End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- train_results.txt +6 -0
- trainer_state.json +1201 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 2.6336010373971255,
|
| 4 |
+
"train_runtime": 9376.0618,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 18.075,
|
| 7 |
+
"train_steps_per_second": 9.037
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 2.6336010373971255,
|
| 4 |
+
"train_runtime": 9376.0618,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 18.075,
|
| 7 |
+
"train_steps_per_second": 9.037
|
| 8 |
+
}
|
train_results.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 4.0
|
| 2 |
+
train_loss = 2.6336010373971255
|
| 3 |
+
train_runtime = 9376.0618
|
| 4 |
+
train_samples = 42367
|
| 5 |
+
train_samples_per_second = 18.075
|
| 6 |
+
train_steps_per_second = 9.037
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.0290679931640625,
|
| 3 |
+
"best_model_checkpoint": "./models/gpt_trinity_test/checkpoint-84000",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 84736,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 3.533160254897333e-06,
|
| 13 |
+
"loss": 3.5765,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_loss": 4.124706745147705,
|
| 19 |
+
"eval_runtime": 5.5178,
|
| 20 |
+
"eval_samples_per_second": 77.749,
|
| 21 |
+
"eval_steps_per_second": 38.965,
|
| 22 |
+
"step": 1000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.09,
|
| 26 |
+
"learning_rate": 7.073400991267406e-06,
|
| 27 |
+
"loss": 3.19,
|
| 28 |
+
"step": 2000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.09,
|
| 32 |
+
"eval_loss": 4.057796955108643,
|
| 33 |
+
"eval_runtime": 5.5495,
|
| 34 |
+
"eval_samples_per_second": 77.305,
|
| 35 |
+
"eval_steps_per_second": 38.742,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.14,
|
| 40 |
+
"learning_rate": 1.061364172763748e-05,
|
| 41 |
+
"loss": 3.1177,
|
| 42 |
+
"step": 3000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.14,
|
| 46 |
+
"eval_loss": 4.070754051208496,
|
| 47 |
+
"eval_runtime": 5.5223,
|
| 48 |
+
"eval_samples_per_second": 77.685,
|
| 49 |
+
"eval_steps_per_second": 38.933,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 1.4153882464007553e-05,
|
| 55 |
+
"loss": 3.1116,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.19,
|
| 60 |
+
"eval_loss": 4.065377712249756,
|
| 61 |
+
"eval_runtime": 5.5251,
|
| 62 |
+
"eval_samples_per_second": 77.646,
|
| 63 |
+
"eval_steps_per_second": 38.913,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.24,
|
| 68 |
+
"learning_rate": 1.7694123200377628e-05,
|
| 69 |
+
"loss": 3.0777,
|
| 70 |
+
"step": 5000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.24,
|
| 74 |
+
"eval_loss": 4.085710525512695,
|
| 75 |
+
"eval_runtime": 5.5077,
|
| 76 |
+
"eval_samples_per_second": 77.89,
|
| 77 |
+
"eval_steps_per_second": 39.036,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.28,
|
| 82 |
+
"learning_rate": 2.12343639367477e-05,
|
| 83 |
+
"loss": 3.1105,
|
| 84 |
+
"step": 6000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.28,
|
| 88 |
+
"eval_loss": 4.112701416015625,
|
| 89 |
+
"eval_runtime": 5.4987,
|
| 90 |
+
"eval_samples_per_second": 78.018,
|
| 91 |
+
"eval_steps_per_second": 39.1,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 2.4771064432381404e-05,
|
| 97 |
+
"loss": 3.1018,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.33,
|
| 102 |
+
"eval_loss": 4.141016483306885,
|
| 103 |
+
"eval_runtime": 5.5233,
|
| 104 |
+
"eval_samples_per_second": 77.671,
|
| 105 |
+
"eval_steps_per_second": 38.926,
|
| 106 |
+
"step": 7000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.38,
|
| 110 |
+
"learning_rate": 2.8311305168751475e-05,
|
| 111 |
+
"loss": 3.0728,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.38,
|
| 116 |
+
"eval_loss": 4.183428764343262,
|
| 117 |
+
"eval_runtime": 5.5153,
|
| 118 |
+
"eval_samples_per_second": 77.783,
|
| 119 |
+
"eval_steps_per_second": 38.982,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.42,
|
| 124 |
+
"learning_rate": 2.9794261886653903e-05,
|
| 125 |
+
"loss": 3.1248,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.42,
|
| 130 |
+
"eval_loss": 4.205781936645508,
|
| 131 |
+
"eval_runtime": 5.4948,
|
| 132 |
+
"eval_samples_per_second": 78.073,
|
| 133 |
+
"eval_steps_per_second": 39.128,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.47,
|
| 138 |
+
"learning_rate": 2.9400881172799034e-05,
|
| 139 |
+
"loss": 3.1035,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.47,
