad_norm": 1.1400635242462158,
"learning_rate": 0.0001,
"loss": 0.6649,
"step": 5
},
{
"epoch": 0.03230148048452221,
"grad_norm": 0.9094105362892151,
"learning_rate": 0.00012,
"loss": 0.5525,
"step": 6
},
{
"epoch": 0.03230148048452221,
"eval_loss": 0.5270073413848877,
"eval_runtime": 7.7898,
"eval_samples_per_second": 10.141,
"eval_steps_per_second": 5.135,
"step": 6
},
{
"epoch": 0.03768506056527591,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.5412,
"step": 7
},
{
"epoch": 0.04306864064602961,
"grad_norm": 0.9600444436073303,
"learning_rate": 0.00014,
"loss": 0.6705,
"step": 8
},
{
"epoch": 0.04845222072678331,
"grad_norm": 1.114023208618164,
"learning_rate": 0.00016,
"loss": 0.4857,
"step": 9
},
{
"epoch": 0.04845222072678331,
"eval_loss": 0.424485981464386,
"eval_runtime": 7.7991,
"eval_samples_per_second": 10.129,
"eval_steps_per_second": 5.129,
"step": 9
},
{
"epoch": 0.05383580080753701,
"grad_norm": 0.8380860686302185,
"learning_rate": 0.00018,
"loss": 0.383,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4716388916658176.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|