Commit
·
d439efe
1
Parent(s):
cb31c93
huggingartists
Browse files- README.md +4 -4
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +5 -1
- tokenizer.json +0 -0
- tokenizer_config.json +10 -1
- trainer_state.json +1385 -7
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -14,7 +14,7 @@ widget:
|
|
| 14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 15 |
<div class="flex">
|
| 16 |
<div
|
| 17 |
-
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/
|
| 18 |
</div>
|
| 19 |
</div>
|
| 20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/madonna")
|
| 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 Madonna'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 |
|
|
|
|
| 14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 15 |
<div class="flex">
|
| 16 |
<div
|
| 17 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/676c1c425eaa8e7600136c56af6dfada.1000x1000x1.jpg')">
|
| 18 |
</div>
|
| 19 |
</div>
|
| 20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/madonna")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2abhif57/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 Madonna's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2eok9fmu) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2eok9fmu/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -37,7 +37,7 @@
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
-
"transformers_version": "4.
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
|
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.20.0",
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 1.
|
|
|
|
| 1 |
+
{"eval_loss": 1.1562458276748657, "eval_runtime": 2.2356, "eval_samples_per_second": 140.904, "eval_steps_per_second": 17.893, "epoch": 7.0}
|
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:b183f932b6e1b0f15eb8b249be6289dc2bba247f996bd190b20496df0370caea
|
| 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:ea3f7591a0adca3a3b98dc49de974b7d297f3f1539fe9164e7fe7c3495012346
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a820a71cbebdc8c969a77130a86384b35e8bcc137c87817368b069d5ec9e35fd
|
| 3 |
+
size 510396521
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d46dbf93ee6615ec3fae58d5cd6ee398ed5760083a374226895338bf2439d78
|
| 3 |
size 14503
|
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 sha256:8d21bbb47b7bf28ce88efd32118fc5bbd03f4e4f2ef87c2963fecf564d95c240
|
| 3 |
size 623
|
special_tokens_map.json
CHANGED
|
@@ -1 +1,5 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1,10 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "huggingartists/madonna",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/madonna/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -564,11 +564,1389 @@
|
|
| 564 |
"eval_samples_per_second": 17.282,
|
| 565 |
"eval_steps_per_second": 2.195,
|
| 566 |
"step": 448
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 567 |
}
|
| 568 |
],
|
| 569 |
-
"max_steps":
|
| 570 |
-
"num_train_epochs":
|
| 571 |
-
"total_flos":
|
| 572 |
"trial_name": null,
|
| 573 |
"trial_params": null
|
| 574 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1562458276748657,
|
| 3 |
+
"best_model_checkpoint": "output/madonna/checkpoint-1561",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"global_step": 1561,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 564 |
"eval_samples_per_second": 17.282,
|
| 565 |
"eval_steps_per_second": 2.195,
|
| 566 |
"step": 448
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.02,
|
| 570 |
+
"learning_rate": 0.00013709110969999672,
|
| 571 |
+
"loss": 1.6748,
|
| 572 |
+
"step": 450
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.04,
|
| 576 |
+
"learning_rate": 0.0001366493352528768,
|
| 577 |
+
"loss": 1.7921,
|
| 578 |
+
"step": 455
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.06,
|
| 582 |
+
"learning_rate": 0.00013587006036997336,
|
| 583 |
+
"loss": 1.6524,
|
| 584 |
+
"step": 460
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.09,
|
| 588 |
+
"learning_rate": 0.00013475714997680845,
|
| 589 |
+
"loss": 1.5413,
|
| 590 |
+
"step": 465
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.11,
|
| 594 |
+
"learning_rate": 0.00013331612371205717,
|
| 595 |
+
"loss": 1.5745,
|
| 596 |
+
"step": 470
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.13,
|
| 600 |
+
"learning_rate": 0.0001315541285521084,
|
| 601 |
+
"loss": 1.4608,
|
| 602 |
+
"step": 475
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.15,
|
| 606 |
+
"learning_rate": 0.0001294799033646105,
|
| 607 |
+
"loss": 1.637,
|
| 608 |
+
"step": 480
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.17,
|
| 612 |
+
"learning_rate": 0.00012710373556680405,
|
| 613 |
+
"loss": 1.5212,
|
| 614 |
+
"step": 485
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.2,
|
| 618 |
+
"learning_rate": 0.00012443741010360104,
|
| 619 |
+
"loss": 1.3742,
|
| 620 |
+
"step": 490
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.22,
|
| 624 |
+
"learning_rate": 0.00012149415099846082,
|
| 625 |
+
"loss": 1.5598,
|
| 626 |
+
"step": 495
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.24,
|
| 630 |
+
"learning_rate": 0.0001182885557669493,
|
| 631 |
+
"loss": 1.5528,
|
| 632 |
+
"step": 500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.26,