|
| 144 |
+
"eval_loss": 4.20481538772583,
|
| 145 |
+
"eval_runtime": 5.5171,
|
| 146 |
+
"eval_samples_per_second": 77.758,
|
| 147 |
+
"eval_steps_per_second": 38.97,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.52,
|
| 152 |
+
"learning_rate": 2.9007893839658023e-05,
|
| 153 |
+
"loss": 3.0943,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.52,
|
| 158 |
+
"eval_loss": 4.189157009124756,
|
| 159 |
+
"eval_runtime": 5.5205,
|
| 160 |
+
"eval_samples_per_second": 77.71,
|
| 161 |
+
"eval_steps_per_second": 38.946,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.57,
|
| 166 |
+
"learning_rate": 2.8614513125803154e-05,
|
| 167 |
+
"loss": 3.0724,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.57,
|
| 172 |
+
"eval_loss": 4.206292629241943,
|
| 173 |
+
"eval_runtime": 5.5117,
|
| 174 |
+
"eval_samples_per_second": 77.834,
|
| 175 |
+
"eval_steps_per_second": 39.008,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.61,
|
| 180 |
+
"learning_rate": 2.822113241194828e-05,
|
| 181 |
+
"loss": 3.0517,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.61,
|
| 186 |
+
"eval_loss": 4.19225549697876,
|
| 187 |
+
"eval_runtime": 5.5111,
|
| 188 |
+
"eval_samples_per_second": 77.843,
|
| 189 |
+
"eval_steps_per_second": 39.012,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.66,
|
| 194 |
+
"learning_rate": 2.782814507880727e-05,
|
| 195 |
+
"loss": 3.0372,
|
| 196 |
+
"step": 14000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.66,
|
| 200 |
+
"eval_loss": 4.2112298011779785,
|
| 201 |
+
"eval_runtime": 5.4935,
|
| 202 |
+
"eval_samples_per_second": 78.093,
|
| 203 |
+
"eval_steps_per_second": 39.138,
|
| 204 |
+
"step": 14000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.71,
|
| 208 |
+
"learning_rate": 2.7434764364952404e-05,
|
| 209 |
+
"loss": 3.0235,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.71,
|
| 214 |
+
"eval_loss": 4.204270362854004,
|
| 215 |
+
"eval_runtime": 5.5028,
|
| 216 |
+
"eval_samples_per_second": 77.961,
|
| 217 |
+
"eval_steps_per_second": 39.071,
|
| 218 |
+
"step": 15000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.76,
|
| 222 |
+
"learning_rate": 2.704177703181139e-05,
|
| 223 |
+
"loss": 3.0329,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.76,
|
| 228 |
+
"eval_loss": 4.163009166717529,
|
| 229 |
+
"eval_runtime": 5.5278,
|
| 230 |
+
"eval_samples_per_second": 77.608,
|
| 231 |
+
"eval_steps_per_second": 38.894,
|
| 232 |
+
"step": 16000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.8,
|
| 236 |
+
"learning_rate": 2.664839631795652e-05,
|
| 237 |
+
"loss": 3.0171,
|
| 238 |
+
"step": 17000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.8,
|
| 242 |
+
"eval_loss": 4.163072109222412,
|
| 243 |
+
"eval_runtime": 5.4985,
|
| 244 |
+
"eval_samples_per_second": 78.021,
|
| 245 |
+
"eval_steps_per_second": 39.102,
|
| 246 |
+
"step": 17000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.85,
|
| 250 |
+
"learning_rate": 2.625501560410165e-05,
|
| 251 |
+
"loss": 2.9997,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.85,
|
| 256 |
+
"eval_loss": 4.156316757202148,
|
| 257 |
+
"eval_runtime": 5.5028,
|
| 258 |
+
"eval_samples_per_second": 77.961,
|
| 259 |
+
"eval_steps_per_second": 39.071,
|
| 260 |
+
"step": 18000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.9,
|
| 264 |
+
"learning_rate": 2.5861634890246782e-05,
|
| 265 |
+
"loss": 2.9913,
|
| 266 |
+
"step": 19000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.9,
|
| 270 |
+
"eval_loss": 4.161618232727051,
|
| 271 |
+
"eval_runtime": 5.5279,
|
| 272 |
+
"eval_samples_per_second": 77.607,
|
| 273 |
+
"eval_steps_per_second": 38.894,
|
| 274 |
+
"step": 19000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.94,
|
| 278 |
+
"learning_rate": 2.546904093781962e-05,
|
| 279 |
+
"loss": 2.9579,
|
| 280 |
+
"step": 20000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.94,
|
| 284 |
+
"eval_loss": 4.149376392364502,
|
| 285 |
+
"eval_runtime": 5.5138,
|
| 286 |
+
"eval_samples_per_second": 77.805,
|
| 287 |
+
"eval_steps_per_second": 38.993,
|
| 288 |
+
"step": 20000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.99,
|
| 292 |
+
"learning_rate": 2.507605360467861e-05,
|
| 293 |
+
"loss": 2.9576,
|
| 294 |
+
"step": 21000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.99,
|
| 298 |
+
"eval_loss": 4.136674880981445,
|
| 299 |
+
"eval_runtime": 5.5162,
|
| 300 |
+
"eval_samples_per_second": 77.77,
|
| 301 |
+
