End of training
Browse files- README.md +14 -2
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1719937148.s_005_m.77202.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +3034 -0
README.md
CHANGED
|
@@ -3,11 +3,23 @@ license: mit
|
|
| 3 |
base_model: openai-community/gpt2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: gpt_train_12_512
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# gpt_train_12_512
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 8.9141
|
| 21 |
- Accuracy: 0.0917
|
|
|
|
| 3 |
base_model: openai-community/gpt2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- gokuls/wiki_book_corpus_raw_dataset_tiny
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: gpt_train_12_512
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Causal Language Modeling
|
| 15 |
+
type: text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: gokuls/wiki_book_corpus_raw_dataset_tiny
|
| 18 |
+
type: gokuls/wiki_book_corpus_raw_dataset_tiny
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.09167533902983765
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 27 |
|
| 28 |
# gpt_train_12_512
|
| 29 |
|
| 30 |
+
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the gokuls/wiki_book_corpus_raw_dataset_tiny dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 8.9141
|
| 33 |
- Accuracy: 0.0917
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0067933301849093615,
|
| 3 |
+
"eval_accuracy": 0.09167533902983765,
|
| 4 |
+
"eval_loss": 8.9140625,
|
| 5 |
+
"eval_runtime": 492.4035,
|
| 6 |
+
"eval_samples": 33767,
|
| 7 |
+
"eval_samples_per_second": 68.576,
|
| 8 |
+
"eval_steps_per_second": 2.857,
|
| 9 |
+
"perplexity": 7435.807790500043,
|
| 10 |
+
"total_flos": 1043124562427904.0,
|
| 11 |
+
"train_loss": 9.606408756684491,
|
| 12 |
+
"train_runtime": 94484.0244,
|
| 13 |
+
"train_samples": 660643,
|
| 14 |
+
"train_samples_per_second": 699.211,
|
| 15 |
+
"train_steps_per_second": 29.134
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0067933301849093615,
|
| 3 |
+
"eval_accuracy": 0.09167533902983765,
|
| 4 |
+
"eval_loss": 8.9140625,
|
| 5 |
+
"eval_runtime": 492.4035,
|
| 6 |
+
"eval_samples": 33767,
|
| 7 |
+
"eval_samples_per_second": 68.576,
|
| 8 |
+
"eval_steps_per_second": 2.857,
|
| 9 |
+
"perplexity": 7435.807790500043
|
| 10 |
+
}
|
logs/events.out.tfevents.1719937148.s_005_m.77202.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16923fcb84b36c0f0c8d189bdf71d8906fdeaf65898b78cf647646b092e5bbe6
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.0067933301849093615,
|
| 3 |
+
"total_flos": 1043124562427904.0,
|
| 4 |
+
"train_loss": 9.606408756684491,
|
| 5 |
+
"train_runtime": 94484.0244,
|
| 6 |
+
"train_samples": 660643,
|
| 7 |
+
"train_samples_per_second": 699.211,
|
| 8 |
+
"train_steps_per_second": 29.134
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3034 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0067933301849093615,
|
| 5 |
+
"eval_steps": 1,
|
| 6 |
+
"global_step": 187,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 3.6327968903258616e-05,
|
| 13 |
+
"grad_norm": 0.0,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 10.8828,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 3.6327968903258616e-05,
|
| 20 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 21 |
+
"eval_loss": 10.8828125,
|
| 22 |
+
"eval_runtime": 507.0426,
|
| 23 |
+
"eval_samples_per_second": 66.596,
|
| 24 |
+
"eval_steps_per_second": 2.775,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 7.265593780651723e-05,
|
| 29 |
+
"grad_norm": 0.0,
|
| 30 |
+
"learning_rate": 1e-05,
|
| 31 |
+
"loss": 10.8984,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 7.265593780651723e-05,
|
| 36 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 37 |
+
"eval_loss": 10.8828125,
|
| 38 |
+
"eval_runtime": 504.4591,
|
| 39 |
+
"eval_samples_per_second": 66.937,
|
| 40 |
+
"eval_steps_per_second": 2.789,
|
| 41 |
+
"step": 2
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.00010898390670977586,
|
| 45 |
+
"grad_norm": 0.0,
|
| 46 |
+
"learning_rate": 1e-05,
|
| 47 |
+
"loss": 10.8906,
|
| 48 |
+
"step": 3
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.00010898390670977586,
|
| 52 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 53 |
+
"eval_loss": 10.8828125,
|
| 54 |
+
"eval_runtime": 506.5358,
|
| 55 |
+
"eval_samples_per_second": 66.663,
|
| 56 |
+
"eval_steps_per_second": 2.778,
|
| 57 |
+
"step": 3
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.00014531187561303446,
|
| 61 |
+
"grad_norm": 0.0,
|
| 62 |
+
"learning_rate": 1e-05,
|
| 63 |
+
"loss": 10.8828,
|
| 64 |
+
"step": 4
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.00014531187561303446,
|
| 68 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 69 |
+
"eval_loss": 10.8828125,
|
| 70 |
+
"eval_runtime": 507.9364,
|
| 71 |
+
"eval_samples_per_second": 66.479,
|
| 72 |
+
"eval_steps_per_second": 2.77,
|
| 73 |
+
"step": 4
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0001816398445162931,
|
| 77 |
+
"grad_norm": 0.0,
|
| 78 |
+
"learning_rate": 1e-05,
|
| 79 |
+
"loss": 10.8828,
|
| 80 |
+
"step": 5
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0001816398445162931,
|
| 84 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 85 |
+
"eval_loss": 10.8828125,
|
| 86 |
+
"eval_runtime": 504.3114,
|
| 87 |
+
"eval_samples_per_second": 66.957,
|
| 88 |
+
"eval_steps_per_second": 2.79,
|
| 89 |
+
"step": 5
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.00021796781341955172,
|
| 93 |
+
"grad_norm": 0.0,
|
| 94 |
+
"learning_rate": 1e-05,
|
| 95 |
+
"loss": 10.8828,
|
| 96 |
+
"step": 6
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.00021796781341955172,
|
| 100 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 101 |
+
"eval_loss": 10.8828125,
|
| 102 |
+
"eval_runtime": 503.6918,
|
| 103 |
+
"eval_samples_per_second": 67.039,
|
| 104 |
+
"eval_steps_per_second": 2.793,
|
| 105 |
+
"step": 6
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.00025429578232281035,
|
| 109 |
+
"grad_norm": 0.0,
|
| 110 |
+
"learning_rate": 1e-05,
|
| 111 |
+
"loss": 10.8906,
|
| 112 |
+
"step": 7
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.00025429578232281035,
|
| 116 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 117 |
+
"eval_loss": 10.8828125,
|
| 118 |
+
"eval_runtime": 503.9607,
|
| 119 |
+
"eval_samples_per_second": 67.003,
|
| 120 |
+
"eval_steps_per_second": 2.792,
|
| 121 |
+
"step": 7
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0002906237512260689,
|
| 125 |
+
"grad_norm": 0.0,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 10.8828,
|
| 128 |
+
"step": 8
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0002906237512260689,
|
| 132 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 133 |
+
"eval_loss": 10.8828125,
|
| 134 |
+
"eval_runtime": 505.4484,
|
| 135 |
+
"eval_samples_per_second": 66.806,
|
| 136 |
+
"eval_steps_per_second": 2.784,
|
| 137 |
+
"step": 8
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.00032695172012932756,
|
| 141 |
+
"grad_norm": 0.0,
|
| 142 |
+
"learning_rate": 1e-05,
|
| 143 |
+
"loss": 10.875,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.00032695172012932756,
|
| 148 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 149 |
+
"eval_loss": 10.8828125,
|
| 150 |
+
"eval_runtime": 503.3281,
|
| 151 |
+
"eval_samples_per_second": 67.087,
|
| 152 |
+
"eval_steps_per_second": 2.795,
|
| 153 |
+
"step": 9
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.0003632796890325862,
|
| 157 |
+
"grad_norm": 0.0,
|
| 158 |
+
"learning_rate": 1e-05,
|
| 159 |
+
"loss": 10.8984,
|
| 160 |
+
"step": 10
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.0003632796890325862,
|
| 164 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 165 |
+
"eval_loss": 10.8828125,
|
| 166 |
+
"eval_runtime": 502.3143,
|
| 167 |
+
"eval_samples_per_second": 67.223,
|
| 168 |
+
"eval_steps_per_second": 2.801,
|
| 169 |
+
"step": 10
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.0003996076579358448,
|
| 173 |
+
"grad_norm": 0.0,
|
| 174 |
+
"learning_rate": 1e-05,
|
| 175 |
+
"loss": 10.8828,
|
| 176 |
+
"step": 11
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.0003996076579358448,
|
| 180 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 181 |
+
"eval_loss": 10.8828125,
|
| 182 |
+
"eval_runtime": 504.0173,
|
| 183 |
+
"eval_samples_per_second": 66.996,
|
| 184 |
+
"eval_steps_per_second": 2.792,
|
| 185 |
+
"step": 11
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.00043593562683910344,
|
| 189 |
+
"grad_norm": 0.0,
|
| 190 |
+
"learning_rate": 1e-05,
|
| 191 |
+
"loss": 10.8906,
|
| 192 |
+
"step": 12
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.00043593562683910344,
|
| 196 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 197 |
+
"eval_loss": 10.8828125,
|
| 198 |
+
"eval_runtime": 502.8909,
|
| 199 |
+
"eval_samples_per_second": 67.146,
|
| 200 |
+
"eval_steps_per_second": 2.798,
|
| 201 |
+
"step": 12
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.000472263595742362,
|
| 205 |
+
"grad_norm": 0.0,
|
| 206 |
+
"learning_rate": 1e-05,
|
| 207 |
+
"loss": 10.8828,
|
| 208 |
+
"step": 13
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.000472263595742362,
|
| 212 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 213 |
+
"eval_loss": 10.8828125,
|
| 214 |
+
"eval_runtime": 505.6586,
|
| 215 |
+
"eval_samples_per_second": 66.778,
|
| 216 |
+
"eval_steps_per_second": 2.783,
|
| 217 |
+
"step": 13
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.0005085915646456207,
|
| 221 |
+
"grad_norm": 0.0,
|
| 222 |
+
"learning_rate": 1e-05,
|
| 223 |
+
"loss": 10.8828,
|
| 224 |
+
"step": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.0005085915646456207,
|
| 228 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 229 |
+
"eval_loss": 10.8828125,
|
| 230 |
+
"eval_runtime": 504.0652,
|
| 231 |
+
"eval_samples_per_second": 66.989,
|
| 232 |
+
"eval_steps_per_second": 2.791,
|
| 233 |
+
"step": 14
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0005449195335488793,
|
| 237 |
+
"grad_norm": 0.0,
|
| 238 |
+
"learning_rate": 1e-05,
|
| 239 |
+
"loss": 10.8828,
|
| 240 |
+
"step": 15
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0005449195335488793,
|
| 244 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 245 |
+
"eval_loss": 10.8828125,
|
| 246 |
+
"eval_runtime": 502.8518,
|
| 247 |
+
"eval_samples_per_second": 67.151,
|
| 248 |
+
"eval_steps_per_second": 2.798,
|
| 249 |
+
"step": 15
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.0005812475024521379,
|
| 253 |
+
"grad_norm": 0.0,
|
| 254 |
+
"learning_rate": 1e-05,
|
| 255 |
+
"loss": 10.8828,
|
| 256 |
+
"step": 16
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.0005812475024521379,
|
| 260 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 261 |
+
"eval_loss": 10.8828125,
|
| 262 |
+
"eval_runtime": 503.4138,
|
| 263 |
+
"eval_samples_per_second": 67.076,
|
| 264 |
+
"eval_steps_per_second": 2.795,
|
| 265 |
+
"step": 16
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.0006175754713553965,
|
| 269 |
+
"grad_norm": 0.0,
|
| 270 |
+
"learning_rate": 1e-05,
|
| 271 |
+
"loss": 10.875,
|
| 272 |
+
"step": 17
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.0006175754713553965,
|
| 276 |
+
"eval_accuracy": 5.786882743483815e-05,
|
| 277 |
+
"eval_loss": 10.8828125,
|
| 278 |
+
"eval_runtime": 504.116,
|
| 279 |
+
"eval_samples_per_second": 66.983,
|
| 280 |
+
"eval_steps_per_second": 2.791,
|
| 281 |
+
"step": 17
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.0006539034402586551,
|
| 285 |
+
"grad_norm": 9.14120864868164,
|
| 286 |
+
"learning_rate": 9.999996367203111e-06,
|
| 287 |
+
"loss": 10.8828,
|
| 288 |
+
"step": 18
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.0006539034402586551,
|
| 292 |
+
"eval_accuracy": 0.019680148945503458,
|
| 293 |
+
"eval_loss": 10.6328125,
|
| 294 |
+
"eval_runtime": 503.1889,
|
| 295 |
+
"eval_samples_per_second": 67.106,
|
| 296 |
+
"eval_steps_per_second": 2.796,
|
| 297 |
+
"step": 18
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0006902314091619138,
|
| 301 |
+
"grad_norm": 7.371621131896973,
|
| 302 |
+
"learning_rate": 9.99999273440622e-06,
|
| 303 |
+
"loss": 10.6641,
|
| 304 |
+
"step": 19
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0006902314091619138,
|
| 308 |
+
"eval_accuracy": 0.04440203625321373,
|
| 309 |
+
"eval_loss": 10.484375,
|
| 310 |
+
"eval_runtime": 502.8755,
|
| 311 |
+
"eval_samples_per_second": 67.148,
|
| 312 |
+
"eval_steps_per_second": 2.798,
|
| 313 |
+
"step": 19
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.0007265593780651724,
|
| 317 |
+
"grad_norm": 5.806190013885498,
|
| 318 |
+
"learning_rate": 9.99998910160933e-06,
|
| 319 |
+
"loss": 10.5078,
|
| 320 |
+
"step": 20
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.0007265593780651724,
|
| 324 |
+
"eval_accuracy": 0.049879571177803755,
|
| 325 |
+
"eval_loss": 10.3828125,
|
| 326 |
+
"eval_runtime": 503.8208,
|
| 327 |
