Commit
·
272cc03
1
Parent(s):
693831a
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +3511 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/bob-dylan")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Bob Dylan's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/bob-dylan")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/12pi332s/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Bob Dylan's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/34f7xa4s) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/34f7xa4s/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "huggingartists/bob-dylan",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss":
|
|
|
|
| 1 |
+
{"eval_loss": 1.7831153869628906, "eval_runtime": 20.4767, "eval_samples_per_second": 21.927, "eval_steps_per_second": 2.784, "epoch": 11.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5455703e728e3cd6ffaf593b10aa5cf2233c7023ca11e9c24155e6a409f30a46
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b57dd3c115876c0c7ea6456370527f6da21f3a6c9135e1da512b9308141a7e4
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d33cb397d94e7ed9e2034a93b3d7fc4a7c2474a08659ab20f0ff40914ebf69
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bb5c4b938e52242f003d2aafdabeacb8b2645526444936a3f4c1786f434041a
|
| 3 |
size 14567
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b7edfdb51a39bca06643e38f8438d076a87c514b98497804d576bdb518cb004
|
| 3 |
size 623
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/bob-dylan", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "output/bob-dylan/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -398,11 +398,3515 @@
|
|
| 398 |
"eval_samples_per_second": 22.833,
|
| 399 |
"eval_steps_per_second": 2.901,
|
| 400 |
"step": 321
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 401 |
}
|
| 402 |
],
|
| 403 |
-
"max_steps":
|
| 404 |
-
"num_train_epochs":
|
| 405 |
-
"total_flos":
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
| 408 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.7831153869628906,
|
| 3 |
+
"best_model_checkpoint": "output/bob-dylan/checkpoint-3180",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 3180,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 398 |
"eval_samples_per_second": 22.833,
|
| 399 |
"eval_steps_per_second": 2.901,
|
| 400 |
"step": 321
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.02,
|
| 404 |
+
"learning_rate": 1.6396932901668288e-07,
|
| 405 |
+
"loss": 2.7644,
|
| 406 |
+
"step": 325
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.04,
|
| 410 |
+
"learning_rate": 4.814968134727319e-07,
|
| 411 |
+
"loss": 2.6609,
|
| 412 |
+
"step": 330
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.05,
|
| 416 |
+
"learning_rate": 9.651980029285235e-07,
|
| 417 |
+
"loss": 2.681,
|
| 418 |
+
"step": 335
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.07,
|
| 422 |
+
"learning_rate": 1.6138929181565879e-06,
|
| 423 |
+
"loss": 2.6512,
|
| 424 |
+
"step": 340
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.08,
|
| 428 |
+
"learning_rate": 2.4259990810865978e-06,
|
| 429 |
+
"loss": 2.6379,
|
| 430 |
+
"step": 345
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1,
|
| 434 |
+
"learning_rate": 3.3995353752283744e-06,
|
| 435 |
+
"loss": 2.9539,
|
| 436 |
+
"step": 350
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.12,
|
| 440 |
+
"learning_rate": 4.532126878565439e-06,
|
| 441 |
+
"loss": 2.7261,
|
| 442 |
+
"step": 355
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.13,
|
| 446 |
+
"learning_rate": 5.821010657128926e-06,
|
| 447 |
+
"loss": 2.8164,
|
| 448 |
+
"step": 360
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.15,
|
| 452 |
+
"learning_rate": 7.26304250511898e-06,
|
| 453 |
+
"loss": 2.8454,
|
| 454 |
+
"step": 365
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.16,
|
| 458 |
+
"learning_rate": 8.854704615130857e-06,
|
| 459 |
+
"loss": 2.7863,
|
| 460 |
+
"step": 370
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.18,
|
| 464 |
+
"learning_rate": 1.0592114159774732e-05,
|
| 465 |
+
"loss": 2.8572,
|
| 466 |
+
"step": 375
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.19,
|
| 470 |
+
"learning_rate": 1.2471032763754147e-05,
|
| 471 |
+
"loss": 2.8415,
|
| 472 |
+
"step": 380
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.21,
|
| 476 |
+
"learning_rate": 1.4486876843296586e-05,
|
| 477 |
+
"loss": 2.6313,
|
| 478 |
+
"step": 385
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.23,
|
| 482 |
+
"learning_rate": 1.663472878771285e-05,
|
| 483 |
+
"loss": 2.7228,
|
| 484 |
+
"step": 390
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.24,
|
| 488 |
+
"learning_rate": 1.8909348955808624e-05,
|
| 489 |
+
"loss": 2.5958,
|
| 490 |
+
"step": 395
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.26,
|
| 494 |
+
"learning_rate": 2.1305188457882567e-05,
|
| 495 |
+
"loss": 2.7318,
|
| 496 |
+
"step": 400
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.27,
|
| 500 |
+
"learning_rate": 2.3816402692130242e-05,
|
| 501 |
+
"loss": 2.7112,
|
| 502 |
+
"step": 405
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.29,
|
| 506 |
+
"learning_rate": 2.6436865602431172e-05,
|
| 507 |
+
"loss": 2.7692,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.31,
|
| 512 |
+
"learning_rate": 2.9160184622738906e-05,
|
| 513 |
+
"loss": 2.7993,
|
| 514 |
+
"step": 415
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.32,
|
| 518 |
+
"learning_rate": 3.197971627161534e-05,
|
| 519 |
+
"loss": 2.8784,
|
| 520 |
+
"step": 420
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.34,
|
| 524 |
+
"learning_rate": 3.4888582358869375e-05,
|
| 525 |
+
"loss": 2.7869,
|
| 526 |
+
"step": 425
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.35,
|
| 530 |
+
"learning_rate": 3.7879686764761624e-05,
|
| 531 |
+
"loss": 2.8056,
|
| 532 |
+
"step": 430
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.37,
|
| 536 |
+
"learning_rate": 4.09457327508451e-05,
|
| 537 |
+
"loss": 2.553,
|
| 538 |
+
"step": 435
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.38,
|
| 542 |
+
"learning_rate": 4.407924076020965e-05,
|
| 543 |
+
"loss": 3.1824,
|
| 544 |
+
"step": 440
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.4,
|
| 548 |
+
"learning_rate": 4.7272566663709714e-05,
|
| 549 |
+
"loss": 2.8178,
|
| 550 |
+
"step": 445
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.42,
|
| 554 |
+
"learning_rate": 5.0517920407661915e-05,
|
| 555 |
+
"loss": 2.6659,
|
| 556 |
+
"step": 450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.43,
|
| 560 |
+
"learning_rate": 5.3807385017522816e-05,
|
| 561 |
+
"loss": 2.5079,
|
| 562 |
+
"step": 455
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.45,
|
| 566 |
+
"learning_rate": 5.7132935911187364e-05,
|
| 567 |
+
"loss": 3.0069,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.46,
|
| 572 |
+
"learning_rate": 6.048646047479427e-05,
|
| 573 |
+
"loss": 2.7084,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.48,
|
| 578 |
+
"learning_rate": 6.385977785328252e-05,
|
| 579 |
+
"loss": 2.738,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.49,
|
| 584 |
+
"learning_rate": 6.724465890742127e-05,
|
| 585 |
+
"loss": 2.7037,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.51,
|
| 590 |
+
"learning_rate": 7.063284628862763e-05,
|
| 591 |
+
"loss": 2.7949,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.53,
|
| 596 |
+
"learning_rate": 7.401607458260099e-05,
|
| 597 |
+
"loss": 2.8525,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.54,
|
| 602 |
+
"learning_rate": 7.738609047263364e-05,
|
| 603 |
+
"loss": 2.7132,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.56,
|
| 608 |
+
"learning_rate": 8.07346728734085e-05,
|
| 609 |
+
"loss": 2.7785,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.57,
|
| 614 |
+
"learning_rate": 8.405365298617048e-05,
|
| 615 |
+
"loss": 2.7346,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.59,
|
| 620 |
+
"learning_rate": 8.733493422634478e-05,
|
| 621 |
+
"loss": 2.8556,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.6,
|
| 626 |
+
"learning_rate": 9.057051197499066e-05,
|
| 627 |
+
"loss": 2.7322,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.62,
|
| 632 |
+
"learning_rate": 9.375249310590655e-05,
|
| 633 |
+
"loss": 2.6462,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.64,
|
| 638 |
+
"learning_rate": 9.687311524075135e-05,
|
| 639 |
+
"loss": 2.7953,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.65,
|
| 644 |
+
"learning_rate": 9.992476568520869e-05,
|
| 645 |
+
"loss": 2.7156,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.67,
|
| 650 |
+
"learning_rate": 0.00010290000000000001,
|
| 651 |
+
"loss": 2.8443,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.68,
|
| 656 |
+
"learning_rate": 0.00010579156016144291,
|
| 657 |
+
"loss": 2.73,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.7,
|
| 662 |
+
"learning_rate": 0.00010859239226725277,
|
| 663 |
+
"loss": 2.6283,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.71,
|
| 668 |
+
"learning_rate": 0.00011129566374439388,
|
| 669 |
+
"loss": 2.7128,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.73,
|
| 674 |
+
"learning_rate": 0.00011389478001700271,
|
| 675 |
+
"loss": 2.848,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.75,
|
| 680 |
+
"learning_rate": 0.00011638340059372158,
|
| 681 |
+
"loss": 2.6623,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.76,
|
| 686 |
+
"learning_rate": 0.00011875545453519892,
|
| 687 |
+
"loss": 2.5335,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.78,
|
| 692 |
+
"learning_rate": 0.00012100515526402216,
|
| 693 |
+
"loss": 2.7063,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.79,
|
| 698 |
+
"learning_rate": 0.00012312701468095605,
|
| 699 |
+
"loss": 2.5592,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.81,
|
| 704 |
+
"learning_rate": 0.00012511585655304897,
|
| 705 |
+
"loss": 2.658,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.82,
|
| 710 |
+
"learning_rate": 0.00012696682914094848,
|
| 711 |
+
"loss": 2.7849,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.84,
|
| 716 |
+
"learning_rate": 0.00012867541703462067,
|
| 717 |
+
"loss": 2.4521,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.86,
|
| 722 |
+
"learning_rate": 0.0001302374521686013,
|
| 723 |
+
"loss": 2.7116,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.87,
|
| 728 |
+
"learning_rate": 0.00013164912398990668,
|
| 729 |
+
"loss": 2.5754,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.89,
|
| 734 |
+
"learning_rate": 0.0001329069887538007,
|
| 735 |
+
"loss": 2.6935,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.9,
|
| 740 |
+
"learning_rate": 0.00013400797792473965,
|
| 741 |
+
"loss": 2.4856,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.92,
|
| 746 |
+
"learning_rate": 0.0001349494056620028,
|
| 747 |
+
"loss": 2.7162,
|
| 748 |
+
"step": 610
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.93,
|
| 752 |
+
"learning_rate": 0.000135728975371746,
|
| 753 |
+
"loss": 2.8196,
|
| 754 |
+
"step": 615
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.95,
|
| 758 |
+
"learning_rate": 0.0001363447853094957,
|
| 759 |
+
"loss": 2.6532,
|
| 760 |
+
"step": 620
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.97,
|
| 764 |
+
"learning_rate": 0.00013679533321941633,
|
| 765 |
+
"loss": 2.5941,
|
| 766 |
+
"step": 625
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.98,
|
| 770 |
+
"learning_rate": 0.00013707951999903246,
|
| 771 |
+
"loss": 2.4365,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.0,
|
| 776 |
+
"learning_rate": 0.00013719665238046719,
|
| 777 |
+
"loss": 2.6559,
|
| 778 |
+
"step": 635
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.0,
|
| 782 |
+
"eval_loss": 2.319049835205078,
|
| 783 |
+
"eval_runtime": 20.2442,
|
| 784 |
+
"eval_samples_per_second": 22.179,
|
| 785 |
+
"eval_steps_per_second": 2.816,
|
| 786 |
+
"step": 636
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.01,
|
| 790 |
+
"learning_rate": 0.00013714644462165502,
|
| 791 |
+
"loss": 2.3683,
|
| 792 |
+
"step": 640
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.03,
|
| 796 |
+
"learning_rate": 0.00013692901920340388,
|
| 797 |
+
"loss": 2.3765,
|
| 798 |
+
"step": 645
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.04,
|
| 802 |
+
"learning_rate": 0.00013654490653060555,
|