"eval_steps_per_second": 38.976,
|
| 302 |
+
"step": 21000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.04,
|
| 306 |
+
"learning_rate": 2.468267289082374e-05,
|
| 307 |
+
"loss": 2.7461,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.04,
|
| 312 |
+
"eval_loss": 4.15926456451416,
|
| 313 |
+
"eval_runtime": 5.5064,
|
| 314 |
+
"eval_samples_per_second": 77.909,
|
| 315 |
+
"eval_steps_per_second": 39.045,
|
| 316 |
+
"step": 22000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.09,
|
| 320 |
+
"learning_rate": 2.4289292176968872e-05,
|
| 321 |
+
"loss": 2.7637,
|
| 322 |
+
"step": 23000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.09,
|
| 326 |
+
"eval_loss": 4.1452813148498535,
|
| 327 |
+
"eval_runtime": 5.5159,
|
| 328 |
+
"eval_samples_per_second": 77.775,
|
| 329 |
+
"eval_steps_per_second": 38.978,
|
| 330 |
+
"step": 23000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.13,
|
| 334 |
+
"learning_rate": 2.3895911463114e-05,
|
| 335 |
+
"loss": 2.741,
|
| 336 |
+
"step": 24000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.13,
|
| 340 |
+
"eval_loss": 4.162442207336426,
|
| 341 |
+
"eval_runtime": 5.5028,
|
| 342 |
+
"eval_samples_per_second": 77.961,
|
| 343 |
+
"eval_steps_per_second": 39.071,
|
| 344 |
+
"step": 24000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.18,
|
| 348 |
+
"learning_rate": 2.3502530749259134e-05,
|
| 349 |
+
"loss": 2.7514,
|
| 350 |
+
"step": 25000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.18,
|
| 354 |
+
"eval_loss": 4.135677814483643,
|
| 355 |
+
"eval_runtime": 5.525,
|
| 356 |
+
"eval_samples_per_second": 77.647,
|
| 357 |
+
"eval_steps_per_second": 38.914,
|
| 358 |
+
"step": 25000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.23,
|
| 362 |
+
"learning_rate": 2.3109150035404265e-05,
|
| 363 |
+
"loss": 2.755,
|
| 364 |
+
"step": 26000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.23,
|
| 368 |
+
"eval_loss": 4.152438163757324,
|
| 369 |
+
"eval_runtime": 5.5218,
|
| 370 |
+
"eval_samples_per_second": 77.692,
|
| 371 |
+
"eval_steps_per_second": 38.937,
|
| 372 |
+
"step": 26000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.27,
|
| 376 |
+
"learning_rate": 2.2715769321549396e-05,
|
| 377 |
+
"loss": 2.7365,
|
| 378 |
+
"step": 27000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.27,
|
| 382 |
+
"eval_loss": 4.139864444732666,
|
| 383 |
+
"eval_runtime": 5.5425,
|
| 384 |
+
"eval_samples_per_second": 77.401,
|
| 385 |
+
"eval_steps_per_second": 38.791,
|
| 386 |
+
"step": 27000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.32,
|
| 390 |
+
"learning_rate": 2.232278198840838e-05,
|
| 391 |
+
"loss": 2.7356,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.32,
|
| 396 |
+
"eval_loss": 4.1285014152526855,
|
| 397 |
+
"eval_runtime": 5.5006,
|
| 398 |
+
"eval_samples_per_second": 77.991,
|
| 399 |
+
"eval_steps_per_second": 39.087,
|
| 400 |
+
"step": 28000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.37,
|
| 404 |
+
"learning_rate": 2.1929401274553512e-05,
|
| 405 |
+
"loss": 2.7386,
|
| 406 |
+
"step": 29000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.37,
|
| 410 |
+
"eval_loss": 4.128605365753174,
|
| 411 |
+
"eval_runtime": 5.5111,
|
| 412 |
+
"eval_samples_per_second": 77.843,
|
| 413 |
+
"eval_steps_per_second": 39.012,
|
| 414 |
+
"step": 29000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.42,
|
| 418 |
+
"learning_rate": 2.15364139414125e-05,
|
| 419 |
+
"loss": 2.7489,
|
| 420 |
+
"step": 30000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.42,
|
| 424 |
+
"eval_loss": 4.123142719268799,
|
| 425 |
+
"eval_runtime": 5.5126,
|
| 426 |
+
"eval_samples_per_second": 77.821,
|
| 427 |
+
"eval_steps_per_second": 39.001,
|
| 428 |
+
"step": 30000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.46,
|
| 432 |
+
"learning_rate": 2.114303322755763e-05,
|
| 433 |
+
"loss": 2.7518,
|
| 434 |
+
"step": 31000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.46,
|
| 438 |
+
"eval_loss": 4.110356330871582,
|
| 439 |
+
"eval_runtime": 5.5003,
|
| 440 |
+
"eval_samples_per_second": 77.995,
|
| 441 |
+
"eval_steps_per_second": 39.089,
|
| 442 |
+
"step": 31000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.51,
|
| 446 |
+
"learning_rate": 2.0750045894416617e-05,
|
| 447 |
+
"loss": 2.7317,
|
| 448 |
+
"step": 32000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.51,
|
| 452 |
+
"eval_loss": 4.120232582092285,
|
| 453 |
+
"eval_runtime": 5.4956,
|
| 454 |