+
"eval_samples_per_second": 67.022,
|
| 328 |
+
"eval_steps_per_second": 2.793,
|
| 329 |
+
"step": 20
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.0007628873469684309,
|
| 333 |
+
"grad_norm": 4.848043441772461,
|
| 334 |
+
"learning_rate": 9.99998546881244e-06,
|
| 335 |
+
"loss": 10.3984,
|
| 336 |
+
"step": 21
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.0007628873469684309,
|
| 340 |
+
"eval_accuracy": 0.05315644057324473,
|
| 341 |
+
"eval_loss": 10.3125,
|
| 342 |
+
"eval_runtime": 505.0758,
|
| 343 |
+
"eval_samples_per_second": 66.855,
|
| 344 |
+
"eval_steps_per_second": 2.786,
|
| 345 |
+
"step": 21
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.0007992153158716896,
|
| 349 |
+
"grad_norm": 3.881626844406128,
|
| 350 |
+
"learning_rate": 9.99998183601555e-06,
|
| 351 |
+
"loss": 10.3438,
|
| 352 |
+
"step": 22
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.0007992153158716896,
|
| 356 |
+
"eval_accuracy": 0.05502066212418083,
|
| 357 |
+
"eval_loss": 10.25,
|
| 358 |
+
"eval_runtime": 508.1599,
|
| 359 |
+
"eval_samples_per_second": 66.45,
|
| 360 |
+
"eval_steps_per_second": 2.769,
|
| 361 |
+
"step": 22
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.0008355432847749482,
|
| 365 |
+
"grad_norm": 3.3826823234558105,
|
| 366 |
+
"learning_rate": 9.999978203218658e-06,
|
| 367 |
+
"loss": 10.2656,
|
| 368 |
+
"step": 23
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.0008355432847749482,
|
| 372 |
+
"eval_accuracy": 0.05621471691417821,
|
| 373 |
+
"eval_loss": 10.203125,
|
| 374 |
+
"eval_runtime": 508.8692,
|
| 375 |
+
"eval_samples_per_second": 66.357,
|
| 376 |
+
"eval_steps_per_second": 2.765,
|
| 377 |
+
"step": 23
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.0008718712536782069,
|
| 381 |
+
"grad_norm": 3.2527709007263184,
|
| 382 |
+
"learning_rate": 9.999974570421768e-06,
|
| 383 |
+
"loss": 10.25,
|
| 384 |
+
"step": 24
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.0008718712536782069,
|
| 388 |
+
"eval_accuracy": 0.05396498301959542,
|
| 389 |
+
"eval_loss": 10.1640625,
|
| 390 |
+
"eval_runtime": 504.6518,
|
| 391 |
+
"eval_samples_per_second": 66.911,
|
| 392 |
+
"eval_steps_per_second": 2.788,
|
| 393 |
+
"step": 24
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.0009081992225814655,
|
| 397 |
+
"grad_norm": 3.0049052238464355,
|
| 398 |
+
"learning_rate": 9.999970937624878e-06,
|
| 399 |
+
"loss": 10.1875,
|
| 400 |
+
"step": 25
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.0009081992225814655,
|
| 404 |
+
"eval_accuracy": 0.04704188536466089,
|
| 405 |
+
"eval_loss": 10.1328125,
|
| 406 |
+
"eval_runtime": 504.5459,
|
| 407 |
+
"eval_samples_per_second": 66.926,
|
| 408 |
+
"eval_steps_per_second": 2.789,
|
| 409 |
+
"step": 25
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.000944527191484724,
|
| 413 |
+
"grad_norm": 2.725101947784424,
|
| 414 |
+
"learning_rate": 9.999967304827988e-06,
|
| 415 |
+
"loss": 10.125,
|
| 416 |
+
"step": 26
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.000944527191484724,
|
| 420 |
+
"eval_accuracy": 0.04612232393221085,
|
| 421 |
+
"eval_loss": 10.109375,
|
| 422 |
+
"eval_runtime": 505.0881,
|
| 423 |
+
"eval_samples_per_second": 66.854,
|
| 424 |
+
"eval_steps_per_second": 2.786,
|
| 425 |
+
"step": 26
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.0009808551603879827,
|
| 429 |
+
"grad_norm": 2.5348708629608154,
|
| 430 |
+
"learning_rate": 9.999963672031098e-06,
|
| 431 |
+
"loss": 10.125,
|
| 432 |
+
"step": 27
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.0009808551603879827,
|
| 436 |
+
"eval_accuracy": 0.04800400166270834,
|
| 437 |
+
"eval_loss": 10.0859375,
|
| 438 |
+
"eval_runtime": 506.8917,
|
| 439 |
+
"eval_samples_per_second": 66.616,
|
| 440 |
+
"eval_steps_per_second": 2.776,
|
| 441 |
+
"step": 27
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.0010171831292912414,
|
| 445 |
+
"grad_norm": 2.571255683898926,
|
| 446 |
+
"learning_rate": 9.999960039234208e-06,
|
| 447 |
+
"loss": 10.0938,
|
| 448 |
+
"step": 28
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.0010171831292912414,
|
| 452 |
+
"eval_accuracy": 0.04744444860343471,
|
| 453 |
+
"eval_loss": 10.0703125,
|
| 454 |
+
"eval_runtime": 506.3522,
|
| 455 |
+
"eval_samples_per_second": 66.687,
|
| 456 |
+
"eval_steps_per_second": 2.779,
|
| 457 |
+
"step": 28
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.0010535110981944999,
|
| 461 |
+
"grad_norm": 2.22050142288208,
|
| 462 |
+
"learning_rate": 9.999956406437317e-06,
|
| 463 |
+
"loss": 10.0625,
|
| 464 |
+
"step": 29
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0010535110981944999,
|
| 468 |
+
"eval_accuracy": 0.0465065914736666,
|
| 469 |
+
"eval_loss": 10.0546875,
|
| 470 |
+
"eval_runtime": 504.6118,
|
| 471 |
+
"eval_samples_per_second": 66.917,
|
| 472 |
+
"eval_steps_per_second": 2.788,
|
| 473 |
+
"step": 29
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.0010898390670977586,
|
| 477 |
+
"grad_norm": 2.1588761806488037,
|
| 478 |
+
"learning_rate": 9.999952773640427e-06,
|
| 479 |
+
"loss": 10.0703,
|
| 480 |
+
"step": 30
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.0010898390670977586,
|
| 484 |
+
"eval_accuracy": 0.04720460706501668,
|
| 485 |
+
"eval_loss": 10.0390625,
|
| 486 |
+
"eval_runtime": 502.6467,
|
| 487 |
+
"eval_samples_per_second": 67.178,
|
| 488 |
+
"eval_steps_per_second": 2.799,
|
| 489 |
+
"step": 30
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.0011261670360010172,
|
| 493 |
+
"grad_norm": 2.2763571739196777,
|
| 494 |
+
"learning_rate": 9.999949140843537e-06,
|
| 495 |
+
"loss": 10.0156,
|
| 496 |
+
"step": 31
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.0011261670360010172,
|
| 500 |
+
"eval_accuracy": 0.05153020783188431,
|
| 501 |
+
"eval_loss": 10.0234375,
|
| 502 |
+
"eval_runtime": 503.4047,
|
| 503 |
+
"eval_samples_per_second": 67.077,
|
| 504 |
+
"eval_steps_per_second": 2.795,
|
| 505 |
+
"step": 31
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.0011624950049042757,
|
| 509 |
+
"grad_norm": 2.1108500957489014,
|
| 510 |
+
"learning_rate": 9.999945508046645e-06,
|
| 511 |
+
"loss": 10.0859,
|
| 512 |
+
"step": 32
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.0011624950049042757,
|
| 516 |
+
"eval_accuracy": 0.05865791622834431,
|
| 517 |
+
"eval_loss": 10.015625,
|
| 518 |
+
"eval_runtime": 509.0053,
|
| 519 |
+
"eval_samples_per_second": 66.339,
|
| 520 |
+
"eval_steps_per_second": 2.764,
|
| 521 |
+
"step": 32
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.0011988229738075344,
|
| 525 |
+
"grad_norm": 2.155444622039795,
|
| 526 |
+
"learning_rate": 9.999941875249755e-06,
|
| 527 |
+
"loss": 9.9922,
|
| 528 |
+
"step": 33
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.0011988229738075344,
|
| 532 |
+
"eval_accuracy": 0.06134457569194863,
|
| 533 |
+
"eval_loss": 10.0078125,
|
| 534 |
+
"eval_runtime": 508.1742,
|
| 535 |
+
"eval_samples_per_second": 66.448,
|
| 536 |
+
"eval_steps_per_second": 2.769,
|
| 537 |
+
"step": 33
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.001235150942710793,
|
| 541 |
+
"grad_norm": 2.6189229488372803,
|
| 542 |
+
"learning_rate": 9.999938242452866e-06,
|
| 543 |
+
"loss": 10.0234,
|
| 544 |
+
"step": 34
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.001235150942710793,
|
| 548 |
+
"eval_accuracy": 0.06076637954869899,
|
| 549 |
+
"eval_loss": 9.9921875,
|
| 550 |
+
"eval_runtime": 506.0763,
|
| 551 |
+
"eval_samples_per_second": 66.723,
|
| 552 |
+
"eval_steps_per_second": 2.78,
|
| 553 |
+
"step": 34
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.0012714789116140518,
|
| 557 |
+
"grad_norm": 2.2233242988586426,
|
| 558 |
+
"learning_rate": 9.999934609655974e-06,
|
| 559 |
+
"loss": 9.9609,
|
| 560 |
+
"step": 35
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.0012714789116140518,
|
| 564 |
+
"eval_accuracy": 0.05996116622448688,
|
| 565 |
+
"eval_loss": 9.984375,
|
| 566 |
+
"eval_runtime": 505.1839,
|
| 567 |
+
"eval_samples_per_second": 66.841,
|
| 568 |
+
"eval_steps_per_second": 2.785,
|
| 569 |
+
"step": 35
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.0013078068805173102,
|
| 573 |
+
"grad_norm": 2.289062261581421,
|
| 574 |
+
"learning_rate": 9.999930976859084e-06,
|
| 575 |
+
"loss": 10.0391,
|
| 576 |
+
"step": 36
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.0013078068805173102,
|
| 580 |
+
"eval_accuracy": 0.06078849649925438,
|
| 581 |
+
"eval_loss": 9.9765625,
|
| 582 |
+
"eval_runtime": 505.7312,
|
| 583 |
+
"eval_samples_per_second": 66.769,
|
| 584 |
+
"eval_steps_per_second": 2.782,
|
| 585 |
+
"step": 36
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.001344134849420569,
|
| 589 |
+
"grad_norm": 2.283668041229248,
|
| 590 |
+
"learning_rate": 9.999927344062194e-06,
|
| 591 |
+
"loss": 9.9922,
|
| 592 |
+
"step": 37
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.001344134849420569,
|
| 596 |
+
"eval_accuracy": 0.061857115756847984,
|
| 597 |
+
"eval_loss": 9.9609375,
|
| 598 |
+
"eval_runtime": 508.2946,
|
| 599 |
+
"eval_samples_per_second": 66.432,
|
| 600 |
+
"eval_steps_per_second": 2.768,
|
| 601 |
+
"step": 37
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.0013804628183238276,
|
| 605 |
+
"grad_norm": 2.189363718032837,
|
| 606 |
+
"learning_rate": 9.999923711265304e-06,
|
| 607 |
+
"loss": 9.9688,
|
| 608 |
+
"step": 38
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.0013804628183238276,
|
| 612 |
+
"eval_accuracy": 0.06226219754889185,
|
| 613 |
+
"eval_loss": 9.953125,
|
| 614 |
+
"eval_runtime": 508.653,
|
| 615 |
+
"eval_samples_per_second": 66.385,
|
| 616 |
+
"eval_steps_per_second": 2.766,
|
| 617 |
+
"step": 38
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.001416790787227086,
|
| 621 |
+
"grad_norm": 2.082035541534424,
|
| 622 |
+
"learning_rate": 9.999920078468414e-06,
|
| 623 |
+
"loss": 9.9453,
|
| 624 |
+
"step": 39
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.001416790787227086,
|
| 628 |
+
"eval_accuracy": 0.06217419292888089,
|
| 629 |
+
"eval_loss": 9.9375,
|
| 630 |
+
"eval_runtime": 507.0173,
|
| 631 |
+
"eval_samples_per_second": 66.599,
|
| 632 |
+
"eval_steps_per_second": 2.775,
|
| 633 |
+
"step": 39
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0014531187561303447,
|
| 637 |
+
"grad_norm": 2.1098358631134033,
|
| 638 |
+
"learning_rate": 9.999916445671524e-06,
|
| 639 |
+
"loss": 9.9609,
|
| 640 |
+
"step": 40
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.0014531187561303447,
|
| 644 |
+
"eval_accuracy": 0.06281911625934278,
|
| 645 |
+
"eval_loss": 9.9296875,
|
| 646 |
+
"eval_runtime": 505.2162,
|
| 647 |
+
"eval_samples_per_second": 66.837,
|
| 648 |
+
"eval_steps_per_second": 2.785,
|
| 649 |
+
"step": 40
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.0014894467250336034,
|
| 653 |
+
"grad_norm": 1.99773108959198,
|
| 654 |
+
"learning_rate": 9.999912812874633e-06,
|
| 655 |
+
"loss": 9.9609,
|
| 656 |
+
"step": 41
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.0014894467250336034,
|
| 660 |
+
"eval_accuracy": 0.06401496588040619,
|
| 661 |
+
"eval_loss": 9.9140625,
|
| 662 |
+
"eval_runtime": 505.419,
|
| 663 |
+
"eval_samples_per_second": 66.81,
|
| 664 |
+
"eval_steps_per_second": 2.784,
|
| 665 |
+
"step": 41
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.0015257746939368619,
|
| 669 |
+
"grad_norm": 2.0331761837005615,
|
| 670 |
+
"learning_rate": 9.999909180077743e-06,
|
| 671 |
+
"loss": 10.0234,
|
| 672 |
+
"step": 42
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.0015257746939368619,
|
| 676 |
+
"eval_accuracy": 0.06490028077816117,
|
| 677 |
+
"eval_loss": 9.8984375,
|
| 678 |
+
"eval_runtime": 508.1771,
|
| 679 |
+
"eval_samples_per_second": 66.447,
|
| 680 |
+
"eval_steps_per_second": 2.769,
|
| 681 |
+
"step": 42
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0015621026628401206,
|
| 685 |
+
"grad_norm": 2.115607500076294,
|
| 686 |
+
"learning_rate": 9.999905547280853e-06,
|
| 687 |
+
"loss": 9.9375,
|
| 688 |
+
"step": 43
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.0015621026628401206,
|
| 692 |
+
"eval_accuracy": 0.06480990234932096,
|
| 693 |
+
"eval_loss": 9.890625,
|
| 694 |
+
"eval_runtime": 509.849,
|
| 695 |
+
"eval_samples_per_second": 66.229,
|
| 696 |
+
"eval_steps_per_second": 2.76,
|
| 697 |
+
"step": 43
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0015984306317433793,
|
| 701 |
+
"grad_norm": 2.163503646850586,
|
| 702 |
+
"learning_rate": 9.999901914483961e-06,
|
| 703 |
+
"loss": 9.8516,
|
| 704 |
+
"step": 44
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.0015984306317433793,
|
| 708 |
+
"eval_accuracy": 0.06442907972555643,
|
| 709 |
+
"eval_loss": 9.875,
|
| 710 |
+
"eval_runtime": 509.7023,
|
| 711 |
+
"eval_samples_per_second": 66.248,
|
| 712 |
+
"eval_steps_per_second": 2.76,
|
| 713 |
+
"step": 44
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.001634758600646638,
|
| 717 |
+
"grad_norm": 2.0586893558502197,
|
| 718 |
+
"learning_rate": 9.999898281687071e-06,