|
| 636 |
+
"learning_rate": 0.00011483652301826763,
|
| 637 |
+
"loss": 1.3306,
|
| 638 |
+
"step": 505
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.29,
|
| 642 |
+
"learning_rate": 0.00011115517360381999,
|
| 643 |
+
"loss": 1.6203,
|
| 644 |
+
"step": 510
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.31,
|
| 648 |
+
"learning_rate": 0.00010726276570389622,
|
| 649 |
+
"loss": 1.5496,
|
| 650 |
+
"step": 515
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.33,
|
| 654 |
+
"learning_rate": 0.00010317860427360839,
|
| 655 |
+
"loss": 1.5886,
|
| 656 |
+
"step": 520
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.35,
|
| 660 |
+
"learning_rate": 9.892294529719824e-05,
|
| 661 |
+
"loss": 1.5832,
|
| 662 |
+
"step": 525
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.38,
|
| 666 |
+
"learning_rate": 9.451689532557822e-05,
|
| 667 |
+
"loss": 1.374,
|
| 668 |
+
"step": 530
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.4,
|
| 672 |
+
"learning_rate": 8.998230679536645e-05,
|
| 673 |
+
"loss": 1.615,
|
| 674 |
+
"step": 535
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.42,
|
| 678 |
+
"learning_rate": 8.534166964859326e-05,
|
| 679 |
+
"loss": 1.2303,
|
| 680 |
+
"step": 540
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.44,
|
| 684 |
+
"learning_rate": 8.061799979060907e-05,
|
| 685 |
+
"loss": 1.5842,
|
| 686 |
+
"step": 545
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.47,
|
| 690 |
+
"learning_rate": 7.5834724939402e-05,
|
| 691 |
+
"loss": 1.6827,
|
| 692 |
+
"step": 550
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.49,
|
| 696 |
+
"learning_rate": 7.10155684324705e-05,
|
| 697 |
+
"loss": 1.3135,
|
| 698 |
+
"step": 555
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.51,
|
| 702 |
+
"learning_rate": 6.618443156752956e-05,
|
| 703 |
+
"loss": 1.2597,
|
| 704 |
+
"step": 560
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.53,
|
| 708 |
+
"learning_rate": 6.136527506059804e-05,
|
| 709 |
+
"loss": 1.3309,
|
| 710 |
+
"step": 565
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.56,
|
| 714 |
+
"learning_rate": 5.658200020939097e-05,
|
| 715 |
+
"loss": 1.3751,
|
| 716 |
+
"step": 570
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.58,
|
| 720 |
+
"learning_rate": 5.185833035140678e-05,
|
| 721 |
+
"loss": 1.4378,
|
| 722 |
+
"step": 575
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.6,
|
| 726 |
+
"learning_rate": 4.721769320463358e-05,
|
| 727 |
+
"loss": 1.3661,
|
| 728 |
+
"step": 580
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.62,
|
| 732 |
+
"learning_rate": 4.268310467442181e-05,
|
| 733 |
+
"loss": 1.4564,
|
| 734 |
+
"step": 585
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.65,
|
| 738 |
+
"learning_rate": 3.827705470280179e-05,
|
| 739 |
+
"loss": 1.2126,
|
| 740 |
+
"step": 590
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.67,
|
| 744 |
+
"learning_rate": 3.4021395726391656e-05,
|
| 745 |
+
"loss": 1.3859,
|
| 746 |
+
"step": 595
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.69,
|
| 750 |
+
"learning_rate": 2.9937234296103807e-05,
|
| 751 |
+
"loss": 1.4162,
|
| 752 |
+
"step": 600
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.71,
|
| 756 |
+
"learning_rate": 2.6044826396180043e-05,
|
| 757 |
+
"loss": 1.3521,
|
| 758 |
+
"step": 605
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.74,
|
| 762 |
+
"learning_rate": 2.236347698173244e-05,
|
| 763 |
+
"loss": 1.4423,
|
| 764 |
+
"step": 610
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.76,
|
| 768 |
+
"learning_rate": 1.8911444233050724e-05,
|
| 769 |
+
"loss": 1.2658,
|
| 770 |
+
"step": 615
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.78,
|
| 774 |
+
"learning_rate": 1.5705849001539244e-05,
|
| 775 |
+
"loss": 1.2766,
|
| 776 |
+
"step": 620
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.8,
|
| 780 |
+
"learning_rate": 1.2762589896399027e-05,
|
| 781 |
+
"loss": 1.2592,
|
| 782 |
+
"step": 625
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.83,
|
| 786 |
+
"learning_rate": 1.0096264433195999e-05,
|
| 787 |
+
"loss": 1.4557,
|
| 788 |
+
"step": 630
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.85,
|
| 792 |
+
"learning_rate": 7.72009663538956e-06,
|
| 793 |
+
"loss": 1.4331,
|
| 794 |
+
"step": 635
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.87,
|
| 798 |
+
"learning_rate": 5.6458714478916046e-06,
|
| 799 |
+
"loss": 1.5097,
|
| 800 |
+
"step": 640
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.89,
|
| 804 |
+
"learning_rate": 3.883876287942861e-06,
|
| 805 |
+
"loss": 1.474,
|
| 806 |
+
"step": 645
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.91,
|
| 810 |
+
"learning_rate": 2.4428500231915692e-06,
|
| 811 |
+
"loss": 1.4667,
|
| 812 |
+
"step": 650
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.94,
|
| 816 |
+
"learning_rate": 1.32993963002664e-06,
|
| 817 |
+
"loss": 1.3699,
|
| 818 |
+
"step": 655
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.96,
|
| 822 |
+
"learning_rate": 5.506647471231935e-07,
|
| 823 |
+
"loss": 1.4343,
|
| 824 |
+
"step": 660
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.98,
|
| 828 |
+
"learning_rate": 1.0889030000328246e-07,