| 803 |
+
"loss": 2.7581,
|
| 804 |
+
"step": 650
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.06,
|
| 808 |
+
"learning_rate": 0.00013599504363832372,
|
| 809 |
+
"loss": 2.5057,
|
| 810 |
+
"step": 655
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.08,
|
| 814 |
+
"learning_rate": 0.00013528077190591619,
|
| 815 |
+
"loss": 2.5706,
|
| 816 |
+
"step": 660
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.09,
|
| 820 |
+
"learning_rate": 0.00013440383378476688,
|
| 821 |
+
"loss": 2.5847,
|
| 822 |
+
"step": 665
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.11,
|
| 826 |
+
"learning_rate": 0.00013336636854761118,
|
| 827 |
+
"loss": 2.3126,
|
| 828 |
+
"step": 670
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.12,
|
| 832 |
+
"learning_rate": 0.00013217090706982377,
|
| 833 |
+
"loss": 2.309,
|
| 834 |
+
"step": 675
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.14,
|
| 838 |
+
"learning_rate": 0.00013082036565539919,
|
| 839 |
+
"loss": 2.5847,
|
| 840 |
+
"step": 680
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.15,
|
| 844 |
+
"learning_rate": 0.00012931803892268768,
|
| 845 |
+
"loss": 2.4275,
|
| 846 |
+
"step": 685
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.17,
|
| 850 |
+
"learning_rate": 0.00012766759176724058,
|
| 851 |
+
"loss": 2.3388,
|
| 852 |
+
"step": 690
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.19,
|
| 856 |
+
"learning_rate": 0.00012587305042137224,
|
| 857 |
+
"loss": 2.4289,
|
| 858 |
+
"step": 695
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.2,
|
| 862 |
+
"learning_rate": 0.00012393879263224768,
|
| 863 |
+
"loss": 2.3432,
|
| 864 |
+
"step": 700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.22,
|
| 868 |
+
"learning_rate": 0.00012186953698245773,
|
| 869 |
+
"loss": 2.1438,
|
| 870 |
+
"step": 705
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.23,
|
| 874 |
+
"learning_rate": 0.00011967033137913228,
|
| 875 |
+
"loss": 2.4482,
|
| 876 |
+
"step": 710
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.25,
|
| 880 |
+
"learning_rate": 0.00011734654073967362,
|
| 881 |
+
"loss": 2.596,
|
| 882 |
+
"step": 715
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.26,
|
| 886 |
+
"learning_rate": 0.00011490383390414927,
|
| 887 |
+
"loss": 2.3528,
|
| 888 |
+
"step": 720
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.28,
|
| 892 |
+
"learning_rate": 0.00011234816980627178,
|
| 893 |
+
"loss": 2.2922,
|
| 894 |
+
"step": 725
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.3,
|
| 898 |
+
"learning_rate": 0.0001096857829367009,
|
| 899 |
+
"loss": 2.2967,
|
| 900 |
+
"step": 730
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.31,
|
| 904 |
+
"learning_rate": 0.00010692316813413058,
|
| 905 |
+
"loss": 2.3893,
|
| 906 |
+
"step": 735
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.33,
|
| 910 |
+
"learning_rate": 0.0001040670647412614,
|
| 911 |
+
"loss": 2.2958,
|
| 912 |
+
"step": 740
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.34,
|
| 916 |
+
"learning_rate": 0.00010112444016431127,
|
| 917 |
+
"loss": 2.3878,
|
| 918 |
+
"step": 745
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.36,
|
| 922 |
+
"learning_rate": 9.810247287616931e-05,
|
| 923 |
+
"loss": 2.0135,
|
| 924 |
+
"step": 750
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.37,
|
| 928 |
+
"learning_rate": 9.500853490465723e-05,
|
| 929 |
+
"loss": 2.5128,
|
| 930 |
+
"step": 755
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.39,
|
| 934 |
+
"learning_rate": 9.185017384861694e-05,
|
| 935 |
+
"loss": 2.2281,
|
| 936 |
+
"step": 760
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.41,
|
| 940 |
+
"learning_rate": 8.86350944656966e-05,
|
| 941 |
+
"loss": 2.2168,
|
| 942 |
+
"step": 765
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 2.42,
|
| 946 |
+
"learning_rate": 8.537113987675077e-05,
|
| 947 |
+
"loss": 2.2228,
|
| 948 |
+
"step": 770
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.44,
|
| 952 |
+
"learning_rate": 8.206627243270665e-05,
|
| 953 |
+
"loss": 2.5163,
|
| 954 |
+
"step": 775
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.45,
|
| 958 |
+
"learning_rate": 7.872855429057025e-05,
|
| 959 |
+
"loss": 2.5593,
|
| 960 |
+
"step": 780
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.47,
|
| 964 |
+
"learning_rate": 7.536612774595843e-05,
|
| 965 |
+
"loss": 1.8992,
|
| 966 |
+
"step": 785
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.48,
|
| 970 |
+
"learning_rate": 7.198719537013403e-05,
|
| 971 |
+
"loss": 2.2331,
|
| 972 |
+
"step": 790
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 2.5,
|
| 976 |
+
"learning_rate": 6.860000000000001e-05,
|
| 977 |
+
"loss": 2.2157,
|
| 978 |
+
"step": 795
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.52,
|
| 982 |
+
"learning_rate": 6.521280462986602e-05,
|
| 983 |
+
"loss": 2.2611,
|
| 984 |
+
"step": 800
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.53,
|
| 988 |
+
"learning_rate": 6.183387225404161e-05,
|
| 989 |
+
"loss": 2.2053,
|
| 990 |
+
"step": 805
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.55,
|
| 994 |
+
"learning_rate": 5.8471445709429735e-05,
|
| 995 |
+
"loss": 2.1826,
|
| 996 |
+
"step": 810
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.56,
|
| 1000 |
+
"learning_rate": 5.513372756729345e-05,
|
| 1001 |
+
"loss": 1.995,
|
| 1002 |
+
"step": 815
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.58,
|
| 1006 |
+
"learning_rate": 5.182886012324932e-05,
|
| 1007 |
+
"loss": 2.3863,
|
| 1008 |
+
"step": 820
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 2.59,
|
| 1012 |
+
"learning_rate": 4.856490553430346e-05,
|
| 1013 |
+
"loss": 2.3232,
|
| 1014 |
+
"step": 825
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.61,
|
| 1018 |
+
"learning_rate": 4.534982615138311e-05,
|
| 1019 |
+
"loss": 2.3315,
|
| 1020 |
+
"step": 830
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.63,
|
| 1024 |
+
"learning_rate": 4.2191465095342816e-05,
|
| 1025 |
+
"loss": 2.3571,
|
| 1026 |
+
"step": 835
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.64,
|
| 1030 |
+
"learning_rate": 3.909752712383074e-05,
|
| 1031 |
+
"loss": 2.1077,
|
| 1032 |
+
"step": 840
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.66,
|
| 1036 |
+
"learning_rate": 3.607555983568871e-05,
|
| 1037 |
+
"loss": 2.1479,
|
| 1038 |
+
"step": 845
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.67,
|
| 1042 |
+
"learning_rate": 3.313293525873858e-05,
|
| 1043 |
+
"loss": 2.2508,
|
| 1044 |
+
"step": 850
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.69,
|
| 1048 |
+
"learning_rate": 3.027683186586951e-05,
|
| 1049 |
+
"loss": 2.5729,
|
| 1050 |
+
"step": 855
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.7,
|
| 1054 |
+
"learning_rate": 2.7514217063299187e-05,
|
| 1055 |
+
"loss": 2.4242,
|
| 1056 |
+
"step": 860
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.72,
|
| 1060 |
+
"learning_rate": 2.485183019372827e-05,
|
| 1061 |
+
"loss": 2.2222,
|
| 1062 |
+
"step": 865
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.74,
|
| 1066 |
+
"learning_rate": 2.2296166095850762e-05,
|
| 1067 |
+
"loss": 2.3744,
|
| 1068 |
+
"step": 870
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.75,
|
| 1072 |
+
"learning_rate": 1.9853459260326405e-05,
|
| 1073 |
+
"loss": 2.2229,
|
| 1074 |
+
"step": 875
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.77,
|
| 1078 |
+
"learning_rate": 1.752966862086776e-05,
|
| 1079 |
+
"loss": 2.4542,
|
| 1080 |
+
"step": 880
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.78,
|
| 1084 |
+
"learning_rate": 1.5330463017542246e-05,
|
| 1085 |
+
"loss": 2.253,
|
| 1086 |
+
"step": 885
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.8,
|
| 1090 |
+
"learning_rate": 1.3261207367752365e-05,
|
| 1091 |
+
"loss": 2.2606,
|
| 1092 |
+
"step": 890
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 2.81,
|
| 1096 |
+
"learning_rate": 1.1326949578627828e-05,
|
| 1097 |
+
"loss": 2.535,
|
| 1098 |
+
"step": 895
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.83,
|
| 1102 |
+
"learning_rate": 9.532408232759462e-06,
|
| 1103 |
+
"loss": 2.3032,
|
| 1104 |
+
"step": 900
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 2.85,
|
| 1108 |
+
"learning_rate": 7.881961077312348e-06,
|
| 1109 |
+
"loss": 2.2779,
|
| 1110 |
+
"step": 905
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.86,
|
| 1114 |
+
"learning_rate": 6.379634344600831e-06,
|
| 1115 |
+
"loss": 2.2839,
|
| 1116 |
+
"step": 910
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.88,
|
| 1120 |
+
"learning_rate": 5.029092930176238e-06,
|
| 1121 |
+
"loss": 2.0958,
|
| 1122 |
+
"step": 915
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.89,
|
| 1126 |
+
"learning_rate": 3.833631452388814e-06,
|
| 1127 |
+
"loss": 2.1064,
|
| 1128 |
+
"step": 920
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.91,
|
| 1132 |
+
"learning_rate": 2.7961662152331326e-06,
|
| 1133 |
+
"loss": 2.3978,
|
| 1134 |
+
"step": 925
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.92,
|
| 1138 |
+
"learning_rate": 1.919228094083838e-06,
|
| 1139 |
+
"loss": 2.2206,
|
| 1140 |
+
"step": 930
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.94,
|
| 1144 |
+
"learning_rate": 1.204956361676291e-06,
|
| 1145 |
+
"loss": 2.2185,
|
| 1146 |
+
"step": 935
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.96,
|
| 1150 |
+
"learning_rate": 6.550934693944858e-07,
|
| 1151 |
+
"loss": 2.4076,
|
| 1152 |
+
"step": 940
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.97,
|
| 1156 |
+
"learning_rate": 2.709807965961209e-07,
|
| 1157 |
+
"loss": 2.2124,
|
| 1158 |
+
"step": 945
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.99,
|
| 1162 |
+
"learning_rate": 5.355537834497188e-08,
|
| 1163 |
+
"loss": 2.6099,
|
| 1164 |
+
"step": 950
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.0,
|
| 1168 |
+
"eval_loss": 2.0997118949890137,
|
| 1169 |
+
"eval_runtime": 20.2461,
|
| 1170 |
+
"eval_samples_per_second": 22.177,
|
| 1171 |
+
"eval_steps_per_second": 2.815,
|
| 1172 |
+
"step": 954
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.0,
|
| 1176 |
+
"learning_rate": 3.347619532822632e-09,
|
| 1177 |
+
"loss": 2.1903,
|
| 1178 |
+
"step": 955
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.02,
|
| 1182 |
+
"learning_rate": 1.2048000096755528e-07,
|
| 1183 |
+
"loss": 2.2037,
|
| 1184 |
+
"step": 960
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 3.03,
|
| 1188 |
+
"learning_rate": 4.0466678058365933e-07,
|
| 1189 |
+
"loss": 1.8544,
|
| 1190 |
+
"step": 965
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.05,
|
| 1194 |
+
"learning_rate": 8.552146905042755e-07,
|
| 1195 |
+
"loss": 2.1987,
|
| 1196 |
+
"step": 970
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 3.07,
|
| 1200 |
+
"learning_rate": 1.4710246282540082e-06,
|
| 1201 |
+
"loss": 2.1019,
|
| 1202 |
+
"step": 975
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.08,
|
| 1206 |
+
"learning_rate": 2.250594337997185e-06,
|
| 1207 |
+
"loss": 2.1517,
|
| 1208 |
+
"step": 980
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.1,
|
| 1212 |
+
"learning_rate": 3.192022075260327e-06,
|
| 1213 |
+
"loss": 2.1346,
|
| 1214 |
+
"step": 985
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.11,
|
| 1218 |
+
"learning_rate": 4.293011246199299e-06,
|
| 1219 |
+
"loss": 2.0847,
|
| 1220 |
+
"step": 990
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.13,
|
| 1224 |
+
"learning_rate": 5.550876010093297e-06,
|
| 1225 |
+
"loss": 1.9358,
|
| 1226 |
+
"step": 995
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.14,
|
| 1230 |
+
"learning_rate": 6.962547831398709e-06,
|
| 1231 |
+
"loss": 2.2579,
|
| 1232 |
+
"step": 1000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 3.16,
|
| 1236 |
+
"learning_rate": 8.524582965379288e-06,
|
| 1237 |
+
"loss": 2.0876,
|
| 1238 |
+
"step": 1005
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 3.18,
|
| 1242 |
+
"learning_rate": 1.0233170859051466e-05,
|
| 1243 |
+
"loss": 1.8737,
|
| 1244 |
+
"step": 1010
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.19,
|
| 1248 |
+
"learning_rate": 1.2084143446950978e-05,
|
| 1249 |
+
"loss": 2.1,
|
| 1250 |
+
"step": 1015
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.21,
|
| 1254 |
+
"learning_rate": 1.4072985319043973e-05,
|
| 1255 |
+
"loss": 2.0016,
|
| 1256 |
+
"step": 1020
