End of training
Browse files- README.md +5 -3
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +10 -0
- trainer_state.json +1354 -0
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/bart-large
|
| 5 |
tags:
|
|
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# bart-large-summary-map-reduce-1024
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Num Input Tokens Seen:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: facebook/bart-large
|
| 7 |
tags:
|
|
|
|
| 16 |
|
| 17 |
# bart-large-summary-map-reduce-1024
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the pszemraj/summary-map-reduce dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7894
|
| 22 |
+
- Num Input Tokens Seen: 14258488
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9906542056074765,
|
| 3 |
+
"eval_loss": 0.78944993019104,
|
| 4 |
+
"eval_runtime": 0.9197,
|
| 5 |
+
"eval_samples": 150,
|
| 6 |
+
"eval_samples_per_second": 163.104,
|
| 7 |
+
"eval_steps_per_second": 41.32,
|
| 8 |
+
"num_input_tokens_seen": 14258488,
|
| 9 |
+
"total_flos": 3.0175424769490944e+16,
|
| 10 |
+
"train_loss": 0.895275863011678,
|
| 11 |
+
"train_runtime": 860.318,
|
| 12 |
+
"train_samples": 16692,
|
| 13 |
+
"train_samples_per_second": 58.206,
|
| 14 |
+
"train_steps_per_second": 0.907
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9906542056074765,
|
| 3 |
+
"eval_loss": 0.78944993019104,
|
| 4 |
+
"eval_runtime": 0.9197,
|
| 5 |
+
"eval_samples": 150,
|
| 6 |
+
"eval_samples_per_second": 163.104,
|
| 7 |
+
"eval_steps_per_second": 41.32,
|
| 8 |
+
"num_input_tokens_seen": 14258488
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9906542056074765,
|
| 3 |
+
"num_input_tokens_seen": 14258488,
|
| 4 |
+
"total_flos": 3.0175424769490944e+16,
|
| 5 |
+
"train_loss": 0.895275863011678,
|
| 6 |
+
"train_runtime": 860.318,
|
| 7 |
+
"train_samples": 16692,
|
| 8 |
+
"train_samples_per_second": 58.206,
|
| 9 |
+
"train_steps_per_second": 0.907
|
| 10 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1354 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9906542056074765,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 780,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01917086029235562,
|
| 13 |
+
"grad_norm": 10.80891227722168,
|
| 14 |
+
"learning_rate": 1.282051282051282e-05,
|
| 15 |
+
"loss": 2.5867,
|
| 16 |
+
"num_input_tokens_seen": 85900,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.03834172058471124,
|
| 21 |
+
"grad_norm": 5.320851802825928,
|
| 22 |
+
"learning_rate": 2.564102564102564e-05,
|
| 23 |
+
"loss": 1.778,
|
| 24 |
+
"num_input_tokens_seen": 168784,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.05751258087706686,
|
| 29 |
+
"grad_norm": 2.427093982696533,
|
| 30 |
+
"learning_rate": 3.846153846153846e-05,
|
| 31 |
+
"loss": 1.5006,
|
| 32 |
+
"num_input_tokens_seen": 262708,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07668344116942248,
|
| 37 |
+
"grad_norm": 2.143993854522705,
|
| 38 |
+
"learning_rate": 5.128205128205128e-05,
|
| 39 |
+
"loss": 1.3452,
|
| 40 |
+
"num_input_tokens_seen": 350572,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.09585430146177809,
|
| 45 |
+
"grad_norm": 2.46453595161438,
|
| 46 |
+
"learning_rate": 6.410256410256412e-05,
|
| 47 |
+
"loss": 1.2953,
|
| 48 |
+
"num_input_tokens_seen": 441976,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.11502516175413371,
|
| 53 |
+
"grad_norm": 2.382268190383911,
|
| 54 |
+
"learning_rate": 7.692307692307693e-05,
|
| 55 |
+
"loss": 1.3104,
|
| 56 |
+
"num_input_tokens_seen": 525052,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.13419602204648934,
|
| 61 |
+
"grad_norm": 2.990694761276245,
|
| 62 |
+
"learning_rate": 8.974358974358975e-05,
|
| 63 |
+
"loss": 1.306,
|
| 64 |
+
"num_input_tokens_seen": 626524,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15336688233884496,
|
| 69 |
+
"grad_norm": 1.8448060750961304,
|
| 70 |
+
"learning_rate": 9.99995506314361e-05,
|
| 71 |
+
"loss": 1.2473,
|
| 72 |
+
"num_input_tokens_seen": 709868,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.17253774263120059,
|
| 77 |
+
"grad_norm": 2.6468124389648438,
|
| 78 |
+
"learning_rate": 9.998382357979809e-05,
|
| 79 |
+
"loss": 1.2091,
|
| 80 |
+
"num_input_tokens_seen": 823312,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.19170860292355618,
|
| 85 |
+
"grad_norm": 1.919690728187561,
|
| 86 |
+
"learning_rate": 9.994563617659665e-05,
|
| 87 |
+
"loss": 1.1985,
|
| 88 |
+
"num_input_tokens_seen": 915100,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.2108794632159118,
|
| 93 |
+
"grad_norm": 2.13997483253479,
|
| 94 |
+
"learning_rate": 9.988500558143337e-05,
|
| 95 |
+
"loss": 1.1922,
|
| 96 |
+
"num_input_tokens_seen": 1014472,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.23005032350826743,
|
| 101 |
+
"grad_norm": 1.7454973459243774,
|
| 102 |
+
"learning_rate": 9.980195903881232e-05,
|
| 103 |
+
"loss": 1.2273,
|
| 104 |
+
"num_input_tokens_seen": 1111288,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.24922118380062305,
|
| 109 |
+
"grad_norm": 2.0489871501922607,
|
| 110 |
+
"learning_rate": 9.969653386589748e-05,
|
| 111 |
+
"loss": 1.1729,
|
| 112 |
+
"num_input_tokens_seen": 1193792,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.2683920440929787,
|
| 117 |
+
"grad_norm": 1.851652979850769,
|
| 118 |
+
"learning_rate": 9.956877743574438e-05,
|
| 119 |
+
"loss": 1.188,
|
| 120 |
+
"num_input_tokens_seen": 1293416,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2875629043853343,
|
| 125 |
+
"grad_norm": 2.3986475467681885,
|
| 126 |
+
"learning_rate": 9.94187471560127e-05,
|
| 127 |
+
"loss": 1.1459,
|
| 128 |
+
"num_input_tokens_seen": 1383712,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3067337646776899,
|
| 133 |
+
"grad_norm": 1.6811550855636597,
|