|
| 829 |
+
"loss": 1.3816,
|
| 830 |
+
"step": 665
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.0,
|
| 834 |
+
"eval_loss": 1.3440579175949097,
|
| 835 |
+
"eval_runtime": 2.2108,
|
| 836 |
+
"eval_samples_per_second": 142.485,
|
| 837 |
+
"eval_steps_per_second": 18.093,
|
| 838 |
+
"step": 669
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.0,
|
| 842 |
+
"learning_rate": 6.807332383425125e-09,
|
| 843 |
+
"loss": 1.2189,
|
| 844 |
+
"step": 670
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 3.03,
|
| 848 |
+
"learning_rate": 2.4492213937922245e-07,
|
| 849 |
+
"loss": 1.2422,
|
| 850 |
+
"step": 675
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 3.05,
|
| 854 |
+
"learning_rate": 8.22053756462089e-07,
|
| 855 |
+
"loss": 1.3055,
|
| 856 |
+
"step": 680
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 3.07,
|
| 860 |
+
"learning_rate": 1.735339816622185e-06,
|
| 861 |
+
"loss": 1.4475,
|
| 862 |
+
"step": 685
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.09,
|
| 866 |
+
"learning_rate": 2.980250746687993e-06,
|
| 867 |
+
"loss": 1.2442,
|
| 868 |
+
"step": 690
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 3.12,
|
| 872 |
+
"learning_rate": 4.550612232394036e-06,
|
| 873 |
+
"loss": 1.4277,
|
| 874 |
+
"step": 695
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.14,
|
| 878 |
+
"learning_rate": 6.438635840777816e-06,
|
| 879 |
+
"loss": 1.3777,
|
| 880 |
+
"step": 700
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.16,
|
| 884 |
+
"learning_rate": 8.634957648029665e-06,
|
| 885 |
+
"loss": 1.3328,
|
| 886 |
+
"step": 705
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 3.18,
|
| 890 |
+
"learning_rate": 1.1128684681215911e-05,
|
| 891 |
+
"loss": 1.3339,
|
| 892 |
+
"step": 710
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.21,
|
| 896 |
+
"learning_rate": 1.3907448943539908e-05,
|
| 897 |
+
"loss": 1.2034,
|
| 898 |
+
"step": 715
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 3.23,
|
| 902 |
+
"learning_rate": 1.6957468755195406e-05,
|
| 903 |
+
"loss": 1.1218,
|
| 904 |
+
"step": 720
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.25,
|
| 908 |
+
"learning_rate": 2.0263617105584107e-05,
|
| 909 |
+
"loss": 1.2544,
|
| 910 |
+
"step": 725
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.27,
|
| 914 |
+
"learning_rate": 2.3809496677893602e-05,
|
| 915 |
+
"loss": 1.1479,
|
| 916 |
+
"step": 730
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.3,
|
| 920 |
+
"learning_rate": 2.757752117394104e-05,
|
| 921 |
+
"loss": 1.1837,
|
| 922 |
+
"step": 735
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 3.32,
|
| 926 |
+
"learning_rate": 3.1549002535941176e-05,
|
| 927 |
+
"loss": 1.3242,
|
| 928 |
+
"step": 740
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.34,
|
| 932 |
+
"learning_rate": 3.570424363260841e-05,
|
| 933 |
+
"loss": 1.1755,
|
| 934 |
+
"step": 745
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.36,
|
| 938 |
+
"learning_rate": 4.002263594990341e-05,
|
| 939 |
+
"loss": 1.2206,
|
| 940 |
+
"step": 750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.39,
|
| 944 |
+
"learning_rate": 4.448276180191424e-05,
|
| 945 |
+
"loss": 1.219,
|
| 946 |
+
"step": 755
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.41,
|
| 950 |
+
"learning_rate": 4.9062500554940324e-05,
|
| 951 |
+
"loss": 1.3741,
|
| 952 |
+
"step": 760
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.43,
|
| 956 |
+
"learning_rate": 5.373913833794688e-05,
|
| 957 |
+
"loss": 1.3206,
|
| 958 |
+
"step": 765
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 3.45,
|
| 962 |
+
"learning_rate": 5.848948069526606e-05,
|
| 963 |
+
"loss": 1.2842,
|
| 964 |
+
"step": 770
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 3.48,
|
| 968 |
+
"learning_rate": 6.32899676228247e-05,
|
| 969 |
+
"loss": 1.4653,
|
| 970 |
+
"step": 775
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 3.5,
|
| 974 |
+
"learning_rate": 6.811679041736369e-05,
|
| 975 |
+
"loss": 1.0829,
|
| 976 |
+
"step": 780
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.52,
|
| 980 |
+
"learning_rate": 7.294600975911534e-05,
|
| 981 |
+
"loss": 1.2317,
|
| 982 |
+
"step": 785
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.54,
|
| 986 |
+
"learning_rate": 7.775367444229201e-05,
|
| 987 |
+
"loss": 1.0955,
|
| 988 |
+
"step": 790
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 3.57,
|
| 992 |
+
"learning_rate": 8.251594016452641e-05,
|
| 993 |
+
"loss": 1.3158,
|
| 994 |
+
"step": 795
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.59,
|
| 998 |
+
"learning_rate": 8.720918778610773e-05,
|
| 999 |
+
"loss": 1.2593,
|
| 1000 |
+
"step": 800
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.61,
|
| 1004 |
+
"learning_rate": 9.181014047249159e-05,
|
| 1005 |
+
"loss": 1.1672,
|
| 1006 |
+
"step": 805
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.63,
|
| 1010 |
+
"learning_rate": 9.629597913909913e-05,
|
| 1011 |
+
"loss": 1.2407,
|
| 1012 |
+
"step": 810
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 3.65,
|
| 1016 |
+
"learning_rate": 0.0001006444556258389,
|
| 1017 |
+
"loss": 1.2637,
|
| 1018 |
+
"step": 815
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.68,