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.22,
|
| 1260 |
+
"learning_rate": 1.619484473597781e-05,
|
| 1261 |
+
"loss": 2.1936,
|
| 1262 |
+
"step": 1025
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.24,
|
| 1266 |
+
"learning_rate": 1.844454546480105e-05,
|
| 1267 |
+
"loss": 2.2236,
|
| 1268 |
+
"step": 1030
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 3.25,
|
| 1272 |
+
"learning_rate": 2.081659940627838e-05,
|
| 1273 |
+
"loss": 1.94,
|
| 1274 |
+
"step": 1035
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 3.27,
|
| 1278 |
+
"learning_rate": 2.330521998299727e-05,
|
| 1279 |
+
"loss": 2.103,
|
| 1280 |
+
"step": 1040
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 3.29,
|
| 1284 |
+
"learning_rate": 2.5904336255606053e-05,
|
| 1285 |
+
"loss": 2.0909,
|
| 1286 |
+
"step": 1045
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.3,
|
| 1290 |
+
"learning_rate": 2.860760773274715e-05,
|
| 1291 |
+
"loss": 2.1943,
|
| 1292 |
+
"step": 1050
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.32,
|
| 1296 |
+
"learning_rate": 3.1408439838557e-05,
|
| 1297 |
+
"loss": 2.3713,
|
| 1298 |
+
"step": 1055
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.33,
|
| 1302 |
+
"learning_rate": 3.4300000000000014e-05,
|
| 1303 |
+
"loss": 2.1534,
|
| 1304 |
+
"step": 1060
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.35,
|
| 1308 |
+
"learning_rate": 3.727523431479128e-05,
|
| 1309 |
+
"loss": 2.1973,
|
| 1310 |
+
"step": 1065
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 3.36,
|
| 1314 |
+
"learning_rate": 4.0326884759248605e-05,
|
| 1315 |
+
"loss": 2.1412,
|
| 1316 |
+
"step": 1070
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 3.38,
|
| 1320 |
+
"learning_rate": 4.3447506894093424e-05,
|
| 1321 |
+
"loss": 2.1419,
|
| 1322 |
+
"step": 1075
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 3.4,
|
| 1326 |
+
"learning_rate": 4.662948802500929e-05,
|
| 1327 |
+
"loss": 2.179,
|
| 1328 |
+
"step": 1080
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.41,
|
| 1332 |
+
"learning_rate": 4.986506577365512e-05,
|
| 1333 |
+
"loss": 2.0405,
|
| 1334 |
+
"step": 1085
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 3.43,
|
| 1338 |
+
"learning_rate": 5.314634701382942e-05,
|
| 1339 |
+
"loss": 2.1397,
|
| 1340 |
+
"step": 1090
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.44,
|
| 1344 |
+
"learning_rate": 5.646532712659141e-05,
|
| 1345 |
+
"loss": 2.0391,
|
| 1346 |
+
"step": 1095
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.46,
|
| 1350 |
+
"learning_rate": 5.9813909527366384e-05,
|
| 1351 |
+
"loss": 2.2312,
|
| 1352 |
+
"step": 1100
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.47,
|
| 1356 |
+
"learning_rate": 6.318392541739896e-05,
|
| 1357 |
+
"loss": 1.8413,
|
| 1358 |
+
"step": 1105
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.49,
|
| 1362 |
+
"learning_rate": 6.656715371137238e-05,
|
| 1363 |
+
"loss": 2.2519,
|
| 1364 |
+
"step": 1110
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 3.51,
|
| 1368 |
+
"learning_rate": 6.995534109257869e-05,
|
| 1369 |
+
"loss": 1.871,
|
| 1370 |
+
"step": 1115
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 3.52,
|
| 1374 |
+
"learning_rate": 7.334022214671738e-05,
|
| 1375 |
+
"loss": 1.9633,
|
| 1376 |
+
"step": 1120
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 3.54,
|
| 1380 |
+
"learning_rate": 7.671353952520564e-05,
|
| 1381 |
+
"loss": 2.3068,
|
| 1382 |
+
"step": 1125
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.55,
|
| 1386 |
+
"learning_rate": 8.006706408881254e-05,
|
| 1387 |
+
"loss": 2.083,
|
| 1388 |
+
"step": 1130
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 3.57,
|
| 1392 |
+
"learning_rate": 8.33926149824772e-05,
|
| 1393 |
+
"loss": 2.1478,
|
| 1394 |
+
"step": 1135
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 3.58,
|
| 1398 |
+
"learning_rate": 8.668207959233806e-05,
|
| 1399 |
+
"loss": 2.1284,
|
| 1400 |
+
"step": 1140
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 3.6,
|
| 1404 |
+
"learning_rate": 8.992743333629024e-05,
|
| 1405 |
+
"loss": 2.1958,
|
| 1406 |
+
"step": 1145
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 3.62,
|
| 1410 |
+
"learning_rate": 9.312075923979032e-05,
|
| 1411 |
+
"loss": 1.9476,
|
| 1412 |
+
"step": 1150
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 3.63,
|
| 1416 |
+
"learning_rate": 9.625426724915486e-05,
|
| 1417 |
+
"loss": 2.1252,
|
| 1418 |
+
"step": 1155
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.65,
|
| 1422 |
+
"learning_rate": 9.932031323523828e-05,
|
| 1423 |
+
"loss": 1.921,
|
| 1424 |
+
"step": 1160
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.66,
|
| 1428 |
+
"learning_rate": 0.00010231141764113059,
|
| 1429 |
+
"loss": 2.1346,
|
| 1430 |
+
"step": 1165
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 3.68,
|
| 1434 |
+
"learning_rate": 0.00010522028372838456,
|
| 1435 |
+
"loss": 2.1729,
|
| 1436 |
+
"step": 1170
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 3.69,
|
| 1440 |
+
"learning_rate": 0.00010803981537726111,
|
| 1441 |
+
"loss": 1.7231,
|
| 1442 |
+
"step": 1175
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 3.71,
|
| 1446 |
+
"learning_rate": 0.0001107631343975688,
|
| 1447 |
+
"loss": 1.9233,
|
| 1448 |
+
"step": 1180
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 3.73,
|
| 1452 |
+
"learning_rate": 0.00011338359730786977,
|
| 1453 |
+
"loss": 2.2671,
|
| 1454 |
+
"step": 1185
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 3.74,
|
| 1458 |
+
"learning_rate": 0.0001158948115421174,
|
| 1459 |
+
"loss": 1.9335,
|
| 1460 |
+
"step": 1190
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 3.76,
|
| 1464 |
+
"learning_rate": 0.00011829065104419134,
|
| 1465 |
+
"loss": 2.0918,
|
| 1466 |
+
"step": 1195
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.77,
|
| 1470 |
+
"learning_rate": 0.00012056527121228711,
|
| 1471 |
+
"loss": 2.2418,
|
| 1472 |
+
"step": 1200
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 3.79,
|
| 1476 |
+
"learning_rate": 0.00012271312315670338,
|
| 1477 |
+
"loss": 2.1403,
|
| 1478 |
+
"step": 1205
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 3.81,
|
| 1482 |
+
"learning_rate": 0.0001247289672362458,
|
| 1483 |
+
"loss": 2.1248,
|
| 1484 |
+
"step": 1210
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 3.82,
|
| 1488 |
+
"learning_rate": 0.00012660788584022527,
|
| 1489 |
+
"loss": 2.0255,
|
| 1490 |
+
"step": 1215
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.84,
|
| 1494 |
+
"learning_rate": 0.00012834529538486916,
|
| 1495 |
+
"loss": 2.1805,
|
| 1496 |
+
"step": 1220
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 3.85,
|
| 1500 |
+
"learning_rate": 0.000129936957494881,
|
| 1501 |
+
"loss": 1.9559,
|
| 1502 |
+
"step": 1225
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 3.87,
|
| 1506 |
+
"learning_rate": 0.00013137898934287106,
|
| 1507 |
+
"loss": 2.1316,
|
| 1508 |
+
"step": 1230
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 3.88,
|
| 1512 |
+
"learning_rate": 0.00013266787312143455,
|
| 1513 |
+
"loss": 2.4223,
|
| 1514 |
+
"step": 1235
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 3.9,
|
| 1518 |
+
"learning_rate": 0.0001338004646247716,
|
| 1519 |
+
"loss": 2.0369,
|
| 1520 |
+
"step": 1240
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 3.92,
|
| 1524 |
+
"learning_rate": 0.00013477400091891338,
|
| 1525 |
+
"loss": 2.0681,
|
| 1526 |
+
"step": 1245
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 3.93,
|
| 1530 |
+
"learning_rate": 0.00013558610708184338,
|
| 1531 |
+
"loss": 2.1821,
|
| 1532 |
+
"step": 1250
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 3.95,
|
| 1536 |
+
"learning_rate": 0.00013623480199707148,
|
| 1537 |
+
"loss": 2.2183,
|
| 1538 |
+
"step": 1255
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 3.96,
|
| 1542 |
+
"learning_rate": 0.00013671850318652728,
|
| 1543 |
+
"loss": 2.0026,
|
| 1544 |
+
"step": 1260
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 3.98,
|
| 1548 |
+
"learning_rate": 0.00013703603067098332,
|
| 1549 |
+
"loss": 1.9368,
|
| 1550 |
+
"step": 1265
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.99,
|
| 1554 |
+
"learning_rate": 0.0001371866098485905,
|
| 1555 |
+
"loss": 2.1825,
|
| 1556 |
+
"step": 1270
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 4.0,
|
| 1560 |
+
"eval_loss": 2.0486814975738525,
|
| 1561 |
+
"eval_runtime": 20.2715,
|
| 1562 |
+
"eval_samples_per_second": 22.149,
|
| 1563 |
+
"eval_steps_per_second": 2.812,
|
| 1564 |
+
"step": 1272
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 4.01,
|
| 1568 |
+
"learning_rate": 0.0001371698733845033,
|
| 1569 |
+
"loss": 2.0223,
|
| 1570 |
+
"step": 1275
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 4.03,
|
| 1574 |
+
"learning_rate": 0.000136985862106986,
|
| 1575 |
+
"loss": 2.0536,
|
| 1576 |
+
"step": 1280
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 4.04,
|
| 1580 |
+
"learning_rate": 0.0001366350249078127,
|
| 1581 |
+
"loss": 1.962,
|
| 1582 |
+
"step": 1285
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 4.06,
|
| 1586 |
+
"learning_rate": 0.00013611821764720515,
|
| 1587 |
+
"loss": 2.0683,
|
| 1588 |
+
"step": 1290
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 4.07,
|
| 1592 |
+
"learning_rate": 0.00013543670106597888,
|
| 1593 |
+
"loss": 1.9271,
|
| 1594 |
+
"step": 1295
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 4.09,
|
| 1598 |
+
"learning_rate": 0.00013459213770999188,
|
| 1599 |
+
"loss": 2.0152,
|
| 1600 |
+
"step": 1300
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 4.1,
|
| 1604 |
+
"learning_rate": 0.00013358658787439754,
|
| 1605 |
+
"loss": 1.7685,
|
| 1606 |
+
"step": 1305
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 4.12,
|
| 1610 |
+
"learning_rate": 0.0001324225045775965,
|
| 1611 |
+
"loss": 2.2589,
|
| 1612 |
+
"step": 1310
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 4.14,
|
| 1616 |
+
"learning_rate": 0.00013110272757714818,
|
| 1617 |
+
"loss": 1.9458,
|
| 1618 |
+
"step": 1315
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 4.15,
|
| 1622 |
+
"learning_rate": 0.00012963047644223968,
|
| 1623 |
+
"loss": 2.0727,
|
| 1624 |
+
"step": 1320
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 4.17,
|
| 1628 |
+
"learning_rate": 0.00012800934269961248,
|
| 1629 |
+
"loss": 2.0622,
|
| 1630 |
+
"step": 1325
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 4.18,
|
| 1634 |
+
"learning_rate": 0.0001262432810721057,
|
| 1635 |
+
"loss": 1.7668,
|
| 1636 |
+
"step": 1330
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 4.2,
|
| 1640 |
+
"learning_rate": 0.00012433659983118975,
|
| 1641 |
+
"loss": 1.6953,
|
| 1642 |
+
"step": 1335
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 4.21,
|
| 1646 |
+
"learning_rate": 0.00012229395028702625,
|
| 1647 |
+
"loss": 2.1107,
|
| 1648 |
+
"step": 1340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 4.23,
|
| 1652 |
+
"learning_rate": 0.00012012031544169091,
|
| 1653 |
+
"loss": 1.7084,
|
| 1654 |
+
"step": 1345
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 4.25,
|
| 1658 |
+
"learning_rate": 0.00011782099783324114,
|
| 1659 |
+
"loss": 2.281,
|
| 1660 |
+
"step": 1350
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 4.26,
|
| 1664 |
+
"learning_rate": 0.00011540160660028247,
|
| 1665 |
+
"loss": 2.0195,
|
| 1666 |
+
"step": 1355
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 4.28,
|
| 1670 |
+
"learning_rate": 0.0001128680437985883,
|
| 1671 |
+
"loss": 1.9339,
|
| 1672 |
+
"step": 1360
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 4.29,
|
| 1676 |
+
"learning_rate": 0.00011022649000315548,
|
| 1677 |
+
"loss": 1.8057,
|
| 1678 |
+
"step": 1365
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 4.31,
|
| 1682 |
+
"learning_rate": 0.00010748338923081677,
|
| 1683 |
+
"loss": 1.9412,
|
| 1684 |
+
"step": 1370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 4.32,
|
| 1688 |
+
"learning_rate": 0.00010464543322019205,
|
| 1689 |
+
"loss": 1.6871,
|
| 1690 |
+
"step": 1375
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 4.34,
|
| 1694 |
+
"learning_rate": 0.0001017195451073291,
|
| 1695 |
+
"loss": 1.8352,
|
| 1696 |
+
"step": 1380
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 4.36,
|
| 1700 |
+
"learning_rate": 9.871286253685277e-05,
|
| 1701 |
+
"loss": 1.8437,
|