| 134 |
+
"learning_rate": 9.924651044317017e-05,
|
| 135 |
+
"loss": 1.1561,
|
| 136 |
+
"num_input_tokens_seen": 1483596,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3259046249700455,
|
| 141 |
+
"grad_norm": 2.3249671459198,
|
| 142 |
+
"learning_rate": 9.90521446921987e-05,
|
| 143 |
+
"loss": 1.1224,
|
| 144 |
+
"num_input_tokens_seen": 1561392,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.34507548526240117,
|
| 149 |
+
"grad_norm": 2.17244553565979,
|
| 150 |
+
"learning_rate": 9.883573724181683e-05,
|
| 151 |
+
"loss": 1.1283,
|
| 152 |
+
"num_input_tokens_seen": 1660352,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.36424634555475677,
|
| 157 |
+
"grad_norm": 2.0246732234954834,
|
| 158 |
+
"learning_rate": 9.859738533523383e-05,
|
| 159 |
+
"loss": 1.155,
|
| 160 |
+
"num_input_tokens_seen": 1751904,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.38341720584711236,
|
| 165 |
+
"grad_norm": 1.6448779106140137,
|
| 166 |
+
"learning_rate": 9.833719607645324e-05,
|
| 167 |
+
"loss": 1.0645,
|
| 168 |
+
"num_input_tokens_seen": 1844404,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.38341720584711236,
|
| 173 |
+
"eval_loss": 0.9265391826629639,
|
| 174 |
+
"eval_runtime": 0.8899,
|
| 175 |
+
"eval_samples_per_second": 168.564,
|
| 176 |
+
"eval_steps_per_second": 42.703,
|
| 177 |
+
"num_input_tokens_seen": 1844404,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.402588066139468,
|
| 182 |
+
"grad_norm": 3.241382598876953,
|
| 183 |
+
"learning_rate": 9.805528638214542e-05,
|
| 184 |
+
"loss": 1.1597,
|
| 185 |
+
"num_input_tokens_seen": 1930376,
|
| 186 |
+
"step": 105
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4217589264318236,
|
| 190 |
+
"grad_norm": 1.7404630184173584,
|
| 191 |
+
"learning_rate": 9.77517829291108e-05,
|
| 192 |
+
"loss": 1.112,
|
| 193 |
+
"num_input_tokens_seen": 2014196,
|
| 194 |
+
"step": 110
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.44092978672417926,
|
| 198 |
+
"grad_norm": 2.0619559288024902,
|
| 199 |
+
"learning_rate": 9.742682209735727e-05,
|
| 200 |
+
"loss": 1.1078,
|
| 201 |
+
"num_input_tokens_seen": 2105080,
|
| 202 |
+
"step": 115
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.46010064701653486,
|
| 206 |
+
"grad_norm": 1.618997573852539,
|
| 207 |
+
"learning_rate": 9.708054990881763e-05,
|
| 208 |
+
"loss": 1.123,
|
| 209 |
+
"num_input_tokens_seen": 2212296,
|
| 210 |
+
"step": 120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.4792715073088905,
|
| 214 |
+
"grad_norm": 2.0891501903533936,
|
| 215 |
+
"learning_rate": 9.671312196173412e-05,
|
| 216 |
+
"loss": 1.1139,
|
| 217 |
+
"num_input_tokens_seen": 2297740,
|
| 218 |
+
"step": 125
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.4984423676012461,
|
| 222 |
+
"grad_norm": 2.8104231357574463,
|
| 223 |
+
"learning_rate": 9.632470336074009e-05,
|
| 224 |
+
"loss": 1.1419,
|
| 225 |
+
"num_input_tokens_seen": 2393552,
|
| 226 |
+
"step": 130
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5176132278936018,
|
| 230 |
+
"grad_norm": 2.313002586364746,
|
| 231 |
+
"learning_rate": 9.591546864266983e-05,
|
| 232 |
+
"loss": 1.1122,
|
| 233 |
+
"num_input_tokens_seen": 2485636,
|
| 234 |
+
"step": 135
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5367840881859574,
|
| 238 |
+
"grad_norm": 1.6471989154815674,
|
| 239 |
+
"learning_rate": 9.548560169812997e-05,
|
| 240 |
+
"loss": 1.0872,
|
| 241 |
+
"num_input_tokens_seen": 2579380,
|
| 242 |
+
"step": 140
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.555954948478313,
|
| 246 |
+
"grad_norm": 1.8052936792373657,
|
| 247 |
+
"learning_rate": 9.50352956888678e-05,
|
| 248 |
+
"loss": 1.1084,
|
| 249 |
+
"num_input_tokens_seen": 2660580,
|
| 250 |
+
"step": 145
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.5751258087706685,
|
| 254 |
+
"grad_norm": 1.9831300973892212,
|
| 255 |
+
"learning_rate": 9.45647529609736e-05,
|
| 256 |
+
"loss": 1.0753,
|
| 257 |
+
"num_input_tokens_seen": 2752664,
|
| 258 |
+
"step": 150
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.5942966690630243,
|
| 262 |
+
"grad_norm": 1.9232532978057861,
|
| 263 |
+
"learning_rate": 9.4074184953956e-05,
|
| 264 |
+
"loss": 1.0932,
|
| 265 |
+
"num_input_tokens_seen": 2835612,
|
| 266 |
+
"step": 155
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.6134675293553798,
|
| 270 |
+
"grad_norm": 3.607057571411133,
|
| 271 |
+
"learning_rate": 9.356381210573091e-05,
|
| 272 |
+
"loss": 1.0856,
|
| 273 |
+
"num_input_tokens_seen": 2927884,
|
| 274 |
+
"step": 160
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6326383896477354,
|
| 278 |
+
"grad_norm": 1.5196906328201294,
|
| 279 |
+
"learning_rate": 9.303386375356752e-05,
|
| 280 |
+
"loss": 1.0765,
|
| 281 |
+
"num_input_tokens_seen": 3011316,
|
| 282 |
+
"step": 165
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.651809249940091,
|
| 286 |
+
"grad_norm": 2.0994279384613037,
|
| 287 |
+
"learning_rate": 9.248457803103476e-05,
|
| 288 |
+
"loss": 1.0743,
|
| 289 |
+
"num_input_tokens_seen": 3113324,
|
| 290 |
+
"step": 170
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6709801102324466,
|
| 294 |
+
"grad_norm": 2.0873262882232666,
|
| 295 |
+
"learning_rate": 9.191620176099558e-05,
|
| 296 |
+
"loss": 1.0799,
|
| 297 |
+
"num_input_tokens_seen": 3205472,
|
| 298 |
+
"step": 175
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.6901509705248023,
|
| 302 |
+
"grad_norm": 1.7372593879699707,
|
| 303 |
+
"learning_rate": 9.132899034469647e-05,
|
| 304 |
+
"loss": 1.095,
|
| 305 |
+
"num_input_tokens_seen": 3303772,
|
| 306 |
+
"step": 180
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.7093218308171579,
|
| 310 |
+
"grad_norm": 1.7090203762054443,
|
| 311 |
+
"learning_rate": 9.072320764700223e-05,
|
| 312 |
+
"loss": 1.0832,
|
| 313 |