|
| 719 |
+
"loss": 9.8672,
|
| 720 |
+
"step": 45
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.001634758600646638,
|
| 724 |
+
"eval_accuracy": 0.06429814390440197,
|
| 725 |
+
"eval_loss": 9.859375,
|
| 726 |
+
"eval_runtime": 506.8968,
|
| 727 |
+
"eval_samples_per_second": 66.615,
|
| 728 |
+
"eval_steps_per_second": 2.776,
|
| 729 |
+
"step": 45
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.0016710865695498964,
|
| 733 |
+
"grad_norm": 1.898136854171753,
|
| 734 |
+
"learning_rate": 9.999894648890181e-06,
|
| 735 |
+
"loss": 9.8984,
|
| 736 |
+
"step": 46
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.0016710865695498964,
|
| 740 |
+
"eval_accuracy": 0.06426870288514172,
|
| 741 |
+
"eval_loss": 9.84375,
|
| 742 |
+
"eval_runtime": 505.4907,
|
| 743 |
+
"eval_samples_per_second": 66.8,
|
| 744 |
+
"eval_steps_per_second": 2.783,
|
| 745 |
+
"step": 46
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.001707414538453155,
|
| 749 |
+
"grad_norm": 1.9898130893707275,
|
| 750 |
+
"learning_rate": 9.99989101609329e-06,
|
| 751 |
+
"loss": 9.875,
|
| 752 |
+
"step": 47
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.001707414538453155,
|
| 756 |
+
"eval_accuracy": 0.06445736278929022,
|
| 757 |
+
"eval_loss": 9.8359375,
|
| 758 |
+
"eval_runtime": 505.8927,
|
| 759 |
+
"eval_samples_per_second": 66.747,
|
| 760 |
+
"eval_steps_per_second": 2.781,
|
| 761 |
+
"step": 47
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.0017437425073564138,
|
| 765 |
+
"grad_norm": 1.9185965061187744,
|
| 766 |
+
"learning_rate": 9.9998873832964e-06,
|
| 767 |
+
"loss": 9.8672,
|
| 768 |
+
"step": 48
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.0017437425073564138,
|
| 772 |
+
"eval_accuracy": 0.06462755330279167,
|
| 773 |
+
"eval_loss": 9.8203125,
|
| 774 |
+
"eval_runtime": 507.6208,
|
| 775 |
+
"eval_samples_per_second": 66.52,
|
| 776 |
+
"eval_steps_per_second": 2.772,
|
| 777 |
+
"step": 48
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.0017800704762596722,
|
| 781 |
+
"grad_norm": 1.8137012720108032,
|
| 782 |
+
"learning_rate": 9.99988375049951e-06,
|
| 783 |
+
"loss": 9.8984,
|
| 784 |
+
"step": 49
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.0017800704762596722,
|
| 788 |
+
"eval_accuracy": 0.06494483311704172,
|
| 789 |
+
"eval_loss": 9.8125,
|
| 790 |
+
"eval_runtime": 506.9398,
|
| 791 |
+
"eval_samples_per_second": 66.609,
|
| 792 |
+
"eval_steps_per_second": 2.775,
|
| 793 |
+
"step": 49
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.001816398445162931,
|
| 797 |
+
"grad_norm": 2.237258195877075,
|
| 798 |
+
"learning_rate": 9.99988011770262e-06,
|
| 799 |
+
"loss": 9.7891,
|
| 800 |
+
"step": 50
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.001816398445162931,
|
| 804 |
+
"eval_accuracy": 0.06534296717592682,
|
| 805 |
+
"eval_loss": 9.8046875,
|
| 806 |
+
"eval_runtime": 504.003,
|
| 807 |
+
"eval_samples_per_second": 66.998,
|
| 808 |
+
"eval_steps_per_second": 2.792,
|
| 809 |
+
"step": 50
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.0018527264140661896,
|
| 813 |
+
"grad_norm": 2.279499053955078,
|
| 814 |
+
"learning_rate": 9.99987648490573e-06,
|
| 815 |
+
"loss": 9.8281,
|
| 816 |
+
"step": 51
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.0018527264140661896,
|
| 820 |
+
"eval_accuracy": 0.06550117284972942,
|
| 821 |
+
"eval_loss": 9.7890625,
|
| 822 |
+
"eval_runtime": 503.0349,
|
| 823 |
+
"eval_samples_per_second": 67.127,
|
| 824 |
+
"eval_steps_per_second": 2.797,
|
| 825 |
+
"step": 51
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.001889054382969448,
|
| 829 |
+
"grad_norm": 1.8227834701538086,
|
| 830 |
+
"learning_rate": 9.99987285210884e-06,
|
| 831 |
+
"loss": 9.8281,
|
| 832 |
+
"step": 52
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.001889054382969448,
|
| 836 |
+
"eval_accuracy": 0.0654096075164746,
|
| 837 |
+
"eval_loss": 9.78125,
|
| 838 |
+
"eval_runtime": 505.4701,
|
| 839 |
+
"eval_samples_per_second": 66.803,
|
| 840 |
+
"eval_steps_per_second": 2.784,
|
| 841 |
+
"step": 52
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.0019253823518727068,
|
| 845 |
+
"grad_norm": 2.207292079925537,
|
| 846 |
+
"learning_rate": 9.99986921931195e-06,
|
| 847 |
+
"loss": 9.7969,
|
| 848 |
+
"step": 53
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.0019253823518727068,
|
| 852 |
+
"eval_accuracy": 0.06596467349808319,
|
| 853 |
+
"eval_loss": 9.7734375,
|
| 854 |
+
"eval_runtime": 506.8878,
|
| 855 |
+
"eval_samples_per_second": 66.616,
|
| 856 |
+
"eval_steps_per_second": 2.776,
|
| 857 |
+
"step": 53
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.0019617103207759654,
|
| 861 |
+
"grad_norm": 1.9478576183319092,
|
| 862 |
+
"learning_rate": 9.999865586515059e-06,
|
| 863 |
+
"loss": 9.7812,
|
| 864 |
+
"step": 54
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.0019617103207759654,
|
| 868 |
+
"eval_accuracy": 0.06697281852830743,
|
| 869 |
+
"eval_loss": 9.765625,
|
| 870 |
+
"eval_runtime": 506.2987,
|
| 871 |
+
"eval_samples_per_second": 66.694,
|
| 872 |
+
"eval_steps_per_second": 2.779,
|
| 873 |
+
"step": 54
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.001998038289679224,
|
| 877 |
+
"grad_norm": 2.4436683654785156,
|
| 878 |
+
"learning_rate": 9.999861953718169e-06,
|
| 879 |
+
"loss": 9.8047,
|
| 880 |
+
"step": 55
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.001998038289679224,
|
| 884 |
+
"eval_accuracy": 0.06823391894328684,
|
| 885 |
+
"eval_loss": 9.75,
|
| 886 |
+
"eval_runtime": 505.1115,
|
| 887 |
+
"eval_samples_per_second": 66.851,
|
| 888 |
+
"eval_steps_per_second": 2.786,
|
| 889 |
+
"step": 55
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.002034366258582483,
|
| 893 |
+
"grad_norm": 1.911065936088562,
|
| 894 |
+
"learning_rate": 9.999858320921279e-06,
|
| 895 |
+
"loss": 9.7969,
|
| 896 |
+
"step": 56
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.002034366258582483,
|
| 900 |
+
"eval_accuracy": 0.0688041251934039,
|
| 901 |
+
"eval_loss": 9.7421875,
|
| 902 |
+
"eval_runtime": 503.4384,
|
| 903 |
+
"eval_samples_per_second": 67.073,
|
| 904 |
+
"eval_steps_per_second": 2.795,
|
| 905 |
+
"step": 56
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.0020706942274857413,
|
| 909 |
+
"grad_norm": 2.6223678588867188,
|
| 910 |
+
"learning_rate": 9.999854688124387e-06,
|
| 911 |
+
"loss": 9.7891,
|
| 912 |
+
"step": 57
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.0020706942274857413,
|
| 916 |
+
"eval_accuracy": 0.0691195522788116,
|
| 917 |
+
"eval_loss": 9.734375,
|
| 918 |
+
"eval_runtime": 504.3798,
|
| 919 |
+
"eval_samples_per_second": 66.948,
|
| 920 |
+
"eval_steps_per_second": 2.79,
|
| 921 |
+
"step": 57
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.0021070221963889997,
|
| 925 |
+
"grad_norm": 2.182452917098999,
|
| 926 |
+
"learning_rate": 9.999851055327497e-06,
|
| 927 |
+
"loss": 9.6875,
|
| 928 |
+
"step": 58
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.0021070221963889997,
|
| 932 |
+
"eval_accuracy": 0.0690351083720445,
|
| 933 |
+
"eval_loss": 9.7265625,
|
| 934 |
+
"eval_runtime": 507.3727,
|
| 935 |
+
"eval_samples_per_second": 66.553,
|
| 936 |
+
"eval_steps_per_second": 2.773,
|
| 937 |
+
"step": 58
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.0021433501652922586,
|
| 941 |
+
"grad_norm": 1.8129832744598389,
|
| 942 |
+
"learning_rate": 9.999847422530608e-06,
|
| 943 |
+
"loss": 9.7188,
|
| 944 |
+
"step": 59
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.0021433501652922586,
|
| 948 |
+
"eval_accuracy": 0.06855982552620901,
|
| 949 |
+
"eval_loss": 9.71875,
|
| 950 |
+
"eval_runtime": 504.2068,
|
| 951 |
+
"eval_samples_per_second": 66.971,
|
| 952 |
+
"eval_steps_per_second": 2.791,
|
| 953 |
+
"step": 59
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.002179678134195517,
|
| 957 |
+
"grad_norm": 1.9449687004089355,
|
| 958 |
+
"learning_rate": 9.999843789733716e-06,
|
| 959 |
+
"loss": 9.7344,
|
| 960 |
+
"step": 60
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.002179678134195517,
|
| 964 |
+
"eval_accuracy": 0.06816276257618588,
|
| 965 |
+
"eval_loss": 9.7109375,
|
| 966 |
+
"eval_runtime": 506.178,
|
| 967 |
+
"eval_samples_per_second": 66.71,
|
| 968 |
+
"eval_steps_per_second": 2.78,
|
| 969 |
+
"step": 60
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.0022160061030987756,
|
| 973 |
+
"grad_norm": 2.0629429817199707,
|
| 974 |
+
"learning_rate": 9.999840156936826e-06,
|
| 975 |
+
"loss": 9.7344,
|
| 976 |
+
"step": 61
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.0022160061030987756,
|
| 980 |
+
"eval_accuracy": 0.06871380466234002,
|
| 981 |
+
"eval_loss": 9.6953125,
|
| 982 |
+
"eval_runtime": 504.7991,
|
| 983 |
+
"eval_samples_per_second": 66.892,
|
| 984 |
+
"eval_steps_per_second": 2.787,
|
| 985 |
+
"step": 61
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.0022523340720020345,
|
| 989 |
+
"grad_norm": 1.7803966999053955,
|
| 990 |
+
"learning_rate": 9.999836524139936e-06,
|
| 991 |
+
"loss": 9.7578,
|
| 992 |
+
"step": 62
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.0022523340720020345,
|
| 996 |
+
"eval_accuracy": 0.06968408454684902,
|
| 997 |
+
"eval_loss": 9.6875,
|
| 998 |
+
"eval_runtime": 503.513,
|
| 999 |
+
"eval_samples_per_second": 67.063,
|
| 1000 |
+
"eval_steps_per_second": 2.794,
|
| 1001 |
+
"step": 62
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.002288662040905293,
|
| 1005 |
+
"grad_norm": 2.0867655277252197,
|
| 1006 |
+
"learning_rate": 9.999832891343046e-06,
|
| 1007 |
+
"loss": 9.6484,
|
| 1008 |
+
"step": 63
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.002288662040905293,
|
| 1012 |
+
"eval_accuracy": 0.07077357595280706,
|
| 1013 |
+
"eval_loss": 9.671875,
|
| 1014 |
+
"eval_runtime": 505.2322,
|
| 1015 |
+
"eval_samples_per_second": 66.835,
|
| 1016 |
+
"eval_steps_per_second": 2.785,
|
| 1017 |
+
"step": 63
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.0023249900098085514,
|
| 1021 |
+
"grad_norm": 2.1032333374023438,
|
| 1022 |
+
"learning_rate": 9.999829258546155e-06,
|
| 1023 |
+
"loss": 9.6328,
|
| 1024 |
+
"step": 64
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.0023249900098085514,
|
| 1028 |
+
"eval_accuracy": 0.07146232789994546,
|
| 1029 |
+
"eval_loss": 9.6640625,
|
| 1030 |
+
"eval_runtime": 503.6458,
|
| 1031 |
+
"eval_samples_per_second": 67.045,
|
| 1032 |
+
"eval_steps_per_second": 2.794,
|
| 1033 |
+
"step": 64
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.0023613179787118103,
|
| 1037 |
+
"grad_norm": 1.6707836389541626,
|
| 1038 |
+
"learning_rate": 9.999825625749265e-06,
|
| 1039 |
+
"loss": 9.7656,
|
| 1040 |
+
"step": 65
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.0023613179787118103,
|
| 1044 |
+
"eval_accuracy": 0.07207561009564684,
|
| 1045 |
+
"eval_loss": 9.65625,
|
| 1046 |
+
"eval_runtime": 503.2725,
|
| 1047 |
+
"eval_samples_per_second": 67.095,
|
| 1048 |
+
"eval_steps_per_second": 2.796,
|
| 1049 |
+
"step": 65
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.0023976459476150688,
|
| 1053 |
+
"grad_norm": 1.7805981636047363,
|
| 1054 |
+
"learning_rate": 9.999821992952375e-06,
|
| 1055 |
+
"loss": 9.6875,
|
| 1056 |
+
"step": 66
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.0023976459476150688,
|
| 1060 |
+
"eval_accuracy": 0.0724615277237278,
|
| 1061 |
+
"eval_loss": 9.6484375,
|
| 1062 |
+
"eval_runtime": 502.4455,
|
| 1063 |
+
"eval_samples_per_second": 67.205,
|
| 1064 |
+
"eval_steps_per_second": 2.8,
|
| 1065 |
+
"step": 66
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.0024339739165183277,
|
| 1069 |
+
"grad_norm": 2.426743745803833,
|
| 1070 |
+
"learning_rate": 9.999818360155485e-06,
|
| 1071 |
+
"loss": 9.6328,
|
| 1072 |
+
"step": 67
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.0024339739165183277,
|
| 1076 |
+
"eval_accuracy": 0.07273411045465647,
|
| 1077 |
+
"eval_loss": 9.640625,
|
| 1078 |
+
"eval_runtime": 502.4056,
|
| 1079 |
+
"eval_samples_per_second": 67.211,
|
| 1080 |
+
"eval_steps_per_second": 2.801,
|
| 1081 |
+
"step": 67
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.002470301885421586,
|
| 1085 |
+
"grad_norm": 1.7032270431518555,
|
| 1086 |
+
"learning_rate": 9.999814727358595e-06,
|
| 1087 |
+
"loss": 9.6953,
|
| 1088 |
+
"step": 68
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.002470301885421586,
|
| 1092 |
+
"eval_accuracy": 0.07335859587007634,
|
| 1093 |
+
"eval_loss": 9.6328125,
|
| 1094 |
+
"eval_runtime": 505.6904,
|
| 1095 |
+
"eval_samples_per_second": 66.774,
|
| 1096 |
+
"eval_steps_per_second": 2.782,
|
| 1097 |
+
"step": 68
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.0025066298543248446,
|
| 1101 |
+
"grad_norm": 1.7397522926330566,
|
| 1102 |
+
"learning_rate": 9.999811094561705e-06,
|
| 1103 |
+
"loss": 9.7188,
|
| 1104 |
+
"step": 69
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.0025066298543248446,
|
| 1108 |
+
"eval_accuracy": 0.07437455710010418,
|
| 1109 |
+
"eval_loss": 9.625,
|
| 1110 |
+