| 1702 |
+
"step": 1385
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 4.37,
|
| 1706 |
+
"learning_rate": 9.56327202498264e-05,
|
| 1707 |
+
"loss": 2.0612,
|
| 1708 |
+
"step": 1390
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 4.39,
|
| 1712 |
+
"learning_rate": 9.248663219079991e-05,
|
| 1713 |
+
"loss": 1.9911,
|
| 1714 |
+
"step": 1395
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 4.4,
|
| 1718 |
+
"learning_rate": 8.928227317769423e-05,
|
| 1719 |
+
"loss": 1.8443,
|
| 1720 |
+
"step": 1400
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 4.42,
|
| 1724 |
+
"learning_rate": 8.602746017923975e-05,
|
| 1725 |
+
"loss": 1.9599,
|
| 1726 |
+
"step": 1405
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 4.43,
|
| 1730 |
+
"learning_rate": 8.273013324563943e-05,
|
| 1731 |
+
"loss": 1.8763,
|
| 1732 |
+
"step": 1410
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 4.45,
|
| 1736 |
+
"learning_rate": 7.939833613897684e-05,
|
| 1737 |
+
"loss": 1.7859,
|
| 1738 |
+
"step": 1415
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 4.47,
|
| 1742 |
+
"learning_rate": 7.60401967106234e-05,
|
| 1743 |
+
"loss": 2.1938,
|
| 1744 |
+
"step": 1420
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 4.48,
|
| 1748 |
+
"learning_rate": 7.266390707350893e-05,
|
| 1749 |
+
"loss": 1.554,
|
| 1750 |
+
"step": 1425
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 4.5,
|
| 1754 |
+
"learning_rate": 6.927770361762858e-05,
|
| 1755 |
+
"loss": 1.9093,
|
| 1756 |
+
"step": 1430
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 4.51,
|
| 1760 |
+
"learning_rate": 6.588984691753754e-05,
|
| 1761 |
+
"loss": 1.6916,
|
| 1762 |
+
"step": 1435
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 4.53,
|
| 1766 |
+
"learning_rate": 6.250860158084673e-05,
|
| 1767 |
+
"loss": 1.9688,
|
| 1768 |
+
"step": 1440
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 4.54,
|
| 1772 |
+
"learning_rate": 5.91422160868796e-05,
|
| 1773 |
+
"loss": 1.9263,
|
| 1774 |
+
"step": 1445
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 4.56,
|
| 1778 |
+
"learning_rate": 5.579890266467603e-05,
|
| 1779 |
+
"loss": 1.6181,
|
| 1780 |
+
"step": 1450
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 4.58,
|
| 1784 |
+
"learning_rate": 5.248681725942451e-05,
|
| 1785 |
+
"loss": 2.0187,
|
| 1786 |
+
"step": 1455
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 4.59,
|
| 1790 |
+
"learning_rate": 4.921403963620125e-05,
|
| 1791 |
+
"loss": 1.6975,
|
| 1792 |
+
"step": 1460
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 4.61,
|
| 1796 |
+
"learning_rate": 4.598855366954619e-05,
|
| 1797 |
+
"loss": 1.995,
|
| 1798 |
+
"step": 1465
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 4.62,
|
| 1802 |
+
"learning_rate": 4.28182278669633e-05,
|
| 1803 |
+
"loss": 1.9041,
|
| 1804 |
+
"step": 1470
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 4.64,
|
| 1808 |
+
"learning_rate": 3.9710796173857146e-05,
|
| 1809 |
+
"loss": 1.8769,
|
| 1810 |
+
"step": 1475
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 4.65,
|
| 1814 |
+
"learning_rate": 3.667383910672967e-05,
|
| 1815 |
+
"loss": 1.6473,
|
| 1816 |
+
"step": 1480
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 4.67,
|
| 1820 |
+
"learning_rate": 3.371476526066344e-05,
|
| 1821 |
+
"loss": 1.5014,
|
| 1822 |
+
"step": 1485
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 4.69,
|
| 1826 |
+
"learning_rate": 3.084079323620596e-05,
|
| 1827 |
+
"loss": 1.8409,
|
| 1828 |
+
"step": 1490
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 4.7,
|
| 1832 |
+
"learning_rate": 2.805893402973855e-05,
|
| 1833 |
+
"loss": 1.8548,
|
| 1834 |
+
"step": 1495
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 4.72,
|
| 1838 |
+
"learning_rate": 2.5375973930294628e-05,
|
| 1839 |
+
"loss": 1.8673,
|
| 1840 |
+
"step": 1500
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 4.73,
|
| 1844 |
+
"learning_rate": 2.2798457964544384e-05,
|
| 1845 |
+
"loss": 1.8588,
|
| 1846 |
+
"step": 1505
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 4.75,
|
| 1850 |
+
"learning_rate": 2.0332673930335255e-05,
|
| 1851 |
+
"loss": 2.0708,
|
| 1852 |
+
"step": 1510
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 4.76,
|
| 1856 |
+
"learning_rate": 1.7984637057737467e-05,
|
| 1857 |
+
"loss": 1.782,
|
| 1858 |
+
"step": 1515
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 4.78,
|
| 1862 |
+
"learning_rate": 1.5760075335011966e-05,
|
| 1863 |
+
"loss": 1.9664,
|
| 1864 |
+
"step": 1520
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 4.8,
|
| 1868 |
+
"learning_rate": 1.3664415535298983e-05,
|
| 1869 |
+
"loss": 1.9151,
|
| 1870 |
+
"step": 1525
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 4.81,
|
| 1874 |
+
"learning_rate": 1.1702769978116211e-05,
|
| 1875 |
+
"loss": 1.9315,
|
| 1876 |
+
"step": 1530
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 4.83,
|
| 1880 |
+
"learning_rate": 9.879924057958108e-06,
|
| 1881 |
+
"loss": 1.8344,
|
| 1882 |
+
"step": 1535
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 4.84,
|
| 1886 |
+
"learning_rate": 8.20032457042391e-06,
|
| 1887 |
+
"loss": 1.8142,
|
| 1888 |
+
"step": 1540
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 4.86,
|
| 1892 |
+
"learning_rate": 6.6680688643500544e-06,
|
| 1893 |
+
"loss": 1.7706,
|
| 1894 |
+
"step": 1545
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 4.87,
|
| 1898 |
+
"learning_rate": 5.2868948464103564e-06,
|
| 1899 |
+
"loss": 2.0751,
|
| 1900 |
+
"step": 1550
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 4.89,
|
| 1904 |
+
"learning_rate": 4.060171862569283e-06,
|
| 1905 |
+
"loss": 2.0826,
|
| 1906 |
+
"step": 1555
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 4.91,
|
| 1910 |
+
"learning_rate": 2.9908924786305843e-06,
|
| 1911 |
+
"loss": 1.9677,
|
| 1912 |
+
"step": 1560
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 4.92,
|
| 1916 |
+
"learning_rate": 2.0816651799335755e-06,
|
| 1917 |
+
"loss": 1.7251,
|
| 1918 |
+
"step": 1565
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 4.94,
|
| 1922 |
+
"learning_rate": 1.3347080080066644e-06,
|
| 1923 |
+
"loss": 1.9202,
|
| 1924 |
+
"step": 1570
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 4.95,
|
| 1928 |
+
"learning_rate": 7.518431496995702e-07,
|
| 1929 |
+
"loss": 1.833,
|
| 1930 |
+
"step": 1575
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 4.97,
|
| 1934 |
+
"learning_rate": 3.34492491995841e-07,
|
| 1935 |
+
"loss": 1.8957,
|
| 1936 |
+
"step": 1580
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 4.98,
|
| 1940 |
+
"learning_rate": 8.367415334837176e-08,
|
| 1941 |
+
"loss": 1.7695,
|
| 1942 |
+
"step": 1585
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 5.0,
|
| 1946 |
+
"learning_rate": 0.0,
|
| 1947 |
+
"loss": 1.9115,
|
| 1948 |
+
"step": 1590
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 5.0,
|
| 1952 |
+
"eval_loss": 1.906249761581421,
|
| 1953 |
+
"eval_runtime": 20.2347,
|
| 1954 |
+
"eval_samples_per_second": 22.19,
|
| 1955 |
+
"eval_steps_per_second": 2.817,
|
| 1956 |
+
"step": 1590
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 5.02,
|
| 1960 |
+
"learning_rate": 8.367415334837176e-08,
|
| 1961 |
+
"loss": 1.6316,
|
| 1962 |
+
"step": 1595
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 5.03,
|
| 1966 |
+
"learning_rate": 3.3449249199583335e-07,
|
| 1967 |
+
"loss": 1.7125,
|
| 1968 |
+
"step": 1600
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 5.05,
|
| 1972 |
+
"learning_rate": 7.51843149699555e-07,
|
| 1973 |
+
"loss": 1.631,
|
| 1974 |
+
"step": 1605
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 5.06,
|
| 1978 |
+
"learning_rate": 1.3347080080066491e-06,
|
| 1979 |
+
"loss": 1.5559,
|
| 1980 |
+
"step": 1610
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 5.08,
|
| 1984 |
+
"learning_rate": 2.0816651799335526e-06,
|
| 1985 |
+
"loss": 1.7693,
|
| 1986 |
+
"step": 1615
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 5.09,
|
| 1990 |
+
"learning_rate": 2.990892478630592e-06,
|
| 1991 |
+
"loss": 1.5954,
|
| 1992 |
+
"step": 1620
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 5.11,
|
| 1996 |
+
"learning_rate": 4.060171862569298e-06,
|
| 1997 |
+
"loss": 1.9519,
|
| 1998 |
+
"step": 1625
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 5.13,
|
| 2002 |
+
"learning_rate": 5.2868948464102726e-06,
|
| 2003 |
+
"loss": 1.5427,
|
| 2004 |
+
"step": 1630
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 5.14,
|
| 2008 |
+
"learning_rate": 6.668068864349971e-06,
|
| 2009 |
+
"loss": 1.5142,
|
| 2010 |
+
"step": 1635
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 5.16,
|
| 2014 |
+
"learning_rate": 8.200324570423812e-06,
|
| 2015 |
+
"loss": 1.4704,
|
| 2016 |
+
"step": 1640
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 5.17,
|
| 2020 |
+
"learning_rate": 9.879924057958001e-06,
|
| 2021 |
+
"loss": 1.724,
|
| 2022 |
+
"step": 1645
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 5.19,
|
| 2026 |
+
"learning_rate": 1.1702769978116166e-05,
|
| 2027 |
+
"loss": 1.7845,
|
| 2028 |
+
"step": 1650
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 5.2,
|
| 2032 |
+
"learning_rate": 1.366441553529893e-05,
|
| 2033 |
+
"loss": 1.5651,
|
| 2034 |
+
"step": 1655
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 5.22,
|
| 2038 |
+
"learning_rate": 1.5760075335011912e-05,
|
| 2039 |
+
"loss": 1.5684,
|
| 2040 |
+
"step": 1660
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 5.24,
|
| 2044 |
+
"learning_rate": 1.7984637057737406e-05,
|
| 2045 |
+
"loss": 1.8357,
|
| 2046 |
+
"step": 1665
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 5.25,
|
| 2050 |
+
"learning_rate": 2.0332673930335194e-05,
|
| 2051 |
+
"loss": 1.6561,
|
| 2052 |
+
"step": 1670
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 5.27,
|
| 2056 |
+
"learning_rate": 2.2798457964544323e-05,
|
| 2057 |
+
"loss": 1.7467,
|
| 2058 |
+
"step": 1675
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 5.28,
|
| 2062 |
+
"learning_rate": 2.5375973930294556e-05,
|
| 2063 |
+
"loss": 1.9728,
|
| 2064 |
+
"step": 1680
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 5.3,
|
| 2068 |
+
"learning_rate": 2.805893402973858e-05,
|
| 2069 |
+
"loss": 1.813,
|
| 2070 |
+
"step": 1685
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 5.31,
|
| 2074 |
+
"learning_rate": 3.084079323620599e-05,
|
| 2075 |
+
"loss": 1.7629,
|
| 2076 |
+
"step": 1690
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 5.33,
|
| 2080 |
+
"learning_rate": 3.3714765260663475e-05,
|
| 2081 |
+
"loss": 1.7309,
|
| 2082 |
+
"step": 1695
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 5.35,
|
| 2086 |
+
"learning_rate": 3.66738391067297e-05,
|
| 2087 |
+
"loss": 1.5675,
|
| 2088 |
+
"step": 1700
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 5.36,
|
| 2092 |
+
"learning_rate": 3.971079617385719e-05,
|
| 2093 |
+
"loss": 1.4041,
|
| 2094 |
+
"step": 1705
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 5.38,
|
| 2098 |
+
"learning_rate": 4.28182278669631e-05,
|
| 2099 |
+
"loss": 1.5323,
|
| 2100 |
+
"step": 1710
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 5.39,
|
| 2104 |
+
"learning_rate": 4.5988553669545996e-05,
|
| 2105 |
+
"loss": 1.7705,
|
| 2106 |
+
"step": 1715
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 5.41,
|
| 2110 |
+
"learning_rate": 4.921403963620105e-05,
|
| 2111 |
+
"loss": 1.7652,
|
| 2112 |
+
"step": 1720
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 5.42,
|
| 2116 |
+
"learning_rate": 5.2486817259424427e-05,
|
| 2117 |
+
"loss": 1.8281,
|
| 2118 |
+
"step": 1725
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 5.44,
|
| 2122 |
+
"learning_rate": 5.579890266467595e-05,
|
| 2123 |
+
"loss": 1.6899,
|
| 2124 |
+
"step": 1730
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 5.46,
|
| 2128 |
+
"learning_rate": 5.914221608687952e-05,
|
| 2129 |
+
"loss": 1.6888,
|
| 2130 |
+
"step": 1735
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 5.47,
|
| 2134 |
+
"learning_rate": 6.250860158084665e-05,
|
| 2135 |
+
"loss": 1.7589,
|
| 2136 |
+
"step": 1740
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 5.49,
|
| 2140 |
+
"learning_rate": 6.588984691753746e-05,
|
| 2141 |
+
"loss": 1.6297,
|
| 2142 |
+
"step": 1745
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 5.5,
|
| 2146 |
+
"learning_rate": 6.92777036176285e-05,