+
"num_input_tokens_seen": 3386080,
|
| 314 |
+
"step": 185
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.7284926911095135,
|
| 318 |
+
"grad_norm": 1.707291603088379,
|
| 319 |
+
"learning_rate": 9.009912587782771e-05,
|
| 320 |
+
"loss": 1.0376,
|
| 321 |
+
"num_input_tokens_seen": 3471524,
|
| 322 |
+
"step": 190
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.7476635514018691,
|
| 326 |
+
"grad_norm": 1.663960576057434,
|
| 327 |
+
"learning_rate": 8.945702546981969e-05,
|
| 328 |
+
"loss": 1.0802,
|
| 329 |
+
"num_input_tokens_seen": 3556336,
|
| 330 |
+
"step": 195
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.7668344116942247,
|
| 334 |
+
"grad_norm": 1.8464930057525635,
|
| 335 |
+
"learning_rate": 8.879719495234363e-05,
|
| 336 |
+
"loss": 1.0769,
|
| 337 |
+
"num_input_tokens_seen": 3640408,
|
| 338 |
+
"step": 200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7668344116942247,
|
| 342 |
+
"eval_loss": 0.862065851688385,
|
| 343 |
+
"eval_runtime": 0.8351,
|
| 344 |
+
"eval_samples_per_second": 179.628,
|
| 345 |
+
"eval_steps_per_second": 45.506,
|
| 346 |
+
"num_input_tokens_seen": 3640408,
|
| 347 |
+
"step": 200
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.7860052719865804,
|
| 351 |
+
"grad_norm": 1.7220999002456665,
|
| 352 |
+
"learning_rate": 8.811993082183243e-05,
|
| 353 |
+
"loss": 1.078,
|
| 354 |
+
"num_input_tokens_seen": 3731324,
|
| 355 |
+
"step": 205
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.805176132278936,
|
| 359 |
+
"grad_norm": 1.7034516334533691,
|
| 360 |
+
"learning_rate": 8.742553740855506e-05,
|
| 361 |
+
"loss": 1.0565,
|
| 362 |
+
"num_input_tokens_seen": 3822944,
|
| 363 |
+
"step": 210
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.8243469925712916,
|
| 367 |
+
"grad_norm": 2.327296257019043,
|
| 368 |
+
"learning_rate": 8.671432673986494e-05,
|
| 369 |
+
"loss": 1.0721,
|
| 370 |
+
"num_input_tokens_seen": 3922476,
|
| 371 |
+
"step": 215
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.8435178528636472,
|
| 375 |
+
"grad_norm": 1.6464370489120483,
|
| 376 |
+
"learning_rate": 8.598661839998972e-05,
|
| 377 |
+
"loss": 1.0573,
|
| 378 |
+
"num_input_tokens_seen": 4003388,
|
| 379 |
+
"step": 220
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.8626887131560029,
|
| 383 |
+
"grad_norm": 2.116698741912842,
|
| 384 |
+
"learning_rate": 8.524273938642538e-05,
|
| 385 |
+
"loss": 1.0459,
|
| 386 |
+
"num_input_tokens_seen": 4084052,
|
| 387 |
+
"step": 225
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8818595734483585,
|
| 391 |
+
"grad_norm": 1.5513197183609009,
|
| 392 |
+
"learning_rate": 8.448302396299905e-05,
|
| 393 |
+
"loss": 1.073,
|
| 394 |
+
"num_input_tokens_seen": 4177072,
|
| 395 |
+
"step": 230
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.9010304337407141,
|
| 399 |
+
"grad_norm": 1.8118634223937988,
|
| 400 |
+
"learning_rate": 8.370781350966683e-05,
|
| 401 |
+
"loss": 1.0786,
|
| 402 |
+
"num_input_tokens_seen": 4272004,
|
| 403 |
+
"step": 235
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.9202012940330697,
|
| 407 |
+
"grad_norm": 1.542823076248169,
|
| 408 |
+
"learning_rate": 8.291745636911382e-05,
|
| 409 |
+
"loss": 1.0556,
|
| 410 |
+
"num_input_tokens_seen": 4367124,
|
| 411 |
+
"step": 240
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.9393721543254253,
|
| 415 |
+
"grad_norm": 1.5214637517929077,
|
| 416 |
+
"learning_rate": 8.211230769022551e-05,
|
| 417 |
+
"loss": 1.052,
|
| 418 |
+
"num_input_tokens_seen": 4454860,
|
| 419 |
+
"step": 245
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.958543014617781,
|
| 423 |
+
"grad_norm": 1.5787030458450317,
|
| 424 |
+
"learning_rate": 8.129272926850079e-05,
|
| 425 |
+
"loss": 1.032,
|
| 426 |
+
"num_input_tokens_seen": 4544744,
|
| 427 |
+
"step": 250
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.9777138749101366,
|
| 431 |
+
"grad_norm": 1.842089295387268,
|
| 432 |
+
"learning_rate": 8.045908938347828e-05,
|
| 433 |
+
"loss": 1.0585,
|
| 434 |
+
"num_input_tokens_seen": 4627284,
|
| 435 |
+
"step": 255
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.9968847352024922,
|
| 439 |
+
"grad_norm": 1.8476406335830688,
|
| 440 |
+
"learning_rate": 7.961176263324901e-05,
|
| 441 |
+
"loss": 1.0045,
|
| 442 |
+
"num_input_tokens_seen": 4715336,
|
| 443 |
+
"step": 260
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0160555954948478,
|
| 447 |
+
"grad_norm": 1.540380835533142,
|
| 448 |
+
"learning_rate": 7.875112976612984e-05,
|
| 449 |
+
"loss": 0.8789,
|
| 450 |
+
"num_input_tokens_seen": 4811720,
|
| 451 |
+
"step": 265
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0352264557872035,
|
| 455 |
+
"grad_norm": 1.593477725982666,
|
| 456 |
+
"learning_rate": 7.787757750957334e-05,
|
| 457 |
+
"loss": 0.8548,
|
| 458 |
+
"num_input_tokens_seen": 4904124,
|
| 459 |
+
"step": 270
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.054397316079559,
|
| 463 |
+
"grad_norm": 2.4607889652252197,
|
| 464 |
+
"learning_rate": 7.699149839639086e-05,
|
| 465 |
+
"loss": 0.8393,
|
| 466 |
+
"num_input_tokens_seen": 4997508,
|
| 467 |
+
"step": 275
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.0735681763719147,
|
| 471 |
+
"grad_norm": 2.0560553073883057,
|
| 472 |
+
"learning_rate": 7.609329058836695e-05,
|
| 473 |
+
"loss": 0.8517,
|
| 474 |
+
"num_input_tokens_seen": 5102324,
|
| 475 |
+
"step": 280
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.0927390366642702,
|
| 479 |
+
"grad_norm": 1.5116240978240967,
|
| 480 |
+
"learning_rate": 7.518335769734439e-05,
|
| 481 |
+
"loss": 0.8498,
|
| 482 |
+
"num_input_tokens_seen": 5203192,
|
| 483 |
+
"step": 285
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.111909896956626,
|
| 487 |
+
"grad_norm": 1.517767071723938,
|
| 488 |
+