|
| 1022 |
+
"learning_rate": 0.00010483400304004644,
|
| 1023 |
+
"loss": 1.4097,
|
| 1024 |
+
"step": 820
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.7,
|
| 1028 |
+
"learning_rate": 0.00010884384272058186,
|
| 1029 |
+
"loss": 1.3197,
|
| 1030 |
+
"step": 825
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.72,
|
| 1034 |
+
"learning_rate": 0.00011265408729257823,
|
| 1035 |
+
"loss": 1.0697,
|
| 1036 |
+
"step": 830
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.74,
|
| 1040 |
+
"learning_rate": 0.00011624583930172985,
|
| 1041 |
+
"loss": 1.079,
|
| 1042 |
+
"step": 835
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.77,
|
| 1046 |
+
"learning_rate": 0.00011960128493892567,
|
| 1047 |
+
"loss": 1.2747,
|
| 1048 |
+
"step": 840
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 3.79,
|
| 1052 |
+
"learning_rate": 0.0001227037823903907,
|
| 1053 |
+
"loss": 1.3586,
|
| 1054 |
+
"step": 845
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 3.81,
|
| 1058 |
+
"learning_rate": 0.000125537944375147,
|
| 1059 |
+
"loss": 1.3766,
|
| 1060 |
+
"step": 850
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 3.83,
|
| 1064 |
+
"learning_rate": 0.00012808971446044075,
|
| 1065 |
+
"loss": 1.2691,
|
| 1066 |
+
"step": 855
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.86,
|
| 1070 |
+
"learning_rate": 0.00013034643677663536,
|
| 1071 |
+
"loss": 1.1551,
|
| 1072 |
+
"step": 860
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.88,
|
| 1076 |
+
"learning_rate": 0.00013229691878581222,
|
| 1077 |
+
"loss": 1.3372,
|
| 1078 |
+
"step": 865
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.9,
|
| 1082 |
+
"learning_rate": 0.00013393148679276723,
|
| 1083 |
+
"loss": 1.2608,
|
| 1084 |
+
"step": 870
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 3.92,
|
| 1088 |
+
"learning_rate": 0.00013524203392308896,
|
| 1089 |
+
"loss": 1.1078,
|
| 1090 |
+
"step": 875
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.95,
|
| 1094 |
+
"learning_rate": 0.00013622206033036527,
|
| 1095 |
+
"loss": 1.0532,
|
| 1096 |
+
"step": 880
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 3.97,
|
| 1100 |
+
"learning_rate": 0.00013686670543310324,
|
| 1101 |
+
"loss": 1.1992,
|
| 1102 |
+
"step": 885
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 3.99,
|
| 1106 |
+
"learning_rate": 0.00013717277202148013,
|
| 1107 |
+
"loss": 1.1418,
|
| 1108 |
+
"step": 890
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 4.0,
|
| 1112 |
+
"eval_loss": 1.3141199350357056,
|
| 1113 |
+
"eval_runtime": 2.2159,
|
| 1114 |
+
"eval_samples_per_second": 142.153,
|
| 1115 |
+
"eval_steps_per_second": 18.051,
|
| 1116 |
+
"step": 892
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.01,
|
| 1120 |
+
"learning_rate": 0.000137138742114364,
|
| 1121 |
+
"loss": 1.0312,
|
| 1122 |
+
"step": 895
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.04,
|
| 1126 |
+
"learning_rate": 0.00013676478448795875,
|
| 1127 |
+
"loss": 1.0096,
|
| 1128 |
+
"step": 900
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.06,
|
| 1132 |
+
"learning_rate": 0.00013605275383873428,
|
| 1133 |
+
"loss": 1.1906,
|
| 1134 |
+
"step": 905
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.08,
|
| 1138 |
+
"learning_rate": 0.00013500618158479363,
|
| 1139 |
+
"loss": 1.1664,
|
| 1140 |
+
"step": 910
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.1,
|
| 1144 |
+
"learning_rate": 0.00013363025835129812,
|
| 1145 |
+
"loss": 1.0422,
|
| 1146 |
+
"step": 915
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.13,
|
| 1150 |
+
"learning_rate": 0.00013193180822681808,
|
| 1151 |
+
"loss": 1.0758,
|
| 1152 |
+
"step": 920
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.15,
|
| 1156 |
+
"learning_rate": 0.0001299192549182867,
|
| 1157 |
+
"loss": 1.3852,
|
| 1158 |
+
"step": 925
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.17,
|
| 1162 |
+
"learning_rate": 0.0001276025799724176,
|
| 1163 |
+
"loss": 1.2089,
|
| 1164 |
+
"step": 930
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.19,
|
| 1168 |
+
"learning_rate": 0.00012499327327079299,
|
| 1169 |
+
"loss": 1.1252,
|
| 1170 |
+
"step": 935
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 4.22,
|
| 1174 |
+
"learning_rate": 0.00012210427604414836,
|
| 1175 |
+
"loss": 1.2521,
|
| 1176 |
+
"step": 940
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 4.24,
|
| 1180 |
+
"learning_rate": 0.00011894991668848237,
|
| 1181 |
+
"loss": 1.2428,
|
| 1182 |
+
"step": 945
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 4.26,
|
| 1186 |
+
"learning_rate": 0.00011554583970132328,
|
| 1187 |
+
"loss": 1.1082,
|
| 1188 |
+
"step": 950
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 4.28,
|
| 1192 |
+
"learning_rate": 0.00011190892809059987,
|
| 1193 |
+
"loss": 1.0971,
|
| 1194 |
+
"step": 955
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 4.3,
|
| 1198 |
+
"learning_rate": 0.00010805721964094202,
|
| 1199 |
+
"loss": 1.0657,
|
| 1200 |
+
"step": 960
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.33,
|
| 1204 |
+
"learning_rate": 0.00010400981745270263,
|
| 1205 |
+
"loss": 1.0439,
|
| 1206 |
+
"step": 965
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.35,
|