|
| 2147 |
+
"loss": 1.8036,
|
| 2148 |
+
"step": 1750
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 5.52,
|
| 2152 |
+
"learning_rate": 7.266390707350887e-05,
|
| 2153 |
+
"loss": 1.8385,
|
| 2154 |
+
"step": 1755
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 5.53,
|
| 2158 |
+
"learning_rate": 7.604019671062332e-05,
|
| 2159 |
+
"loss": 1.7527,
|
| 2160 |
+
"step": 1760
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 5.55,
|
| 2164 |
+
"learning_rate": 7.939833613897687e-05,
|
| 2165 |
+
"loss": 1.5839,
|
| 2166 |
+
"step": 1765
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 5.57,
|
| 2170 |
+
"learning_rate": 8.273013324563949e-05,
|
| 2171 |
+
"loss": 1.9817,
|
| 2172 |
+
"step": 1770
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 5.58,
|
| 2176 |
+
"learning_rate": 8.602746017923979e-05,
|
| 2177 |
+
"loss": 2.1168,
|
| 2178 |
+
"step": 1775
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 5.6,
|
| 2182 |
+
"learning_rate": 8.928227317769404e-05,
|
| 2183 |
+
"loss": 1.8069,
|
| 2184 |
+
"step": 1780
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 5.61,
|
| 2188 |
+
"learning_rate": 9.248663219079973e-05,
|
| 2189 |
+
"loss": 1.886,
|
| 2190 |
+
"step": 1785
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 5.63,
|
| 2194 |
+
"learning_rate": 9.56327202498262e-05,
|
| 2195 |
+
"loss": 1.8172,
|
| 2196 |
+
"step": 1790
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 5.64,
|
| 2200 |
+
"learning_rate": 9.871286253685269e-05,
|
| 2201 |
+
"loss": 1.6818,
|
| 2202 |
+
"step": 1795
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 5.66,
|
| 2206 |
+
"learning_rate": 0.00010171954510732892,
|
| 2207 |
+
"loss": 1.4689,
|
| 2208 |
+
"step": 1800
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 5.68,
|
| 2212 |
+
"learning_rate": 0.00010464543322019198,
|
| 2213 |
+
"loss": 1.3972,
|
| 2214 |
+
"step": 1805
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 5.69,
|
| 2218 |
+
"learning_rate": 0.00010748338923081671,
|
| 2219 |
+
"loss": 1.8636,
|
| 2220 |
+
"step": 1810
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 5.71,
|
| 2224 |
+
"learning_rate": 0.0001102264900031554,
|
| 2225 |
+
"loss": 1.5656,
|
| 2226 |
+
"step": 1815
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 5.72,
|
| 2230 |
+
"learning_rate": 0.00011286804379858823,
|
| 2231 |
+
"loss": 1.834,
|
| 2232 |
+
"step": 1820
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 5.74,
|
| 2236 |
+
"learning_rate": 0.00011540160660028242,
|
| 2237 |
+
"loss": 1.6874,
|
| 2238 |
+
"step": 1825
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 5.75,
|
| 2242 |
+
"learning_rate": 0.00011782099783324108,
|
| 2243 |
+
"loss": 1.7932,
|
| 2244 |
+
"step": 1830
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 5.77,
|
| 2248 |
+
"learning_rate": 0.00012012031544169092,
|
| 2249 |
+
"loss": 1.8093,
|
| 2250 |
+
"step": 1835
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 5.79,
|
| 2254 |
+
"learning_rate": 0.00012229395028702622,
|
| 2255 |
+
"loss": 1.4865,
|
| 2256 |
+
"step": 1840
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 5.8,
|
| 2260 |
+
"learning_rate": 0.00012433659983118975,
|
| 2261 |
+
"loss": 1.7283,
|
| 2262 |
+
"step": 1845
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 5.82,
|
| 2266 |
+
"learning_rate": 0.0001262432810721057,
|
| 2267 |
+
"loss": 1.5611,
|
| 2268 |
+
"step": 1850
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 5.83,
|
| 2272 |
+
"learning_rate": 0.00012800934269961248,
|
| 2273 |
+
"loss": 1.7974,
|
| 2274 |
+
"step": 1855
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 5.85,
|
| 2278 |
+
"learning_rate": 0.0001296304764422396,
|
| 2279 |
+
"loss": 1.6754,
|
| 2280 |
+
"step": 1860
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 5.86,
|
| 2284 |
+
"learning_rate": 0.0001311027275771481,
|
| 2285 |
+
"loss": 1.5481,
|
| 2286 |
+
"step": 1865
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 5.88,
|
| 2290 |
+
"learning_rate": 0.0001324225045775964,
|
| 2291 |
+
"loss": 1.7931,
|
| 2292 |
+
"step": 1870
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 5.9,
|
| 2296 |
+
"learning_rate": 0.0001335865878743975,
|
| 2297 |
+
"loss": 1.9985,
|
| 2298 |
+
"step": 1875
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 5.91,
|
| 2302 |
+
"learning_rate": 0.00013459213770999182,
|
| 2303 |
+
"loss": 1.9837,
|
| 2304 |
+
"step": 1880
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 5.93,
|
| 2308 |
+
"learning_rate": 0.00013543670106597888,
|
| 2309 |
+
"loss": 1.7165,
|
| 2310 |
+
"step": 1885
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 5.94,
|
| 2314 |
+
"learning_rate": 0.00013611821764720515,
|
| 2315 |
+
"loss": 1.9364,
|
| 2316 |
+
"step": 1890
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 5.96,
|
| 2320 |
+
"learning_rate": 0.0001366350249078127,
|
| 2321 |
+
"loss": 1.6662,
|
| 2322 |
+
"step": 1895
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 5.97,
|
| 2326 |
+
"learning_rate": 0.000136985862106986,
|
| 2327 |
+
"loss": 1.8671,
|
| 2328 |
+
"step": 1900
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 5.99,
|
| 2332 |
+
"learning_rate": 0.0001371698733845033,
|
| 2333 |
+
"loss": 1.7105,
|
| 2334 |
+
"step": 1905
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 6.0,
|
| 2338 |
+
"eval_loss": 1.9032058715820312,
|
| 2339 |
+
"eval_runtime": 20.2363,
|
| 2340 |
+
"eval_samples_per_second": 22.188,
|
| 2341 |
+
"eval_steps_per_second": 2.817,
|
| 2342 |
+
"step": 1908
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 6.01,
|
| 2346 |
+
"learning_rate": 0.0001371866098485905,
|
| 2347 |
+
"loss": 1.4646,
|
| 2348 |
+
"step": 1910
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 6.02,
|
| 2352 |
+
"learning_rate": 0.00013703603067098332,
|
| 2353 |
+
"loss": 1.572,
|
| 2354 |
+
"step": 1915
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 6.04,
|
| 2358 |
+
"learning_rate": 0.00013671850318652725,
|
| 2359 |
+
"loss": 1.6881,
|
| 2360 |
+
"step": 1920
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 6.05,
|
| 2364 |
+
"learning_rate": 0.00013623480199707148,
|
| 2365 |
+
"loss": 1.8478,
|
| 2366 |
+
"step": 1925
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 6.07,
|
| 2370 |
+
"learning_rate": 0.00013558610708184343,
|
| 2371 |
+
"loss": 1.6836,
|
| 2372 |
+
"step": 1930
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 6.08,
|
| 2376 |
+
"learning_rate": 0.0001347740009189134,
|
| 2377 |
+
"loss": 1.7053,
|
| 2378 |
+
"step": 1935
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 6.1,
|
| 2382 |
+
"learning_rate": 0.00013380046462477165,
|
| 2383 |
+
"loss": 1.5923,
|
| 2384 |
+
"step": 1940
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 6.12,
|
| 2388 |
+
"learning_rate": 0.00013266787312143458,
|
| 2389 |
+
"loss": 1.5511,
|
| 2390 |
+
"step": 1945
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 6.13,
|
| 2394 |
+
"learning_rate": 0.00013137898934287114,
|
| 2395 |
+
"loss": 1.6041,
|
| 2396 |
+
"step": 1950
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 6.15,
|
| 2400 |
+
"learning_rate": 0.00012993695749488105,
|
| 2401 |
+
"loss": 1.5811,
|
| 2402 |
+
"step": 1955
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 6.16,
|
| 2406 |
+
"learning_rate": 0.0001283452953848691,
|
| 2407 |
+
"loss": 1.6477,
|
| 2408 |
+
"step": 1960
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 6.18,
|
| 2412 |
+
"learning_rate": 0.00012660788584022533,
|
| 2413 |
+
"loss": 1.6821,
|
| 2414 |
+
"step": 1965
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 6.19,
|
| 2418 |
+
"learning_rate": 0.00012472896723624585,
|
| 2419 |
+
"loss": 1.9101,
|
| 2420 |
+
"step": 1970
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 6.21,
|
| 2424 |
+
"learning_rate": 0.00012271312315670352,
|
| 2425 |
+
"loss": 1.7961,
|
| 2426 |
+
"step": 1975
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 6.23,
|
| 2430 |
+
"learning_rate": 0.00012056527121228716,
|
| 2431 |
+
"loss": 1.7949,
|
| 2432 |
+
"step": 1980
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 6.24,
|
| 2436 |
+
"learning_rate": 0.00011829065104419132,
|
| 2437 |
+
"loss": 1.4401,
|
| 2438 |
+
"step": 1985
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 6.26,
|
| 2442 |
+
"learning_rate": 0.00011589481154211747,
|
| 2443 |
+
"loss": 1.6164,
|
| 2444 |
+
"step": 1990
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 6.27,
|
| 2448 |
+
"learning_rate": 0.00011338359730786976,
|
| 2449 |
+
"loss": 1.8185,
|
| 2450 |
+
"step": 1995
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 6.29,
|
| 2454 |
+
"learning_rate": 0.00011076313439756885,
|
| 2455 |
+
"loss": 1.9472,
|
| 2456 |
+
"step": 2000
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 6.31,
|
| 2460 |
+
"learning_rate": 0.00010803981537726108,
|
| 2461 |
+
"loss": 1.5825,
|
| 2462 |
+
"step": 2005
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 6.32,
|
| 2466 |
+
"learning_rate": 0.00010522028372838475,
|
| 2467 |
+
"loss": 1.6182,
|
| 2468 |
+
"step": 2010
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 6.34,
|
| 2472 |
+
"learning_rate": 0.00010231141764113088,
|
| 2473 |
+
"loss": 1.6272,
|
| 2474 |
+
"step": 2015
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 6.35,
|
| 2478 |
+
"learning_rate": 9.932031323523847e-05,
|
| 2479 |
+
"loss": 1.4251,
|
| 2480 |
+
"step": 2020
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 6.37,
|
| 2484 |
+
"learning_rate": 9.625426724915494e-05,
|
| 2485 |
+
"loss": 1.5946,
|
| 2486 |
+
"step": 2025
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 6.38,
|
| 2490 |
+
"learning_rate": 9.31207592397905e-05,
|
| 2491 |
+
"loss": 1.5311,
|
| 2492 |
+
"step": 2030
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 6.4,
|
| 2496 |
+
"learning_rate": 8.992743333629033e-05,
|
| 2497 |
+
"loss": 1.7549,
|
| 2498 |
+
"step": 2035
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 6.42,
|
| 2502 |
+
"learning_rate": 8.6682079592338e-05,
|
| 2503 |
+
"loss": 1.7651,
|
| 2504 |
+
"step": 2040
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 6.43,
|
| 2508 |
+
"learning_rate": 8.339261498247729e-05,
|
| 2509 |
+
"loss": 1.7894,
|
| 2510 |
+
"step": 2045
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 6.45,
|
| 2514 |
+
"learning_rate": 8.006706408881262e-05,
|
| 2515 |
+
"loss": 1.2016,
|
| 2516 |
+
"step": 2050
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 6.46,
|
| 2520 |
+
"learning_rate": 7.671353952520582e-05,
|
| 2521 |
+
"loss": 1.5423,
|
| 2522 |
+
"step": 2055
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 6.48,
|
| 2526 |
+
"learning_rate": 7.334022214671746e-05,
|
| 2527 |
+
"loss": 1.2711,
|
| 2528 |
+
"step": 2060
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 6.49,
|
| 2532 |
+
"learning_rate": 6.995534109257865e-05,
|
| 2533 |
+
"loss": 1.582,
|
| 2534 |
+
"step": 2065
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 6.51,
|
| 2538 |
+
"learning_rate": 6.656715371137246e-05,
|
| 2539 |
+
"loss": 1.55,
|
| 2540 |
+
"step": 2070
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 6.53,
|
| 2544 |
+
"learning_rate": 6.318392541739893e-05,
|
| 2545 |
+
"loss": 1.5744,
|
| 2546 |
+
"step": 2075
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 6.54,
|
| 2550 |
+
"learning_rate": 5.9813909527366465e-05,
|
| 2551 |
+
"loss": 1.7316,
|
| 2552 |
+
"step": 2080
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 6.56,
|
| 2556 |
+
"learning_rate": 5.646532712659148e-05,
|
| 2557 |
+
"loss": 1.5926,
|
| 2558 |
+
"step": 2085
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 6.57,
|
| 2562 |
+
"learning_rate": 5.314634701382963e-05,
|
| 2563 |
+
"loss": 1.3707,
|
| 2564 |
+
"step": 2090
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 6.59,
|
| 2568 |
+
"learning_rate": 4.98650657736552e-05,
|
| 2569 |
+
"loss": 1.3874,
|
| 2570 |
+
"step": 2095
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 6.6,
|
| 2574 |
+
"learning_rate": 4.6629488025009487e-05,
|
| 2575 |
+
"loss": 1.6198,
|
| 2576 |
+
"step": 2100
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 6.62,
|
| 2580 |
+
"learning_rate": 4.3447506894093505e-05,
|
| 2581 |
+
"loss": 1.6056,
|
| 2582 |
+
"step": 2105
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 6.64,
|
| 2586 |
+
"learning_rate": 4.0326884759248795e-05,
|
| 2587 |
+
"loss": 1.3487,
|
| 2588 |
+
"step": 2110
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 6.65,
