Upload checkpoint-100/trainer_state.json with huggingface_hub
Browse files
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3988035892323031,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03988035892323031,
|
| 13 |
+
"grad_norm": 16.628543853759766,
|
| 14 |
+
"learning_rate": 0.00012,
|
| 15 |
+
"loss": 2.1274,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07976071784646062,
|
| 20 |
+
"grad_norm": 12.371907234191895,
|
| 21 |
+
"learning_rate": 0.00019950829025450114,
|
| 22 |
+
"loss": 0.7722,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11964107676969092,
|
| 27 |
+
"grad_norm": 9.106270790100098,
|
| 28 |
+
"learning_rate": 0.00019652089102773488,
|
| 29 |
+
"loss": 0.4456,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15952143569292124,
|
| 34 |
+
"grad_norm": 5.712669372558594,
|
| 35 |
+
"learning_rate": 0.00019090065350491626,
|
| 36 |
+
"loss": 0.3662,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19940179461615154,
|
| 41 |
+
"grad_norm": 2.922630548477173,
|
| 42 |
+
"learning_rate": 0.00018280088311480201,
|
| 43 |
+
"loss": 0.2983,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23928215353938184,
|
| 48 |
+
"grad_norm": 5.451596260070801,
|
| 49 |
+
"learning_rate": 0.00017244252047910892,
|
| 50 |
+
"loss": 0.3034,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.27916251246261214,
|
| 55 |
+
"grad_norm": 3.604940414428711,
|
| 56 |
+
"learning_rate": 0.00016010811472830252,
|
| 57 |
+
"loss": 0.2754,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3190428713858425,
|
| 62 |
+
"grad_norm": 2.805121660232544,
|
| 63 |
+
"learning_rate": 0.0001461341162978688,
|
| 64 |
+
"loss": 0.2659,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3589232303090728,
|
| 69 |
+
"grad_norm": 3.4018733501434326,
|
| 70 |
+
"learning_rate": 0.00013090169943749476,
|
| 71 |
+
"loss": 0.2767,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3988035892323031,
|
| 76 |
+
"grad_norm": 3.0557034015655518,
|
| 77 |
+
"learning_rate": 0.0001148263647711842,
|
| 78 |
+
"loss": 0.286,
|
| 79 |
+
"step": 100
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"logging_steps": 10,
|
| 83 |
+
"max_steps": 200,
|
| 84 |
+
"num_input_tokens_seen": 0,
|
| 85 |
+
"num_train_epochs": 1,
|
| 86 |
+
"save_steps": 100,
|
| 87 |
+
"stateful_callbacks": {
|
| 88 |
+
"TrainerControl": {
|
| 89 |
+
"args": {
|
| 90 |
+
"should_epoch_stop": false,
|
| 91 |
+
"should_evaluate": false,
|
| 92 |
+
"should_log": false,
|
| 93 |
+
"should_save": true,
|
| 94 |
+
"should_training_stop": false
|
| 95 |
+
},
|
| 96 |
+
"attributes": {}
|
| 97 |
+
}
|
| 98 |
+
},
|
| 99 |
+
"total_flos": 1450485964480512.0,
|
| 100 |
+
"train_batch_size": 1,
|
| 101 |
+
"trial_name": null,
|
| 102 |
+
"trial_params": null
|
| 103 |
+
}
|