+
"eval_samples_per_second": 78.063,
|
| 455 |
+
"eval_steps_per_second": 39.122,
|
| 456 |
+
"step": 32000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.56,
|
| 460 |
+
"learning_rate": 2.0356665180561748e-05,
|
| 461 |
+
"loss": 2.7378,
|
| 462 |
+
"step": 33000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.56,
|
| 466 |
+
"eval_loss": 4.113248825073242,
|
| 467 |
+
"eval_runtime": 5.4916,
|
| 468 |
+
"eval_samples_per_second": 78.119,
|
| 469 |
+
"eval_steps_per_second": 39.151,
|
| 470 |
+
"step": 33000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.6,
|
| 474 |
+
"learning_rate": 1.9963677847420733e-05,
|
| 475 |
+
"loss": 2.7309,
|
| 476 |
+
"step": 34000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.6,
|
| 480 |
+
"eval_loss": 4.104722499847412,
|
| 481 |
+
"eval_runtime": 5.5185,
|
| 482 |
+
"eval_samples_per_second": 77.739,
|
| 483 |
+
"eval_steps_per_second": 38.96,
|
| 484 |
+
"step": 34000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.65,
|
| 488 |
+
"learning_rate": 1.9570297133565864e-05,
|
| 489 |
+
"loss": 2.7791,
|
| 490 |
+
"step": 35000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.65,
|
| 494 |
+
"eval_loss": 4.09762716293335,
|
| 495 |
+
"eval_runtime": 5.5051,
|
| 496 |
+
"eval_samples_per_second": 77.928,
|
| 497 |
+
"eval_steps_per_second": 39.055,
|
| 498 |
+
"step": 35000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.7,
|
| 502 |
+
"learning_rate": 1.9176916419710998e-05,
|
| 503 |
+
"loss": 2.7427,
|
| 504 |
+
"step": 36000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.7,
|
| 508 |
+
"eval_loss": 4.087375164031982,
|
| 509 |
+
"eval_runtime": 5.502,
|
| 510 |
+
"eval_samples_per_second": 77.972,
|
| 511 |
+
"eval_steps_per_second": 39.077,
|
| 512 |
+
"step": 36000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.75,
|
| 516 |
+
"learning_rate": 1.8784322467283838e-05,
|
| 517 |
+
"loss": 2.7184,
|
| 518 |
+
"step": 37000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.75,
|
| 522 |
+
"eval_loss": 4.0953216552734375,
|
| 523 |
+
"eval_runtime": 5.4993,
|
| 524 |
+
"eval_samples_per_second": 78.01,
|
| 525 |
+
"eval_steps_per_second": 39.096,
|
| 526 |
+
"step": 37000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.79,
|
| 530 |
+
"learning_rate": 1.8390941753428972e-05,
|
| 531 |
+
"loss": 2.7107,
|
| 532 |
+
"step": 38000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.79,
|
| 536 |
+
"eval_loss": 4.09627103805542,
|
| 537 |
+
"eval_runtime": 5.5281,
|
| 538 |
+
"eval_samples_per_second": 77.604,
|
| 539 |
+
"eval_steps_per_second": 38.892,
|
| 540 |
+
"step": 38000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.84,
|
| 544 |
+
"learning_rate": 1.7997561039574103e-05,
|
| 545 |
+
"loss": 2.7122,
|
| 546 |
+
"step": 39000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.84,
|
| 550 |
+
"eval_loss": 4.0841288566589355,
|
| 551 |
+
"eval_runtime": 5.5134,
|
| 552 |
+
"eval_samples_per_second": 77.811,
|
| 553 |
+
"eval_steps_per_second": 38.996,
|
| 554 |
+
"step": 39000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.89,
|
| 558 |
+
"learning_rate": 1.760418032571923e-05,
|
| 559 |
+
"loss": 2.7172,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.89,
|
| 564 |
+
"eval_loss": 4.085172176361084,
|
| 565 |
+
"eval_runtime": 5.5109,
|
| 566 |
+
"eval_samples_per_second": 77.845,
|
| 567 |
+
"eval_steps_per_second": 39.013,
|
| 568 |
+
"step": 40000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.94,
|
| 572 |
+
"learning_rate": 1.721119299257822e-05,
|
| 573 |
+
"loss": 2.7126,
|
| 574 |
+
"step": 41000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.94,
|
| 578 |
+
"eval_loss": 4.063177108764648,
|
| 579 |
+
"eval_runtime": 5.484,
|
| 580 |
+
"eval_samples_per_second": 78.227,
|
| 581 |
+
"eval_steps_per_second": 39.205,
|
| 582 |
+
"step": 41000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.98,
|
| 586 |
+
"learning_rate": 1.681781227872335e-05,
|
| 587 |
+
"loss": 2.7063,
|
| 588 |
+
"step": 42000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.98,
|
| 592 |
+
"eval_loss": 4.064344882965088,
|
| 593 |
+
"eval_runtime": 5.5064,
|
| 594 |
+
"eval_samples_per_second": 77.909,
|
| 595 |
+
"eval_steps_per_second": 39.045,
|
| 596 |
+
"step": 42000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.03,
|
| 600 |
+
"learning_rate": 1.642443156486848e-05,
|
| 601 |
+
"loss": 2.5311,
|
| 602 |
+
"step": 43000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.03,
|
| 606 |
+