"learning_rate": 7.426210860386031e-05,
|
| 489 |
+
"loss": 0.8269,
|
| 490 |
+
"num_input_tokens_seen": 5300184,
|
| 491 |
+
"step": 290
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.1310807572489816,
|
| 495 |
+
"grad_norm": 1.6254216432571411,
|
| 496 |
+
"learning_rate": 7.332995727341462e-05,
|
| 497 |
+
"loss": 0.8496,
|
| 498 |
+
"num_input_tokens_seen": 5405724,
|
| 499 |
+
"step": 295
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.150251617541337,
|
| 503 |
+
"grad_norm": 1.6421043872833252,
|
| 504 |
+
"learning_rate": 7.238732257045372e-05,
|
| 505 |
+
"loss": 0.849,
|
| 506 |
+
"num_input_tokens_seen": 5504644,
|
| 507 |
+
"step": 300
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.150251617541337,
|
| 511 |
+
"eval_loss": 0.8501759767532349,
|
| 512 |
+
"eval_runtime": 0.8525,
|
| 513 |
+
"eval_samples_per_second": 175.946,
|
| 514 |
+
"eval_steps_per_second": 44.573,
|
| 515 |
+
"num_input_tokens_seen": 5504644,
|
| 516 |
+
"step": 300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1694224778336928,
|
| 520 |
+
"grad_norm": 1.7481452226638794,
|
| 521 |
+
"learning_rate": 7.143462807015271e-05,
|
| 522 |
+
"loss": 0.8823,
|
| 523 |
+
"num_input_tokens_seen": 5597560,
|
| 524 |
+
"step": 305
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.1885933381260485,
|
| 528 |
+
"grad_norm": 1.725755214691162,
|
| 529 |
+
"learning_rate": 7.047230186808085e-05,
|
| 530 |
+
"loss": 0.8701,
|
| 531 |
+
"num_input_tokens_seen": 5691244,
|
| 532 |
+
"step": 310
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.207764198418404,
|
| 536 |
+
"grad_norm": 1.4096667766571045,
|
| 537 |
+
"learning_rate": 6.950077638783578e-05,
|
| 538 |
+
"loss": 0.8501,
|
| 539 |
+
"num_input_tokens_seen": 5773336,
|
| 540 |
+
"step": 315
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.2269350587107597,
|
| 544 |
+
"grad_norm": 1.5906323194503784,
|
| 545 |
+
"learning_rate": 6.8520488186733e-05,
|
| 546 |
+
"loss": 0.8684,
|
| 547 |
+
"num_input_tokens_seen": 5849224,
|
| 548 |
+
"step": 320
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.2461059190031152,
|
| 552 |
+
"grad_norm": 2.2204673290252686,
|
| 553 |
+
"learning_rate": 6.753187775963773e-05,
|
| 554 |
+
"loss": 0.8688,
|
| 555 |
+
"num_input_tokens_seen": 5943104,
|
| 556 |
+
"step": 325
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.2652767792954709,
|
| 560 |
+
"grad_norm": 1.40131413936615,
|
| 561 |
+
"learning_rate": 6.653538934102743e-05,
|
| 562 |
+
"loss": 0.8495,
|
| 563 |
+
"num_input_tokens_seen": 6051232,
|
| 564 |
+
"step": 330
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.2844476395878264,
|
| 568 |
+
"grad_norm": 1.578782558441162,
|
| 569 |
+
"learning_rate": 6.553147070537413e-05,
|
| 570 |
+
"loss": 0.8218,
|
| 571 |
+
"num_input_tokens_seen": 6137520,
|
| 572 |
+
"step": 335
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.303618499880182,
|
| 576 |
+
"grad_norm": 1.5068399906158447,
|
| 577 |
+
"learning_rate": 6.452057296593568e-05,
|
| 578 |
+
"loss": 0.8964,
|
| 579 |
+
"num_input_tokens_seen": 6237012,
|
| 580 |
+
"step": 340
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.3227893601725378,
|
| 584 |
+
"grad_norm": 1.6630327701568604,
|
| 585 |
+
"learning_rate": 6.350315037204714e-05,
|
| 586 |
+
"loss": 0.8748,
|
| 587 |
+
"num_input_tokens_seen": 6332764,
|
| 588 |
+
"step": 345
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.3419602204648933,
|
| 592 |
+
"grad_norm": 1.569263219833374,
|
| 593 |
+
"learning_rate": 6.247966010500258e-05,
|
| 594 |
+
"loss": 0.8478,
|
| 595 |
+
"num_input_tokens_seen": 6416688,
|
| 596 |
+
"step": 350
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.361131080757249,
|
| 600 |
+
"grad_norm": 1.4157441854476929,
|
| 601 |
+
"learning_rate": 6.145056207261964e-05,
|
| 602 |
+
"loss": 0.8624,
|
| 603 |
+
"num_input_tokens_seen": 6507660,
|
| 604 |
+
"step": 355
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3803019410496047,
|
| 608 |
+
"grad_norm": 1.4510629177093506,
|
| 609 |
+
"learning_rate": 6.0416318702578826e-05,
|
| 610 |
+
"loss": 0.851,
|
| 611 |
+
"num_input_tokens_seen": 6608708,
|
| 612 |
+
"step": 360
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.3994728013419602,
|
| 616 |
+
"grad_norm": 1.660876989364624,
|
| 617 |
+
"learning_rate": 5.9377394734630464e-05,
|
| 618 |
+
"loss": 0.8401,
|
| 619 |
+
"num_input_tokens_seen": 6700852,
|
| 620 |
+
"step": 365
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.4186436616343159,
|
| 624 |
+
"grad_norm": 1.4707056283950806,
|
| 625 |
+
"learning_rate": 5.833425701176294e-05,
|
| 626 |
+
"loss": 0.8646,
|
| 627 |
+
"num_input_tokens_seen": 6792244,
|
| 628 |
+
"step": 370
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.4378145219266716,
|
| 632 |
+
"grad_norm": 1.563291311264038,
|
| 633 |
+
"learning_rate": 5.728737427042548e-05,
|
| 634 |
+
"loss": 0.8732,
|
| 635 |
+
"num_input_tokens_seen": 6875536,
|
| 636 |
+
"step": 375
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.456985382219027,
|
| 640 |
+
"grad_norm": 1.286574125289917,
|
| 641 |
+
"learning_rate": 5.623721692990039e-05,
|
| 642 |
+
"loss": 0.8449,
|
| 643 |
+
"num_input_tokens_seen": 6958384,
|
| 644 |
+
"step": 380
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.4761562425113828,
|
| 648 |
+
"grad_norm": 1.413732886314392,
|
| 649 |
+
"learning_rate": 5.518425688091906e-05,
|
| 650 |
+
"loss": 0.8459,
|
| 651 |
+
"num_input_tokens_seen": 7040740,
|
| 652 |
+
"step": 385
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.4953271028037383,
|
| 656 |
+
"grad_norm": 1.3040345907211304,
|
| 657 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 658 |
+
"loss": 0.8539,
|
| 659 |
+
"num_input_tokens_seen": 7132892,
|
| 660 |
+
"step": 390
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.514497963096094,