"eval_runtime": 505.9561,
|
| 1111 |
+
"eval_samples_per_second": 66.739,
|
| 1112 |
+
"eval_steps_per_second": 2.781,
|
| 1113 |
+
"step": 69
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.0025429578232281035,
|
| 1117 |
+
"grad_norm": 1.6626527309417725,
|
| 1118 |
+
"learning_rate": 9.999807461764813e-06,
|
| 1119 |
+
"loss": 9.6875,
|
| 1120 |
+
"step": 70
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.0025429578232281035,
|
| 1124 |
+
"eval_accuracy": 0.075310387807701,
|
| 1125 |
+
"eval_loss": 9.6171875,
|
| 1126 |
+
"eval_runtime": 505.7964,
|
| 1127 |
+
"eval_samples_per_second": 66.76,
|
| 1128 |
+
"eval_steps_per_second": 2.782,
|
| 1129 |
+
"step": 70
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.002579285792131362,
|
| 1133 |
+
"grad_norm": 2.158742666244507,
|
| 1134 |
+
"learning_rate": 9.999803828967923e-06,
|
| 1135 |
+
"loss": 9.625,
|
| 1136 |
+
"step": 71
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.002579285792131362,
|
| 1140 |
+
"eval_accuracy": 0.07634256041509926,
|
| 1141 |
+
"eval_loss": 9.609375,
|
| 1142 |
+
"eval_runtime": 504.0869,
|
| 1143 |
+
"eval_samples_per_second": 66.986,
|
| 1144 |
+
"eval_steps_per_second": 2.791,
|
| 1145 |
+
"step": 71
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.0026156137610346204,
|
| 1149 |
+
"grad_norm": 1.8259432315826416,
|
| 1150 |
+
"learning_rate": 9.999800196171034e-06,
|
| 1151 |
+
"loss": 9.6172,
|
| 1152 |
+
"step": 72
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.0026156137610346204,
|
| 1156 |
+
"eval_accuracy": 0.07690020284775424,
|
| 1157 |
+
"eval_loss": 9.6015625,
|
| 1158 |
+
"eval_runtime": 504.7109,
|
| 1159 |
+
"eval_samples_per_second": 66.904,
|
| 1160 |
+
"eval_steps_per_second": 2.788,
|
| 1161 |
+
"step": 72
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0026519417299378793,
|
| 1165 |
+
"grad_norm": 1.7585749626159668,
|
| 1166 |
+
"learning_rate": 9.999796563374142e-06,
|
| 1167 |
+
"loss": 9.6016,
|
| 1168 |
+
"step": 73
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.0026519417299378793,
|
| 1172 |
+
"eval_accuracy": 0.07706367721920222,
|
| 1173 |
+
"eval_loss": 9.59375,
|
| 1174 |
+
"eval_runtime": 505.9779,
|
| 1175 |
+
"eval_samples_per_second": 66.736,
|
| 1176 |
+
"eval_steps_per_second": 2.781,
|
| 1177 |
+
"step": 73
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.002688269698841138,
|
| 1181 |
+
"grad_norm": 1.8018831014633179,
|
| 1182 |
+
"learning_rate": 9.999792930577252e-06,
|
| 1183 |
+
"loss": 9.6094,
|
| 1184 |
+
"step": 74
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.002688269698841138,
|
| 1188 |
+
"eval_accuracy": 0.07714539993048214,
|
| 1189 |
+
"eval_loss": 9.5859375,
|
| 1190 |
+
"eval_runtime": 505.2425,
|
| 1191 |
+
"eval_samples_per_second": 66.833,
|
| 1192 |
+
"eval_steps_per_second": 2.785,
|
| 1193 |
+
"step": 74
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.0027245976677443963,
|
| 1197 |
+
"grad_norm": 1.7233467102050781,
|
| 1198 |
+
"learning_rate": 9.999789297780362e-06,
|
| 1199 |
+
"loss": 9.5859,
|
| 1200 |
+
"step": 75
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.0027245976677443963,
|
| 1204 |
+
"eval_accuracy": 0.07710901117806314,
|
| 1205 |
+
"eval_loss": 9.578125,
|
| 1206 |
+
"eval_runtime": 505.5998,
|
| 1207 |
+
"eval_samples_per_second": 66.786,
|
| 1208 |
+
"eval_steps_per_second": 2.783,
|
| 1209 |
+
"step": 75
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.002760925636647655,
|
| 1213 |
+
"grad_norm": 1.9081038236618042,
|
| 1214 |
+
"learning_rate": 9.99978566498347e-06,
|
| 1215 |
+
"loss": 9.5859,
|
| 1216 |
+
"step": 76
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.002760925636647655,
|
| 1220 |
+
"eval_accuracy": 0.07673672847630625,
|
| 1221 |
+
"eval_loss": 9.5703125,
|
| 1222 |
+
"eval_runtime": 503.3457,
|
| 1223 |
+
"eval_samples_per_second": 67.085,
|
| 1224 |
+
"eval_steps_per_second": 2.795,
|
| 1225 |
+
"step": 76
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.0027972536055509136,
|
| 1229 |
+
"grad_norm": 1.7332507371902466,
|
| 1230 |
+
"learning_rate": 9.99978203218658e-06,
|
| 1231 |
+
"loss": 9.5859,
|
| 1232 |
+
"step": 77
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.0027972536055509136,
|
| 1236 |
+
"eval_accuracy": 0.07650699009985658,
|
| 1237 |
+
"eval_loss": 9.5625,
|
| 1238 |
+
"eval_runtime": 502.974,
|
| 1239 |
+
"eval_samples_per_second": 67.135,
|
| 1240 |
+
"eval_steps_per_second": 2.797,
|
| 1241 |
+
"step": 77
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.002833581574454172,
|
| 1245 |
+
"grad_norm": 1.8088840246200562,
|
| 1246 |
+
"learning_rate": 9.99977839938969e-06,
|
| 1247 |
+
"loss": 9.5781,
|
| 1248 |
+
"step": 78
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.002833581574454172,
|
| 1252 |
+
"eval_accuracy": 0.07642793068628753,
|
| 1253 |
+
"eval_loss": 9.5546875,
|
| 1254 |
+
"eval_runtime": 505.8316,
|
| 1255 |
+
"eval_samples_per_second": 66.755,
|
| 1256 |
+
"eval_steps_per_second": 2.782,
|
| 1257 |
+
"step": 78
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.002869909543357431,
|
| 1261 |
+
"grad_norm": 1.6268699169158936,
|
| 1262 |
+
"learning_rate": 9.9997747665928e-06,
|
| 1263 |
+
"loss": 9.6172,
|
| 1264 |
+
"step": 79
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.002869909543357431,
|
| 1268 |
+
"eval_accuracy": 0.07634560004835622,
|
| 1269 |
+
"eval_loss": 9.546875,
|
| 1270 |
+
"eval_runtime": 505.9115,
|
| 1271 |
+
"eval_samples_per_second": 66.745,
|
| 1272 |
+
"eval_steps_per_second": 2.781,
|
| 1273 |
+
"step": 79
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.0029062375122606895,
|
| 1277 |
+
"grad_norm": 1.8675007820129395,
|
| 1278 |
+
"learning_rate": 9.999771133795911e-06,
|
| 1279 |
+
"loss": 9.5859,
|
| 1280 |
+
"step": 80
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.0029062375122606895,
|
| 1284 |
+
"eval_accuracy": 0.07677149609098821,
|
| 1285 |
+
"eval_loss": 9.5390625,
|
| 1286 |
+
"eval_runtime": 505.7348,
|
| 1287 |
+
"eval_samples_per_second": 66.768,
|
| 1288 |
+
"eval_steps_per_second": 2.782,
|
| 1289 |
+
"step": 80
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.002942565481163948,
|
| 1293 |
+
"grad_norm": 1.9098700284957886,
|
| 1294 |
+
"learning_rate": 9.999767500999021e-06,
|
| 1295 |
+
"loss": 9.5859,
|
| 1296 |
+
"step": 81
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 0.002942565481163948,
|
| 1300 |
+
"eval_accuracy": 0.07698542837450169,
|
| 1301 |
+
"eval_loss": 9.53125,
|
| 1302 |
+
"eval_runtime": 502.794,
|
| 1303 |
+
"eval_samples_per_second": 67.159,
|
| 1304 |
+
"eval_steps_per_second": 2.798,
|
| 1305 |
+
"step": 81
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.002978893450067207,
|
| 1309 |
+
"grad_norm": 1.8791757822036743,
|
| 1310 |
+
"learning_rate": 9.99976386820213e-06,
|
| 1311 |
+
"loss": 9.5391,
|
| 1312 |
+
"step": 82
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.002978893450067207,
|
| 1316 |
+
"eval_accuracy": 0.07695144237980009,
|
| 1317 |
+
"eval_loss": 9.5234375,
|
| 1318 |
+
"eval_runtime": 503.0464,
|
| 1319 |
+
"eval_samples_per_second": 67.125,
|
| 1320 |
+
"eval_steps_per_second": 2.797,
|
| 1321 |
+
"step": 82
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.0030152214189704653,
|
| 1325 |
+
"grad_norm": 1.704999566078186,
|
| 1326 |
+
"learning_rate": 9.99976023540524e-06,
|
| 1327 |
+
"loss": 9.5391,
|
| 1328 |
+
"step": 83
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.0030152214189704653,
|
| 1332 |
+
"eval_accuracy": 0.0764418551014932,
|
| 1333 |
+
"eval_loss": 9.5234375,
|
| 1334 |
+
"eval_runtime": 505.8882,
|
| 1335 |
+
"eval_samples_per_second": 66.748,
|
| 1336 |
+
"eval_steps_per_second": 2.781,
|
| 1337 |
+
"step": 83
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.0030515493878737238,
|
| 1341 |
+
"grad_norm": 1.6351501941680908,
|
| 1342 |
+
"learning_rate": 9.99975660260835e-06,
|
| 1343 |
+
"loss": 9.5312,
|
| 1344 |
+
"step": 84
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.0030515493878737238,
|
| 1348 |
+
"eval_accuracy": 0.07578613383574707,
|
| 1349 |
+
"eval_loss": 9.515625,
|
| 1350 |
+
"eval_runtime": 506.1511,
|
| 1351 |
+
"eval_samples_per_second": 66.713,
|
| 1352 |
+
"eval_steps_per_second": 2.78,
|
| 1353 |
+
"step": 84
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.0030878773567769827,
|
| 1357 |
+
"grad_norm": 1.8447389602661133,
|
| 1358 |
+
"learning_rate": 9.999752969811458e-06,
|
| 1359 |
+
"loss": 9.5547,
|
| 1360 |
+
"step": 85
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.0030878773567769827,
|
| 1364 |
+
"eval_accuracy": 0.07570536643777649,
|
| 1365 |
+
"eval_loss": 9.5078125,
|
| 1366 |
+
"eval_runtime": 504.3987,
|
| 1367 |
+
"eval_samples_per_second": 66.945,
|
| 1368 |
+
"eval_steps_per_second": 2.789,
|
| 1369 |
+
"step": 85
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.003124205325680241,
|
| 1373 |
+
"grad_norm": 1.743525743484497,
|
| 1374 |
+
"learning_rate": 9.999749337014568e-06,
|
| 1375 |
+
"loss": 9.5781,
|
| 1376 |
+
"step": 86
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 0.003124205325680241,
|
| 1380 |
+
"eval_accuracy": 0.07604039192046953,
|
| 1381 |
+
"eval_loss": 9.5,
|
| 1382 |
+
"eval_runtime": 504.8644,
|
| 1383 |
+
"eval_samples_per_second": 66.883,
|
| 1384 |
+
"eval_steps_per_second": 2.787,
|
| 1385 |
+
"step": 86
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.0031605332945835,
|
| 1389 |
+
"grad_norm": 1.7386131286621094,
|
| 1390 |
+
"learning_rate": 9.999745704217678e-06,
|
| 1391 |
+
"loss": 9.5703,
|
| 1392 |
+
"step": 87
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.0031605332945835,
|
| 1396 |
+
"eval_accuracy": 0.0763665879922733,
|
| 1397 |
+
"eval_loss": 9.4921875,
|
| 1398 |
+
"eval_runtime": 503.9366,
|
| 1399 |
+
"eval_samples_per_second": 67.006,
|
| 1400 |
+
"eval_steps_per_second": 2.792,
|
| 1401 |
+
"step": 87
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.0031968612634867585,
|
| 1405 |
+
"grad_norm": 1.8193249702453613,
|
| 1406 |
+
"learning_rate": 9.999742071420788e-06,
|
| 1407 |
+
"loss": 9.4844,
|
| 1408 |
+
"step": 88
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.0031968612634867585,
|
| 1412 |
+
"eval_accuracy": 0.0764146431466214,
|
| 1413 |
+
"eval_loss": 9.484375,
|
| 1414 |
+
"eval_runtime": 504.69,
|
| 1415 |
+
"eval_samples_per_second": 66.906,
|
| 1416 |
+
"eval_steps_per_second": 2.788,
|
| 1417 |
+
"step": 88
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.003233189232390017,
|
| 1421 |
+
"grad_norm": 1.7229965925216675,
|
| 1422 |
+
"learning_rate": 9.999738438623897e-06,
|
| 1423 |
+
"loss": 9.5312,
|
| 1424 |
+
"step": 89
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.003233189232390017,
|
| 1428 |
+
"eval_accuracy": 0.07648345465378129,
|
| 1429 |
+
"eval_loss": 9.4765625,
|
| 1430 |
+
"eval_runtime": 504.1538,
|
| 1431 |
+
"eval_samples_per_second": 66.978,
|
| 1432 |
+
"eval_steps_per_second": 2.791,
|
| 1433 |
+
"step": 89
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.003269517201293276,
|
| 1437 |
+
"grad_norm": 1.7293239831924438,
|
| 1438 |
+
"learning_rate": 9.999734805827007e-06,
|
| 1439 |
+
"loss": 9.5312,
|
| 1440 |
+
"step": 90
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.003269517201293276,
|
| 1444 |
+
"eval_accuracy": 0.07651958286620683,
|
| 1445 |
+
"eval_loss": 9.46875,
|
| 1446 |
+
"eval_runtime": 504.9175,
|
| 1447 |
+
"eval_samples_per_second": 66.876,
|
| 1448 |
+
"eval_steps_per_second": 2.787,
|
| 1449 |
+
"step": 90
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.0033058451701965343,
|
| 1453 |
+
"grad_norm": 1.6052281856536865,
|
| 1454 |
+
"learning_rate": 9.999731173030117e-06,
|
| 1455 |
+
"loss": 9.5078,
|
| 1456 |
+
"step": 91
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.0033058451701965343,
|
| 1460 |
+
"eval_accuracy": 0.07662689639462152,
|
| 1461 |
+
"eval_loss": 9.46875,
|
| 1462 |
+
"eval_runtime": 505.1868,
|
| 1463 |
+
"eval_samples_per_second": 66.841,
|
| 1464 |
+
"eval_steps_per_second": 2.785,
|
| 1465 |
+
"step": 91
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.003342173139099793,
|
| 1469 |
+
"grad_norm": 1.6207119226455688,
|
| 1470 |
+
"learning_rate": 9.999727540233227e-06,
|
| 1471 |
+
"loss": 9.5,
|
| 1472 |
+
"step": 92
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.003342173139099793,
|
| 1476 |
+
"eval_accuracy": 0.07678099132630518,
|
| 1477 |
+
"eval_loss": 9.4609375,
|
| 1478 |
+
"eval_runtime": 503.2555,
|
| 1479 |
+
"eval_samples_per_second": 67.097,
|
| 1480 |
+
"eval_steps_per_second": 2.796,
|
| 1481 |
+
"step": 92
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.0033785011080030517,
|
| 1485 |
+
"grad_norm": 1.7734899520874023,
|
| 1486 |
+
"learning_rate": 9.999723907436337e-06,
|
| 1487 |
+
"loss": 9.4844,
|
| 1488 |
+
"step": 93
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.0033785011080030517,
|
| 1492 |
+
"eval_accuracy": 0.07692313036717814,
|
| 1493 |
+
"eval_loss": 9.453125,
|
| 1494 |
+
"eval_runtime": 505.6253,
|
| 1495 |
+
"eval_samples_per_second": 66.783,
|
| 1496 |