|
| 2592 |
+
"learning_rate": 3.7275234314791357e-05,
|
| 2593 |
+
"loss": 1.5276,
|
| 2594 |
+
"step": 2115
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 6.67,
|
| 2598 |
+
"learning_rate": 3.429999999999998e-05,
|
| 2599 |
+
"loss": 1.6535,
|
| 2600 |
+
"step": 2120
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 6.68,
|
| 2604 |
+
"learning_rate": 3.140843983855718e-05,
|
| 2605 |
+
"loss": 1.8044,
|
| 2606 |
+
"step": 2125
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 6.7,
|
| 2610 |
+
"learning_rate": 2.860760773274722e-05,
|
| 2611 |
+
"loss": 1.705,
|
| 2612 |
+
"step": 2130
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 6.71,
|
| 2616 |
+
"learning_rate": 2.5904336255606023e-05,
|
| 2617 |
+
"loss": 1.4356,
|
| 2618 |
+
"step": 2135
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 6.73,
|
| 2622 |
+
"learning_rate": 2.3305219982997338e-05,
|
| 2623 |
+
"loss": 1.4672,
|
| 2624 |
+
"step": 2140
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 6.75,
|
| 2628 |
+
"learning_rate": 2.0816599406278358e-05,
|
| 2629 |
+
"loss": 1.5759,
|
| 2630 |
+
"step": 2145
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 6.76,
|
| 2634 |
+
"learning_rate": 1.8444545464801106e-05,
|
| 2635 |
+
"loss": 1.655,
|
| 2636 |
+
"step": 2150
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 6.78,
|
| 2640 |
+
"learning_rate": 1.6194844735977787e-05,
|
| 2641 |
+
"loss": 1.5595,
|
| 2642 |
+
"step": 2155
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 6.79,
|
| 2646 |
+
"learning_rate": 1.4072985319044027e-05,
|
| 2647 |
+
"loss": 1.5155,
|
| 2648 |
+
"step": 2160
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 6.81,
|
| 2652 |
+
"learning_rate": 1.208414344695116e-05,
|
| 2653 |
+
"loss": 1.6561,
|
| 2654 |
+
"step": 2165
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 6.82,
|
| 2658 |
+
"learning_rate": 1.0233170859051572e-05,
|
| 2659 |
+
"loss": 1.4243,
|
| 2660 |
+
"step": 2170
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 6.84,
|
| 2664 |
+
"learning_rate": 8.524582965379327e-06,
|
| 2665 |
+
"loss": 1.3178,
|
| 2666 |
+
"step": 2175
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 6.86,
|
| 2670 |
+
"learning_rate": 6.9625478313988e-06,
|
| 2671 |
+
"loss": 1.2895,
|
| 2672 |
+
"step": 2180
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 6.87,
|
| 2676 |
+
"learning_rate": 5.5508760100933275e-06,
|
| 2677 |
+
"loss": 1.8021,
|
| 2678 |
+
"step": 2185
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 6.89,
|
| 2682 |
+
"learning_rate": 4.293011246199375e-06,
|
| 2683 |
+
"loss": 1.2922,
|
| 2684 |
+
"step": 2190
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 6.9,
|
| 2688 |
+
"learning_rate": 3.19202207526035e-06,
|
| 2689 |
+
"loss": 1.514,
|
| 2690 |
+
"step": 2195
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 6.92,
|
| 2694 |
+
"learning_rate": 2.2505943379971774e-06,
|
| 2695 |
+
"loss": 1.7064,
|
| 2696 |
+
"step": 2200
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 6.93,
|
| 2700 |
+
"learning_rate": 1.4710246282540463e-06,
|
| 2701 |
+
"loss": 1.7752,
|
| 2702 |
+
"step": 2205
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 6.95,
|
| 2706 |
+
"learning_rate": 8.552146905042831e-07,
|
| 2707 |
+
"loss": 1.4982,
|
| 2708 |
+
"step": 2210
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 6.97,
|
| 2712 |
+
"learning_rate": 4.0466678058365933e-07,
|
| 2713 |
+
"loss": 1.4699,
|
| 2714 |
+
"step": 2215
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 6.98,
|
| 2718 |
+
"learning_rate": 1.2048000096755528e-07,
|
| 2719 |
+
"loss": 1.7008,
|
| 2720 |
+
"step": 2220
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 7.0,
|
| 2724 |
+
"learning_rate": 3.347619532822632e-09,
|
| 2725 |
+
"loss": 1.5587,
|
| 2726 |
+
"step": 2225
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 7.0,
|
| 2730 |
+
"eval_loss": 1.8221737146377563,
|
| 2731 |
+
"eval_runtime": 20.3992,
|
| 2732 |
+
"eval_samples_per_second": 22.011,
|
| 2733 |
+
"eval_steps_per_second": 2.794,
|
| 2734 |
+
"step": 2226
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 7.01,
|
| 2738 |
+
"learning_rate": 5.355537834497188e-08,
|
| 2739 |
+
"loss": 1.248,
|
| 2740 |
+
"step": 2230
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 7.03,
|
| 2744 |
+
"learning_rate": 2.709807965961209e-07,
|
| 2745 |
+
"loss": 1.3298,
|
| 2746 |
+
"step": 2235
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 7.04,
|
| 2750 |
+
"learning_rate": 6.550934693944553e-07,
|
| 2751 |
+
"loss": 1.4704,
|
| 2752 |
+
"step": 2240
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 7.06,
|
| 2756 |
+
"learning_rate": 1.2049563616762301e-06,
|
| 2757 |
+
"loss": 1.4347,
|
| 2758 |
+
"step": 2245
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"epoch": 7.08,
|
| 2762 |
+
"learning_rate": 1.919228094083792e-06,
|
| 2763 |
+
"loss": 1.3554,
|
| 2764 |
+
"step": 2250
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 7.09,
|
| 2768 |
+
"learning_rate": 2.7961662152331403e-06,
|
| 2769 |
+
"loss": 1.428,
|
| 2770 |
+
"step": 2255
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 7.11,
|
| 2774 |
+
"learning_rate": 3.833631452388745e-06,
|
| 2775 |
+
"loss": 1.4177,
|
| 2776 |
+
"step": 2260
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 7.12,
|
| 2780 |
+
"learning_rate": 5.029092930176208e-06,
|
| 2781 |
+
"loss": 1.3861,
|
| 2782 |
+
"step": 2265
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 7.14,
|
| 2786 |
+
"learning_rate": 6.379634344600846e-06,
|
| 2787 |
+
"loss": 1.3699,
|
| 2788 |
+
"step": 2270
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 7.15,
|
| 2792 |
+
"learning_rate": 7.88196107731231e-06,
|
| 2793 |
+
"loss": 1.4377,
|
| 2794 |
+
"step": 2275
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 7.17,
|
| 2798 |
+
"learning_rate": 9.532408232759425e-06,
|
| 2799 |
+
"loss": 1.4078,
|
| 2800 |
+
"step": 2280
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 7.19,
|
| 2804 |
+
"learning_rate": 1.1326949578627714e-05,
|
| 2805 |
+
"loss": 1.4196,
|
| 2806 |
+
"step": 2285
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 7.2,
|
| 2810 |
+
"learning_rate": 1.3261207367752312e-05,
|
| 2811 |
+
"loss": 1.4826,
|
| 2812 |
+
"step": 2290
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 7.22,
|
| 2816 |
+
"learning_rate": 1.533046301754235e-05,
|
| 2817 |
+
"loss": 1.4701,
|
| 2818 |
+
"step": 2295
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 7.23,
|
| 2822 |
+
"learning_rate": 1.7529668620867698e-05,
|
| 2823 |
+
"loss": 1.4641,
|
| 2824 |
+
"step": 2300
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 7.25,
|
| 2828 |
+
"learning_rate": 1.985345926032643e-05,
|
| 2829 |
+
"loss": 1.4294,
|
| 2830 |
+
"step": 2305
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 7.26,
|
| 2834 |
+
"learning_rate": 2.22961660958507e-05,
|
| 2835 |
+
"loss": 1.4558,
|
| 2836 |
+
"step": 2310
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 7.28,
|
| 2840 |
+
"learning_rate": 2.4851830193728118e-05,
|
| 2841 |
+
"loss": 1.5906,
|
| 2842 |
+
"step": 2315
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 7.3,
|
| 2846 |
+
"learning_rate": 2.751421706329902e-05,
|
| 2847 |
+
"loss": 1.6085,
|
| 2848 |
+
"step": 2320
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 7.31,
|
| 2852 |
+
"learning_rate": 3.027683186586924e-05,
|
| 2853 |
+
"loss": 1.2953,
|
| 2854 |
+
"step": 2325
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 7.33,
|
| 2858 |
+
"learning_rate": 3.313293525873851e-05,
|
| 2859 |
+
"loss": 1.4112,
|
| 2860 |
+
"step": 2330
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 7.34,
|
| 2864 |
+
"learning_rate": 3.607555983568874e-05,
|
| 2865 |
+
"loss": 1.3934,
|
| 2866 |
+
"step": 2335
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 7.36,
|
| 2870 |
+
"learning_rate": 3.909752712383054e-05,
|
| 2871 |
+
"loss": 1.3835,
|
| 2872 |
+
"step": 2340
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 7.37,
|
| 2876 |
+
"learning_rate": 4.219146509534274e-05,
|
| 2877 |
+
"loss": 1.4961,
|
| 2878 |
+
"step": 2345
|
| 2879 |
+
},
|
| 2880 |
+
{
|
| 2881 |
+
"epoch": 7.39,
|
| 2882 |
+
"learning_rate": 4.5349826151383146e-05,
|
| 2883 |
+
"loss": 1.2224,
|
| 2884 |
+
"step": 2350
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"epoch": 7.41,
|
| 2888 |
+
"learning_rate": 4.856490553430337e-05,
|
| 2889 |
+
"loss": 1.4432,
|
| 2890 |
+
"step": 2355
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 7.42,
|
| 2894 |
+
"learning_rate": 5.182886012324924e-05,
|
| 2895 |
+
"loss": 1.5696,
|
| 2896 |
+
"step": 2360
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 7.44,
|
| 2900 |
+
"learning_rate": 5.5133727567293246e-05,
|
| 2901 |
+
"loss": 1.6135,
|
| 2902 |
+
"step": 2365
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 7.45,
|
| 2906 |
+
"learning_rate": 5.8471445709429775e-05,
|
| 2907 |
+
"loss": 1.3836,
|
| 2908 |
+
"step": 2370
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 7.47,
|
| 2912 |
+
"learning_rate": 6.18338722540417e-05,
|
| 2913 |
+
"loss": 1.0351,
|
| 2914 |
+
"step": 2375
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 7.48,
|
| 2918 |
+
"learning_rate": 6.521280462986592e-05,
|
| 2919 |
+
"loss": 1.5105,
|
| 2920 |
+
"step": 2380
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 7.5,
|
| 2924 |
+
"learning_rate": 6.859999999999982e-05,
|
| 2925 |
+
"loss": 1.6121,
|
| 2926 |
+
"step": 2385
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 7.52,
|
| 2930 |
+
"learning_rate": 7.198719537013396e-05,
|
| 2931 |
+
"loss": 1.6241,
|
| 2932 |
+
"step": 2390
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 7.53,
|
| 2936 |
+
"learning_rate": 7.536612774595818e-05,
|
| 2937 |
+
"loss": 1.522,
|
| 2938 |
+
"step": 2395
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 7.55,
|
| 2942 |
+
"learning_rate": 7.872855429057012e-05,
|
| 2943 |
+
"loss": 1.4888,
|
| 2944 |
+
"step": 2400
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 7.56,
|
| 2948 |
+
"learning_rate": 8.206627243270664e-05,
|
| 2949 |
+
"loss": 1.4955,
|
| 2950 |
+
"step": 2405
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 7.58,
|
| 2954 |
+
"learning_rate": 8.537113987675064e-05,
|
| 2955 |
+
"loss": 1.4161,
|
| 2956 |
+
"step": 2410
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 7.59,
|
| 2960 |
+
"learning_rate": 8.86350944656965e-05,
|
| 2961 |
+
"loss": 1.8936,
|
| 2962 |
+
"step": 2415
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 7.61,
|
| 2966 |
+
"learning_rate": 9.185017384861673e-05,
|
| 2967 |
+
"loss": 1.6053,
|
| 2968 |
+
"step": 2420
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 7.63,
|
| 2972 |
+
"learning_rate": 9.500853490465716e-05,
|
| 2973 |
+
"loss": 1.5626,
|
| 2974 |
+
"step": 2425
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 7.64,
|
| 2978 |
+
"learning_rate": 9.810247287616934e-05,
|
| 2979 |
+
"loss": 1.1654,
|
| 2980 |
+
"step": 2430
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 7.66,
|
| 2984 |
+
"learning_rate": 0.00010112444016431114,
|
| 2985 |
+
"loss": 1.353,
|
| 2986 |
+
"step": 2435
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 7.67,
|
| 2990 |
+
"learning_rate": 0.00010406706474126137,
|
| 2991 |
+
"loss": 1.5396,
|
| 2992 |
+
"step": 2440
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 7.69,
|
| 2996 |
+
"learning_rate": 0.00010692316813413065,
|
| 2997 |
+
"loss": 1.3699,
|
| 2998 |
+
"step": 2445
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 7.7,
|
| 3002 |
+
"learning_rate": 0.0001096857829367009,
|
| 3003 |
+
"loss": 1.3597,
|
| 3004 |
+
"step": 2450
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 7.72,
|
| 3008 |
+
"learning_rate": 0.0001123481698062718,
|
| 3009 |
+
"loss": 1.5768,
|
| 3010 |
+
"step": 2455
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"epoch": 7.74,
|
| 3014 |
+
"learning_rate": 0.00011490383390414922,
|
| 3015 |
+
"loss": 1.3661,
|
| 3016 |
+
"step": 2460
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 7.75,
|
| 3020 |
+
"learning_rate": 0.00011734654073967348,
|
| 3021 |
+
"loss": 1.4304,
|
| 3022 |
+
"step": 2465
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 7.77,
|
| 3026 |
+
"learning_rate": 0.00011967033137913221,
|
| 3027 |
+
"loss": 1.4475,
|
| 3028 |
+
"step": 2470
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 7.78,
|
| 3032 |
+
"learning_rate": 0.00012186953698245757,
|
| 3033 |
