Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +173 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.3823704586063132,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11911852293031566,
|
| 13 |
+
"grad_norm": 0.3590008318424225,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 0.7627,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.23823704586063132,
|
| 20 |
+
"grad_norm": 0.5137978196144104,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 0.6067,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.357355568790947,
|
| 27 |
+
"grad_norm": 0.46571800112724304,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 0.5131,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.47647409172126265,
|
| 34 |
+
"grad_norm": 0.48380178213119507,
|
| 35 |
+
"learning_rate": 4.957432749209755e-05,
|
| 36 |
+
"loss": 0.4791,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5955926146515783,
|
| 41 |
+
"grad_norm": 0.5578784942626953,
|
| 42 |
+
"learning_rate": 4.8311805735108894e-05,
|
| 43 |
+
"loss": 0.4766,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.714711137581894,
|
| 48 |
+
"grad_norm": 0.4985765516757965,
|
| 49 |
+
"learning_rate": 4.625542839324036e-05,
|
| 50 |
+
"loss": 0.4803,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8338296605122096,
|
| 55 |
+
"grad_norm": 0.5892139673233032,
|
| 56 |
+
"learning_rate": 4.347522293051648e-05,
|
| 57 |
+
"loss": 0.4718,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.9529481834425253,
|
| 62 |
+
"grad_norm": 0.5380077362060547,
|
| 63 |
+
"learning_rate": 4.0065865909481417e-05,
|
| 64 |
+
"loss": 0.4626,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.072066706372841,
|
| 69 |
+
"grad_norm": 0.576122522354126,
|
| 70 |
+
"learning_rate": 3.6143458894413465e-05,
|
| 71 |
+
"loss": 0.4564,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.1911852293031566,
|
| 76 |
+
"grad_norm": 0.543662428855896,
|
| 77 |
+
"learning_rate": 3.1841574751802076e-05,
|
| 78 |
+
"loss": 0.4526,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.3103037522334722,
|
| 83 |
+
"grad_norm": 0.6222002506256104,
|
| 84 |
+
"learning_rate": 2.7306708986582553e-05,
|
| 85 |
+
"loss": 0.4626,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.429422275163788,
|
| 90 |
+
"grad_norm": 0.5597625374794006,
|
| 91 |
+
"learning_rate": 2.2693291013417453e-05,
|
| 92 |
+
"loss": 0.4581,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.5485407980941037,
|
| 97 |
+
"grad_norm": 0.8017860651016235,
|
| 98 |
+
"learning_rate": 1.815842524819793e-05,
|
| 99 |
+
"loss": 0.4646,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.6676593210244193,
|
| 104 |
+
"grad_norm": 0.696183443069458,
|
| 105 |
+
"learning_rate": 1.3856541105586545e-05,
|
| 106 |
+
"loss": 0.4548,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.7867778439547348,
|
| 111 |
+
"grad_norm": 0.6249508261680603,
|
| 112 |
+
"learning_rate": 9.934134090518593e-06,
|
| 113 |
+
"loss": 0.4668,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.9058963668850506,
|
| 118 |
+
"grad_norm": 0.679349422454834,
|
| 119 |
+
"learning_rate": 6.524777069483526e-06,
|
| 120 |
+
"loss": 0.4519,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.0250148898153664,
|
| 125 |
+
"grad_norm": 0.6183383464813232,
|
| 126 |
+
"learning_rate": 3.7445716067596503e-06,
|
| 127 |
+
"loss": 0.4554,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.144133412745682,
|
| 132 |
+
"grad_norm": 0.7539538145065308,
|
| 133 |
+
"learning_rate": 1.6881942648911076e-06,
|
| 134 |
+
"loss": 0.4568,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.2632519356759975,
|
| 139 |
+
"grad_norm": 0.7621870636940002,
|
| 140 |
+
"learning_rate": 4.256725079024554e-07,
|
| 141 |
+
"loss": 0.4577,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.3823704586063132,
|
| 146 |
+
"grad_norm": 0.45056673884391785,
|
| 147 |
+
"learning_rate": 0.0,
|
| 148 |
+
"loss": 0.4445,
|
| 149 |
+
"step": 2000
|
| 150 |
+
}
|
| 151 |
+
],
|
| 152 |
+
"logging_steps": 100,
|
| 153 |
+
"max_steps": 2000,
|
| 154 |
+
"num_input_tokens_seen": 0,
|
| 155 |
+
"num_train_epochs": 3,
|
| 156 |
+
"save_steps": 200,
|
| 157 |
+
"stateful_callbacks": {
|
| 158 |
+
"TrainerControl": {
|
| 159 |
+
"args": {
|
| 160 |
+
"should_epoch_stop": false,
|
| 161 |
+
"should_evaluate": false,
|
| 162 |
+
"should_log": false,
|
| 163 |
+
"should_save": true,
|
| 164 |
+
"should_training_stop": true
|
| 165 |
+
},
|
| 166 |
+
"attributes": {}
|
| 167 |
+
}
|
| 168 |
+
},
|
| 169 |
+
"total_flos": 6.15307218125783e+16,
|
| 170 |
+
"train_batch_size": 8,
|
| 171 |
+
"trial_name": null,
|
| 172 |
+
"trial_params": null
|
| 173 |
+
}
|