"eval_loss": 4.084793567657471,
|
| 607 |
+
"eval_runtime": 5.5081,
|
| 608 |
+
"eval_samples_per_second": 77.885,
|
| 609 |
+
"eval_steps_per_second": 39.033,
|
| 610 |
+
"step": 43000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.08,
|
| 614 |
+
"learning_rate": 1.6031444231727466e-05,
|
| 615 |
+
"loss": 2.4496,
|
| 616 |
+
"step": 44000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.08,
|
| 620 |
+
"eval_loss": 4.094330310821533,
|
| 621 |
+
"eval_runtime": 5.4892,
|
| 622 |
+
"eval_samples_per_second": 78.153,
|
| 623 |
+
"eval_steps_per_second": 39.167,
|
| 624 |
+
"step": 44000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.12,
|
| 628 |
+
"learning_rate": 1.563845689858645e-05,
|
| 629 |
+
"loss": 2.4597,
|
| 630 |
+
"step": 45000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.12,
|
| 634 |
+
"eval_loss": 4.079880714416504,
|
| 635 |
+
"eval_runtime": 5.4837,
|
| 636 |
+
"eval_samples_per_second": 78.232,
|
| 637 |
+
"eval_steps_per_second": 39.207,
|
| 638 |
+
"step": 45000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.17,
|
| 642 |
+
"learning_rate": 1.5245076184731584e-05,
|
| 643 |
+
"loss": 2.4472,
|
| 644 |
+
"step": 46000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.17,
|
| 648 |
+
"eval_loss": 4.080161094665527,
|
| 649 |
+
"eval_runtime": 5.4997,
|
| 650 |
+
"eval_samples_per_second": 78.005,
|
| 651 |
+
"eval_steps_per_second": 39.093,
|
| 652 |
+
"step": 46000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.22,
|
| 656 |
+
"learning_rate": 1.4851695470876715e-05,
|
| 657 |
+
"loss": 2.4628,
|
| 658 |
+
"step": 47000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.22,
|
| 662 |
+
"eval_loss": 4.088040828704834,
|
| 663 |
+
"eval_runtime": 5.492,
|
| 664 |
+
"eval_samples_per_second": 78.114,
|
| 665 |
+
"eval_steps_per_second": 39.148,
|
| 666 |
+
"step": 47000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.27,
|
| 670 |
+
"learning_rate": 1.4458314757021846e-05,
|
| 671 |
+
"loss": 2.4508,
|
| 672 |
+
"step": 48000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.27,
|
| 676 |
+
"eval_loss": 4.079111576080322,
|
| 677 |
+
"eval_runtime": 5.4843,
|
| 678 |
+
"eval_samples_per_second": 78.224,
|
| 679 |
+
"eval_steps_per_second": 39.203,
|
| 680 |
+
"step": 48000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.31,
|
| 684 |
+
"learning_rate": 1.4065327423880831e-05,
|
| 685 |
+
"loss": 2.4743,
|
| 686 |
+
"step": 49000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.31,
|
| 690 |
+
"eval_loss": 4.076536655426025,
|
| 691 |
+
"eval_runtime": 5.5106,
|
| 692 |
+
"eval_samples_per_second": 77.85,
|
| 693 |
+
"eval_steps_per_second": 39.016,
|
| 694 |
+
"step": 49000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.36,
|
| 698 |
+
"learning_rate": 1.3671946710025964e-05,
|
| 699 |
+
"loss": 2.4692,
|
| 700 |
+
"step": 50000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.36,
|
| 704 |
+
"eval_loss": 4.073933124542236,
|
| 705 |
+
"eval_runtime": 5.4811,
|
| 706 |
+
"eval_samples_per_second": 78.269,
|
| 707 |
+
"eval_steps_per_second": 39.226,
|
| 708 |
+
"step": 50000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.41,
|
| 712 |
+
"learning_rate": 1.327895937688495e-05,
|
| 713 |
+
"loss": 2.4651,
|
| 714 |
+
"step": 51000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.41,
|
| 718 |
+
"eval_loss": 4.068994522094727,
|
| 719 |
+
"eval_runtime": 5.4881,
|
| 720 |
+
"eval_samples_per_second": 78.168,
|
| 721 |
+
"eval_steps_per_second": 39.175,
|
| 722 |
+
"step": 51000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.45,
|
| 726 |
+
"learning_rate": 1.2885578663030082e-05,
|
| 727 |
+
"loss": 2.4885,
|
| 728 |
+
"step": 52000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.45,
|
| 732 |
+
"eval_loss": 4.072272300720215,
|
| 733 |
+
"eval_runtime": 5.4901,
|
| 734 |
+
"eval_samples_per_second": 78.141,
|
| 735 |
+
"eval_steps_per_second": 39.162,
|
| 736 |
+
"step": 52000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.5,
|
| 740 |
+
"learning_rate": 1.2492591329889067e-05,
|
| 741 |
+
"loss": 2.5023,
|
| 742 |
+
"step": 53000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.5,
|
| 746 |
+
"eval_loss": 4.06748104095459,
|
| 747 |
+
"eval_runtime": 5.5201,
|
| 748 |
+
"eval_samples_per_second": 77.716,
|
| 749 |
+
"eval_steps_per_second": 38.948,
|
| 750 |
+
"step": 53000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.55,
|
| 754 |
+
"learning_rate": 1.2099210616034198e-05,
|
| 755 |
+