| 1210 |
+
"learning_rate": 9.978679519739164e-05,
|
| 1211 |
+
"loss": 1.1785,
|
| 1212 |
+
"step": 970
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 4.37,
|
| 1216 |
+
"learning_rate": 9.540909755942318e-05,
|
| 1217 |
+
"loss": 1.1708,
|
| 1218 |
+
"step": 975
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 4.39,
|
| 1222 |
+
"learning_rate": 9.089843635795119e-05,
|
| 1223 |
+
"loss": 1.0215,
|
| 1224 |
+
"step": 980
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 4.42,
|
| 1228 |
+
"learning_rate": 8.627718286398852e-05,
|
| 1229 |
+
"loss": 1.1393,
|
| 1230 |
+
"step": 985
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 4.44,
|
| 1234 |
+
"learning_rate": 8.156825684687972e-05,
|
| 1235 |
+
"loss": 1.0526,
|
| 1236 |
+
"step": 990
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 4.46,
|
| 1240 |
+
"learning_rate": 7.679501290041993e-05,
|
| 1241 |
+
"loss": 0.9887,
|
| 1242 |
+
"step": 995
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 4.48,
|
| 1246 |
+
"learning_rate": 7.198112461239741e-05,
|
| 1247 |
+
"loss": 0.8743,
|
| 1248 |
+
"step": 1000
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.51,
|
| 1252 |
+
"learning_rate": 6.715046715204013e-05,
|
| 1253 |
+
"loss": 0.9096,
|
| 1254 |
+
"step": 1005
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 4.53,
|
| 1258 |
+
"learning_rate": 6.232699885769075e-05,
|
| 1259 |
+
"loss": 1.2684,
|
| 1260 |
+
"step": 1010
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.55,
|
| 1264 |
+
"learning_rate": 5.753464241199265e-05,
|
| 1265 |
+
"loss": 1.0412,
|
| 1266 |
+
"step": 1015
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.57,
|
| 1270 |
+
"learning_rate": 5.279716619391422e-05,
|
| 1271 |
+
"loss": 0.9954,
|
| 1272 |
+
"step": 1020
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 4.6,
|
| 1276 |
+
"learning_rate": 4.813806639606615e-05,
|
| 1277 |
+
"loss": 0.8753,
|
| 1278 |
+
"step": 1025
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 4.62,
|
| 1282 |
+
"learning_rate": 4.358045049196426e-05,
|
| 1283 |
+
"loss": 0.8638,
|
| 1284 |
+
"step": 1030
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 4.64,
|
| 1288 |
+
"learning_rate": 3.9146922631201556e-05,
|
| 1289 |
+
"loss": 1.0574,
|
| 1290 |
+
"step": 1035
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.66,
|
| 1294 |
+
"learning_rate": 3.485947153092735e-05,
|
| 1295 |
+
"loss": 0.8752,
|
| 1296 |
+
"step": 1040
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 4.69,
|
| 1300 |
+
"learning_rate": 3.073936141965131e-05,
|
| 1301 |
+
"loss": 1.0359,
|
| 1302 |
+
"step": 1045
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.71,
|
| 1306 |
+
"learning_rate": 2.680702657425298e-05,
|
| 1307 |
+
"loss": 1.0701,
|
| 1308 |
+
"step": 1050
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 4.73,
|
| 1312 |
+
"learning_rate": 2.3081969973255665e-05,
|
| 1313 |
+
"loss": 0.9777,
|
| 1314 |
+
"step": 1055
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 4.75,
|
| 1318 |
+
"learning_rate": 1.9582666569008116e-05,
|
| 1319 |
+
"loss": 0.9861,
|
| 1320 |
+
"step": 1060
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 4.78,
|
| 1324 |
+
"learning_rate": 1.632647165850912e-05,
|
| 1325 |
+
"loss": 1.0365,
|
| 1326 |
+
"step": 1065
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 4.8,
|
| 1330 |
+
"learning_rate": 1.3329534807322873e-05,
|
| 1331 |
+
"loss": 0.9034,
|
| 1332 |
+
"step": 1070
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.82,
|
| 1336 |
+
"learning_rate": 1.0606719753493918e-05,
|
| 1337 |
+
"loss": 1.0476,
|
| 1338 |
+
"step": 1075
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 4.84,
|
| 1342 |
+
"learning_rate": 8.171530688706377e-06,
|
| 1343 |
+
"loss": 1.0288,
|
| 1344 |
+
"step": 1080
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.87,
|
| 1348 |
+
"learning_rate": 6.036045282308682e-06,
|
| 1349 |
+
"loss": 1.1233,
|
| 1350 |
+
"step": 1085
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 4.89,
|
| 1354 |
+
"learning_rate": 4.210854780381334e-06,
|
| 1355 |
+
"loss": 0.9158,
|
| 1356 |
+
"step": 1090
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 4.91,
|
| 1360 |
+
"learning_rate": 2.705011476932832e-06,
|
| 1361 |
+
"loss": 1.0037,
|
| 1362 |
+
"step": 1095
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.93,
|
| 1366 |
+
"learning_rate": 1.5259838177494246e-06,
|
| 1367 |
+
"loss": 1.279,
|
| 1368 |
+
"step": 1100
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.96,
|
| 1372 |
+
"learning_rate": 6.796193595677371e-07,
|
| 1373 |
+
"loss": 1.0122,
|
| 1374 |
+
"step": 1105
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.98,
|
| 1378 |
+
"learning_rate": 1.7011576827836676e-07,
|
| 1379 |
+
"loss": 1.058,
|
| 1380 |
+
"step": 1110
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 5.0,
|
| 1384 |
+
"learning_rate": 0.0,
|
| 1385 |
+
"loss": 1.0917,
|
| 1386 |
+
"step": 1115
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 5.0,
|
| 1390 |
+
"eval_loss": 1.2071579694747925,
|
| 1391 |
+
"eval_runtime": 2.221,
|
| 1392 |
+
"eval_samples_per_second": 141.829,
|
| 1393 |
+
"eval_steps_per_second": 18.01,
|
| 1394 |
+
"step": 1115
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 5.02,
|
