End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.140449285507202,
|
| 4 |
+
"eval_runtime": 78.7959,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 12.691,
|
| 7 |
+
"eval_steps_per_second": 1.586,
|
| 8 |
+
"perplexity": 8.50325716099811,
|
| 9 |
+
"train_loss": 2.1918378117108586,
|
| 10 |
+
"train_runtime": 5252.1602,
|
| 11 |
+
"train_samples": 19004,
|
| 12 |
+
"train_samples_per_second": 3.618,
|
| 13 |
+
"train_steps_per_second": 0.057
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.140449285507202,
|
| 4 |
+
"eval_runtime": 78.7959,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 12.691,
|
| 7 |
+
"eval_steps_per_second": 1.586,
|
| 8 |
+
"perplexity": 8.50325716099811
|
| 9 |
+
}
|
runs/Nov17_15-48-22_b8c9aa7e6ded/events.out.tfevents.1637164174.b8c9aa7e6ded.2400.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5f2ee89c4ae82311208d3d95fa0126bc0cb1ef25eb0a87ae8351cc708070ada
|
| 3 |
+
size 3772
|
runs/Nov17_15-48-22_b8c9aa7e6ded/events.out.tfevents.1637169513.b8c9aa7e6ded.2400.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b47ec9d8b0ed50663390faa4dc773fde3fb4ca436d62d32bac81ef65d5b573
|
| 3 |
+
size 311
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.1918378117108586,
|
| 4 |
+
"train_runtime": 5252.1602,
|
| 5 |
+
"train_samples": 19004,
|
| 6 |
+
"train_samples_per_second": 3.618,
|
| 7 |
+
"train_steps_per_second": 0.057
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 297,
|
| 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 |
+
"eval_loss": 2.1775870323181152,
|
| 13 |
+
"eval_runtime": 78.5997,
|
| 14 |
+
"eval_samples_per_second": 12.723,
|
| 15 |
+
"eval_steps_per_second": 1.59,
|
| 16 |
+
"step": 297
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"step": 297,
|
| 21 |
+
"total_flos": 5001918049701888.0,
|
| 22 |
+
"train_loss": 2.1918378117108586,
|
| 23 |
+
"train_runtime": 5252.1602,
|
| 24 |
+
"train_samples_per_second": 3.618,
|
| 25 |
+
"train_steps_per_second": 0.057
|
| 26 |
+
}
|
| 27 |
+
],
|
| 28 |
+
"max_steps": 297,
|
| 29 |
+
"num_train_epochs": 1,
|
| 30 |
+
"total_flos": 5001918049701888.0,
|
| 31 |
+
"trial_name": null,
|
| 32 |
+
"trial_params": null
|
| 33 |
+
}
|