"loss": 2.4651,
|
| 756 |
+
"step": 54000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.55,
|
| 760 |
+
"eval_loss": 4.064865589141846,
|
| 761 |
+
"eval_runtime": 5.5135,
|
| 762 |
+
"eval_samples_per_second": 77.809,
|
| 763 |
+
"eval_steps_per_second": 38.995,
|
| 764 |
+
"step": 54000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.6,
|
| 768 |
+
"learning_rate": 1.1706223282893185e-05,
|
| 769 |
+
"loss": 2.4774,
|
| 770 |
+
"step": 55000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.6,
|
| 774 |
+
"eval_loss": 4.06947660446167,
|
| 775 |
+
"eval_runtime": 5.4995,
|
| 776 |
+
"eval_samples_per_second": 78.006,
|
| 777 |
+
"eval_steps_per_second": 39.094,
|
| 778 |
+
"step": 55000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.64,
|
| 782 |
+
"learning_rate": 1.1312842569038316e-05,
|
| 783 |
+
"loss": 2.4717,
|
| 784 |
+
"step": 56000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.64,
|
| 788 |
+
"eval_loss": 4.055931091308594,
|
| 789 |
+
"eval_runtime": 5.4978,
|
| 790 |
+
"eval_samples_per_second": 78.032,
|
| 791 |
+
"eval_steps_per_second": 39.107,
|
| 792 |
+
"step": 56000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.69,
|
| 796 |
+
"learning_rate": 1.0919461855183447e-05,
|
| 797 |
+
"loss": 2.4856,
|
| 798 |
+
"step": 57000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.69,
|
| 802 |
+
"eval_loss": 4.051236629486084,
|
| 803 |
+
"eval_runtime": 5.5101,
|
| 804 |
+
"eval_samples_per_second": 77.857,
|
| 805 |
+
"eval_steps_per_second": 39.019,
|
| 806 |
+
"step": 57000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.74,
|
| 810 |
+
"learning_rate": 1.0526474522042433e-05,
|
| 811 |
+
"loss": 2.4572,
|
| 812 |
+
"step": 58000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.74,
|
| 816 |
+
"eval_loss": 4.0473432540893555,
|
| 817 |
+
"eval_runtime": 5.5015,
|
| 818 |
+
"eval_samples_per_second": 77.979,
|
| 819 |
+
"eval_steps_per_second": 39.08,
|
| 820 |
+
"step": 58000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.79,
|
| 824 |
+
"learning_rate": 1.0133093808187564e-05,
|
| 825 |
+
"loss": 2.486,
|
| 826 |
+
"step": 59000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.79,
|
| 830 |
+
"eval_loss": 4.043802261352539,
|
| 831 |
+
"eval_runtime": 5.52,
|
| 832 |
+
"eval_samples_per_second": 77.717,
|
| 833 |
+
"eval_steps_per_second": 38.949,
|
| 834 |
+
"step": 59000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.83,
|
| 838 |
+
"learning_rate": 9.74010647504655e-06,
|
| 839 |
+
"loss": 2.449,
|
| 840 |
+
"step": 60000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.83,
|
| 844 |
+
"eval_loss": 4.038473606109619,
|
| 845 |
+
"eval_runtime": 5.5095,
|
| 846 |
+
"eval_samples_per_second": 77.866,
|
| 847 |
+
"eval_steps_per_second": 39.024,
|
| 848 |
+
"step": 60000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.88,
|
| 852 |
+
"learning_rate": 9.34672576119168e-06,
|
| 853 |
+
"loss": 2.456,
|
| 854 |
+
"step": 61000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.88,
|
| 858 |
+
"eval_loss": 4.035487651824951,
|
| 859 |
+
"eval_runtime": 5.5078,
|
| 860 |
+
"eval_samples_per_second": 77.889,
|
| 861 |
+
"eval_steps_per_second": 39.035,
|
| 862 |
+
"step": 61000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.93,
|
| 866 |
+
"learning_rate": 8.953345047336813e-06,
|
| 867 |
+
"loss": 2.4802,
|
| 868 |
+
"step": 62000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.93,
|
| 872 |
+
"eval_loss": 4.0377516746521,
|
| 873 |
+
"eval_runtime": 5.5124,
|
| 874 |
+
"eval_samples_per_second": 77.824,
|
| 875 |
+
"eval_steps_per_second": 39.003,
|
| 876 |
+
"step": 62000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.97,
|
| 880 |
+
"learning_rate": 8.559964333481944e-06,
|
| 881 |
+
"loss": 2.4635,
|
| 882 |
+
"step": 63000
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.97,
|
| 886 |
+
"eval_loss": 4.03075647354126,
|
| 887 |
+
"eval_runtime": 5.5127,
|
| 888 |
+
"eval_samples_per_second": 77.82,
|
| 889 |
+
"eval_steps_per_second": 39.001,
|
| 890 |
+
"step": 63000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.02,
|
| 894 |
+
"learning_rate": 8.16697700034093e-06,
|
| 895 |
+
"loss": 2.3742,
|
| 896 |
+
"step": 64000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.02,
|
| 900 |
+
"eval_loss": 4.048806667327881,
|
| 901 |
+
"eval_runtime": 5.5265,
|
| 902 |
+
"eval_samples_per_second": 77.626,
|
| 903 |
+
"eval_steps_per_second": 38.904,
|
| 904 |
+
"step": 64000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.07,
