checkpoint: Add trainer_state.json
Browse files- trainer_state.json +152 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8842,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0565482922415743,
|
| 13 |
+
"grad_norm": 6.099003791809082,
|
| 14 |
+
"learning_rate": 4.7172585387921285e-05,
|
| 15 |
+
"loss": 5.2788,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1130965844831486,
|
| 20 |
+
"grad_norm": 4.438333988189697,
|
| 21 |
+
"learning_rate": 4.434517077584257e-05,
|
| 22 |
+
"loss": 4.8237,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16964487672472292,
|
| 27 |
+
"grad_norm": 5.307681083679199,
|
| 28 |
+
"learning_rate": 4.1517756163763856e-05,
|
| 29 |
+
"loss": 4.737,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2261931689662972,
|
| 34 |
+
"grad_norm": 5.611371040344238,
|
| 35 |
+
"learning_rate": 3.869034155168514e-05,
|
| 36 |
+
"loss": 4.6918,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2827414612078715,
|
| 41 |
+
"grad_norm": 5.551920413970947,
|
| 42 |
+
"learning_rate": 3.586292693960643e-05,
|
| 43 |
+
"loss": 4.6628,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.33928975344944584,
|
| 48 |
+
"grad_norm": 5.272426605224609,
|
| 49 |
+
"learning_rate": 3.303551232752771e-05,
|
| 50 |
+
"loss": 4.6474,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.39583804569102016,
|
| 55 |
+
"grad_norm": 5.137388229370117,
|
| 56 |
+
"learning_rate": 3.0208097715448996e-05,
|
| 57 |
+
"loss": 4.6272,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4523863379325944,
|
| 62 |
+
"grad_norm": 6.018069744110107,
|
| 63 |
+
"learning_rate": 2.7380683103370282e-05,
|
| 64 |
+
"loss": 4.6025,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5089346301741687,
|
| 69 |
+
"grad_norm": 5.987523555755615,
|
| 70 |
+
"learning_rate": 2.4553268491291564e-05,
|
| 71 |
+
"loss": 4.5791,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.565482922415743,
|
| 76 |
+
"grad_norm": 5.519354820251465,
|
| 77 |
+
"learning_rate": 2.172585387921285e-05,
|
| 78 |
+
"loss": 4.5844,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6220312146573174,
|
| 83 |
+
"grad_norm": 5.536919593811035,
|
| 84 |
+
"learning_rate": 1.8898439267134132e-05,
|
| 85 |
+
"loss": 4.5647,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6785795068988917,
|
| 90 |
+
"grad_norm": 5.017457962036133,
|
| 91 |
+
"learning_rate": 1.6071024655055418e-05,
|
| 92 |
+
"loss": 4.5574,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.735127799140466,
|
| 97 |
+
"grad_norm": 5.590214252471924,
|
| 98 |
+
"learning_rate": 1.3243610042976704e-05,
|
| 99 |
+
"loss": 4.548,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7916760913820403,
|
| 104 |
+
"grad_norm": 4.2981181144714355,
|
| 105 |
+
"learning_rate": 1.0416195430897988e-05,
|
| 106 |
+
"loss": 4.5641,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8482243836236145,
|
| 111 |
+
"grad_norm": 5.723196983337402,
|
| 112 |
+
"learning_rate": 7.588780818819271e-06,
|
| 113 |
+
"loss": 4.5633,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9047726758651888,
|
| 118 |
+
"grad_norm": 5.700985431671143,
|
| 119 |
+
"learning_rate": 4.761366206740556e-06,
|
| 120 |
+
"loss": 4.5486,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9613209681067632,
|
| 125 |
+
"grad_norm": 5.034333229064941,
|
| 126 |
+
"learning_rate": 1.9339515946618415e-06,
|
| 127 |
+
"loss": 4.5307,
|
| 128 |
+
"step": 8500
|
| 129 |
+
}
|
| 130 |
+
],
|
| 131 |
+
"logging_steps": 500,
|
| 132 |
+
"max_steps": 8842,
|
| 133 |
+
"num_input_tokens_seen": 0,
|
| 134 |
+
"num_train_epochs": 1,
|
| 135 |
+
"save_steps": 5000,
|
| 136 |
+
"stateful_callbacks": {
|
| 137 |
+
"TrainerControl": {
|
| 138 |
+
"args": {
|
| 139 |
+
"should_epoch_stop": false,
|
| 140 |
+
"should_evaluate": false,
|
| 141 |
+
"should_log": false,
|
| 142 |
+
"should_save": true,
|
| 143 |
+
"should_training_stop": true
|
| 144 |
+
},
|
| 145 |
+
"attributes": {}
|
| 146 |
+
}
|
| 147 |
+
},
|
| 148 |
+
"total_flos": 1.3333874049690624e+17,
|
| 149 |
+
"train_batch_size": 32,
|
| 150 |
+
"trial_name": null,
|
| 151 |
+
"trial_params": null
|
| 152 |
+
}
|