Training in progress, step 9320
Browse files- all_results.json +18 -0
- train_results.json +18 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"before_init_mem_cpu": 1174028288,
|
| 3 |
+
"before_init_mem_gpu": 0,
|
| 4 |
+
"epoch": 19.35,
|
| 5 |
+
"init_mem_cpu_alloc_delta": 2783887360,
|
| 6 |
+
"init_mem_cpu_peaked_delta": 414412800,
|
| 7 |
+
"init_mem_gpu_alloc_delta": 497994240,
|
| 8 |
+
"init_mem_gpu_peaked_delta": 512,
|
| 9 |
+
"train_loss": 0.2542688299146333,
|
| 10 |
+
"train_mem_cpu_alloc_delta": 8443502592,
|
| 11 |
+
"train_mem_cpu_peaked_delta": 383119360,
|
| 12 |
+
"train_mem_gpu_alloc_delta": 2006973440,
|
| 13 |
+
"train_mem_gpu_peaked_delta": 15468135424,
|
| 14 |
+
"train_runtime": 73469.8819,
|
| 15 |
+
"train_samples": 3825056,
|
| 16 |
+
"train_samples_per_second": 1041.258,
|
| 17 |
+
"train_steps_per_second": 0.127
|
| 18 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"before_init_mem_cpu": 1174028288,
|
| 3 |
+
"before_init_mem_gpu": 0,
|
| 4 |
+
"epoch": 19.35,
|
| 5 |
+
"init_mem_cpu_alloc_delta": 2783887360,
|
| 6 |
+
"init_mem_cpu_peaked_delta": 414412800,
|
| 7 |
+
"init_mem_gpu_alloc_delta": 497994240,
|
| 8 |
+
"init_mem_gpu_peaked_delta": 512,
|
| 9 |
+
"train_loss": 0.2542688299146333,
|
| 10 |
+
"train_mem_cpu_alloc_delta": 8443502592,
|
| 11 |
+
"train_mem_cpu_peaked_delta": 383119360,
|
| 12 |
+
"train_mem_gpu_alloc_delta": 2006973440,
|
| 13 |
+
"train_mem_gpu_peaked_delta": 15468135424,
|
| 14 |
+
"train_runtime": 73469.8819,
|
| 15 |
+
"train_samples": 3825056,
|
| 16 |
+
"train_samples_per_second": 1041.258,
|
| 17 |
+
"train_steps_per_second": 0.127
|
| 18 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|