| 1398 |
+
"learning_rate": 1.7011576827835916e-07,
|
| 1399 |
+
"loss": 0.9624,
|
| 1400 |
+
"step": 1120
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 5.04,
|
| 1404 |
+
"learning_rate": 6.796193595677219e-07,
|
| 1405 |
+
"loss": 1.0903,
|
| 1406 |
+
"step": 1125
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 5.07,
|
| 1410 |
+
"learning_rate": 1.5259838177494094e-06,
|
| 1411 |
+
"loss": 0.8195,
|
| 1412 |
+
"step": 1130
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 5.09,
|
| 1416 |
+
"learning_rate": 2.705011476932809e-06,
|
| 1417 |
+
"loss": 0.9007,
|
| 1418 |
+
"step": 1135
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 5.11,
|
| 1422 |
+
"learning_rate": 4.210854780381303e-06,
|
| 1423 |
+
"loss": 0.6803,
|
| 1424 |
+
"step": 1140
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 5.13,
|
| 1428 |
+
"learning_rate": 6.036045282308651e-06,
|
| 1429 |
+
"loss": 0.9312,
|
| 1430 |
+
"step": 1145
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 5.16,
|
| 1434 |
+
"learning_rate": 8.171530688706338e-06,
|
| 1435 |
+
"loss": 1.0329,
|
| 1436 |
+
"step": 1150
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 5.18,
|
| 1440 |
+
"learning_rate": 1.0606719753493872e-05,
|
| 1441 |
+
"loss": 0.9101,
|
| 1442 |
+
"step": 1155
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 5.2,
|
| 1446 |
+
"learning_rate": 1.3329534807322828e-05,
|
| 1447 |
+
"loss": 0.8229,
|
| 1448 |
+
"step": 1160
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 5.22,
|
| 1452 |
+
"learning_rate": 1.6326471658509066e-05,
|
| 1453 |
+
"loss": 1.0693,
|
| 1454 |
+
"step": 1165
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 5.25,
|
| 1458 |
+
"learning_rate": 1.9582666569008055e-05,
|
| 1459 |
+
"loss": 0.7779,
|
| 1460 |
+
"step": 1170
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 5.27,
|
| 1464 |
+
"learning_rate": 2.3081969973255604e-05,
|
| 1465 |
+
"loss": 0.7962,
|
| 1466 |
+
"step": 1175
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 5.29,
|
| 1470 |
+
"learning_rate": 2.680702657425292e-05,
|
| 1471 |
+
"loss": 0.9127,
|
| 1472 |
+
"step": 1180
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 5.31,
|
| 1476 |
+
"learning_rate": 3.073936141965114e-05,
|
| 1477 |
+
"loss": 0.8227,
|
| 1478 |
+
"step": 1185
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 5.34,
|
| 1482 |
+
"learning_rate": 3.4859471530927266e-05,
|
| 1483 |
+
"loss": 0.9535,
|
| 1484 |
+
"step": 1190
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 5.36,
|
| 1488 |
+
"learning_rate": 3.914692263120148e-05,
|
| 1489 |
+
"loss": 0.7736,
|
| 1490 |
+
"step": 1195
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 5.38,
|
| 1494 |
+
"learning_rate": 4.358045049196419e-05,
|
| 1495 |
+
"loss": 0.9111,
|
| 1496 |
+
"step": 1200
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 5.4,
|
| 1500 |
+
"learning_rate": 4.813806639606595e-05,
|
| 1501 |
+
"loss": 0.9058,
|
| 1502 |
+
"step": 1205
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 5.43,
|
| 1506 |
+
"learning_rate": 5.279716619391414e-05,
|
| 1507 |
+
"loss": 0.8259,
|
| 1508 |
+
"step": 1210
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 5.45,
|
| 1512 |
+
"learning_rate": 5.753464241199256e-05,
|
| 1513 |
+
"loss": 0.9812,
|
| 1514 |
+
"step": 1215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 5.47,
|
| 1518 |
+
"learning_rate": 6.232699885769054e-05,
|
| 1519 |
+
"loss": 1.0264,
|
| 1520 |
+
"step": 1220
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 5.49,
|
| 1524 |
+
"learning_rate": 6.715046715203992e-05,
|
| 1525 |
+
"loss": 0.8185,
|
| 1526 |
+
"step": 1225
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 5.52,
|
| 1530 |
+
"learning_rate": 7.198112461239733e-05,
|
| 1531 |
+
"loss": 0.8403,
|
| 1532 |
+
"step": 1230
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 5.54,
|
| 1536 |
+
"learning_rate": 7.679501290041973e-05,
|
| 1537 |
+
"loss": 0.914,
|
| 1538 |
+
"step": 1235
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 5.56,
|
| 1542 |
+
"learning_rate": 8.15682568468795e-05,
|
| 1543 |
+
"loss": 0.9836,
|
| 1544 |
+
"step": 1240
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 5.58,
|
| 1548 |
+
"learning_rate": 8.627718286398833e-05,
|
| 1549 |
+
"loss": 0.9734,
|
| 1550 |
+
"step": 1245
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 5.61,
|
| 1554 |
+
"learning_rate": 9.089843635795102e-05,
|
| 1555 |
+
"loss": 0.8468,
|
| 1556 |
+
"step": 1250
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 5.63,
|
| 1560 |
+
"learning_rate": 9.540909755942299e-05,
|
| 1561 |
+
"loss": 0.835,
|
| 1562 |
+
"step": 1255
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 5.65,
|
| 1566 |
+
"learning_rate": 9.978679519739145e-05,
|
| 1567 |
+
"loss": 1.0896,
|
| 1568 |
+
"step": 1260
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 5.67,
|
| 1572 |
+
"learning_rate": 0.00010400981745270244,
|
| 1573 |
+
"loss": 0.7718,
|
| 1574 |
+
"step": 1265
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 5.7,
|
| 1578 |
+
"learning_rate": 0.00010805721964094184,
|
| 1579 |
+
"loss": 0.8329,
|
| 1580 |
+
"step": 1270
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 5.72,
|
| 1584 |
+
"learning_rate": 0.0001119089280905997,