|
| 908 |
+
"learning_rate": 7.77359628648606e-06,
|
| 909 |
+
"loss": 2.2371,
|
| 910 |
+
"step": 65000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.07,
|
| 914 |
+
"eval_loss": 4.057917594909668,
|
| 915 |
+
"eval_runtime": 5.5266,
|
| 916 |
+
"eval_samples_per_second": 77.625,
|
| 917 |
+
"eval_steps_per_second": 38.903,
|
| 918 |
+
"step": 65000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.12,
|
| 922 |
+
"learning_rate": 7.380608953345048e-06,
|
| 923 |
+
"loss": 2.2496,
|
| 924 |
+
"step": 66000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 3.12,
|
| 928 |
+
"eval_loss": 4.062958717346191,
|
| 929 |
+
"eval_runtime": 5.4861,
|
| 930 |
+
"eval_samples_per_second": 78.197,
|
| 931 |
+
"eval_steps_per_second": 39.19,
|
| 932 |
+
"step": 66000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.16,
|
| 936 |
+
"learning_rate": 6.987228239490178e-06,
|
| 937 |
+
"loss": 2.2758,
|
| 938 |
+
"step": 67000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.16,
|
| 942 |
+
"eval_loss": 4.05156135559082,
|
| 943 |
+
"eval_runtime": 5.5178,
|
| 944 |
+
"eval_samples_per_second": 77.748,
|
| 945 |
+
"eval_steps_per_second": 38.965,
|
| 946 |
+
"step": 67000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.21,
|
| 950 |
+
"learning_rate": 6.594240906349165e-06,
|
| 951 |
+
"loss": 2.2489,
|
| 952 |
+
"step": 68000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.21,
|
| 956 |
+
"eval_loss": 4.058535575866699,
|
| 957 |
+
"eval_runtime": 5.4932,
|
| 958 |
+
"eval_samples_per_second": 78.097,
|
| 959 |
+
"eval_steps_per_second": 39.14,
|
| 960 |
+
"step": 68000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.26,
|
| 964 |
+
"learning_rate": 6.200860192494296e-06,
|
| 965 |
+
"loss": 2.2374,
|
| 966 |
+
"step": 69000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.26,
|
| 970 |
+
"eval_loss": 4.071547031402588,
|
| 971 |
+
"eval_runtime": 5.5054,
|
| 972 |
+
"eval_samples_per_second": 77.923,
|
| 973 |
+
"eval_steps_per_second": 39.052,
|
| 974 |
+
"step": 69000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.3,
|
| 978 |
+
"learning_rate": 5.807872859353283e-06,
|
| 979 |
+
"loss": 2.2862,
|
| 980 |
+
"step": 70000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.3,
|
| 984 |
+
"eval_loss": 4.050685405731201,
|
| 985 |
+
"eval_runtime": 5.492,
|
| 986 |
+
"eval_samples_per_second": 78.114,
|
| 987 |
+
"eval_steps_per_second": 39.148,
|
| 988 |
+
"step": 70000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.35,
|
| 992 |
+
"learning_rate": 5.414492145498413e-06,
|
| 993 |
+
"loss": 2.2502,
|
| 994 |
+
"step": 71000
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.35,
|
| 998 |
+
"eval_loss": 4.051216125488281,
|
| 999 |
+
"eval_runtime": 5.5012,
|
| 1000 |
+
"eval_samples_per_second": 77.983,
|
| 1001 |
+
"eval_steps_per_second": 39.082,
|
| 1002 |
+
"step": 71000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 3.4,
|
| 1006 |
+
"learning_rate": 5.021504812357399e-06,
|
| 1007 |
+
"loss": 2.238,
|
| 1008 |
+
"step": 72000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.4,
|
| 1012 |
+
"eval_loss": 4.054477214813232,
|
| 1013 |
+
"eval_runtime": 5.4933,
|
| 1014 |
+
"eval_samples_per_second": 78.095,
|
| 1015 |
+
"eval_steps_per_second": 39.139,
|
| 1016 |
+
"step": 72000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.45,
|
| 1020 |
+
"learning_rate": 4.628517479216386e-06,
|
| 1021 |
+
"loss": 2.2407,
|
| 1022 |
+
"step": 73000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.45,
|
| 1026 |
+
"eval_loss": 4.045898914337158,
|
| 1027 |
+
"eval_runtime": 5.483,
|
| 1028 |
+
"eval_samples_per_second": 78.241,
|
| 1029 |
+
"eval_steps_per_second": 39.212,
|
| 1030 |
+
"step": 73000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.49,
|
| 1034 |
+
"learning_rate": 4.235136765361517e-06,
|
| 1035 |
+
"loss": 2.2529,
|
| 1036 |
+
"step": 74000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.49,
|
| 1040 |
+
"eval_loss": 4.04516077041626,
|
| 1041 |
+
"eval_runtime": 5.4909,
|
| 1042 |
+
"eval_samples_per_second": 78.129,
|
| 1043 |
+
"eval_steps_per_second": 39.156,
|
| 1044 |
+
"step": 74000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.54,
|
| 1048 |
+
"learning_rate": 3.841756051506649e-06,
|
| 1049 |
+
"loss": 2.2453,
|
| 1050 |
+
"step": 75000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.54,
|
| 1054 |
+
"eval_loss": 4.045854091644287,
|
| 1055 |
+
"eval_runtime": 5.4906,
|
| 1056 |
+
