Commit
•
888fc09
1
Parent(s):
a915d8a
Upload trainer_state.json
Browse files- trainer_state.json +92 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 129888,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.6666695181310364e-05,
|
| 13 |
+
"loss": 0.6085,
|
| 14 |
+
"step": 32472
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_gen_len": 18.2164,
|
| 19 |
+
"eval_loss": 0.16991940140724182,
|
| 20 |
+
"eval_rouge1": 17.6159,
|
| 21 |
+
"eval_rouge2": 10.0939,
|
| 22 |
+
"eval_rougeL": 17.5541,
|
| 23 |
+
"eval_rougeLsum": 17.5459,
|
| 24 |
+
"eval_runtime": 1185.7292,
|
| 25 |
+
"eval_samples_per_second": 70.419,
|
| 26 |
+
"eval_steps_per_second": 1.957,
|
| 27 |
+
"step": 32472
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"learning_rate": 1.1111130120873575e-05,
|
| 32 |
+
"loss": 0.178,
|
| 33 |
+
"step": 64944
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_gen_len": 18.2056,
|
| 38 |
+
"eval_loss": 0.14107763767242432,
|
| 39 |
+
"eval_rouge1": 17.7228,
|
| 40 |
+
"eval_rouge2": 10.1174,
|
| 41 |
+
"eval_rougeL": 17.6623,
|
| 42 |
+
"eval_rougeLsum": 17.6545,
|
| 43 |
+
"eval_runtime": 1187.4291,
|
| 44 |
+
"eval_samples_per_second": 70.318,
|
| 45 |
+
"eval_steps_per_second": 1.954,
|
| 46 |
+
"step": 64944
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"learning_rate": 5.5555650604367875e-06,
|
| 51 |
+
"loss": 0.1504,
|
| 52 |
+
"step": 97416
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 3.0,
|
| 56 |
+
"eval_gen_len": 18.2497,
|
| 57 |
+
"eval_loss": 0.13206903636455536,
|
| 58 |
+
"eval_rouge1": 17.9419,
|
| 59 |
+
"eval_rouge2": 10.3186,
|
| 60 |
+
"eval_rougeL": 17.8803,
|
| 61 |
+
"eval_rougeLsum": 17.869,
|
| 62 |
+
"eval_runtime": 1186.9555,
|
| 63 |
+
"eval_samples_per_second": 70.346,
|
| 64 |
+
"eval_steps_per_second": 1.955,
|
| 65 |
+
"step": 97416
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"learning_rate": 0.0,
|
| 70 |
+
"loss": 0.1376,
|
| 71 |
+
"step": 129888
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_gen_len": 18.253,
|
| 76 |
+
"eval_loss": 0.12918101251125336,
|
| 77 |
+
"eval_rouge1": 17.9188,
|
| 78 |
+
"eval_rouge2": 10.2616,
|
| 79 |
+
"eval_rougeL": 17.863,
|
| 80 |
+
"eval_rougeLsum": 17.85,
|
| 81 |
+
"eval_runtime": 1184.3447,
|
| 82 |
+
"eval_samples_per_second": 70.501,
|
| 83 |
+
"eval_steps_per_second": 1.959,
|
| 84 |
+
"step": 129888
|
| 85 |
+
}
|
| 86 |
+
],
|
| 87 |
+
"max_steps": 129888,
|
| 88 |
+
"num_train_epochs": 4,
|
| 89 |
+
"total_flos": 1.4647320279945216e+17,
|
| 90 |
+
"trial_name": null,
|
| 91 |
+
"trial_params": null
|
| 92 |
+
}
|