+
"eval_steps_per_second": 2.783,
|
| 1497 |
+
"step": 93
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.00341482907690631,
|
| 1501 |
+
"grad_norm": 1.8365049362182617,
|
| 1502 |
+
"learning_rate": 9.999720274639447e-06,
|
| 1503 |
+
"loss": 9.4688,
|
| 1504 |
+
"step": 94
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.00341482907690631,
|
| 1508 |
+
"eval_accuracy": 0.0772882916424473,
|
| 1509 |
+
"eval_loss": 9.4453125,
|
| 1510 |
+
"eval_runtime": 504.8802,
|
| 1511 |
+
"eval_samples_per_second": 66.881,
|
| 1512 |
+
"eval_steps_per_second": 2.787,
|
| 1513 |
+
"step": 94
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.0034511570458095686,
|
| 1517 |
+
"grad_norm": 1.5928810834884644,
|
| 1518 |
+
"learning_rate": 9.999716641842555e-06,
|
| 1519 |
+
"loss": 9.5156,
|
| 1520 |
+
"step": 95
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.0034511570458095686,
|
| 1524 |
+
"eval_accuracy": 0.07773769418226642,
|
| 1525 |
+
"eval_loss": 9.4375,
|
| 1526 |
+
"eval_runtime": 508.082,
|
| 1527 |
+
"eval_samples_per_second": 66.46,
|
| 1528 |
+
"eval_steps_per_second": 2.769,
|
| 1529 |
+
"step": 95
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.0034874850147128275,
|
| 1533 |
+
"grad_norm": 1.648245096206665,
|
| 1534 |
+
"learning_rate": 9.999713009045665e-06,
|
| 1535 |
+
"loss": 9.4453,
|
| 1536 |
+
"step": 96
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.0034874850147128275,
|
| 1540 |
+
"eval_accuracy": 0.07832689090301743,
|
| 1541 |
+
"eval_loss": 9.4296875,
|
| 1542 |
+
"eval_runtime": 504.0456,
|
| 1543 |
+
"eval_samples_per_second": 66.992,
|
| 1544 |
+
"eval_steps_per_second": 2.791,
|
| 1545 |
+
"step": 96
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.003523812983616086,
|
| 1549 |
+
"grad_norm": 1.7062604427337646,
|
| 1550 |
+
"learning_rate": 9.999709376248776e-06,
|
| 1551 |
+
"loss": 9.4766,
|
| 1552 |
+
"step": 97
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.003523812983616086,
|
| 1556 |
+
"eval_accuracy": 0.07944866031927555,
|
| 1557 |
+
"eval_loss": 9.421875,
|
| 1558 |
+
"eval_runtime": 504.2362,
|
| 1559 |
+
"eval_samples_per_second": 66.967,
|
| 1560 |
+
"eval_steps_per_second": 2.79,
|
| 1561 |
+
"step": 97
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.0035601409525193445,
|
| 1565 |
+
"grad_norm": 1.7384364604949951,
|
| 1566 |
+
"learning_rate": 9.999705743451884e-06,
|
| 1567 |
+
"loss": 9.4219,
|
| 1568 |
+
"step": 98
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.0035601409525193445,
|
| 1572 |
+
"eval_accuracy": 0.08043025921905568,
|
| 1573 |
+
"eval_loss": 9.421875,
|
| 1574 |
+
"eval_runtime": 505.9376,
|
| 1575 |
+
"eval_samples_per_second": 66.741,
|
| 1576 |
+
"eval_steps_per_second": 2.781,
|
| 1577 |
+
"step": 98
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.0035964689214226034,
|
| 1581 |
+
"grad_norm": 1.6508241891860962,
|
| 1582 |
+
"learning_rate": 9.999702110654994e-06,
|
| 1583 |
+
"loss": 9.4531,
|
| 1584 |
+
"step": 99
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.0035964689214226034,
|
| 1588 |
+
"eval_accuracy": 0.08138432772619424,
|
| 1589 |
+
"eval_loss": 9.4140625,
|
| 1590 |
+
"eval_runtime": 506.1211,
|
| 1591 |
+
"eval_samples_per_second": 66.717,
|
| 1592 |
+
"eval_steps_per_second": 2.78,
|
| 1593 |
+
"step": 99
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.003632796890325862,
|
| 1597 |
+
"grad_norm": 1.690098762512207,
|
| 1598 |
+
"learning_rate": 9.999698477858104e-06,
|
| 1599 |
+
"loss": 9.4141,
|
| 1600 |
+
"step": 100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.003632796890325862,
|
| 1604 |
+
"eval_accuracy": 0.08187622723383445,
|
| 1605 |
+
"eval_loss": 9.40625,
|
| 1606 |
+
"eval_runtime": 505.2427,
|
| 1607 |
+
"eval_samples_per_second": 66.833,
|
| 1608 |
+
"eval_steps_per_second": 2.785,
|
| 1609 |
+
"step": 100
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.0036691248592291203,
|
| 1613 |
+
"grad_norm": 1.738881230354309,
|
| 1614 |
+
"learning_rate": 9.999694845061213e-06,
|
| 1615 |
+
"loss": 9.375,
|
| 1616 |
+
"step": 101
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.0036691248592291203,
|
| 1620 |
+
"eval_accuracy": 0.08247908782979768,
|
| 1621 |
+
"eval_loss": 9.3984375,
|
| 1622 |
+
"eval_runtime": 504.9005,
|
| 1623 |
+
"eval_samples_per_second": 66.879,
|
| 1624 |
+
"eval_steps_per_second": 2.787,
|
| 1625 |
+
"step": 101
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.003705452828132379,
|
| 1629 |
+
"grad_norm": 1.5808320045471191,
|
| 1630 |
+
"learning_rate": 9.999691212264323e-06,
|
| 1631 |
+
"loss": 9.4219,
|
| 1632 |
+
"step": 102
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 0.003705452828132379,
|
| 1636 |
+
"eval_accuracy": 0.08282250849005755,
|
| 1637 |
+
"eval_loss": 9.390625,
|
| 1638 |
+
"eval_runtime": 502.7993,
|
| 1639 |
+
"eval_samples_per_second": 67.158,
|
| 1640 |
+
"eval_steps_per_second": 2.798,
|
| 1641 |
+
"step": 102
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.0037417807970356377,
|
| 1645 |
+
"grad_norm": 1.6801838874816895,
|
| 1646 |
+
"learning_rate": 9.999687579467433e-06,
|
| 1647 |
+
"loss": 9.3828,
|
| 1648 |
+
"step": 103
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.0037417807970356377,
|
| 1652 |
+
"eval_accuracy": 0.08283837248077006,
|
| 1653 |
+
"eval_loss": 9.3828125,
|
| 1654 |
+
"eval_runtime": 505.0748,
|
| 1655 |
+
"eval_samples_per_second": 66.855,
|
| 1656 |
+
"eval_steps_per_second": 2.786,
|
| 1657 |
+
"step": 103
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.003778108765938896,
|
| 1661 |
+
"grad_norm": 1.6030634641647339,
|
| 1662 |
+
"learning_rate": 9.999683946670543e-06,
|
| 1663 |
+
"loss": 9.375,
|
| 1664 |
+
"step": 104
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.003778108765938896,
|
| 1668 |
+
"eval_accuracy": 0.08272639818136136,
|
| 1669 |
+
"eval_loss": 9.3828125,
|
| 1670 |
+
"eval_runtime": 505.0381,
|
| 1671 |
+
"eval_samples_per_second": 66.86,
|
| 1672 |
+
"eval_steps_per_second": 2.786,
|
| 1673 |
+
"step": 104
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.003814436734842155,
|
| 1677 |
+
"grad_norm": 2.755161762237549,
|
| 1678 |
+
"learning_rate": 9.999680313873651e-06,
|
| 1679 |
+
"loss": 9.3516,
|
| 1680 |
+
"step": 105
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.003814436734842155,
|
| 1684 |
+
"eval_accuracy": 0.08249729668045126,
|
| 1685 |
+
"eval_loss": 9.375,
|
| 1686 |
+
"eval_runtime": 506.1198,
|
| 1687 |
+
"eval_samples_per_second": 66.717,
|
| 1688 |
+
"eval_steps_per_second": 2.78,
|
| 1689 |
+
"step": 105
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.0038507647037454135,
|
| 1693 |
+
"grad_norm": 1.700968861579895,
|
| 1694 |
+
"learning_rate": 9.999676681076761e-06,
|
| 1695 |
+
"loss": 9.3906,
|
| 1696 |
+
"step": 106
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.0038507647037454135,
|
| 1700 |
+
"eval_accuracy": 0.0824550023548473,
|
| 1701 |
+
"eval_loss": 9.3671875,
|
| 1702 |
+
"eval_runtime": 504.8911,
|
| 1703 |
+
"eval_samples_per_second": 66.88,
|
| 1704 |
+
"eval_steps_per_second": 2.787,
|
| 1705 |
+
"step": 106
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.0038870926726486724,
|
| 1709 |
+
"grad_norm": 1.7681119441986084,
|
| 1710 |
+
"learning_rate": 9.999673048279871e-06,
|
| 1711 |
+
"loss": 9.3672,
|
| 1712 |
+
"step": 107
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.0038870926726486724,
|
| 1716 |
+
"eval_accuracy": 0.08233683299337206,
|
| 1717 |
+
"eval_loss": 9.359375,
|
| 1718 |
+
"eval_runtime": 503.3036,
|
| 1719 |
+
"eval_samples_per_second": 67.091,
|
| 1720 |
+
"eval_steps_per_second": 2.796,
|
| 1721 |
+
"step": 107
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.003923420641551931,
|
| 1725 |
+
"grad_norm": 1.7191691398620605,
|
| 1726 |
+
"learning_rate": 9.999669415482981e-06,
|
| 1727 |
+
"loss": 9.3359,
|
| 1728 |
+
"step": 108
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.003923420641551931,
|
| 1732 |
+
"eval_accuracy": 0.08216516608657437,
|
| 1733 |
+
"eval_loss": 9.3515625,
|
| 1734 |
+
"eval_runtime": 504.9663,
|
| 1735 |
+
"eval_samples_per_second": 66.87,
|
| 1736 |
+
"eval_steps_per_second": 2.786,
|
| 1737 |
+
"step": 108
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.00395974861045519,
|
| 1741 |
+
"grad_norm": 1.5659282207489014,
|
| 1742 |
+
"learning_rate": 9.999665782686092e-06,
|
| 1743 |
+
"loss": 9.4062,
|
| 1744 |
+
"step": 109
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 0.00395974861045519,
|
| 1748 |
+
"eval_accuracy": 0.08175872369678691,
|
| 1749 |
+
"eval_loss": 9.34375,
|
| 1750 |
+
"eval_runtime": 505.2603,
|
| 1751 |
+
"eval_samples_per_second": 66.831,
|
| 1752 |
+
"eval_steps_per_second": 2.785,
|
| 1753 |
+
"step": 109
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.003996076579358448,
|
| 1757 |
+
"grad_norm": 1.8398549556732178,
|
| 1758 |
+
"learning_rate": 9.999662149889202e-06,
|
| 1759 |
+
"loss": 9.3906,
|
| 1760 |
+
"step": 110
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.003996076579358448,
|
| 1764 |
+
"eval_accuracy": 0.08157759050356041,
|
| 1765 |
+
"eval_loss": 9.34375,
|
| 1766 |
+
"eval_runtime": 506.1037,
|
| 1767 |
+
"eval_samples_per_second": 66.72,
|
| 1768 |
+
"eval_steps_per_second": 2.78,
|
| 1769 |
+
"step": 110
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 0.004032404548261707,
|
| 1773 |
+
"grad_norm": 2.4529032707214355,
|
| 1774 |
+
"learning_rate": 9.99965851709231e-06,
|
| 1775 |
+
"loss": 9.25,
|
| 1776 |
+
"step": 111
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 0.004032404548261707,
|
| 1780 |
+
"eval_accuracy": 0.08160373134957025,
|
| 1781 |
+
"eval_loss": 9.3359375,
|
| 1782 |
+
"eval_runtime": 504.6658,
|
| 1783 |
+
"eval_samples_per_second": 66.91,
|
| 1784 |
+
"eval_steps_per_second": 2.788,
|
| 1785 |
+
"step": 111
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.004068732517164966,
|
| 1789 |
+
"grad_norm": 1.7243255376815796,
|
| 1790 |
+
"learning_rate": 9.99965488429542e-06,
|
| 1791 |
+
"loss": 9.3281,
|
| 1792 |
+
"step": 112
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.004068732517164966,
|
| 1796 |
+
"eval_accuracy": 0.08156398452612451,
|
| 1797 |
+
"eval_loss": 9.328125,
|
| 1798 |
+
"eval_runtime": 501.5913,
|
| 1799 |
+
"eval_samples_per_second": 67.32,
|
| 1800 |
+
"eval_steps_per_second": 2.805,
|
| 1801 |
+
"step": 112
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.004105060486068224,
|
| 1805 |
+
"grad_norm": 1.617632508277893,
|
| 1806 |
+
"learning_rate": 9.99965125149853e-06,
|
| 1807 |
+
"loss": 9.375,
|
| 1808 |
+
"step": 113
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.004105060486068224,
|
| 1812 |
+
"eval_accuracy": 0.08125842901157987,
|
| 1813 |
+
"eval_loss": 9.3203125,
|
| 1814 |
+
"eval_runtime": 504.3056,
|
| 1815 |
+
"eval_samples_per_second": 66.957,
|
| 1816 |
+
"eval_steps_per_second": 2.79,
|
| 1817 |
+
"step": 113
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.0041413884549714826,
|
| 1821 |
+
"grad_norm": 1.7473822832107544,
|
| 1822 |
+
"learning_rate": 9.999647618701639e-06,
|
| 1823 |
+
"loss": 9.3906,
|
| 1824 |
+
"step": 114
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 0.0041413884549714826,
|
| 1828 |
+
"eval_accuracy": 0.0812115607616464,
|
| 1829 |
+
"eval_loss": 9.3203125,
|
| 1830 |
+
"eval_runtime": 507.2626,
|
| 1831 |
+
"eval_samples_per_second": 66.567,
|
| 1832 |
+
"eval_steps_per_second": 2.774,
|
| 1833 |
+
"step": 114
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.0041777164238747415,
|
| 1837 |
+
"grad_norm": 1.7480499744415283,
|
| 1838 |
+
"learning_rate": 9.999643985904749e-06,
|
| 1839 |
+
"loss": 9.3203,
|
| 1840 |
+
"step": 115
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.0041777164238747415,
|
| 1844 |
+
"eval_accuracy": 0.08121138706831743,
|
| 1845 |
+
"eval_loss": 9.3125,
|
| 1846 |
+
"eval_runtime": 505.5579,
|
| 1847 |
+
"eval_samples_per_second": 66.792,
|
| 1848 |
+
"eval_steps_per_second": 2.783,
|
| 1849 |
+
"step": 115
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.0042140443927779995,
|
| 1853 |
+
"grad_norm": 1.645756721496582,
|
| 1854 |
+
"learning_rate": 9.999640353107859e-06,
|
| 1855 |
+
"loss": 9.3125,
|
| 1856 |
+
"step": 116
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.0042140443927779995,
|
| 1860 |
+
"eval_accuracy": 0.08107075336962886,
|
| 1861 |
+
"eval_loss": 9.3046875,
|
| 1862 |
+
"eval_runtime": 504.2295,
|
| 1863 |
+
"eval_samples_per_second": 66.968,
|
| 1864 |
+
"eval_steps_per_second": 2.79,
|
| 1865 |
+
"step": 116
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.004250372361681258,
|
| 1869 |
+
"grad_norm": 1.6185376644134521,
|
| 1870 |
+
"learning_rate": 9.999636720310967e-06,
|
| 1871 |
+
"loss": 9.3359,
|
| 1872 |
+
"step": 117
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.004250372361681258,
|
| 1876 |
+
"eval_accuracy": 0.08092007440674827,
|
| 1877 |
+
"eval_loss": 9.296875,
|
| 1878 |
+
"eval_runtime": 502.016,
|
| 1879 |
+
"eval_samples_per_second": 67.263,
|
| 1880 |
+
"eval_steps_per_second": 2.803,