|
| 1585 |
+
"loss": 0.9622,
|
| 1586 |
+
"step": 1275
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 5.74,
|
| 1590 |
+
"learning_rate": 0.0001155458397013233,
|
| 1591 |
+
"loss": 0.8208,
|
| 1592 |
+
"step": 1280
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 5.76,
|
| 1596 |
+
"learning_rate": 0.00011894991668848222,
|
| 1597 |
+
"loss": 0.9137,
|
| 1598 |
+
"step": 1285
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 5.78,
|
| 1602 |
+
"learning_rate": 0.00012210427604414823,
|
| 1603 |
+
"loss": 1.0149,
|
| 1604 |
+
"step": 1290
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 5.81,
|
| 1608 |
+
"learning_rate": 0.000124993273270793,
|
| 1609 |
+
"loss": 0.9856,
|
| 1610 |
+
"step": 1295
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 5.83,
|
| 1614 |
+
"learning_rate": 0.0001276025799724176,
|
| 1615 |
+
"loss": 0.9686,
|
| 1616 |
+
"step": 1300
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 5.85,
|
| 1620 |
+
"learning_rate": 0.0001299192549182866,
|
| 1621 |
+
"loss": 0.9409,
|
| 1622 |
+
"step": 1305
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 5.87,
|
| 1626 |
+
"learning_rate": 0.00013193180822681808,
|
| 1627 |
+
"loss": 1.214,
|
| 1628 |
+
"step": 1310
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 5.9,
|
| 1632 |
+
"learning_rate": 0.00013363025835129815,
|
| 1633 |
+
"loss": 0.8486,
|
| 1634 |
+
"step": 1315
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 5.92,
|
| 1638 |
+
"learning_rate": 0.00013500618158479366,
|
| 1639 |
+
"loss": 1.0083,
|
| 1640 |
+
"step": 1320
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 5.94,
|
| 1644 |
+
"learning_rate": 0.00013605275383873428,
|
| 1645 |
+
"loss": 0.9284,
|
| 1646 |
+
"step": 1325
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 5.96,
|
| 1650 |
+
"learning_rate": 0.00013676478448795875,
|
| 1651 |
+
"loss": 1.0467,
|
| 1652 |
+
"step": 1330
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 5.99,
|
| 1656 |
+
"learning_rate": 0.00013713874211436402,
|
| 1657 |
+
"loss": 0.9702,
|
| 1658 |
+
"step": 1335
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 6.0,
|
| 1662 |
+
"eval_loss": 1.2323447465896606,
|
| 1663 |
+
"eval_runtime": 2.2212,
|
| 1664 |
+
"eval_samples_per_second": 141.817,
|
| 1665 |
+
"eval_steps_per_second": 18.008,
|
| 1666 |
+
"step": 1338
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 6.01,
|
| 1670 |
+
"learning_rate": 0.00013717277202148013,
|
| 1671 |
+
"loss": 0.9361,
|
| 1672 |
+
"step": 1340
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 6.03,
|
| 1676 |
+
"learning_rate": 0.00013686670543310324,
|
| 1677 |
+
"loss": 0.951,
|
| 1678 |
+
"step": 1345
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 6.05,
|
| 1682 |
+
"learning_rate": 0.00013622206033036527,
|
| 1683 |
+
"loss": 0.7387,
|
| 1684 |
+
"step": 1350
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 6.08,
|
| 1688 |
+
"learning_rate": 0.0001352420339230889,
|
| 1689 |
+
"loss": 0.8237,
|
| 1690 |
+
"step": 1355
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 6.1,
|
| 1694 |
+
"learning_rate": 0.0001339314867927672,
|
| 1695 |
+
"loss": 0.8428,
|
| 1696 |
+
"step": 1360
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 6.12,
|
| 1700 |
+
"learning_rate": 0.00013229691878581222,
|
| 1701 |
+
"loss": 0.8352,
|
| 1702 |
+
"step": 1365
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 6.14,
|
| 1706 |
+
"learning_rate": 0.00013034643677663527,
|
| 1707 |
+
"loss": 0.8816,
|
| 1708 |
+
"step": 1370
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 6.17,
|
| 1712 |
+
"learning_rate": 0.00012808971446044072,
|
| 1713 |
+
"loss": 0.781,
|
| 1714 |
+
"step": 1375
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 6.19,
|
| 1718 |
+
"learning_rate": 0.00012553794437514699,
|
| 1719 |
+
"loss": 0.7146,
|
| 1720 |
+
"step": 1380
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 6.21,
|
| 1724 |
+
"learning_rate": 0.0001227037823903906,
|
| 1725 |
+
"loss": 0.9361,
|
| 1726 |
+
"step": 1385
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 6.23,
|
| 1730 |
+
"learning_rate": 0.00011960128493892572,
|
| 1731 |
+
"loss": 0.8889,
|
| 1732 |
+
"step": 1390
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 6.26,
|
| 1736 |
+
"learning_rate": 0.00011624583930172982,
|
| 1737 |
+
"loss": 0.9329,
|
| 1738 |
+
"step": 1395
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 6.28,
|
| 1742 |
+
"learning_rate": 0.0001126540872925782,
|
| 1743 |
+
"loss": 0.7853,
|
| 1744 |
+
"step": 1400
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 6.3,
|
| 1748 |
+
"learning_rate": 0.00010884384272058193,
|
| 1749 |
+
"loss": 0.7188,
|
| 1750 |
+
"step": 1405
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 6.32,
|
| 1754 |
+
"learning_rate": 0.00010483400304004653,
|
| 1755 |
+
"loss": 0.7662,
|
| 1756 |
+
"step": 1410
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 6.35,
|
| 1760 |
+
"learning_rate": 0.00010064445562583886,
|
| 1761 |
+
"loss": 0.7705,
|
| 1762 |
+
"step": 1415
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 6.37,
|
| 1766 |
+
"learning_rate": 9.629597913909932e-05,
|
| 1767 |
+
"loss": 0.9695,
|
| 1768 |
+
"step": 1420
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 6.39,