"eval_samples_per_second": 78.134,
|
| 1057 |
+
"eval_steps_per_second": 39.158,
|
| 1058 |
+
"step": 75000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.59,
|
| 1062 |
+
"learning_rate": 3.4483753376517792e-06,
|
| 1063 |
+
"loss": 2.2314,
|
| 1064 |
+
"step": 76000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.59,
|
| 1068 |
+
"eval_loss": 4.041632175445557,
|
| 1069 |
+
"eval_runtime": 5.4892,
|
| 1070 |
+
"eval_samples_per_second": 78.153,
|
| 1071 |
+
"eval_steps_per_second": 39.168,
|
| 1072 |
+
"step": 76000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.63,
|
| 1076 |
+
"learning_rate": 3.0553880045107656e-06,
|
| 1077 |
+
"loss": 2.2408,
|
| 1078 |
+
"step": 77000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.63,
|
| 1082 |
+
"eval_loss": 4.037862300872803,
|
| 1083 |
+
"eval_runtime": 5.5221,
|
| 1084 |
+
"eval_samples_per_second": 77.687,
|
| 1085 |
+
"eval_steps_per_second": 38.934,
|
| 1086 |
+
"step": 77000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 3.68,
|
| 1090 |
+
"learning_rate": 2.662007290655897e-06,
|
| 1091 |
+
"loss": 2.2497,
|
| 1092 |
+
"step": 78000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.68,
|
| 1096 |
+
"eval_loss": 4.034841060638428,
|
| 1097 |
+
"eval_runtime": 5.5069,
|
| 1098 |
+
"eval_samples_per_second": 77.903,
|
| 1099 |
+
"eval_steps_per_second": 39.042,
|
| 1100 |
+
"step": 78000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.73,
|
| 1104 |
+
"learning_rate": 2.269413338228738e-06,
|
| 1105 |
+
"loss": 2.2475,
|
| 1106 |
+
"step": 79000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.73,
|
| 1110 |
+
"eval_loss": 4.037409782409668,
|
| 1111 |
+
"eval_runtime": 5.525,
|
| 1112 |
+
"eval_samples_per_second": 77.647,
|
| 1113 |
+
"eval_steps_per_second": 38.914,
|
| 1114 |
+
"step": 79000
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 3.78,
|
| 1118 |
+
"learning_rate": 1.876032624373869e-06,
|
| 1119 |
+
"loss": 2.2376,
|
| 1120 |
+
"step": 80000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.78,
|
| 1124 |
+
"eval_loss": 4.03186559677124,
|
| 1125 |
+
"eval_runtime": 5.5186,
|
| 1126 |
+
"eval_samples_per_second": 77.737,
|
| 1127 |
+
"eval_steps_per_second": 38.959,
|
| 1128 |
+
"step": 80000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 3.82,
|
| 1132 |
+
"learning_rate": 1.4826519105190004e-06,
|
| 1133 |
+
"loss": 2.244,
|
| 1134 |
+
"step": 81000
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.82,
|
| 1138 |
+
"eval_loss": 4.033052921295166,
|
| 1139 |
+
"eval_runtime": 5.5134,
|
| 1140 |
+
"eval_samples_per_second": 77.81,
|
| 1141 |
+
"eval_steps_per_second": 38.996,
|
| 1142 |
+
"step": 81000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.87,
|
| 1146 |
+
"learning_rate": 1.0892711966641317e-06,
|
| 1147 |
+
"loss": 2.2611,
|
| 1148 |
+
"step": 82000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.87,
|
| 1152 |
+
"eval_loss": 4.030561923980713,
|
| 1153 |
+
"eval_runtime": 5.5018,
|
| 1154 |
+
"eval_samples_per_second": 77.974,
|
| 1155 |
+
"eval_steps_per_second": 39.078,
|
| 1156 |
+
"step": 82000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 3.92,
|
| 1160 |
+
"learning_rate": 6.962838635231176e-07,
|
| 1161 |
+
"loss": 2.237,
|
| 1162 |
+
"step": 83000
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.92,
|
| 1166 |
+
"eval_loss": 4.030078411102295,
|
| 1167 |
+
"eval_runtime": 5.5145,
|
| 1168 |
+
"eval_samples_per_second": 77.795,
|
| 1169 |
+
"eval_steps_per_second": 38.988,
|
| 1170 |
+
"step": 83000
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 3.97,
|
| 1174 |
+
"learning_rate": 3.0290314966824894e-07,
|
| 1175 |
+
"loss": 2.2337,
|
| 1176 |
+
"step": 84000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.97,
|
| 1180 |
+
"eval_loss": 4.0290679931640625,
|
| 1181 |
+
"eval_runtime": 5.5016,
|
| 1182 |
+
"eval_samples_per_second": 77.978,
|
| 1183 |
+
"eval_steps_per_second": 39.08,
|
| 1184 |
+
"step": 84000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.0,
|
| 1188 |
+
"step": 84736,
|
| 1189 |
+
"total_flos": 4.4280638078976e+16,
|
| 1190 |
+
"train_loss": 2.6336010373971255,
|
| 1191 |
+
"train_runtime": 9376.0618,
|
| 1192 |
+
"train_samples_per_second": 18.075,
|
| 1193 |
+
"train_steps_per_second": 9.037
|
| 1194 |
+
}
|
| 1195 |
+
],
|
| 1196 |
+
"max_steps": 84736,
|
| 1197 |
+
"num_train_epochs": 4,
|
| 1198 |
+
"total_flos": 4.4280638078976e+16,
|
| 1199 |
+
"trial_name": null,
|
| 1200 |
+
"trial_params": null
|
| 1201 |
+
}
|