+
"loss": 1.5644,
|
| 3034 |
+
"step": 2475
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 7.8,
|
| 3038 |
+
"learning_rate": 0.00012393879263224763,
|
| 3039 |
+
"loss": 1.2184,
|
| 3040 |
+
"step": 2480
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 7.81,
|
| 3044 |
+
"learning_rate": 0.00012587305042137222,
|
| 3045 |
+
"loss": 1.55,
|
| 3046 |
+
"step": 2485
|
| 3047 |
+
},
|
| 3048 |
+
{
|
| 3049 |
+
"epoch": 7.83,
|
| 3050 |
+
"learning_rate": 0.00012766759176724053,
|
| 3051 |
+
"loss": 1.5614,
|
| 3052 |
+
"step": 2490
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 7.85,
|
| 3056 |
+
"learning_rate": 0.00012931803892268765,
|
| 3057 |
+
"loss": 1.4788,
|
| 3058 |
+
"step": 2495
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 7.86,
|
| 3062 |
+
"learning_rate": 0.0001308203656553991,
|
| 3063 |
+
"loss": 1.3325,
|
| 3064 |
+
"step": 2500
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 7.88,
|
| 3068 |
+
"learning_rate": 0.00013217090706982374,
|
| 3069 |
+
"loss": 1.6197,
|
| 3070 |
+
"step": 2505
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 7.89,
|
| 3074 |
+
"learning_rate": 0.0001333663685476112,
|
| 3075 |
+
"loss": 1.5014,
|
| 3076 |
+
"step": 2510
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 7.91,
|
| 3080 |
+
"learning_rate": 0.00013440383378476682,
|
| 3081 |
+
"loss": 1.4764,
|
| 3082 |
+
"step": 2515
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 7.92,
|
| 3086 |
+
"learning_rate": 0.00013528077190591619,
|
| 3087 |
+
"loss": 1.8615,
|
| 3088 |
+
"step": 2520
|
| 3089 |
+
},
|
| 3090 |
+
{
|
| 3091 |
+
"epoch": 7.94,
|
| 3092 |
+
"learning_rate": 0.00013599504363832375,
|
| 3093 |
+
"loss": 1.2448,
|
| 3094 |
+
"step": 2525
|
| 3095 |
+
},
|
| 3096 |
+
{
|
| 3097 |
+
"epoch": 7.96,
|
| 3098 |
+
"learning_rate": 0.00013654490653060552,
|
| 3099 |
+
"loss": 1.3242,
|
| 3100 |
+
"step": 2530
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 7.97,
|
| 3104 |
+
"learning_rate": 0.00013692901920340386,
|
| 3105 |
+
"loss": 1.3224,
|
| 3106 |
+
"step": 2535
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 7.99,
|
| 3110 |
+
"learning_rate": 0.00013714644462165502,
|
| 3111 |
+
"loss": 1.4513,
|
| 3112 |
+
"step": 2540
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 8.0,
|
| 3116 |
+
"eval_loss": 1.8965427875518799,
|
| 3117 |
+
"eval_runtime": 20.4074,
|
| 3118 |
+
"eval_samples_per_second": 22.002,
|
| 3119 |
+
"eval_steps_per_second": 2.793,
|
| 3120 |
+
"step": 2544
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 8.0,
|
| 3124 |
+
"learning_rate": 0.00013719665238046719,
|
| 3125 |
+
"loss": 1.3932,
|
| 3126 |
+
"step": 2545
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 8.02,
|
| 3130 |
+
"learning_rate": 0.00013707951999903246,
|
| 3131 |
+
"loss": 1.2432,
|
| 3132 |
+
"step": 2550
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 8.03,
|
| 3136 |
+
"learning_rate": 0.00013679533321941633,
|
| 3137 |
+
"loss": 1.2907,
|
| 3138 |
+
"step": 2555
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 8.05,
|
| 3142 |
+
"learning_rate": 0.00013634478530949573,
|
| 3143 |
+
"loss": 1.2857,
|
| 3144 |
+
"step": 2560
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 8.07,
|
| 3148 |
+
"learning_rate": 0.00013572897537174604,
|
| 3149 |
+
"loss": 1.3178,
|
| 3150 |
+
"step": 2565
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"epoch": 8.08,
|
| 3154 |
+
"learning_rate": 0.00013494940566200278,
|
| 3155 |
+
"loss": 1.3444,
|
| 3156 |
+
"step": 2570
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 8.1,
|
| 3160 |
+
"learning_rate": 0.0001340079779247397,
|
| 3161 |
+
"loss": 1.3778,
|
| 3162 |
+
"step": 2575
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 8.11,
|
| 3166 |
+
"learning_rate": 0.00013290698875380075,
|
| 3167 |
+
"loss": 1.5204,
|
| 3168 |
+
"step": 2580
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 8.13,
|
| 3172 |
+
"learning_rate": 0.00013164912398990663,
|
| 3173 |
+
"loss": 1.196,
|
| 3174 |
+
"step": 2585
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 8.14,
|
| 3178 |
+
"learning_rate": 0.00013023745216860123,
|
| 3179 |
+
"loss": 1.5108,
|
| 3180 |
+
"step": 2590
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 8.16,
|
| 3184 |
+
"learning_rate": 0.00012867541703462073,
|
| 3185 |
+
"loss": 1.414,
|
| 3186 |
+
"step": 2595
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 8.18,
|
| 3190 |
+
"learning_rate": 0.00012696682914094848,
|
| 3191 |
+
"loss": 1.299,
|
| 3192 |
+
"step": 2600
|
| 3193 |
+
},
|
| 3194 |
+
{
|
| 3195 |
+
"epoch": 8.19,
|
| 3196 |
+
"learning_rate": 0.00012511585655304892,
|
| 3197 |
+
"loss": 1.5168,
|
| 3198 |
+
"step": 2605
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 8.21,
|
| 3202 |
+
"learning_rate": 0.00012312701468095605,
|
| 3203 |
+
"loss": 1.4117,
|
| 3204 |
+
"step": 2610
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 8.22,
|
| 3208 |
+
"learning_rate": 0.0001210051552640223,
|
| 3209 |
+
"loss": 1.4762,
|
| 3210 |
+
"step": 2615
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 8.24,
|
| 3214 |
+
"learning_rate": 0.00011875545453519897,
|
| 3215 |
+
"loss": 1.3127,
|
| 3216 |
+
"step": 2620
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 8.25,
|
| 3220 |
+
"learning_rate": 0.00011638340059372173,
|
| 3221 |
+
"loss": 1.5447,
|
| 3222 |
+
"step": 2625
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 8.27,
|
| 3226 |
+
"learning_rate": 0.00011389478001700295,
|
| 3227 |
+
"loss": 1.3891,
|
| 3228 |
+
"step": 2630
|
| 3229 |
+
},
|
| 3230 |
+
{
|
| 3231 |
+
"epoch": 8.29,
|
| 3232 |
+
"learning_rate": 0.00011129566374439389,
|
| 3233 |
+
"loss": 1.7022,
|
| 3234 |
+
"step": 2635
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 8.3,
|
| 3238 |
+
"learning_rate": 0.00010859239226725287,
|
| 3239 |
+
"loss": 1.2989,
|
| 3240 |
+
"step": 2640
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"epoch": 8.32,
|
| 3244 |
+
"learning_rate": 0.00010579156016144313,
|
| 3245 |
+
"loss": 1.4672,
|
| 3246 |
+
"step": 2645
|
| 3247 |
+
},
|
| 3248 |
+
{
|
| 3249 |
+
"epoch": 8.33,
|
| 3250 |
+
"learning_rate": 0.00010289999999999993,
|
| 3251 |
+
"loss": 1.4019,
|
| 3252 |
+
"step": 2650
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 8.35,
|
| 3256 |
+
"learning_rate": 9.992476568520875e-05,
|
| 3257 |
+
"loss": 1.3174,
|
| 3258 |
+
"step": 2655
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 8.36,
|
| 3262 |
+
"learning_rate": 9.687311524075153e-05,
|
| 3263 |
+
"loss": 1.4993,
|
| 3264 |
+
"step": 2660
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 8.38,
|
| 3268 |
+
"learning_rate": 9.375249310590639e-05,
|
| 3269 |
+
"loss": 1.4268,
|
| 3270 |
+
"step": 2665
|
| 3271 |
+
},
|
| 3272 |
+
{
|
| 3273 |
+
"epoch": 8.4,
|
| 3274 |
+
"learning_rate": 9.057051197499064e-05,
|
| 3275 |
+
"loss": 1.3762,
|
| 3276 |
+
"step": 2670
|
| 3277 |
+
},
|
| 3278 |
+
{
|
| 3279 |
+
"epoch": 8.41,
|
| 3280 |
+
"learning_rate": 8.733493422634493e-05,
|
| 3281 |
+
"loss": 1.6376,
|
| 3282 |
+
"step": 2675
|
| 3283 |
+
},
|
| 3284 |
+
{
|
| 3285 |
+
"epoch": 8.43,
|
| 3286 |
+
"learning_rate": 8.405365298617051e-05,
|
| 3287 |
+
"loss": 1.3535,
|
| 3288 |
+
"step": 2680
|
| 3289 |
+
},
|
| 3290 |
+
{
|
| 3291 |
+
"epoch": 8.44,
|
| 3292 |
+
"learning_rate": 8.073467287340865e-05,
|
| 3293 |
+
"loss": 1.4565,
|
| 3294 |
+
"step": 2685
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 8.46,
|
| 3298 |
+
"learning_rate": 7.738609047263366e-05,
|
| 3299 |
+
"loss": 1.4825,
|
| 3300 |
+
"step": 2690
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 8.47,
|
| 3304 |
+
"learning_rate": 7.401607458260121e-05,
|
| 3305 |
+
"loss": 1.2098,
|
| 3306 |
+
"step": 2695
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 8.49,
|
| 3310 |
+
"learning_rate": 7.063284628862766e-05,
|
| 3311 |
+
"loss": 1.114,
|
| 3312 |
+
"step": 2700
|
| 3313 |
+
},
|
| 3314 |
+
{
|
| 3315 |
+
"epoch": 8.51,
|
| 3316 |
+
"learning_rate": 6.724465890742147e-05,
|
| 3317 |
+
"loss": 1.1928,
|
| 3318 |
+
"step": 2705
|
| 3319 |
+
},
|
| 3320 |
+
{
|
| 3321 |
+
"epoch": 8.52,
|
| 3322 |
+
"learning_rate": 6.385977785328291e-05,
|
| 3323 |
+
"loss": 1.2321,
|
| 3324 |
+
"step": 2710
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 8.54,
|
| 3328 |
+
"learning_rate": 6.048646047479429e-05,
|
| 3329 |
+
"loss": 1.4018,
|
| 3330 |
+
"step": 2715
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"epoch": 8.55,
|
| 3334 |
+
"learning_rate": 5.71329359111875e-05,
|
| 3335 |
+
"loss": 1.4829,
|
| 3336 |
+
"step": 2720
|
| 3337 |
+
},
|
| 3338 |
+
{
|
| 3339 |
+
"epoch": 8.57,
|
| 3340 |
+
"learning_rate": 5.3807385017523074e-05,
|
| 3341 |
+
"loss": 1.3501,
|
| 3342 |
+
"step": 2725
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 8.58,
|
| 3346 |
+
"learning_rate": 5.051792040766187e-05,
|
| 3347 |
+
"loss": 1.344,
|
| 3348 |
+
"step": 2730
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 8.6,
|
| 3352 |
+
"learning_rate": 4.7272566663709795e-05,
|
| 3353 |
+
"loss": 1.0449,
|
| 3354 |
+
"step": 2735
|
| 3355 |
+
},
|
| 3356 |
+
{
|
| 3357 |
+
"epoch": 8.62,
|
| 3358 |
+
"learning_rate": 4.407924076020983e-05,
|
| 3359 |
+
"loss": 1.3851,
|
| 3360 |
+
"step": 2740
|
| 3361 |
+
},
|
| 3362 |
+
{
|
| 3363 |
+
"epoch": 8.63,
|
| 3364 |
+
"learning_rate": 4.0945732750844954e-05,
|
| 3365 |
+
"loss": 1.3359,
|
| 3366 |
+
"step": 2745
|
| 3367 |
+
},
|
| 3368 |
+
{
|
| 3369 |
+
"epoch": 8.65,
|
| 3370 |
+
"learning_rate": 3.787968676476165e-05,
|
| 3371 |
+
"loss": 1.2086,
|
| 3372 |
+
"step": 2750
|
| 3373 |
+
},
|
| 3374 |
+
{
|
| 3375 |
+
"epoch": 8.66,
|
| 3376 |
+
"learning_rate": 3.488858235886944e-05,
|
| 3377 |
+
"loss": 1.2969,
|
| 3378 |
+
"step": 2755
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 8.68,
|
| 3382 |
+
"learning_rate": 3.1979716271615364e-05,
|
| 3383 |
+
"loss": 1.1869,
|
| 3384 |
+
"step": 2760
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 8.69,
|
| 3388 |
+
"learning_rate": 2.916018462273902e-05,
|
| 3389 |
+
"loss": 1.4603,
|
| 3390 |
+
"step": 2765
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 8.71,
|
| 3394 |
+
"learning_rate": 2.643686560243124e-05,
|
| 3395 |
+
"loss": 1.2891,
|
| 3396 |
+
"step": 2770
|
| 3397 |
+
},
|
| 3398 |
+
{
|
| 3399 |
+
"epoch": 8.73,
|
| 3400 |
+
"learning_rate": 2.3816402692130164e-05,
|
| 3401 |
+
"loss": 1.4753,
|
| 3402 |
+
"step": 2775
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"epoch": 8.74,
|
| 3406 |
+
"learning_rate": 2.1305188457882628e-05,
|
| 3407 |
+
"loss": 1.4468,
|
| 3408 |
+
"step": 2780
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 8.76,
|
| 3412 |
+
"learning_rate": 1.890934895580877e-05,
|
| 3413 |
+
"loss": 1.2143,
|
| 3414 |
+
"step": 2785
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 8.77,
|
| 3418 |
+
"learning_rate": 1.6634728787713087e-05,
|
| 3419 |
+
"loss": 1.4829,
|
| 3420 |
+
"step": 2790
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 8.79,
|
| 3424 |
+
"learning_rate": 1.4486876843296578e-05,
|
| 3425 |
+
"loss": 1.5124,
|
| 3426 |
+
"step": 2795
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 8.81,
|
| 3430 |
+
"learning_rate": 1.247103276375423e-05,
|
| 3431 |
+
"loss": 1.1507,
|
| 3432 |
+
"step": 2800
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 8.82,
|
| 3436 |
+
"learning_rate": 1.0592114159774876e-05,
|
| 3437 |
+
"loss": 1.2259,
|
| 3438 |
+
"step": 2805
|
| 3439 |
+
},
|
| 3440 |
+
{
|
| 3441 |
+
"epoch": 8.84,
|
| 3442 |
+
"learning_rate": 8.854704615130826e-06,
|
| 3443 |
+
"loss": 1.3434,
|
| 3444 |
+
"step": 2810
|
| 3445 |
+
},
|
| 3446 |
+
{
|
| 3447 |
+
"epoch": 8.85,
|
| 3448 |
+
"learning_rate": 7.263042505119003e-06,
|
| 3449 |
+
"loss": 1.4906,
|
| 3450 |
+
"step": 2815
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 8.87,
|
| 3454 |
+
"learning_rate": 5.82101065712901e-06,
|
| 3455 |
+
"loss": 1.2034,
|
| 3456 |
+
"step": 2820
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 8.88,
|
| 3460 |
+
"learning_rate": 4.532126878565386e-06,
|
| 3461 |
+
"loss": 1.3118,
|
| 3462 |
+
"step": 2825
|
| 3463 |
+
},
|
| 3464 |
+
{
|
| 3465 |
+
"epoch": 8.9,
|
| 3466 |
+
"learning_rate": 3.3995353752283744e-06,
|
| 3467 |
+
"loss": 1.4476,
|
| 3468 |
+
"step": 2830
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 8.92,
|
| 3472 |
+
"learning_rate": 2.4259990810866283e-06,
|
| 3473 |
+
"loss": 1.5325,
|
| 3474 |
+
"step": 2835
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 8.93,