|
| 664 |
+
"grad_norm": 1.4091562032699585,
|
| 665 |
+
"learning_rate": 5.307182230492088e-05,
|
| 666 |
+
"loss": 0.816,
|
| 667 |
+
"num_input_tokens_seen": 7217480,
|
| 668 |
+
"step": 395
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.5336688233884495,
|
| 672 |
+
"grad_norm": 1.5895339250564575,
|
| 673 |
+
"learning_rate": 5.201329700547076e-05,
|
| 674 |
+
"loss": 0.8612,
|
| 675 |
+
"num_input_tokens_seen": 7316212,
|
| 676 |
+
"step": 400
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.5336688233884495,
|
| 680 |
+
"eval_loss": 0.8288899064064026,
|
| 681 |
+
"eval_runtime": 0.8525,
|
| 682 |
+
"eval_samples_per_second": 175.948,
|
| 683 |
+
"eval_steps_per_second": 44.574,
|
| 684 |
+
"num_input_tokens_seen": 7316212,
|
| 685 |
+
"step": 400
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.5528396836808052,
|
| 689 |
+
"grad_norm": 1.523808240890503,
|
| 690 |
+
"learning_rate": 5.095386702616012e-05,
|
| 691 |
+
"loss": 0.8411,
|
| 692 |
+
"num_input_tokens_seen": 7397436,
|
| 693 |
+
"step": 405
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.5720105439731609,
|
| 697 |
+
"grad_norm": 1.4366319179534912,
|
| 698 |
+
"learning_rate": 4.989400842440289e-05,
|
| 699 |
+
"loss": 0.8179,
|
| 700 |
+
"num_input_tokens_seen": 7489804,
|
| 701 |
+
"step": 410
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.5911814042655164,
|
| 705 |
+
"grad_norm": 1.335564136505127,
|
| 706 |
+
"learning_rate": 4.883419745021554e-05,
|
| 707 |
+
"loss": 0.8321,
|
| 708 |
+
"num_input_tokens_seen": 7575200,
|
| 709 |
+
"step": 415
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.610352264557872,
|
| 713 |
+
"grad_norm": 1.5225696563720703,
|
| 714 |
+
"learning_rate": 4.7774910332213e-05,
|
| 715 |
+
"loss": 0.8408,
|
| 716 |
+
"num_input_tokens_seen": 7661620,
|
| 717 |
+
"step": 420
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.6295231248502278,
|
| 721 |
+
"grad_norm": 1.286909580230713,
|
| 722 |
+
"learning_rate": 4.6716623063614094e-05,
|
| 723 |
+
"loss": 0.8335,
|
| 724 |
+
"num_input_tokens_seen": 7751008,
|
| 725 |
+
"step": 425
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6486939851425833,
|
| 729 |
+
"grad_norm": 1.399095058441162,
|
| 730 |
+
"learning_rate": 4.565981118835299e-05,
|
| 731 |
+
"loss": 0.8586,
|
| 732 |
+
"num_input_tokens_seen": 7847504,
|
| 733 |
+
"step": 430
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.6678648454349387,
|
| 737 |
+
"grad_norm": 1.5877128839492798,
|
| 738 |
+
"learning_rate": 4.4604949587392234e-05,
|
| 739 |
+
"loss": 0.8451,
|
| 740 |
+
"num_input_tokens_seen": 7940004,
|
| 741 |
+
"step": 435
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.6870357057272947,
|
| 745 |
+
"grad_norm": 1.661634087562561,
|
| 746 |
+
"learning_rate": 4.355251226533396e-05,
|
| 747 |
+
"loss": 0.8517,
|
| 748 |
+
"num_input_tokens_seen": 8037312,
|
| 749 |
+
"step": 440
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.7062065660196502,
|
| 753 |
+
"grad_norm": 1.2558486461639404,
|
| 754 |
+
"learning_rate": 4.250297213742473e-05,
|
| 755 |
+
"loss": 0.8115,
|
| 756 |
+
"num_input_tokens_seen": 8134436,
|
| 757 |
+
"step": 445
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.7253774263120056,
|
| 761 |
+
"grad_norm": 1.4006855487823486,
|
| 762 |
+
"learning_rate": 4.145680081704989e-05,
|
| 763 |
+
"loss": 0.8471,
|
| 764 |
+
"num_input_tokens_seen": 8223592,
|
| 765 |
+
"step": 450
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.7445482866043613,
|
| 769 |
+
"grad_norm": 1.5870461463928223,
|
| 770 |
+
"learning_rate": 4.0414468403813095e-05,
|
| 771 |
+
"loss": 0.8582,
|
| 772 |
+
"num_input_tokens_seen": 8312984,
|
| 773 |
+
"step": 455
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.763719146896717,
|
| 777 |
+
"grad_norm": 1.4359045028686523,
|
| 778 |
+
"learning_rate": 3.937644327229572e-05,
|
| 779 |
+
"loss": 0.8146,
|
| 780 |
+
"num_input_tokens_seen": 8402888,
|
| 781 |
+
"step": 460
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.7828900071890725,
|
| 785 |
+
"grad_norm": 1.4591436386108398,
|
| 786 |
+
"learning_rate": 3.8343191861591795e-05,
|
| 787 |
+
"loss": 0.8276,
|
| 788 |
+
"num_input_tokens_seen": 8503552,
|
| 789 |
+
"step": 465
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.8020608674814282,
|
| 793 |
+
"grad_norm": 1.6432543992996216,
|
| 794 |
+
"learning_rate": 3.7315178465712366e-05,
|
| 795 |
+
"loss": 0.8524,
|
| 796 |
+
"num_input_tokens_seen": 8604500,
|
| 797 |
+
"step": 470
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.821231727773784,
|
| 801 |
+
"grad_norm": 1.58722984790802,
|
| 802 |
+
"learning_rate": 3.629286502495394e-05,
|
| 803 |
+
"loss": 0.8257,
|
| 804 |
+
"num_input_tokens_seen": 8690612,
|
| 805 |
+
"step": 475
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.8404025880661394,
|
| 809 |
+
"grad_norm": 1.3321154117584229,
|
| 810 |
+
"learning_rate": 3.52767109183244e-05,
|
| 811 |
+
"loss": 0.8194,
|
| 812 |
+
"num_input_tokens_seen": 8785132,
|
| 813 |
+
"step": 480
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.8595734483584951,
|
| 817 |
+
"grad_norm": 1.8727712631225586,
|
| 818 |
+
"learning_rate": 3.426717275712e-05,
|
| 819 |
+
"loss": 0.8414,
|
| 820 |
+
"num_input_tokens_seen": 8882700,
|
| 821 |
+
"step": 485
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8787443086508508,
|
| 825 |
+
"grad_norm": 1.427962303161621,
|
| 826 |
+
"learning_rate": 3.326470417974604e-05,
|
| 827 |
+
"loss": 0.8275,
|
| 828 |
+
"num_input_tokens_seen": 8982636,
|
| 829 |
+
"step": 490
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.8979151689432063,
|
| 833 |
+
"grad_norm": 1.391340970993042,
|
| 834 |
+
"learning_rate": 3.226975564787322e-05,
|
| 835 |
+
"loss": 0.8115,
|
| 836 |
+
"num_input_tokens_seen": 9090140,
|
| 837 |
+
"step": 495