|
| 1881 |
+
"step": 117
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 0.004286700330584517,
|
| 1885 |
+
"grad_norm": 1.718162178993225,
|
| 1886 |
+
"learning_rate": 9.999633087514077e-06,
|
| 1887 |
+
"loss": 9.2812,
|
| 1888 |
+
"step": 118
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 0.004286700330584517,
|
| 1892 |
+
"eval_accuracy": 0.08078224875021137,
|
| 1893 |
+
"eval_loss": 9.296875,
|
| 1894 |
+
"eval_runtime": 503.8149,
|
| 1895 |
+
"eval_samples_per_second": 67.023,
|
| 1896 |
+
"eval_steps_per_second": 2.793,
|
| 1897 |
+
"step": 118
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 0.004323028299487775,
|
| 1901 |
+
"grad_norm": 2.7064478397369385,
|
| 1902 |
+
"learning_rate": 9.999629454717187e-06,
|
| 1903 |
+
"loss": 9.2031,
|
| 1904 |
+
"step": 119
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.004323028299487775,
|
| 1908 |
+
"eval_accuracy": 0.08067389306182286,
|
| 1909 |
+
"eval_loss": 9.2890625,
|
| 1910 |
+
"eval_runtime": 506.662,
|
| 1911 |
+
"eval_samples_per_second": 66.646,
|
| 1912 |
+
"eval_steps_per_second": 2.777,
|
| 1913 |
+
"step": 119
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.004359356268391034,
|
| 1917 |
+
"grad_norm": 1.9571579694747925,
|
| 1918 |
+
"learning_rate": 9.999625821920297e-06,
|
| 1919 |
+
"loss": 9.2422,
|
| 1920 |
+
"step": 120
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.004359356268391034,
|
| 1924 |
+
"eval_accuracy": 0.08080248402303625,
|
| 1925 |
+
"eval_loss": 9.28125,
|
| 1926 |
+
"eval_runtime": 506.1232,
|
| 1927 |
+
"eval_samples_per_second": 66.717,
|
| 1928 |
+
"eval_steps_per_second": 2.78,
|
| 1929 |
+
"step": 120
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.004395684237294293,
|
| 1933 |
+
"grad_norm": 1.6557737588882446,
|
| 1934 |
+
"learning_rate": 9.999622189123407e-06,
|
| 1935 |
+
"loss": 9.3047,
|
| 1936 |
+
"step": 121
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.004395684237294293,
|
| 1940 |
+
"eval_accuracy": 0.08088458306986226,
|
| 1941 |
+
"eval_loss": 9.28125,
|
| 1942 |
+
"eval_runtime": 503.855,
|
| 1943 |
+
"eval_samples_per_second": 67.017,
|
| 1944 |
+
"eval_steps_per_second": 2.792,
|
| 1945 |
+
"step": 121
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.004432012206197551,
|
| 1949 |
+
"grad_norm": 1.657261848449707,
|
| 1950 |
+
"learning_rate": 9.999618556326518e-06,
|
| 1951 |
+
"loss": 9.2969,
|
| 1952 |
+
"step": 122
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.004432012206197551,
|
| 1956 |
+
"eval_accuracy": 0.08103369879278215,
|
| 1957 |
+
"eval_loss": 9.2734375,
|
| 1958 |
+
"eval_runtime": 503.3156,
|
| 1959 |
+
"eval_samples_per_second": 67.089,
|
| 1960 |
+
"eval_steps_per_second": 2.795,
|
| 1961 |
+
"step": 122
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.00446834017510081,
|
| 1965 |
+
"grad_norm": 1.9978619813919067,
|
| 1966 |
+
"learning_rate": 9.999614923529626e-06,
|
| 1967 |
+
"loss": 9.25,
|
| 1968 |
+
"step": 123
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.00446834017510081,
|
| 1972 |
+
"eval_accuracy": 0.08151164493632851,
|
| 1973 |
+
"eval_loss": 9.265625,
|
| 1974 |
+
"eval_runtime": 503.1303,
|
| 1975 |
+
"eval_samples_per_second": 67.114,
|
| 1976 |
+
"eval_steps_per_second": 2.796,
|
| 1977 |
+
"step": 123
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.004504668144004069,
|
| 1981 |
+
"grad_norm": 1.604614019393921,
|
| 1982 |
+
"learning_rate": 9.999611290732736e-06,
|
| 1983 |
+
"loss": 9.3281,
|
| 1984 |
+
"step": 124
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.004504668144004069,
|
| 1988 |
+
"eval_accuracy": 0.0825292273040934,
|
| 1989 |
+
"eval_loss": 9.2578125,
|
| 1990 |
+
"eval_runtime": 505.0968,
|
| 1991 |
+
"eval_samples_per_second": 66.853,
|
| 1992 |
+
"eval_steps_per_second": 2.786,
|
| 1993 |
+
"step": 124
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 0.004540996112907327,
|
| 1997 |
+
"grad_norm": 1.707974910736084,
|
| 1998 |
+
"learning_rate": 9.999607657935846e-06,
|
| 1999 |
+
"loss": 9.2656,
|
| 2000 |
+
"step": 125
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 0.004540996112907327,
|
| 2004 |
+
"eval_accuracy": 0.08359170939739675,
|
| 2005 |
+
"eval_loss": 9.2578125,
|
| 2006 |
+
"eval_runtime": 506.8511,
|
| 2007 |
+
"eval_samples_per_second": 66.621,
|
| 2008 |
+
"eval_steps_per_second": 2.776,
|
| 2009 |
+
"step": 125
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 0.004577324081810586,
|
| 2013 |
+
"grad_norm": 1.7586125135421753,
|
| 2014 |
+
"learning_rate": 9.999604025138955e-06,
|
| 2015 |
+
"loss": 9.3047,
|
| 2016 |
+
"step": 126
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.004577324081810586,
|
| 2020 |
+
"eval_accuracy": 0.08447563474851999,
|
| 2021 |
+
"eval_loss": 9.25,
|
| 2022 |
+
"eval_runtime": 504.2303,
|
| 2023 |
+
"eval_samples_per_second": 66.967,
|
| 2024 |
+
"eval_steps_per_second": 2.79,
|
| 2025 |
+
"step": 126
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.004613652050713845,
|
| 2029 |
+
"grad_norm": 1.7619037628173828,
|
| 2030 |
+
"learning_rate": 9.999600392342065e-06,
|
| 2031 |
+
"loss": 9.25,
|
| 2032 |
+
"step": 127
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.004613652050713845,
|
| 2036 |
+
"eval_accuracy": 0.08498837745563648,
|
| 2037 |
+
"eval_loss": 9.2421875,
|
| 2038 |
+
"eval_runtime": 502.809,
|
| 2039 |
+
"eval_samples_per_second": 67.157,
|
| 2040 |
+
"eval_steps_per_second": 2.798,
|
| 2041 |
+
"step": 127
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 0.004649980019617103,
|
| 2045 |
+
"grad_norm": 1.6512857675552368,
|
| 2046 |
+
"learning_rate": 9.999596759545175e-06,
|
| 2047 |
+
"loss": 9.2969,
|
| 2048 |
+
"step": 128
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.004649980019617103,
|
| 2052 |
+
"eval_accuracy": 0.08521718946766497,
|
| 2053 |
+
"eval_loss": 9.234375,
|
| 2054 |
+
"eval_runtime": 504.7926,
|
| 2055 |
+
"eval_samples_per_second": 66.893,
|
| 2056 |
+
"eval_steps_per_second": 2.787,
|
| 2057 |
+
"step": 128
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 0.004686307988520362,
|
| 2061 |
+
"grad_norm": 1.7101061344146729,
|
| 2062 |
+
"learning_rate": 9.999593126748285e-06,
|
| 2063 |
+
"loss": 9.3203,
|
| 2064 |
+
"step": 129
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 0.004686307988520362,
|
| 2068 |
+
"eval_accuracy": 0.08527115019519801,
|
| 2069 |
+
"eval_loss": 9.234375,
|
| 2070 |
+
"eval_runtime": 505.6873,
|
| 2071 |
+
"eval_samples_per_second": 66.774,
|
| 2072 |
+
"eval_steps_per_second": 2.782,
|
| 2073 |
+
"step": 129
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.004722635957423621,
|
| 2077 |
+
"grad_norm": 2.3074684143066406,
|
| 2078 |
+
"learning_rate": 9.999589493951393e-06,
|
| 2079 |
+
"loss": 9.25,
|
| 2080 |
+
"step": 130
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.004722635957423621,
|
| 2084 |
+
"eval_accuracy": 0.08533631414244955,
|
| 2085 |
+
"eval_loss": 9.2265625,
|
| 2086 |
+
"eval_runtime": 504.004,
|
| 2087 |
+
"eval_samples_per_second": 66.997,
|
| 2088 |
+
"eval_steps_per_second": 2.792,
|
| 2089 |
+
"step": 130
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.004758963926326879,
|
| 2093 |
+
"grad_norm": 1.86430025100708,
|
| 2094 |
+
"learning_rate": 9.999585861154503e-06,
|
| 2095 |
+
"loss": 9.2422,
|
| 2096 |
+
"step": 131
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.004758963926326879,
|
| 2100 |
+
"eval_accuracy": 0.08537788474584947,
|
| 2101 |
+
"eval_loss": 9.21875,
|
| 2102 |
+
"eval_runtime": 502.5558,
|
| 2103 |
+
"eval_samples_per_second": 67.191,
|
| 2104 |
+
"eval_steps_per_second": 2.8,
|
| 2105 |
+
"step": 131
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 0.0047952918952301376,
|
| 2109 |
+
"grad_norm": 1.7045161724090576,
|
| 2110 |
+
"learning_rate": 9.999582228357613e-06,
|
| 2111 |
+
"loss": 9.1641,
|
| 2112 |
+
"step": 132
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 0.0047952918952301376,
|
| 2116 |
+
"eval_accuracy": 0.08549750155173277,
|
| 2117 |
+
"eval_loss": 9.2109375,
|
| 2118 |
+
"eval_runtime": 501.7481,
|
| 2119 |
+
"eval_samples_per_second": 67.299,
|
| 2120 |
+
"eval_steps_per_second": 2.804,
|
| 2121 |
+
"step": 132
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.0048316198641333965,
|
| 2125 |
+
"grad_norm": 1.769091248512268,
|
| 2126 |
+
"learning_rate": 9.999578595560723e-06,
|
| 2127 |
+
"loss": 9.2109,
|
| 2128 |
+
"step": 133
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.0048316198641333965,
|
| 2132 |
+
"eval_accuracy": 0.08575407554750815,
|
| 2133 |
+
"eval_loss": 9.2109375,
|
| 2134 |
+
"eval_runtime": 503.2243,
|
| 2135 |
+
"eval_samples_per_second": 67.101,
|
| 2136 |
+
"eval_steps_per_second": 2.796,
|
| 2137 |
+
"step": 133
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.004867947833036655,
|
| 2141 |
+
"grad_norm": 1.7396882772445679,
|
| 2142 |
+
"learning_rate": 9.999574962763834e-06,
|
| 2143 |
+
"loss": 9.2422,
|
| 2144 |
+
"step": 134
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.004867947833036655,
|
| 2148 |
+
"eval_accuracy": 0.08600703093226333,
|
| 2149 |
+
"eval_loss": 9.203125,
|
| 2150 |
+
"eval_runtime": 505.0001,
|
| 2151 |
+
"eval_samples_per_second": 66.865,
|
| 2152 |
+
"eval_steps_per_second": 2.786,
|
| 2153 |
+
"step": 134
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 0.004904275801939913,
|
| 2157 |
+
"grad_norm": 1.5990197658538818,
|
| 2158 |
+
"learning_rate": 9.999571329966944e-06,
|
| 2159 |
+
"loss": 9.2188,
|
| 2160 |
+
"step": 135
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 0.004904275801939913,
|
| 2164 |
+
"eval_accuracy": 0.08614508817990553,
|
| 2165 |
+
"eval_loss": 9.1953125,
|
| 2166 |
+
"eval_runtime": 503.7618,
|
| 2167 |
+
"eval_samples_per_second": 67.03,
|
| 2168 |
+
"eval_steps_per_second": 2.793,
|
| 2169 |
+
"step": 135
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.004940603770843172,
|
| 2173 |
+
"grad_norm": 1.5657048225402832,
|
| 2174 |
+
"learning_rate": 9.999567697170052e-06,
|
| 2175 |
+
"loss": 9.3047,
|
| 2176 |
+
"step": 136
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 0.004940603770843172,
|
| 2180 |
+
"eval_accuracy": 0.08612786359144943,
|
| 2181 |
+
"eval_loss": 9.1875,
|
| 2182 |
+
"eval_runtime": 504.5155,
|
| 2183 |
+
"eval_samples_per_second": 66.93,
|
| 2184 |
+
"eval_steps_per_second": 2.789,
|
| 2185 |
+
"step": 136
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 0.004976931739746431,
|
| 2189 |
+
"grad_norm": 1.7186903953552246,
|
| 2190 |
+
"learning_rate": 9.999564064373162e-06,
|
| 2191 |
+
"loss": 9.1641,
|
| 2192 |
+
"step": 137
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.004976931739746431,
|
| 2196 |
+
"eval_accuracy": 0.08613209012912101,
|
| 2197 |
+
"eval_loss": 9.1875,
|
| 2198 |
+
"eval_runtime": 504.0325,
|
| 2199 |
+
"eval_samples_per_second": 66.994,
|
| 2200 |
+
"eval_steps_per_second": 2.791,
|
| 2201 |
+
"step": 137
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.005013259708649689,
|
| 2205 |
+
"grad_norm": 1.6939176321029663,
|
| 2206 |
+
"learning_rate": 9.999560431576272e-06,
|
| 2207 |
+
"loss": 9.2188,
|
| 2208 |
+
"step": 138
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.005013259708649689,
|
| 2212 |
+
"eval_accuracy": 0.08593219805636586,
|
| 2213 |
+
"eval_loss": 9.1796875,
|
| 2214 |
+
"eval_runtime": 502.3491,
|
| 2215 |
+
"eval_samples_per_second": 67.218,
|
| 2216 |
+
"eval_steps_per_second": 2.801,
|
| 2217 |
+
"step": 138
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.005049587677552948,
|
| 2221 |
+
"grad_norm": 1.617654800415039,
|
| 2222 |
+
"learning_rate": 9.99955679877938e-06,
|
| 2223 |
+
"loss": 9.2422,
|
| 2224 |
+
"step": 139
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 0.005049587677552948,
|
| 2228 |
+
"eval_accuracy": 0.08563775891487524,
|
| 2229 |
+
"eval_loss": 9.171875,
|
| 2230 |
+
"eval_runtime": 503.9529,
|
| 2231 |
+
"eval_samples_per_second": 67.004,
|
| 2232 |
+
"eval_steps_per_second": 2.792,
|
| 2233 |
+
"step": 139
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 0.005085915646456207,
|
| 2237 |
+
"grad_norm": 1.570475697517395,
|
| 2238 |
+
"learning_rate": 9.99955316598249e-06,
|
| 2239 |
+
"loss": 9.2422,
|
| 2240 |
+
"step": 140
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.005085915646456207,
|
| 2244 |
+
"eval_accuracy": 0.0854915380807715,
|
| 2245 |
+
"eval_loss": 9.171875,
|
| 2246 |
+
"eval_runtime": 502.4421,
|
| 2247 |
+
"eval_samples_per_second": 67.206,
|
| 2248 |
+
"eval_steps_per_second": 2.8,
|
| 2249 |
+
"step": 140
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.005122243615359465,
|
| 2253 |
+
"grad_norm": 1.7714993953704834,
|
| 2254 |
+
"learning_rate": 9.9995495331856e-06,
|
| 2255 |
+
"loss": 9.1484,
|
| 2256 |
+
"step": 141
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.005122243615359465,
|
| 2260 |
+
"eval_accuracy": 0.08518311662629889,
|
| 2261 |
+
"eval_loss": 9.1640625,
|
| 2262 |
+
"eval_runtime": 503.434,
|
| 2263 |
+
"eval_samples_per_second": 67.073,
|
| 2264 |
+
"eval_steps_per_second": 2.795,
|
| 2265 |
+
"step": 141
