Training in progress, step 200
Browse files- all_results.json +14 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- train_results.json +9 -0
- trainer_state.json +104 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.6,
|
| 3 |
+
"eval_loss": 0.5873731970787048,
|
| 4 |
+
"eval_runtime": 1.7661,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 566.226,
|
| 7 |
+
"eval_steps_per_second": 35.672,
|
| 8 |
+
"total_flos": 364154381869824.0,
|
| 9 |
+
"train_loss": 0.6259692611694336,
|
| 10 |
+
"train_runtime": 219.9954,
|
| 11 |
+
"train_samples": 10000,
|
| 12 |
+
"train_samples_per_second": 72.729,
|
| 13 |
+
"train_steps_per_second": 4.546
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.6,
|
| 3 |
+
"eval_loss": 0.5873731970787048,
|
| 4 |
+
"eval_runtime": 1.7661,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 566.226,
|
| 7 |
+
"eval_steps_per_second": 35.672
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 470640124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3562d78a8cdfd318cc7afe759507b5c53b9ac074096f3a133742639f535fb22b
|
| 3 |
size 470640124
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.6,
|
| 3 |
+
"total_flos": 364154381869824.0,
|
| 4 |
+
"train_loss": 0.6259692611694336,
|
| 5 |
+
"train_runtime": 219.9954,
|
| 6 |
+
"train_samples": 10000,
|
| 7 |
+
"train_samples_per_second": 72.729,
|
| 8 |
+
"train_steps_per_second": 4.546
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.6,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24,
|
| 13 |
+
"learning_rate": 8.260869565217392e-06,
|
| 14 |
+
"loss": 0.693,
|
| 15 |
+
"step": 150
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"eval_loss": 0.6899820566177368,
|
| 20 |
+
"eval_runtime": 1.6725,
|
| 21 |
+
"eval_samples_per_second": 597.893,
|
| 22 |
+
"eval_steps_per_second": 37.667,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.48,
|
| 27 |
+
"learning_rate": 5.652173913043479e-06,
|
| 28 |
+
"loss": 0.6843,
|
| 29 |
+
"step": 300
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.64,
|
| 33 |
+
"eval_loss": 0.6105484366416931,
|
| 34 |
+
"eval_runtime": 1.7064,
|
| 35 |
+
"eval_samples_per_second": 586.021,
|
| 36 |
+
"eval_steps_per_second": 36.919,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.72,
|
| 41 |
+
"learning_rate": 3.043478260869566e-06,
|
| 42 |
+
"loss": 0.6336,
|
| 43 |
+
"step": 450
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.96,
|
| 47 |
+
"learning_rate": 4.347826086956522e-07,
|
| 48 |
+
"loss": 0.5981,
|
| 49 |
+
"step": 600
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.96,
|
| 53 |
+
"eval_loss": 0.5873401165008545,
|
| 54 |
+
"eval_runtime": 1.7375,
|
| 55 |
+
"eval_samples_per_second": 575.544,
|
| 56 |
+
"eval_steps_per_second": 36.259,
|
| 57 |
+
"step": 600
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.2,
|
| 61 |
+
"learning_rate": 0.0,
|
| 62 |
+
"loss": 0.5851,
|
| 63 |
+
"step": 750
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.28,
|
| 67 |
+
"eval_loss": 0.5873731970787048,
|
| 68 |
+
"eval_runtime": 1.7565,
|
| 69 |
+
"eval_samples_per_second": 569.31,
|
| 70 |
+
"eval_steps_per_second": 35.867,
|
| 71 |
+
"step": 800
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.44,
|
| 75 |
+
"learning_rate": 0.0,
|
| 76 |
+
"loss": 0.5863,
|
| 77 |
+
"step": 900
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.6,
|
| 81 |
+
"eval_loss": 0.5873731970787048,
|
| 82 |
+
"eval_runtime": 1.7602,
|
| 83 |
+
"eval_samples_per_second": 568.102,
|
| 84 |
+
"eval_steps_per_second": 35.79,
|
| 85 |
+
"step": 1000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.6,
|
| 89 |
+
"step": 1000,
|
| 90 |
+
"total_flos": 364154381869824.0,
|
| 91 |
+
"train_loss": 0.6259692611694336,
|
| 92 |
+
"train_runtime": 219.9954,
|
| 93 |
+
"train_samples_per_second": 72.729,
|
| 94 |
+
"train_steps_per_second": 4.546
|
| 95 |
+
}
|
| 96 |
+
],
|
| 97 |
+
"logging_steps": 150,
|
| 98 |
+
"max_steps": 1000,
|
| 99 |
+
"num_train_epochs": 2,
|
| 100 |
+
"save_steps": 200,
|
| 101 |
+
"total_flos": 364154381869824.0,
|
| 102 |
+
"trial_name": null,
|
| 103 |
+
"trial_params": null
|
| 104 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b08fb405bdf743fa9a77d90ca2c82976b61e66000d364e6ef36f0c21cbc227a
|
| 3 |
size 4536
|