Commit
•
89524e5
1
Parent(s):
59639c2
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +125 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9388753056234719,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07823960880195599,
|
| 13 |
+
"grad_norm": 339.19366455078125,
|
| 14 |
+
"learning_rate": 1.5e-06,
|
| 15 |
+
"loss": 1.7327,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15647921760391198,
|
| 20 |
+
"grad_norm": 343.84027099609375,
|
| 21 |
+
"learning_rate": 3e-06,
|
| 22 |
+
"loss": 1.6942,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23471882640586797,
|
| 27 |
+
"grad_norm": 55.34988784790039,
|
| 28 |
+
"learning_rate": 4.5e-06,
|
| 29 |
+
"loss": 0.2441,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.31295843520782396,
|
| 34 |
+
"grad_norm": 22.917522430419922,
|
| 35 |
+
"learning_rate": 6e-06,
|
| 36 |
+
"loss": 0.0951,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.39119804400978,
|
| 41 |
+
"grad_norm": 4.5077643394470215,
|
| 42 |
+
"learning_rate": 7.5e-06,
|
| 43 |
+
"loss": 0.0653,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46943765281173594,
|
| 48 |
+
"grad_norm": 16.18638801574707,
|
| 49 |
+
"learning_rate": 9e-06,
|
| 50 |
+
"loss": 0.1845,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5476772616136919,
|
| 55 |
+
"grad_norm": 3.779344081878662,
|
| 56 |
+
"learning_rate": 1.05e-05,
|
| 57 |
+
"loss": 0.0566,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6259168704156479,
|
| 62 |
+
"grad_norm": 2.3550302982330322,
|
| 63 |
+
"learning_rate": 1.2e-05,
|
| 64 |
+
"loss": 0.0463,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7041564792176039,
|
| 69 |
+
"grad_norm": 3.7851593494415283,
|
| 70 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 71 |
+
"loss": 0.0531,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.78239608801956,
|
| 76 |
+
"grad_norm": 5.353140354156494,
|
| 77 |
+
"learning_rate": 1.5e-05,
|
| 78 |
+
"loss": 0.0633,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8606356968215159,
|
| 83 |
+
"grad_norm": 3.454190969467163,
|
| 84 |
+
"learning_rate": 1.65e-05,
|
| 85 |
+
"loss": 0.0633,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9388753056234719,
|
| 90 |
+
"grad_norm": 8.502099990844727,
|
| 91 |
+
"learning_rate": 1.8e-05,
|
| 92 |
+
"loss": 0.0409,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.9388753056234719,
|
| 97 |
+
"eval_loss": 0.041706331074237823,
|
| 98 |
+
"eval_runtime": 69.2407,
|
| 99 |
+
"eval_samples_per_second": 1.314,
|
| 100 |
+
"eval_steps_per_second": 1.314,
|
| 101 |
+
"step": 12
|
| 102 |
+
}
|
| 103 |
+
],
|
| 104 |
+
"logging_steps": 1,
|
| 105 |
+
"max_steps": 36,
|
| 106 |
+
"num_input_tokens_seen": 0,
|
| 107 |
+
"num_train_epochs": 3,
|
| 108 |
+
"save_steps": 500,
|
| 109 |
+
"stateful_callbacks": {
|
| 110 |
+
"TrainerControl": {
|
| 111 |
+
"args": {
|
| 112 |
+
"should_epoch_stop": false,
|
| 113 |
+
"should_evaluate": false,
|
| 114 |
+
"should_log": false,
|
| 115 |
+
"should_save": true,
|
| 116 |
+
"should_training_stop": false
|
| 117 |
+
},
|
| 118 |
+
"attributes": {}
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"total_flos": 2.4308284688464896e+16,
|
| 122 |
+
"train_batch_size": 1,
|
| 123 |
+
"trial_name": null,
|
| 124 |
+
"trial_params": null
|
| 125 |
+
}
|