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 0.005158571584262724,
|
| 2269 |
+
"grad_norm": 1.7324341535568237,
|
| 2270 |
+
"learning_rate": 9.999545900388709e-06,
|
| 2271 |
+
"loss": 9.2422,
|
| 2272 |
+
"step": 142
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 0.005158571584262724,
|
| 2276 |
+
"eval_accuracy": 0.08514038806737252,
|
| 2277 |
+
"eval_loss": 9.15625,
|
| 2278 |
+
"eval_runtime": 502.9892,
|
| 2279 |
+
"eval_samples_per_second": 67.133,
|
| 2280 |
+
"eval_steps_per_second": 2.797,
|
| 2281 |
+
"step": 142
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 0.005194899553165983,
|
| 2285 |
+
"grad_norm": 1.5842994451522827,
|
| 2286 |
+
"learning_rate": 9.99954226759182e-06,
|
| 2287 |
+
"loss": 9.1953,
|
| 2288 |
+
"step": 143
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.005194899553165983,
|
| 2292 |
+
"eval_accuracy": 0.0852237898141658,
|
| 2293 |
+
"eval_loss": 9.1484375,
|
| 2294 |
+
"eval_runtime": 502.9366,
|
| 2295 |
+
"eval_samples_per_second": 67.14,
|
| 2296 |
+
"eval_steps_per_second": 2.798,
|
| 2297 |
+
"step": 143
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.005231227522069241,
|
| 2301 |
+
"grad_norm": 1.8025195598602295,
|
| 2302 |
+
"learning_rate": 9.99953863479493e-06,
|
| 2303 |
+
"loss": 9.1641,
|
| 2304 |
+
"step": 144
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.005231227522069241,
|
| 2308 |
+
"eval_accuracy": 0.08531526830075614,
|
| 2309 |
+
"eval_loss": 9.1484375,
|
| 2310 |
+
"eval_runtime": 503.3947,
|
| 2311 |
+
"eval_samples_per_second": 67.079,
|
| 2312 |
+
"eval_steps_per_second": 2.795,
|
| 2313 |
+
"step": 144
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.0052675554909725,
|
| 2317 |
+
"grad_norm": 1.6925685405731201,
|
| 2318 |
+
"learning_rate": 9.99953500199804e-06,
|
| 2319 |
+
"loss": 9.1875,
|
| 2320 |
+
"step": 145
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.0052675554909725,
|
| 2324 |
+
"eval_accuracy": 0.0853937197876738,
|
| 2325 |
+
"eval_loss": 9.140625,
|
| 2326 |
+
"eval_runtime": 503.2502,
|
| 2327 |
+
"eval_samples_per_second": 67.098,
|
| 2328 |
+
"eval_steps_per_second": 2.796,
|
| 2329 |
+
"step": 145
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 0.005303883459875759,
|
| 2333 |
+
"grad_norm": 1.6498448848724365,
|
| 2334 |
+
"learning_rate": 9.99953136920115e-06,
|
| 2335 |
+
"loss": 9.1172,
|
| 2336 |
+
"step": 146
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.005303883459875759,
|
| 2340 |
+
"eval_accuracy": 0.0855044782337797,
|
| 2341 |
+
"eval_loss": 9.1328125,
|
| 2342 |
+
"eval_runtime": 501.7641,
|
| 2343 |
+
"eval_samples_per_second": 67.297,
|
| 2344 |
+
"eval_steps_per_second": 2.804,
|
| 2345 |
+
"step": 146
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 0.005340211428779017,
|
| 2349 |
+
"grad_norm": 1.6799402236938477,
|
| 2350 |
+
"learning_rate": 9.999527736404258e-06,
|
| 2351 |
+
"loss": 9.1094,
|
| 2352 |
+
"step": 147
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 0.005340211428779017,
|
| 2356 |
+
"eval_accuracy": 0.0855554572258321,
|
| 2357 |
+
"eval_loss": 9.1328125,
|
| 2358 |
+
"eval_runtime": 501.8847,
|
| 2359 |
+
"eval_samples_per_second": 67.28,
|
| 2360 |
+
"eval_steps_per_second": 2.803,
|
| 2361 |
+
"step": 147
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.005376539397682276,
|
| 2365 |
+
"grad_norm": 1.672473669052124,
|
| 2366 |
+
"learning_rate": 9.999524103607368e-06,
|
| 2367 |
+
"loss": 9.1328,
|
| 2368 |
+
"step": 148
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.005376539397682276,
|
| 2372 |
+
"eval_accuracy": 0.0858869798930576,
|
| 2373 |
+
"eval_loss": 9.125,
|
| 2374 |
+
"eval_runtime": 502.0405,
|
| 2375 |
+
"eval_samples_per_second": 67.26,
|
| 2376 |
+
"eval_steps_per_second": 2.803,
|
| 2377 |
+
"step": 148
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 0.0054128673665855345,
|
| 2381 |
+
"grad_norm": 1.6717029809951782,
|
| 2382 |
+
"learning_rate": 9.999520470810478e-06,
|
| 2383 |
+
"loss": 9.1641,
|
| 2384 |
+
"step": 149
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 0.0054128673665855345,
|
| 2388 |
+
"eval_accuracy": 0.0863320400996525,
|
| 2389 |
+
"eval_loss": 9.1171875,
|
| 2390 |
+
"eval_runtime": 501.7116,
|
| 2391 |
+
"eval_samples_per_second": 67.304,
|
| 2392 |
+
"eval_steps_per_second": 2.804,
|
| 2393 |
+
"step": 149
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 0.0054491953354887926,
|
| 2397 |
+
"grad_norm": 1.5716333389282227,
|
| 2398 |
+
"learning_rate": 9.999516838013588e-06,
|
| 2399 |
+
"loss": 9.1641,
|
| 2400 |
+
"step": 150
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 0.0054491953354887926,
|
| 2404 |
+
"eval_accuracy": 0.08683835615359713,
|
| 2405 |
+
"eval_loss": 9.109375,
|
| 2406 |
+
"eval_runtime": 502.3324,
|
| 2407 |
+
"eval_samples_per_second": 67.22,
|
| 2408 |
+
"eval_steps_per_second": 2.801,
|
| 2409 |
+
"step": 150
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.0054855233043920515,
|
| 2413 |
+
"grad_norm": 1.624820351600647,
|
| 2414 |
+
"learning_rate": 9.999513205216698e-06,
|
| 2415 |
+
"loss": 9.1875,
|
| 2416 |
+
"step": 151
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.0054855233043920515,
|
| 2420 |
+
"eval_accuracy": 0.08733792711660013,
|
| 2421 |
+
"eval_loss": 9.109375,
|
| 2422 |
+
"eval_runtime": 502.804,
|
| 2423 |
+
"eval_samples_per_second": 67.157,
|
| 2424 |
+
"eval_steps_per_second": 2.798,
|
| 2425 |
+
"step": 151
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.00552185127329531,
|
| 2429 |
+
"grad_norm": 1.614936113357544,
|
| 2430 |
+
"learning_rate": 9.999509572419807e-06,
|
| 2431 |
+
"loss": 9.2031,
|
| 2432 |
+
"step": 152
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.00552185127329531,
|
| 2436 |
+
"eval_accuracy": 0.08752846869847912,
|
| 2437 |
+
"eval_loss": 9.1015625,
|
| 2438 |
+
"eval_runtime": 502.8248,
|
| 2439 |
+
"eval_samples_per_second": 67.155,
|
| 2440 |
+
"eval_steps_per_second": 2.798,
|
| 2441 |
+
"step": 152
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 0.005558179242198568,
|
| 2445 |
+
"grad_norm": 1.8622063398361206,
|
| 2446 |
+
"learning_rate": 9.999505939622917e-06,
|
| 2447 |
+
"loss": 9.0703,
|
| 2448 |
+
"step": 153
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 0.005558179242198568,
|
| 2452 |
+
"eval_accuracy": 0.08799966975108385,
|
| 2453 |
+
"eval_loss": 9.09375,
|
| 2454 |
+
"eval_runtime": 501.9847,
|
| 2455 |
+
"eval_samples_per_second": 67.267,
|
| 2456 |
+
"eval_steps_per_second": 2.803,
|
| 2457 |
+
"step": 153
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 0.005594507211101827,
|
| 2461 |
+
"grad_norm": 1.615602731704712,
|
| 2462 |
+
"learning_rate": 9.999502306826027e-06,
|
| 2463 |
+
"loss": 9.1484,
|
| 2464 |
+
"step": 154
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"epoch": 0.005594507211101827,
|
| 2468 |
+
"eval_accuracy": 0.08840796486971365,
|
| 2469 |
+
"eval_loss": 9.0859375,
|
| 2470 |
+
"eval_runtime": 501.6895,
|
| 2471 |
+
"eval_samples_per_second": 67.307,
|
| 2472 |
+
"eval_steps_per_second": 2.805,
|
| 2473 |
+
"step": 154
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.005630835180005086,
|
| 2477 |
+
"grad_norm": 1.661203384399414,
|
| 2478 |
+
"learning_rate": 9.999498674029135e-06,
|
| 2479 |
+
"loss": 9.0625,
|
| 2480 |
+
"step": 155
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.005630835180005086,
|
| 2484 |
+
"eval_accuracy": 0.08875231189439468,
|
| 2485 |
+
"eval_loss": 9.0859375,
|
| 2486 |
+
"eval_runtime": 501.9752,
|
| 2487 |
+
"eval_samples_per_second": 67.268,
|
| 2488 |
+
"eval_steps_per_second": 2.803,
|
| 2489 |
+
"step": 155
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 0.005667163148908344,
|
| 2493 |
+
"grad_norm": 1.7897155284881592,
|
| 2494 |
+
"learning_rate": 9.999495041232245e-06,
|
| 2495 |
+
"loss": 9.0781,
|
| 2496 |
+
"step": 156
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 0.005667163148908344,
|
| 2500 |
+
"eval_accuracy": 0.08888113444671336,
|
| 2501 |
+
"eval_loss": 9.078125,
|
| 2502 |
+
"eval_runtime": 502.8161,
|
| 2503 |
+
"eval_samples_per_second": 67.156,
|
| 2504 |
+
"eval_steps_per_second": 2.798,
|
| 2505 |
+
"step": 156
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 0.005703491117811603,
|
| 2509 |
+
"grad_norm": 1.9064967632293701,
|
| 2510 |
+
"learning_rate": 9.999491408435355e-06,
|
| 2511 |
+
"loss": 9.0234,
|
| 2512 |
+
"step": 157
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 0.005703491117811603,
|
| 2516 |
+
"eval_accuracy": 0.08920223551420071,
|
| 2517 |
+
"eval_loss": 9.0703125,
|
| 2518 |
+
"eval_runtime": 502.0043,
|
| 2519 |
+
"eval_samples_per_second": 67.264,
|
| 2520 |
+
"eval_steps_per_second": 2.803,
|
| 2521 |
+
"step": 157
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.005739819086714862,
|
| 2525 |
+
"grad_norm": 1.635931134223938,
|
| 2526 |
+
"learning_rate": 9.999487775638464e-06,
|
| 2527 |
+
"loss": 9.0781,
|
| 2528 |
+
"step": 158
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 0.005739819086714862,
|
| 2532 |
+
"eval_accuracy": 0.08936993642332029,
|
| 2533 |
+
"eval_loss": 9.0703125,
|
| 2534 |
+
"eval_runtime": 503.082,
|
| 2535 |
+
"eval_samples_per_second": 67.12,
|
| 2536 |
+
"eval_steps_per_second": 2.797,
|
| 2537 |
+
"step": 158
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.00577614705561812,
|
| 2541 |
+
"grad_norm": 1.833716869354248,
|
| 2542 |
+
"learning_rate": 9.999484142841574e-06,
|
| 2543 |
+
"loss": 9.0,
|
| 2544 |
+
"step": 159
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.00577614705561812,
|
| 2548 |
+
"eval_accuracy": 0.08952518931053041,
|
| 2549 |
+
"eval_loss": 9.0625,
|
| 2550 |
+
"eval_runtime": 501.8316,
|
| 2551 |
+
"eval_samples_per_second": 67.288,
|
| 2552 |
+
"eval_steps_per_second": 2.804,
|
| 2553 |
+
"step": 159
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 0.005812475024521379,
|
| 2557 |
+
"grad_norm": 1.7018239498138428,
|
| 2558 |
+
"learning_rate": 9.999480510044684e-06,
|
| 2559 |
+
"loss": 9.0312,
|
| 2560 |
+
"step": 160
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 0.005812475024521379,
|
| 2564 |
+
"eval_accuracy": 0.08957336026043114,
|
| 2565 |
+
"eval_loss": 9.0546875,
|
| 2566 |
+
"eval_runtime": 502.712,
|
| 2567 |
+
"eval_samples_per_second": 67.17,
|
| 2568 |
+
"eval_steps_per_second": 2.799,
|
| 2569 |
+
"step": 160
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 0.005848802993424638,
|
| 2573 |
+
"grad_norm": 1.6031908988952637,
|
| 2574 |
+
"learning_rate": 9.999476877247794e-06,
|
| 2575 |
+
"loss": 9.0391,
|
| 2576 |
+
"step": 161
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.005848802993424638,
|
| 2580 |
+
"eval_accuracy": 0.08980457503017704,
|
| 2581 |
+
"eval_loss": 9.0546875,
|
| 2582 |
+
"eval_runtime": 504.1644,
|
| 2583 |
+
"eval_samples_per_second": 66.976,
|
| 2584 |
+
"eval_steps_per_second": 2.791,
|
| 2585 |
+
"step": 161
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.005885130962327896,
|
| 2589 |
+
"grad_norm": 1.8437420129776,
|
| 2590 |
+
"learning_rate": 9.999473244450904e-06,
|
| 2591 |
+
"loss": 9.0469,
|
| 2592 |
+
"step": 162
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.005885130962327896,
|
| 2596 |
+
"eval_accuracy": 0.09014976157261477,
|
| 2597 |
+
"eval_loss": 9.046875,
|
| 2598 |
+
"eval_runtime": 504.1854,
|
| 2599 |
+
"eval_samples_per_second": 66.973,
|
| 2600 |
+
"eval_steps_per_second": 2.791,
|
| 2601 |
+
"step": 162
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 0.005921458931231155,
|
| 2605 |
+
"grad_norm": 1.765324354171753,
|
| 2606 |
+
"learning_rate": 9.999469611654014e-06,
|
| 2607 |
+
"loss": 9.0859,
|
| 2608 |
+
"step": 163
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 0.005921458931231155,
|
| 2612 |
+
"eval_accuracy": 0.09048160267761005,
|
| 2613 |
+
"eval_loss": 9.0390625,
|
| 2614 |
+
"eval_runtime": 502.1677,
|
| 2615 |
+
"eval_samples_per_second": 67.242,
|
| 2616 |
+
"eval_steps_per_second": 2.802,
|
| 2617 |
+
"step": 163
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 0.005957786900134414,
|
| 2621 |
+
"grad_norm": 1.6684796810150146,
|
| 2622 |
+
"learning_rate": 9.999465978857123e-06,
|
| 2623 |
+
"loss": 9.0078,
|
| 2624 |
+
"step": 164
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.005957786900134414,
|
| 2628 |
+
"eval_accuracy": 0.0907586435373156,
|
| 2629 |
+
"eval_loss": 9.03125,
|
| 2630 |
+
"eval_runtime": 503.5057,
|
| 2631 |
+
"eval_samples_per_second": 67.064,
|
| 2632 |
+
"eval_steps_per_second": 2.794,
|
| 2633 |
+
"step": 164
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.005994114869037672,
|
| 2637 |
+
"grad_norm": 1.840463399887085,
|
| 2638 |
+
"learning_rate": 9.999462346060233e-06,
|
| 2639 |
+
"loss": 9.0156,
|
| 2640 |
+
"step": 165
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 0.005994114869037672,
|
| 2644 |
+
"eval_accuracy": 0.09093132365519895,
|
| 2645 |
+
"eval_loss": 9.03125,
|
| 2646 |
+
"eval_runtime": 502.0204,
|
| 2647 |
+
"eval_samples_per_second": 67.262,
|
| 2648 |
+
"eval_steps_per_second": 2.803,
|
| 2649 |
+