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.9170860292355618,
|
| 841 |
+
"grad_norm": 1.465030312538147,
|
| 842 |
+
"learning_rate": 3.1282774244021715e-05,
|
| 843 |
+
"loss": 0.7934,
|
| 844 |
+
"num_input_tokens_seen": 9167936,
|
| 845 |
+
"step": 500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.9170860292355618,
|
| 849 |
+
"eval_loss": 0.8071622252464294,
|
| 850 |
+
"eval_runtime": 0.8763,
|
| 851 |
+
"eval_samples_per_second": 171.177,
|
| 852 |
+
"eval_steps_per_second": 43.365,
|
| 853 |
+
"num_input_tokens_seen": 9167936,
|
| 854 |
+
"step": 500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.9362568895279175,
|
| 858 |
+
"grad_norm": 1.6803951263427734,
|
| 859 |
+
"learning_rate": 3.0304203470663505e-05,
|
| 860 |
+
"loss": 0.821,
|
| 861 |
+
"num_input_tokens_seen": 9252204,
|
| 862 |
+
"step": 505
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.9554277498202732,
|
| 866 |
+
"grad_norm": 1.4982653856277466,
|
| 867 |
+
"learning_rate": 2.9334483050933503e-05,
|
| 868 |
+
"loss": 0.7982,
|
| 869 |
+
"num_input_tokens_seen": 9326444,
|
| 870 |
+
"step": 510
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.9745986101126287,
|
| 874 |
+
"grad_norm": 1.5553169250488281,
|
| 875 |
+
"learning_rate": 2.8374048731038898e-05,
|
| 876 |
+
"loss": 0.8183,
|
| 877 |
+
"num_input_tokens_seen": 9412396,
|
| 878 |
+
"step": 515
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.9937694704049844,
|
| 882 |
+
"grad_norm": 1.176651954650879,
|
| 883 |
+
"learning_rate": 2.7423332084455544e-05,
|
| 884 |
+
"loss": 0.7837,
|
| 885 |
+
"num_input_tokens_seen": 9497412,
|
| 886 |
+
"step": 520
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.01294033069734,
|
| 890 |
+
"grad_norm": 1.2269119024276733,
|
| 891 |
+
"learning_rate": 2.648276031799934e-05,
|
| 892 |
+
"loss": 0.726,
|
| 893 |
+
"num_input_tokens_seen": 9594720,
|
| 894 |
+
"step": 525
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.0321111909896956,
|
| 898 |
+
"grad_norm": 1.4332973957061768,
|
| 899 |
+
"learning_rate": 2.5552756079859903e-05,
|
| 900 |
+
"loss": 0.6847,
|
| 901 |
+
"num_input_tokens_seen": 9675564,
|
| 902 |
+
"step": 530
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 2.051282051282051,
|
| 906 |
+
"grad_norm": 1.3018600940704346,
|
| 907 |
+
"learning_rate": 2.4633737269682543e-05,
|
| 908 |
+
"loss": 0.682,
|
| 909 |
+
"num_input_tokens_seen": 9772140,
|
| 910 |
+
"step": 535
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.070452911574407,
|
| 914 |
+
"grad_norm": 1.2701021432876587,
|
| 915 |
+
"learning_rate": 2.3726116850783985e-05,
|
| 916 |
+
"loss": 0.6643,
|
| 917 |
+
"num_input_tokens_seen": 9850508,
|
| 918 |
+
"step": 540
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.0896237718667625,
|
| 922 |
+
"grad_norm": 1.2966877222061157,
|
| 923 |
+
"learning_rate": 2.283030266458644e-05,
|
| 924 |
+
"loss": 0.6868,
|
| 925 |
+
"num_input_tokens_seen": 9949592,
|
| 926 |
+
"step": 545
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.108794632159118,
|
| 930 |
+
"grad_norm": 1.4499340057373047,
|
| 931 |
+
"learning_rate": 2.194669724735296e-05,
|
| 932 |
+
"loss": 0.6713,
|
| 933 |
+
"num_input_tokens_seen": 10041244,
|
| 934 |
+
"step": 550
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.127965492451474,
|
| 938 |
+
"grad_norm": 1.791567325592041,
|
| 939 |
+
"learning_rate": 2.1075697649306835e-05,
|
| 940 |
+
"loss": 0.6893,
|
| 941 |
+
"num_input_tokens_seen": 10140004,
|
| 942 |
+
"step": 555
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.1471363527438294,
|
| 946 |
+
"grad_norm": 1.4607737064361572,
|
| 947 |
+
"learning_rate": 2.0217695256216195e-05,
|
| 948 |
+
"loss": 0.6784,
|
| 949 |
+
"num_input_tokens_seen": 10233820,
|
| 950 |
+
"step": 560
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.166307213036185,
|
| 954 |
+
"grad_norm": 1.4586418867111206,
|
| 955 |
+
"learning_rate": 1.937307561352373e-05,
|
| 956 |
+
"loss": 0.6829,
|
| 957 |
+
"num_input_tokens_seen": 10324844,
|
| 958 |
+
"step": 565
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 2.1854780733285404,
|
| 962 |
+
"grad_norm": 1.4719526767730713,
|
| 963 |
+
"learning_rate": 1.854221825310103e-05,
|
| 964 |
+
"loss": 0.6775,
|
| 965 |
+
"num_input_tokens_seen": 10413592,
|
| 966 |
+
"step": 570
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.2046489336208963,
|
| 970 |
+
"grad_norm": 1.4231044054031372,
|
| 971 |
+
"learning_rate": 1.7725496522704998e-05,
|
| 972 |
+
"loss": 0.6872,
|
| 973 |
+
"num_input_tokens_seen": 10503432,
|
| 974 |
+
"step": 575
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.223819793913252,
|
| 978 |
+
"grad_norm": 1.3985334634780884,
|
| 979 |
+
"learning_rate": 1.6923277418213117e-05,
|
| 980 |
+
"loss": 0.65,
|
| 981 |
+
"num_input_tokens_seen": 10600988,
|
| 982 |
+
"step": 580
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.2429906542056073,
|
| 986 |
+
"grad_norm": 1.3148375749588013,
|
| 987 |
+
"learning_rate": 1.6135921418712956e-05,
|
| 988 |
+
"loss": 0.6901,
|
| 989 |
+
"num_input_tokens_seen": 10692664,
|
| 990 |
+
"step": 585
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.262161514497963,
|
| 994 |
+
"grad_norm": 1.3653095960617065,
|
| 995 |
+
"learning_rate": 1.536378232452003e-05,
|
| 996 |
+
"loss": 0.6661,
|
| 997 |
+
"num_input_tokens_seen": 10781516,
|
| 998 |
+
"step": 590
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.2813323747903187,
|
| 1002 |
+
"grad_norm": 1.4331799745559692,
|
| 1003 |
+
"learning_rate": 1.4607207098196852e-05,
|
| 1004 |
+
"loss": 0.669,
|
| 1005 |
+
"num_input_tokens_seen": 10874028,
|
| 1006 |
+
"step": 595
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.300503235082674,
|
| 1010 |
+
"grad_norm": 1.3715401887893677,
|
| 1011 |
+
"learning_rate": 1.3866535708644334e-05,