|
| 3478 |
+
"learning_rate": 1.6138929181565955e-06,
|
| 3479 |
+
"loss": 1.3443,
|
| 3480 |
+
"step": 2840
|
| 3481 |
+
},
|
| 3482 |
+
{
|
| 3483 |
+
"epoch": 8.95,
|
| 3484 |
+
"learning_rate": 9.651980029285464e-07,
|
| 3485 |
+
"loss": 1.665,
|
| 3486 |
+
"step": 2845
|
| 3487 |
+
},
|
| 3488 |
+
{
|
| 3489 |
+
"epoch": 8.96,
|
| 3490 |
+
"learning_rate": 4.814968134727699e-07,
|
| 3491 |
+
"loss": 1.3313,
|
| 3492 |
+
"step": 2850
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"epoch": 8.98,
|
| 3496 |
+
"learning_rate": 1.6396932901667525e-07,
|
| 3497 |
+
"loss": 1.504,
|
| 3498 |
+
"step": 2855
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 8.99,
|
| 3502 |
+
"learning_rate": 1.339015140952895e-08,
|
| 3503 |
+
"loss": 1.2679,
|
| 3504 |
+
"step": 2860
|
| 3505 |
+
},
|
| 3506 |
+
{
|
| 3507 |
+
"epoch": 9.0,
|
| 3508 |
+
"eval_loss": 1.7906934022903442,
|
| 3509 |
+
"eval_runtime": 20.4159,
|
| 3510 |
+
"eval_samples_per_second": 21.993,
|
| 3511 |
+
"eval_steps_per_second": 2.792,
|
| 3512 |
+
"step": 2862
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 9.01,
|
| 3516 |
+
"learning_rate": 3.01266154967001e-08,
|
| 3517 |
+
"loss": 1.4496,
|
| 3518 |
+
"step": 2865
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 9.03,
|
| 3522 |
+
"learning_rate": 2.1413789301401304e-07,
|
| 3523 |
+
"loss": 1.2338,
|
| 3524 |
+
"step": 2870
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 9.04,
|
| 3528 |
+
"learning_rate": 5.649750921872831e-07,
|
| 3529 |
+
"loss": 1.1185,
|
| 3530 |
+
"step": 2875
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 9.06,
|
| 3534 |
+
"learning_rate": 1.0817823527948346e-06,
|
| 3535 |
+
"loss": 1.0349,
|
| 3536 |
+
"step": 2880
|
| 3537 |
+
},
|
| 3538 |
+
{
|
| 3539 |
+
"epoch": 9.07,
|
| 3540 |
+
"learning_rate": 1.7632989340210505e-06,
|
| 3541 |
+
"loss": 1.1285,
|
| 3542 |
+
"step": 2885
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 9.09,
|
| 3546 |
+
"learning_rate": 2.6078622900081364e-06,
|
| 3547 |
+
"loss": 1.1348,
|
| 3548 |
+
"step": 2890
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 9.1,
|
| 3552 |
+
"learning_rate": 3.613412125602455e-06,
|
| 3553 |
+
"loss": 1.0489,
|
| 3554 |
+
"step": 2895
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 9.12,
|
| 3558 |
+
"learning_rate": 4.777495422403447e-06,
|
| 3559 |
+
"loss": 1.1893,
|
| 3560 |
+
"step": 2900
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 9.14,
|
| 3564 |
+
"learning_rate": 6.0972724228519425e-06,
|
| 3565 |
+
"loss": 1.3905,
|
| 3566 |
+
"step": 2905
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 9.15,
|
| 3570 |
+
"learning_rate": 7.569523557760349e-06,
|
| 3571 |
+
"loss": 1.2451,
|
| 3572 |
+
"step": 2910
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 9.17,
|
| 3576 |
+
"learning_rate": 9.190657300387452e-06,
|
| 3577 |
+
"loss": 1.2443,
|
| 3578 |
+
"step": 2915
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 9.18,
|
| 3582 |
+
"learning_rate": 1.0956718927894355e-05,
|
| 3583 |
+
"loss": 1.2626,
|
| 3584 |
+
"step": 2920
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"epoch": 9.2,
|
| 3588 |
+
"learning_rate": 1.2863400168810178e-05,
|
| 3589 |
+
"loss": 1.0339,
|
| 3590 |
+
"step": 2925
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 9.21,
|
| 3594 |
+
"learning_rate": 1.4906049712973553e-05,
|
| 3595 |
+
"loss": 1.1284,
|
| 3596 |
+
"step": 2930
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 9.23,
|
| 3600 |
+
"learning_rate": 1.7079684558309144e-05,
|
| 3601 |
+
"loss": 1.2964,
|
| 3602 |
+
"step": 2935
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 9.25,
|
| 3606 |
+
"learning_rate": 1.9379002166758836e-05,
|
| 3607 |
+
"loss": 0.9701,
|
| 3608 |
+
"step": 2940
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 9.26,
|
| 3612 |
+
"learning_rate": 2.1798393399717496e-05,
|
| 3613 |
+
"loss": 1.2379,
|
| 3614 |
+
"step": 2945
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 9.28,
|
| 3618 |
+
"learning_rate": 2.4331956201411865e-05,
|
| 3619 |
+
"loss": 1.2294,
|
| 3620 |
+
"step": 2950
|
| 3621 |
+
},
|
| 3622 |
+
{
|
| 3623 |
+
"epoch": 9.29,
|
| 3624 |
+
"learning_rate": 2.69735099968445e-05,
|
| 3625 |
+
"loss": 1.2279,
|
| 3626 |
+
"step": 2955
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 9.31,
|
| 3630 |
+
"learning_rate": 2.9716610769183196e-05,
|
| 3631 |
+
"loss": 1.1694,
|
| 3632 |
+
"step": 2960
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 9.32,
|
| 3636 |
+
"learning_rate": 3.255456677980771e-05,
|
| 3637 |
+
"loss": 1.3376,
|
| 3638 |
+
"step": 2965
|
| 3639 |
+
},
|
| 3640 |
+
{
|
| 3641 |
+
"epoch": 9.34,
|
| 3642 |
+
"learning_rate": 3.548045489267097e-05,
|
| 3643 |
+
"loss": 1.1979,
|
| 3644 |
+
"step": 2970
|
| 3645 |
+
},
|
| 3646 |
+
{
|
| 3647 |
+
"epoch": 9.36,
|
| 3648 |
+
"learning_rate": 3.848713746314718e-05,
|
| 3649 |
+
"loss": 1.0518,
|
| 3650 |
+
"step": 2975
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 9.37,
|
| 3654 |
+
"learning_rate": 4.1567279750173456e-05,
|
| 3655 |
+
"loss": 1.1192,
|
| 3656 |
+
"step": 2980
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 9.39,
|
| 3660 |
+
"learning_rate": 4.471336780920016e-05,
|
| 3661 |
+
"loss": 1.258,
|
| 3662 |
+
"step": 2985
|
| 3663 |
+
},
|
| 3664 |
+
{
|
| 3665 |
+
"epoch": 9.4,
|
| 3666 |
+
"learning_rate": 4.791772682230585e-05,
|
| 3667 |
+
"loss": 1.1698,
|
| 3668 |
+
"step": 2990
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"epoch": 9.42,
|
| 3672 |
+
"learning_rate": 5.1172539820760084e-05,
|
| 3673 |
+
"loss": 1.2648,
|
| 3674 |
+
"step": 2995
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 9.43,
|
| 3678 |
+
"learning_rate": 5.4469866754360636e-05,
|
| 3679 |
+
"loss": 1.1929,
|
| 3680 |
+
"step": 3000
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 9.45,
|
| 3684 |
+
"learning_rate": 5.7801663861022995e-05,
|
| 3685 |
+
"loss": 1.1723,
|
| 3686 |
+
"step": 3005
|
| 3687 |
+
},
|
| 3688 |
+
{
|
| 3689 |
+
"epoch": 9.47,
|
| 3690 |
+
"learning_rate": 6.115980328937633e-05,
|
| 3691 |
+
"loss": 1.225,
|
| 3692 |
+
"step": 3010
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 9.48,
|
| 3696 |
+
"learning_rate": 6.453609292649126e-05,
|
| 3697 |
+
"loss": 1.281,
|
| 3698 |
+
"step": 3015
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 9.5,
|
| 3702 |
+
"learning_rate": 6.792229638237138e-05,
|
| 3703 |
+
"loss": 1.1719,
|
| 3704 |
+
"step": 3020
|
| 3705 |
+
},
|
| 3706 |
+
{
|
| 3707 |
+
"epoch": 9.51,
|
| 3708 |
+
"learning_rate": 7.131015308246217e-05,
|
| 3709 |
+
"loss": 1.3758,
|
| 3710 |
+
"step": 3025
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"epoch": 9.53,
|
| 3714 |
+
"learning_rate": 7.469139841915347e-05,
|
| 3715 |
+
"loss": 1.3241,
|
| 3716 |
+
"step": 3030
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 9.54,
|
| 3720 |
+
"learning_rate": 7.805778391312036e-05,
|
| 3721 |
+
"loss": 1.1407,
|
| 3722 |
+
"step": 3035
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 9.56,
|
| 3726 |
+
"learning_rate": 8.140109733532393e-05,
|
| 3727 |
+
"loss": 1.2411,
|
| 3728 |
+
"step": 3040
|
| 3729 |
+
},
|
| 3730 |
+
{
|
| 3731 |
+
"epoch": 9.58,
|
| 3732 |
+
"learning_rate": 8.471318274057568e-05,
|
| 3733 |
+
"loss": 1.413,
|
| 3734 |
+
"step": 3045
|
| 3735 |
+
},
|
| 3736 |
+
{
|
| 3737 |
+
"epoch": 9.59,
|
| 3738 |
+
"learning_rate": 8.798596036379883e-05,
|
| 3739 |
+
"loss": 1.222,
|
| 3740 |
+
"step": 3050
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 9.61,
|
| 3744 |
+
"learning_rate": 9.121144633045388e-05,
|
| 3745 |
+
"loss": 1.3584,
|
| 3746 |
+
"step": 3055
|
| 3747 |
+
},
|
| 3748 |
+
{
|
| 3749 |
+
"epoch": 9.62,
|
| 3750 |
+
"learning_rate": 9.438177213303655e-05,
|
| 3751 |
+
"loss": 1.1437,
|
| 3752 |
+
"step": 3060
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"epoch": 9.64,
|
| 3756 |
+
"learning_rate": 9.74892038261427e-05,
|
| 3757 |
+
"loss": 1.2668,
|
| 3758 |
+
"step": 3065
|
| 3759 |
+
},
|
| 3760 |
+
{
|
| 3761 |
+
"epoch": 9.65,
|
| 3762 |
+
"learning_rate": 0.00010052616089327018,
|
| 3763 |
+
"loss": 1.3637,
|
| 3764 |
+
"step": 3070
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 9.67,
|
| 3768 |
+
"learning_rate": 0.00010348523473933642,
|
| 3769 |
+
"loss": 1.1909,
|
| 3770 |
+
"step": 3075
|
| 3771 |
+
},
|
| 3772 |
+
{
|
| 3773 |
+
"epoch": 9.69,
|
| 3774 |
+
"learning_rate": 0.0001063592067637941,
|
| 3775 |
+
"loss": 1.3763,
|
| 3776 |
+
"step": 3080
|
| 3777 |
+
},
|
| 3778 |
+
{
|
| 3779 |
+
"epoch": 9.7,
|
| 3780 |
+
"learning_rate": 0.00010914106597026132,
|
| 3781 |
+
"loss": 1.4548,
|
| 3782 |
+
"step": 3085
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 9.72,
|
| 3786 |
+
"learning_rate": 0.00011182402606970514,
|
| 3787 |
+
"loss": 1.3378,
|
| 3788 |
+
"step": 3090
|
| 3789 |
+
},
|
| 3790 |
+
{
|
| 3791 |
+
"epoch": 9.73,
|
| 3792 |
+
"learning_rate": 0.00011440154203545576,
|
| 3793 |
+
"loss": 1.3677,
|
| 3794 |
+
"step": 3095
|
| 3795 |
+
},
|
| 3796 |
+
{
|
| 3797 |
+
"epoch": 9.75,
|
| 3798 |
+
"learning_rate": 0.00011686732606966472,
|
| 3799 |
+
"loss": 1.2485,
|
| 3800 |
+
"step": 3100
|
| 3801 |
+
},
|
| 3802 |
+
{
|
| 3803 |
+
"epoch": 9.76,
|
| 3804 |
+
"learning_rate": 0.00011921536294226233,
|
| 3805 |
+
"loss": 1.3363,
|
| 3806 |
+
"step": 3105
|
| 3807 |
+
},
|
| 3808 |
+
{
|
| 3809 |
+
"epoch": 9.78,
|
| 3810 |
+
"learning_rate": 0.00012143992466498816,
|
| 3811 |
+
"loss": 1.1575,
|
| 3812 |
+
"step": 3110
|
| 3813 |
+
},
|
| 3814 |
+
{
|
| 3815 |
+
"epoch": 9.8,
|
| 3816 |
+
"learning_rate": 0.00012353558446470098,
|
| 3817 |
+
"loss": 1.1208,
|
| 3818 |
+
"step": 3115
|
| 3819 |
+
},
|
| 3820 |
+
{
|
| 3821 |
+
"epoch": 9.81,
|
| 3822 |
+
"learning_rate": 0.00012549723002188375,
|
| 3823 |
+
"loss": 1.4087,
|
| 3824 |
+
"step": 3120
|
| 3825 |
+
},
|
| 3826 |
+
{
|
| 3827 |
+
"epoch": 9.83,
|
| 3828 |
+
"learning_rate": 0.00012732007594204206,
|
| 3829 |
+
"loss": 1.3399,
|
| 3830 |
+
"step": 3125
|
| 3831 |
+
},
|
| 3832 |
+
{
|
| 3833 |
+
"epoch": 9.84,
|
| 3834 |
+
"learning_rate": 0.00012899967542957612,
|
| 3835 |
+
"loss": 1.4988,
|
| 3836 |
+
"step": 3130
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"epoch": 9.86,
|
| 3840 |
+
"learning_rate": 0.00013053193113564998,
|
| 3841 |
+
"loss": 0.989,
|
| 3842 |
+
"step": 3135
|
| 3843 |
+
},
|
| 3844 |
+
{
|
| 3845 |
+
"epoch": 9.87,
|
| 3846 |
+
"learning_rate": 0.00013191310515358958,
|
| 3847 |
+
"loss": 1.349,
|
| 3848 |
+
"step": 3140
|
| 3849 |
+
},
|
| 3850 |
+
{
|
| 3851 |
+
"epoch": 9.89,
|
| 3852 |
+
"learning_rate": 0.00013313982813743067,
|
| 3853 |
+
"loss": 1.1874,
|
| 3854 |
+
"step": 3145
|
| 3855 |
+
},
|
| 3856 |
+
{
|
| 3857 |
+
"epoch": 9.91,
|
| 3858 |
+
"learning_rate": 0.00013420910752136937,
|
| 3859 |
+
"loss": 1.2978,
|
| 3860 |
+
"step": 3150
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"epoch": 9.92,
|
| 3864 |
+
"learning_rate": 0.00013511833482006638,
|
| 3865 |
+
"loss": 1.5572,
|
| 3866 |
+
"step": 3155
|
| 3867 |
+
},
|
| 3868 |
+
{
|
| 3869 |
+
"epoch": 9.94,
|
| 3870 |
+
"learning_rate": 0.00013586529199199334,
|
| 3871 |
+
"loss": 1.3689,
|
| 3872 |
+
"step": 3160
|
| 3873 |
+
},
|
| 3874 |
+
{
|
| 3875 |
+
"epoch": 9.95,
|
| 3876 |
+
"learning_rate": 0.00013644815685030044,
|
| 3877 |
+
"loss": 1.1297,
|
| 3878 |
+
"step": 3165
|
| 3879 |
+
},
|
| 3880 |
+
{
|
| 3881 |
+
"epoch": 9.97,
|
| 3882 |
+
"learning_rate": 0.00013686550750800414,
|
| 3883 |
+
"loss": 1.3856,
|
| 3884 |
+
"step": 3170
|
| 3885 |
+
},
|
| 3886 |
+
{
|
| 3887 |
+
"epoch": 9.98,
|
| 3888 |
+
"learning_rate": 0.00013711632584665164,
|
| 3889 |
+
"loss": 1.2732,
|
| 3890 |
+
"step": 3175
|
| 3891 |
+
},
|
| 3892 |
+
{
|
| 3893 |
+
"epoch": 10.0,
|
| 3894 |
+
"learning_rate": 0.0001372,
|
| 3895 |
+
"loss": 1.5975,
|
| 3896 |
+
"step": 3180
|
| 3897 |
+
},
|
| 3898 |
+
{
|
| 3899 |
+
"epoch": 10.0,
|
| 3900 |
+
"eval_loss": 1.7831153869628906,
|
| 3901 |
+
"eval_runtime": 20.3518,
|
| 3902 |
+
"eval_samples_per_second": 22.062,
|
| 3903 |
+
"eval_steps_per_second": 2.801,
|
| 3904 |
+
"step": 3180
|
| 3905 |
}
|
| 3906 |
],
|
| 3907 |
+
"max_steps": 3498,
|
| 3908 |
+
"num_train_epochs": 11,
|
| 3909 |
+
"total_flos": 3314620071936000.0,
|
| 3910 |
"trial_name": null,
|
| 3911 |
"trial_params": null
|
| 3912 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca4b64b447bcbc63fee889d7ebeafbf9eae6a003aa7f37b487c1df50308adc16
|
| 3 |
size 2863
|