"step": 165
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.006030442837940931,
|
| 2653 |
+
"grad_norm": 1.782490849494934,
|
| 2654 |
+
"learning_rate": 9.999458713263343e-06,
|
| 2655 |
+
"loss": 9.0469,
|
| 2656 |
+
"step": 166
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.006030442837940931,
|
| 2660 |
+
"eval_accuracy": 0.09093610022174559,
|
| 2661 |
+
"eval_loss": 9.0234375,
|
| 2662 |
+
"eval_runtime": 502.0137,
|
| 2663 |
+
"eval_samples_per_second": 67.263,
|
| 2664 |
+
"eval_steps_per_second": 2.803,
|
| 2665 |
+
"step": 166
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 0.0060667708068441895,
|
| 2669 |
+
"grad_norm": 2.1105000972747803,
|
| 2670 |
+
"learning_rate": 9.999455080466451e-06,
|
| 2671 |
+
"loss": 8.9219,
|
| 2672 |
+
"step": 167
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.0060667708068441895,
|
| 2676 |
+
"eval_accuracy": 0.09079144262760257,
|
| 2677 |
+
"eval_loss": 9.0234375,
|
| 2678 |
+
"eval_runtime": 503.1259,
|
| 2679 |
+
"eval_samples_per_second": 67.114,
|
| 2680 |
+
"eval_steps_per_second": 2.797,
|
| 2681 |
+
"step": 167
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 0.0061030987757474476,
|
| 2685 |
+
"grad_norm": 1.6616843938827515,
|
| 2686 |
+
"learning_rate": 9.999451447669561e-06,
|
| 2687 |
+
"loss": 9.0312,
|
| 2688 |
+
"step": 168
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"epoch": 0.0061030987757474476,
|
| 2692 |
+
"eval_accuracy": 0.09065688819542793,
|
| 2693 |
+
"eval_loss": 9.015625,
|
| 2694 |
+
"eval_runtime": 502.4938,
|
| 2695 |
+
"eval_samples_per_second": 67.199,
|
| 2696 |
+
"eval_steps_per_second": 2.8,
|
| 2697 |
+
"step": 168
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.0061394267446507065,
|
| 2701 |
+
"grad_norm": 1.6470061540603638,
|
| 2702 |
+
"learning_rate": 9.999447814872671e-06,
|
| 2703 |
+
"loss": 9.0938,
|
| 2704 |
+
"step": 169
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.0061394267446507065,
|
| 2708 |
+
"eval_accuracy": 0.09056121212005416,
|
| 2709 |
+
"eval_loss": 9.0078125,
|
| 2710 |
+
"eval_runtime": 503.0903,
|
| 2711 |
+
"eval_samples_per_second": 67.119,
|
| 2712 |
+
"eval_steps_per_second": 2.797,
|
| 2713 |
+
"step": 169
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 0.006175754713553965,
|
| 2717 |
+
"grad_norm": 1.594428539276123,
|
| 2718 |
+
"learning_rate": 9.999444182075781e-06,
|
| 2719 |
+
"loss": 9.0156,
|
| 2720 |
+
"step": 170
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.006175754713553965,
|
| 2724 |
+
"eval_accuracy": 0.09015482762804303,
|
| 2725 |
+
"eval_loss": 9.0,
|
| 2726 |
+
"eval_runtime": 502.1605,
|
| 2727 |
+
"eval_samples_per_second": 67.243,
|
| 2728 |
+
"eval_steps_per_second": 2.802,
|
| 2729 |
+
"step": 170
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 0.006212082682457223,
|
| 2733 |
+
"grad_norm": 1.5892345905303955,
|
| 2734 |
+
"learning_rate": 9.99944054927889e-06,
|
| 2735 |
+
"loss": 9.0312,
|
| 2736 |
+
"step": 171
|
| 2737 |
+
},
|
| 2738 |
+
{
|
| 2739 |
+
"epoch": 0.006212082682457223,
|
| 2740 |
+
"eval_accuracy": 0.08973292653197733,
|
| 2741 |
+
"eval_loss": 9.0,
|
| 2742 |
+
"eval_runtime": 500.8624,
|
| 2743 |
+
"eval_samples_per_second": 67.418,
|
| 2744 |
+
"eval_steps_per_second": 2.809,
|
| 2745 |
+
"step": 171
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 0.006248410651360482,
|
| 2749 |
+
"grad_norm": 1.5640125274658203,
|
| 2750 |
+
"learning_rate": 9.999436916482e-06,
|
| 2751 |
+
"loss": 9.0625,
|
| 2752 |
+
"step": 172
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 0.006248410651360482,
|
| 2756 |
+
"eval_accuracy": 0.08926792054143916,
|
| 2757 |
+
"eval_loss": 8.9921875,
|
| 2758 |
+
"eval_runtime": 501.8903,
|
| 2759 |
+
"eval_samples_per_second": 67.28,
|
| 2760 |
+
"eval_steps_per_second": 2.803,
|
| 2761 |
+
"step": 172
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.006284738620263741,
|
| 2765 |
+
"grad_norm": 2.097386121749878,
|
| 2766 |
+
"learning_rate": 9.99943328368511e-06,
|
| 2767 |
+
"loss": 8.9844,
|
| 2768 |
+
"step": 173
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.006284738620263741,
|
| 2772 |
+
"eval_accuracy": 0.08908942169703535,
|
| 2773 |
+
"eval_loss": 8.984375,
|
| 2774 |
+
"eval_runtime": 503.348,
|
| 2775 |
+
"eval_samples_per_second": 67.085,
|
| 2776 |
+
"eval_steps_per_second": 2.795,
|
| 2777 |
+
"step": 173
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 0.006321066589167,
|
| 2781 |
+
"grad_norm": 1.6901289224624634,
|
| 2782 |
+
"learning_rate": 9.99942965088822e-06,
|
| 2783 |
+
"loss": 9.0703,
|
| 2784 |
+
"step": 174
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 0.006321066589167,
|
| 2788 |
+
"eval_accuracy": 0.08940612253352216,
|
| 2789 |
+
"eval_loss": 8.984375,
|
| 2790 |
+
"eval_runtime": 506.45,
|
| 2791 |
+
"eval_samples_per_second": 66.674,
|
| 2792 |
+
"eval_steps_per_second": 2.778,
|
| 2793 |
+
"step": 174
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 0.006357394558070258,
|
| 2797 |
+
"grad_norm": 1.6152195930480957,
|
| 2798 |
+
"learning_rate": 9.99942601809133e-06,
|
| 2799 |
+
"loss": 8.9609,
|
| 2800 |
+
"step": 175
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 0.006357394558070258,
|
| 2804 |
+
"eval_accuracy": 0.08984990898903795,
|
| 2805 |
+
"eval_loss": 8.9765625,
|
| 2806 |
+
"eval_runtime": 504.771,
|
| 2807 |
+
"eval_samples_per_second": 66.896,
|
| 2808 |
+
"eval_steps_per_second": 2.787,
|
| 2809 |
+
"step": 175
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.006393722526973517,
|
| 2813 |
+
"grad_norm": 1.6358169317245483,
|
| 2814 |
+
"learning_rate": 9.99942238529444e-06,
|
| 2815 |
+
"loss": 8.9922,
|
| 2816 |
+
"step": 176
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.006393722526973517,
|
| 2820 |
+
"eval_accuracy": 0.09047048630455602,
|
| 2821 |
+
"eval_loss": 8.9765625,
|
| 2822 |
+
"eval_runtime": 504.0679,
|
| 2823 |
+
"eval_samples_per_second": 66.989,
|
| 2824 |
+
"eval_steps_per_second": 2.791,
|
| 2825 |
+
"step": 176
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.006430050495876776,
|
| 2829 |
+
"grad_norm": 1.662377953529358,
|
| 2830 |
+
"learning_rate": 9.999418752497549e-06,
|
| 2831 |
+
"loss": 9.0234,
|
| 2832 |
+
"step": 177
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.006430050495876776,
|
| 2836 |
+
"eval_accuracy": 0.09099935354237847,
|
| 2837 |
+
"eval_loss": 8.96875,
|
| 2838 |
+
"eval_runtime": 504.1525,
|
| 2839 |
+
"eval_samples_per_second": 66.978,
|
| 2840 |
+
"eval_steps_per_second": 2.791,
|
| 2841 |
+
"step": 177
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 0.006466378464780034,
|
| 2845 |
+
"grad_norm": 1.6537806987762451,
|
| 2846 |
+
"learning_rate": 9.999415119700659e-06,
|
| 2847 |
+
"loss": 9.0234,
|
| 2848 |
+
"step": 178
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 0.006466378464780034,
|
| 2852 |
+
"eval_accuracy": 0.0914514483287966,
|
| 2853 |
+
"eval_loss": 8.9609375,
|
| 2854 |
+
"eval_runtime": 502.7884,
|
| 2855 |
+
"eval_samples_per_second": 67.159,
|
| 2856 |
+
"eval_steps_per_second": 2.798,
|
| 2857 |
+
"step": 178
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 0.006502706433683293,
|
| 2861 |
+
"grad_norm": 1.7109649181365967,
|
| 2862 |
+
"learning_rate": 9.999411486903769e-06,
|
| 2863 |
+
"loss": 8.9219,
|
| 2864 |
+
"step": 179
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 0.006502706433683293,
|
| 2868 |
+
"eval_accuracy": 0.09188437895125184,
|
| 2869 |
+
"eval_loss": 8.953125,
|
| 2870 |
+
"eval_runtime": 501.2279,
|
| 2871 |
+
"eval_samples_per_second": 67.369,
|
| 2872 |
+
"eval_steps_per_second": 2.807,
|
| 2873 |
+
"step": 179
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.006539034402586552,
|
| 2877 |
+
"grad_norm": 1.64595365524292,
|
| 2878 |
+
"learning_rate": 9.999407854106877e-06,
|
| 2879 |
+
"loss": 9.0234,
|
| 2880 |
+
"step": 180
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.006539034402586552,
|
| 2884 |
+
"eval_accuracy": 0.09202229145445322,
|
| 2885 |
+
"eval_loss": 8.953125,
|
| 2886 |
+
"eval_runtime": 501.0383,
|
| 2887 |
+
"eval_samples_per_second": 67.394,
|
| 2888 |
+
"eval_steps_per_second": 2.808,
|
| 2889 |
+
"step": 180
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.00657536237148981,
|
| 2893 |
+
"grad_norm": 1.5911909341812134,
|
| 2894 |
+
"learning_rate": 9.999404221309987e-06,
|
| 2895 |
+
"loss": 8.9375,
|
| 2896 |
+
"step": 181
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.00657536237148981,
|
| 2900 |
+
"eval_accuracy": 0.09211403048103702,
|
| 2901 |
+
"eval_loss": 8.9453125,
|
| 2902 |
+
"eval_runtime": 503.6267,
|
| 2903 |
+
"eval_samples_per_second": 67.048,
|
| 2904 |
+
"eval_steps_per_second": 2.794,
|
| 2905 |
+
"step": 181
|
| 2906 |
+
},
|
| 2907 |
+
{
|
| 2908 |
+
"epoch": 0.006611690340393069,
|
| 2909 |
+
"grad_norm": 1.4985125064849854,
|
| 2910 |
+
"learning_rate": 9.999400588513097e-06,
|
| 2911 |
+
"loss": 8.9688,
|
| 2912 |
+
"step": 182
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 0.006611690340393069,
|
| 2916 |
+
"eval_accuracy": 0.09187829968473793,
|
| 2917 |
+
"eval_loss": 8.9375,
|
| 2918 |
+
"eval_runtime": 504.6287,
|
| 2919 |
+
"eval_samples_per_second": 66.915,
|
| 2920 |
+
"eval_steps_per_second": 2.788,
|
| 2921 |
+
"step": 182
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.006648018309296328,
|
| 2925 |
+
"grad_norm": 1.7256035804748535,
|
| 2926 |
+
"learning_rate": 9.999396955716206e-06,
|
| 2927 |
+
"loss": 8.9375,
|
| 2928 |
+
"step": 183
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 0.006648018309296328,
|
| 2932 |
+
"eval_accuracy": 0.09130482221025861,
|
| 2933 |
+
"eval_loss": 8.9375,
|
| 2934 |
+
"eval_runtime": 502.7855,
|
| 2935 |
+
"eval_samples_per_second": 67.16,
|
| 2936 |
+
"eval_steps_per_second": 2.798,
|
| 2937 |
+
"step": 183
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 0.006684346278199586,
|
| 2941 |
+
"grad_norm": 1.5093938112258911,
|
| 2942 |
+
"learning_rate": 9.999393322919316e-06,
|
| 2943 |
+
"loss": 9.0,
|
| 2944 |
+
"step": 184
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 0.006684346278199586,
|
| 2948 |
+
"eval_accuracy": 0.09121345951922091,
|
| 2949 |
+
"eval_loss": 8.9296875,
|
| 2950 |
+
"eval_runtime": 502.1658,
|
| 2951 |
+
"eval_samples_per_second": 67.243,
|
| 2952 |
+
"eval_steps_per_second": 2.802,
|
| 2953 |
+
"step": 184
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 0.0067206742471028445,
|
| 2957 |
+
"grad_norm": 1.540442943572998,
|
| 2958 |
+
"learning_rate": 9.999389690122426e-06,
|
| 2959 |
+
"loss": 8.9375,
|
| 2960 |
+
"step": 185
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.0067206742471028445,
|
| 2964 |
+
"eval_accuracy": 0.09127399164436661,
|
| 2965 |
+
"eval_loss": 8.921875,
|
| 2966 |
+
"eval_runtime": 502.1504,
|
| 2967 |
+
"eval_samples_per_second": 67.245,
|
| 2968 |
+
"eval_steps_per_second": 2.802,
|
| 2969 |
+
"step": 185
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 0.006757002216006103,
|
| 2973 |
+
"grad_norm": 1.5126348733901978,
|
| 2974 |
+
"learning_rate": 9.999386057325536e-06,
|
| 2975 |
+
"loss": 8.9609,
|
| 2976 |
+
"step": 186
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 0.006757002216006103,
|
| 2980 |
+
"eval_accuracy": 0.09126880979338571,
|
| 2981 |
+
"eval_loss": 8.921875,
|
| 2982 |
+
"eval_runtime": 500.7274,
|
| 2983 |
+
"eval_samples_per_second": 67.436,
|
| 2984 |
+
"eval_steps_per_second": 2.81,
|
| 2985 |
+
"step": 186
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.0067933301849093615,
|
| 2989 |
+
"grad_norm": 1.6009377241134644,
|
| 2990 |
+
"learning_rate": 9.999382424528646e-06,
|
| 2991 |
+
"loss": 8.9688,
|
| 2992 |
+
"step": 187
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.0067933301849093615,
|
| 2996 |
+
"eval_accuracy": 0.09167533902983765,
|
| 2997 |
+
"eval_loss": 8.9140625,
|
| 2998 |
+
"eval_runtime": 498.1171,
|
| 2999 |
+
"eval_samples_per_second": 67.789,
|
| 3000 |
+
"eval_steps_per_second": 2.825,
|
| 3001 |
+
"step": 187
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.0067933301849093615,
|
| 3005 |
+
"step": 187,
|
| 3006 |
+
"total_flos": 1043124562427904.0,
|
| 3007 |
+
"train_loss": 9.606408756684491,
|
| 3008 |
+
"train_runtime": 94484.0244,
|
| 3009 |
+
"train_samples_per_second": 699.211,
|
| 3010 |
+
"train_steps_per_second": 29.134
|
| 3011 |
+
}
|
| 3012 |
+
],
|
| 3013 |
+
"logging_steps": 1,
|
| 3014 |
+
"max_steps": 2752700,
|
| 3015 |
+
"num_input_tokens_seen": 0,
|
| 3016 |
+
"num_train_epochs": 100,
|
| 3017 |
+
"save_steps": 1000000,
|
| 3018 |
+
"stateful_callbacks": {
|
| 3019 |
+
"TrainerControl": {
|
| 3020 |
+
"args": {
|
| 3021 |
+
"should_epoch_stop": false,
|
| 3022 |
+
"should_evaluate": false,
|
| 3023 |
+
"should_log": false,
|
| 3024 |
+
"should_save": false,
|
| 3025 |
+
"should_training_stop": false
|
| 3026 |
+
},
|
| 3027 |
+
"attributes": {}
|
| 3028 |
+
}
|
| 3029 |
+
},
|
| 3030 |
+
"total_flos": 1043124562427904.0,
|
| 3031 |
+
"train_batch_size": 24,
|
| 3032 |
+
"trial_name": null,
|
| 3033 |
+
"trial_params": null
|
| 3034 |
+
}
|