|
| 1012 |
+
"loss": 0.6701,
|
| 1013 |
+
"num_input_tokens_seen": 10969348,
|
| 1014 |
+
"step": 600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.300503235082674,
|
| 1018 |
+
"eval_loss": 0.8050560355186462,
|
| 1019 |
+
"eval_runtime": 0.8838,
|
| 1020 |
+
"eval_samples_per_second": 169.723,
|
| 1021 |
+
"eval_steps_per_second": 42.997,
|
| 1022 |
+
"num_input_tokens_seen": 10969348,
|
| 1023 |
+
"step": 600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.31967409537503,
|
| 1027 |
+
"grad_norm": 1.2875298261642456,
|
| 1028 |
+
"learning_rate": 1.3142100978336069e-05,
|
| 1029 |
+
"loss": 0.6877,
|
| 1030 |
+
"num_input_tokens_seen": 11064696,
|
| 1031 |
+
"step": 605
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.3388449556673856,
|
| 1035 |
+
"grad_norm": 1.2775810956954956,
|
| 1036 |
+
"learning_rate": 1.2434228433763657e-05,
|
| 1037 |
+
"loss": 0.6752,
|
| 1038 |
+
"num_input_tokens_seen": 11157516,
|
| 1039 |
+
"step": 610
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.358015815959741,
|
| 1043 |
+
"grad_norm": 1.3270821571350098,
|
| 1044 |
+
"learning_rate": 1.1743236159160653e-05,
|
| 1045 |
+
"loss": 0.6915,
|
| 1046 |
+
"num_input_tokens_seen": 11236376,
|
| 1047 |
+
"step": 615
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.377186676252097,
|
| 1051 |
+
"grad_norm": 1.2592318058013916,
|
| 1052 |
+
"learning_rate": 1.1069434653570631e-05,
|
| 1053 |
+
"loss": 0.6786,
|
| 1054 |
+
"num_input_tokens_seen": 11343512,
|
| 1055 |
+
"step": 620
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.3963575365444525,
|
| 1059 |
+
"grad_norm": 1.4185535907745361,
|
| 1060 |
+
"learning_rate": 1.0413126691323666e-05,
|
| 1061 |
+
"loss": 0.6876,
|
| 1062 |
+
"num_input_tokens_seen": 11433156,
|
| 1063 |
+
"step": 625
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.415528396836808,
|
| 1067 |
+
"grad_norm": 1.5168098211288452,
|
| 1068 |
+
"learning_rate": 9.774607185984002e-06,
|
| 1069 |
+
"loss": 0.6911,
|
| 1070 |
+
"num_input_tokens_seen": 11517328,
|
| 1071 |
+
"step": 630
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.4346992571291635,
|
| 1075 |
+
"grad_norm": 1.2858244180679321,
|
| 1076 |
+
"learning_rate": 9.154163057829879e-06,
|
| 1077 |
+
"loss": 0.6618,
|
| 1078 |
+
"num_input_tokens_seen": 11602144,
|
| 1079 |
+
"step": 635
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.4538701174215194,
|
| 1083 |
+
"grad_norm": 1.2297165393829346,
|
| 1084 |
+
"learning_rate": 8.552073104925295e-06,
|
| 1085 |
+
"loss": 0.6804,
|
| 1086 |
+
"num_input_tokens_seen": 11691216,
|
| 1087 |
+
"step": 640
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.473040977713875,
|
| 1091 |
+
"grad_norm": 1.2545212507247925,
|
| 1092 |
+
"learning_rate": 7.968607877841332e-06,
|
| 1093 |
+
"loss": 0.6669,
|
| 1094 |
+
"num_input_tokens_seen": 11789340,
|
| 1095 |
+
"step": 645
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.4922118380062304,
|
| 1099 |
+
"grad_norm": 1.3260319232940674,
|
| 1100 |
+
"learning_rate": 7.404029558083653e-06,
|
| 1101 |
+
"loss": 0.6847,
|
| 1102 |
+
"num_input_tokens_seen": 11884208,
|
| 1103 |
+
"step": 650
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.5113826982985863,
|
| 1107 |
+
"grad_norm": 1.2979117631912231,
|
| 1108 |
+
"learning_rate": 6.858591840280626e-06,
|
| 1109 |
+
"loss": 0.6592,
|
| 1110 |
+
"num_input_tokens_seen": 11972124,
|
| 1111 |
+
"step": 655
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 2.5305535585909418,
|
| 1115 |
+
"grad_norm": 1.2984734773635864,
|
| 1116 |
+
"learning_rate": 6.3325398181849845e-06,
|
| 1117 |
+
"loss": 0.6579,
|
| 1118 |
+
"num_input_tokens_seen": 12057320,
|
| 1119 |
+
"step": 660
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.5497244188832973,
|
| 1123 |
+
"grad_norm": 1.2366037368774414,
|
| 1124 |
+
"learning_rate": 5.826109874540409e-06,
|
| 1125 |
+
"loss": 0.6666,
|
| 1126 |
+
"num_input_tokens_seen": 12154952,
|
| 1127 |
+
"step": 665
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.5688952791756527,
|
| 1131 |
+
"grad_norm": 1.2756296396255493,
|
| 1132 |
+
"learning_rate": 5.33952957486234e-06,
|
| 1133 |
+
"loss": 0.6903,
|
| 1134 |
+
"num_input_tokens_seen": 12256604,
|
| 1135 |
+
"step": 670
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.5880661394680087,
|
| 1139 |
+
"grad_norm": 1.3016470670700073,
|
| 1140 |
+
"learning_rate": 4.873017565180871e-06,
|
| 1141 |
+
"loss": 0.6654,
|
| 1142 |
+
"num_input_tokens_seen": 12341988,
|
| 1143 |
+
"step": 675
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.607236999760364,
|
| 1147 |
+
"grad_norm": 1.3244975805282593,
|
| 1148 |
+
"learning_rate": 4.4267834737916296e-06,
|
| 1149 |
+
"loss": 0.6597,
|
| 1150 |
+
"num_input_tokens_seen": 12442644,
|
| 1151 |
+
"step": 680
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.62640786005272,
|
| 1155 |
+
"grad_norm": 1.4668656587600708,
|
| 1156 |
+
"learning_rate": 4.001027817058789e-06,
|
| 1157 |
+
"loss": 0.6709,
|
| 1158 |
+
"num_input_tokens_seen": 12538688,
|
| 1159 |
+
"step": 685
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.6455787203450756,
|
| 1163 |
+
"grad_norm": 1.4666439294815063,
|
| 1164 |
+
"learning_rate": 3.5959419093125946e-06,
|
| 1165 |
+
"loss": 0.6793,
|
| 1166 |
+
"num_input_tokens_seen": 12621632,
|
| 1167 |
+
"step": 690
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.664749580637431,
|
| 1171 |
+
"grad_norm": 1.2680643796920776,
|
| 1172 |
+
"learning_rate": 3.211707776881739e-06,
|
| 1173 |
+
"loss": 0.6562,
|
| 1174 |
+
"num_input_tokens_seen": 12715832,
|
| 1175 |
+
"step": 695
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.6839204409297865,
|
| 1179 |
+
"grad_norm": 1.3070735931396484,
|
| 1180 |
+
"learning_rate": 2.848498076299483e-06,
|
| 1181 |
+
"loss": 0.6579,
|
| 1182 |
+