|
| 1772 |
+
"learning_rate": 9.181014047249165e-05,
|
| 1773 |
+
"loss": 0.6245,
|
| 1774 |
+
"step": 1425
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 6.41,
|
| 1778 |
+
"learning_rate": 8.72091877861077e-05,
|
| 1779 |
+
"loss": 0.9465,
|
| 1780 |
+
"step": 1430
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 6.43,
|
| 1784 |
+
"learning_rate": 8.25159401645266e-05,
|
| 1785 |
+
"loss": 0.8094,
|
| 1786 |
+
"step": 1435
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 6.46,
|
| 1790 |
+
"learning_rate": 7.775367444229211e-05,
|
| 1791 |
+
"loss": 0.8367,
|
| 1792 |
+
"step": 1440
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 6.48,
|
| 1796 |
+
"learning_rate": 7.29460097591153e-05,
|
| 1797 |
+
"loss": 0.5786,
|
| 1798 |
+
"step": 1445
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 6.5,
|
| 1802 |
+
"learning_rate": 6.81167904173639e-05,
|
| 1803 |
+
"loss": 0.8389,
|
| 1804 |
+
"step": 1450
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 6.52,
|
| 1808 |
+
"learning_rate": 6.328996762282478e-05,
|
| 1809 |
+
"loss": 0.9198,
|
| 1810 |
+
"step": 1455
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 6.55,
|
| 1814 |
+
"learning_rate": 5.848948069526602e-05,
|
| 1815 |
+
"loss": 0.8697,
|
| 1816 |
+
"step": 1460
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 6.57,
|
| 1820 |
+
"learning_rate": 5.3739138337947083e-05,
|
| 1821 |
+
"loss": 0.805,
|
| 1822 |
+
"step": 1465
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 6.59,
|
| 1826 |
+
"learning_rate": 4.90625005549404e-05,
|
| 1827 |
+
"loss": 0.7912,
|
| 1828 |
+
"step": 1470
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 6.61,
|
| 1832 |
+
"learning_rate": 4.448276180191432e-05,
|
| 1833 |
+
"loss": 0.7832,
|
| 1834 |
+
"step": 1475
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 6.64,
|
| 1838 |
+
"learning_rate": 4.0022635949903595e-05,
|
| 1839 |
+
"loss": 0.7555,
|
| 1840 |
+
"step": 1480
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 6.66,
|
| 1844 |
+
"learning_rate": 3.570424363260848e-05,
|
| 1845 |
+
"loss": 0.88,
|
| 1846 |
+
"step": 1485
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 6.68,
|
| 1850 |
+
"learning_rate": 3.1549002535941244e-05,
|
| 1851 |
+
"loss": 0.7924,
|
| 1852 |
+
"step": 1490
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 6.7,
|
| 1856 |
+
"learning_rate": 2.75775211739412e-05,
|
| 1857 |
+
"loss": 0.7299,
|
| 1858 |
+
"step": 1495
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 6.73,
|
| 1862 |
+
"learning_rate": 2.3809496677893663e-05,
|
| 1863 |
+
"loss": 0.9469,
|
| 1864 |
+
"step": 1500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 6.75,
|
| 1868 |
+
"learning_rate": 2.0263617105584168e-05,
|
| 1869 |
+
"loss": 0.6995,
|
| 1870 |
+
"step": 1505
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 6.77,
|
| 1874 |
+
"learning_rate": 1.6957468755195542e-05,
|
| 1875 |
+
"loss": 0.8889,
|
| 1876 |
+
"step": 1510
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 6.79,
|
| 1880 |
+
"learning_rate": 1.3907448943539954e-05,
|
| 1881 |
+
"loss": 0.8217,
|
| 1882 |
+
"step": 1515
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 6.82,
|
| 1886 |
+
"learning_rate": 1.1128684681215955e-05,
|
| 1887 |
+
"loss": 0.7166,
|
| 1888 |
+
"step": 1520
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 6.84,
|
| 1892 |
+
"learning_rate": 8.63495764802965e-06,
|
| 1893 |
+
"loss": 0.873,
|
| 1894 |
+
"step": 1525
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 6.86,
|
| 1898 |
+
"learning_rate": 6.4386358407778465e-06,
|
| 1899 |
+
"loss": 0.906,
|
| 1900 |
+
"step": 1530
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 6.88,
|
| 1904 |
+
"learning_rate": 4.550612232394066e-06,
|
| 1905 |
+
"loss": 0.9969,
|
| 1906 |
+
"step": 1535
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 6.91,
|
| 1910 |
+
"learning_rate": 2.9802507466879855e-06,
|
| 1911 |
+
"loss": 0.6348,
|
| 1912 |
+
"step": 1540
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 6.93,
|
| 1916 |
+
"learning_rate": 1.735339816622208e-06,
|
| 1917 |
+
"loss": 0.7365,
|
| 1918 |
+
"step": 1545
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 6.95,
|
| 1922 |
+
"learning_rate": 8.220537564620966e-07,
|
| 1923 |
+
"loss": 0.9509,
|
| 1924 |
+
"step": 1550
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 6.97,
|
| 1928 |
+
"learning_rate": 2.4492213937922245e-07,
|
| 1929 |
+
"loss": 0.8438,
|
| 1930 |
+
"step": 1555
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 7.0,
|
| 1934 |
+
"learning_rate": 6.807332383425125e-09,
|
| 1935 |
+
"loss": 0.9895,
|
| 1936 |
+
"step": 1560
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 7.0,
|
| 1940 |
+
"eval_loss": 1.1562458276748657,
|
| 1941 |
+
"eval_runtime": 2.2177,
|
| 1942 |
+
"eval_samples_per_second": 142.037,
|
| 1943 |
+
"eval_steps_per_second": 18.036,
|
| 1944 |
+
"step": 1561
|
| 1945 |
}
|
| 1946 |
],
|
| 1947 |
+
"max_steps": 1561,
|
| 1948 |
+
"num_train_epochs": 7,
|
| 1949 |
+
"total_flos": 1630331633664000.0,
|
| 1950 |
"trial_name": null,
|
| 1951 |
"trial_params": null
|
| 1952 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a45c13f86e007d237bf70ffcf99d8136f61ccf6dd43efe67c5d795076fd2fde
|
| 3 |
+
size 3311
|