"num_input_tokens_seen": 12814620,
|
| 1183 |
+
"step": 700
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.6839204409297865,
|
| 1187 |
+
"eval_loss": 0.7903470396995544,
|
| 1188 |
+
"eval_runtime": 0.941,
|
| 1189 |
+
"eval_samples_per_second": 159.398,
|
| 1190 |
+
"eval_steps_per_second": 40.381,
|
| 1191 |
+
"num_input_tokens_seen": 12814620,
|
| 1192 |
+
"step": 700
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.7030913012221425,
|
| 1196 |
+
"grad_norm": 1.4454238414764404,
|
| 1197 |
+
"learning_rate": 2.506476016719922e-06,
|
| 1198 |
+
"loss": 0.6818,
|
| 1199 |
+
"num_input_tokens_seen": 12909896,
|
| 1200 |
+
"step": 705
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.722262161514498,
|
| 1204 |
+
"grad_norm": 1.249842882156372,
|
| 1205 |
+
"learning_rate": 2.1857952865796614e-06,
|
| 1206 |
+
"loss": 0.6655,
|
| 1207 |
+
"num_input_tokens_seen": 13001288,
|
| 1208 |
+
"step": 710
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.7414330218068534,
|
| 1212 |
+
"grad_norm": 1.312296986579895,
|
| 1213 |
+
"learning_rate": 1.8865999845374793e-06,
|
| 1214 |
+
"loss": 0.656,
|
| 1215 |
+
"num_input_tokens_seen": 13094568,
|
| 1216 |
+
"step": 715
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.7606038820992094,
|
| 1220 |
+
"grad_norm": 1.1614197492599487,
|
| 1221 |
+
"learning_rate": 1.6090245547232707e-06,
|
| 1222 |
+
"loss": 0.6664,
|
| 1223 |
+
"num_input_tokens_seen": 13181872,
|
| 1224 |
+
"step": 720
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.779774742391565,
|
| 1228 |
+
"grad_norm": 1.249230146408081,
|
| 1229 |
+
"learning_rate": 1.353193726325247e-06,
|
| 1230 |
+
"loss": 0.6643,
|
| 1231 |
+
"num_input_tokens_seen": 13276044,
|
| 1232 |
+
"step": 725
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 2.7989456026839203,
|
| 1236 |
+
"grad_norm": 1.3258079290390015,
|
| 1237 |
+
"learning_rate": 1.1192224575425848e-06,
|
| 1238 |
+
"loss": 0.6352,
|
| 1239 |
+
"num_input_tokens_seen": 13361008,
|
| 1240 |
+
"step": 730
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 2.818116462976276,
|
| 1244 |
+
"grad_norm": 1.364700198173523,
|
| 1245 |
+
"learning_rate": 9.072158839286748e-07,
|
| 1246 |
+
"loss": 0.6686,
|
| 1247 |
+
"num_input_tokens_seen": 13458560,
|
| 1248 |
+
"step": 735
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.8372873232686318,
|
| 1252 |
+
"grad_norm": 1.3140686750411987,
|
| 1253 |
+
"learning_rate": 7.172692711482021e-07,
|
| 1254 |
+
"loss": 0.6623,
|
| 1255 |
+
"num_input_tokens_seen": 13551928,
|
| 1256 |
+
"step": 740
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.8564581835609872,
|
| 1260 |
+
"grad_norm": 1.4460844993591309,
|
| 1261 |
+
"learning_rate": 5.494679721693152e-07,
|
| 1262 |
+
"loss": 0.6658,
|
| 1263 |
+
"num_input_tokens_seen": 13632792,
|
| 1264 |
+
"step": 745
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.875629043853343,
|
| 1268 |
+
"grad_norm": 1.2111197710037231,
|
| 1269 |
+
"learning_rate": 4.0388738891002366e-07,
|
| 1270 |
+
"loss": 0.6239,
|
| 1271 |
+
"num_input_tokens_seen": 13723172,
|
| 1272 |
+
"step": 750
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.8947999041456987,
|
| 1276 |
+
"grad_norm": 1.2612218856811523,
|
| 1277 |
+
"learning_rate": 2.8059293835620003e-07,
|
| 1278 |
+
"loss": 0.6682,
|
| 1279 |
+
"num_input_tokens_seen": 13820332,
|
| 1280 |
+
"step": 755
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.913970764438054,
|
| 1284 |
+
"grad_norm": 1.3601187467575073,
|
| 1285 |
+
"learning_rate": 1.7964002316628315e-07,
|
| 1286 |
+
"loss": 0.6729,
|
| 1287 |
+
"num_input_tokens_seen": 13907996,
|
| 1288 |
+
"step": 760
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 2.9331416247304096,
|
| 1292 |
+
"grad_norm": 1.3947527408599854,
|
| 1293 |
+
"learning_rate": 1.0107400677596412e-07,
|
| 1294 |
+
"loss": 0.6736,
|
| 1295 |
+
"num_input_tokens_seen": 13993196,
|
| 1296 |
+
"step": 765
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.9523124850227656,
|
| 1300 |
+
"grad_norm": 1.2355984449386597,
|
| 1301 |
+
"learning_rate": 4.493019301401446e-08,
|
| 1302 |
+
"loss": 0.6655,
|
| 1303 |
+
"num_input_tokens_seen": 14084984,
|
| 1304 |
+
"step": 770
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.971483345315121,
|
| 1308 |
+
"grad_norm": 1.2893033027648926,
|
| 1309 |
+
"learning_rate": 1.1233810238425735e-08,
|
| 1310 |
+
"loss": 0.657,
|
| 1311 |
+
"num_input_tokens_seen": 14169848,
|
| 1312 |
+
"step": 775
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.9906542056074765,
|
| 1316 |
+
"grad_norm": 1.3213859796524048,
|
| 1317 |
+
"learning_rate": 0.0,
|
| 1318 |
+
"loss": 0.6589,
|
| 1319 |
+
"num_input_tokens_seen": 14258488,
|
| 1320 |
+
"step": 780
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.9906542056074765,
|
| 1324 |
+
"num_input_tokens_seen": 14258488,
|
| 1325 |
+
"step": 780,
|
| 1326 |
+
"total_flos": 3.0175424769490944e+16,
|
| 1327 |
+
"train_loss": 0.895275863011678,
|
| 1328 |
+
"train_runtime": 860.318,
|
| 1329 |
+
"train_samples_per_second": 58.206,
|
| 1330 |
+
"train_steps_per_second": 0.907
|
| 1331 |
+
}
|
| 1332 |
+
],
|
| 1333 |
+
"logging_steps": 5,
|
| 1334 |
+
"max_steps": 780,
|
| 1335 |
+
"num_input_tokens_seen": 14258488,
|
| 1336 |
+
"num_train_epochs": 3,
|
| 1337 |
+
"save_steps": 100,
|
| 1338 |
+
"stateful_callbacks": {
|
| 1339 |
+
"TrainerControl": {
|
| 1340 |
+
"args": {
|
| 1341 |
+
"should_epoch_stop": false,
|
| 1342 |
+
"should_evaluate": false,
|
| 1343 |
+
"should_log": false,
|
| 1344 |
+
"should_save": true,
|
| 1345 |
+
"should_training_stop": true
|
| 1346 |
+
},
|
| 1347 |
+
"attributes": {}
|
| 1348 |
+
}
|
| 1349 |
+
},
|
| 1350 |
+
"total_flos": 3.0175424769490944e+16,
|
| 1351 |
+
"train_batch_size": 4,
|
| 1352 |
+
"trial_name": null,
|
| 1353 |
+
"trial_params": null
|
| 1354 |
+
}
|