Commit
•
0f9a51e
1
Parent(s):
3062cd9
huggingartists
Browse files- README.md +4 -4
- config.json +4 -2
- 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 +663 -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/rihanna")
|
| 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 Rihanna'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/f83548d76e427d0a4fdcafdf2f62b647.1000x1000x1.png')">
|
| 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/rihanna")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3c5muzh8/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 Rihanna's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/uywap06b/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"
|
|
@@ -18,7 +18,9 @@
|
|
| 18 |
"n_inner": null,
|
| 19 |
"n_layer": 12,
|
| 20 |
"n_positions": 1024,
|
|
|
|
| 21 |
"resid_pdrop": 0.1,
|
|
|
|
| 22 |
"scale_attn_weights": true,
|
| 23 |
"summary_activation": null,
|
| 24 |
"summary_first_dropout": 0.1,
|
|
@@ -35,7 +37,7 @@
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "rihanna",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 18 |
"n_inner": null,
|
| 19 |
"n_layer": 12,
|
| 20 |
"n_positions": 1024,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
"scale_attn_weights": true,
|
| 25 |
"summary_activation": null,
|
| 26 |
"summary_first_dropout": 0.1,
|
|
|
|
| 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 |
+
{"eval_loss": 1.752521276473999, "eval_runtime": 4.2607, "eval_samples_per_second": 45.532, "eval_steps_per_second": 5.868, "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:b41a408893cb0ef0914b7c69fe63100edbcfd9827c5b8d83eff838506cbe6e73
|
| 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:f3006a0c685ddebea1136f939b292ab67e24da1f0edd23faadf7a85985f46b34
|
| 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 sha256:4e5b73d16cb2c0edc96673fe23be7a5214f61a1c9d00aaf44aacd9f96d1ea618
|
| 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 sha256:26e82f1222285d031b8e21d934b74558389b98a783bb42db1010d0f55af3bc16
|
| 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:cfc3e0c06b55e5f6cc34f1c4c7ab6e7fc251827bfa5f1b3ed68bfe476fa6cc0c
|
| 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/rihanna",
|
| 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":
|
| 3 |
-
"best_model_checkpoint": "output/rihanna/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -334,11 +334,667 @@
|
|
| 334 |
"eval_samples_per_second": 22.521,
|
| 335 |
"eval_steps_per_second": 2.89,
|
| 336 |
"step": 262
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 337 |
}
|
| 338 |
],
|
| 339 |
-
"max_steps":
|
| 340 |
-
"num_train_epochs":
|
| 341 |
-
"total_flos":
|
| 342 |
"trial_name": null,
|
| 343 |
"trial_params": null
|
| 344 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.752521276473999,
|
| 3 |
+
"best_model_checkpoint": "output/rihanna/checkpoint-780",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 780,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 334 |
"eval_samples_per_second": 22.521,
|
| 335 |
"eval_steps_per_second": 2.89,
|
| 336 |
"step": 262
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.04,
|
| 340 |
+
"learning_rate": 0.0001366998287631265,
|
| 341 |
+
"loss": 2.0176,
|
| 342 |
+
"step": 265
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.08,
|
| 346 |
+
"learning_rate": 0.00013520660867542716,
|
| 347 |
+
"loss": 2.0043,
|
| 348 |
+
"step": 270
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.12,
|
| 352 |
+
"learning_rate": 0.00013274211424821946,
|
| 353 |
+
"loss": 1.743,
|
| 354 |
+
"step": 275
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.15,
|
| 358 |
+
"learning_rate": 0.00012934228335981023,
|
| 359 |
+
"loss": 2.0598,
|
| 360 |
+
"step": 280
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.19,
|
| 364 |
+
"learning_rate": 0.00012505669320030482,
|
| 365 |
+
"loss": 1.9087,
|
| 366 |
+
"step": 285
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.23,
|
| 370 |
+
"learning_rate": 0.00011994783732453754,
|
| 371 |
+
"loss": 1.6869,
|
| 372 |
+
"step": 290
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.27,
|
| 376 |
+
"learning_rate": 0.00011409021435531858,
|
| 377 |
+
"loss": 1.726,
|
| 378 |
+
"step": 295
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.31,
|
| 382 |
+
"learning_rate": 0.00010756924162575734,
|
| 383 |
+
"loss": 1.966,
|
| 384 |
+
"step": 300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.35,
|
| 388 |
+
"learning_rate": 0.00010048000960220251,
|
| 389 |
+
"loss": 2.0242,
|
| 390 |
+
"step": 305
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.38,
|
| 394 |
+
"learning_rate": 9.292589525111797e-05,
|
| 395 |
+
"loss": 1.804,
|
| 396 |
+
"step": 310
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.42,
|
| 400 |
+
"learning_rate": 8.501705457012652e-05,
|
| 401 |
+
"loss": 1.7316,
|
| 402 |
+
"step": 315
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.46,
|
| 406 |
+
"learning_rate": 7.686881626551514e-05,
|
| 407 |
+
"loss": 2.1338,
|
| 408 |
+
"step": 320
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.5,
|
| 412 |
+
"learning_rate": 6.860000000000001e-05,
|
| 413 |
+
"loss": 2.067,
|
| 414 |
+
"step": 325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.54,
|
| 418 |
+
"learning_rate": 6.03311837344849e-05,
|
| 419 |
+
"loss": 1.993,
|
| 420 |
+
"step": 330
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.58,
|
| 424 |
+
"learning_rate": 5.218294542987351e-05,
|
| 425 |
+
"loss": 1.8933,
|
| 426 |
+
"step": 335
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.62,
|
| 430 |
+
"learning_rate": 4.427410474888207e-05,
|
| 431 |
+
"loss": 1.7142,
|
| 432 |
+
"step": 340
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.65,
|
| 436 |
+
"learning_rate": 3.6719990397797524e-05,
|
| 437 |
+
"loss": 1.9927,
|
| 438 |
+
"step": 345
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.69,
|
| 442 |
+
"learning_rate": 2.9630758374242683e-05,
|
| 443 |
+
"loss": 1.8104,
|
| 444 |
+
"step": 350
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.73,
|
| 448 |
+
"learning_rate": 2.310978564468145e-05,
|
| 449 |
+
"loss": 1.8292,
|
| 450 |
+
"step": 355
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.77,
|
| 454 |
+
"learning_rate": 1.7252162675462497e-05,
|
| 455 |
+
"loss": 2.0388,
|
| 456 |
+
"step": 360
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.81,
|
| 460 |
+
"learning_rate": 1.214330679969522e-05,
|
| 461 |
+
"loss": 1.8121,
|
| 462 |
+
"step": 365
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.85,
|
| 466 |
+
"learning_rate": 7.8577166401898e-06,
|
| 467 |
+
"loss": 1.8632,
|
| 468 |
+
"step": 370
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.88,
|
| 472 |
+
"learning_rate": 4.457885751780558e-06,
|
| 473 |
+
"loss": 2.0386,
|
| 474 |
+
"step": 375
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.92,
|
| 478 |
+
"learning_rate": 1.9933913245728472e-06,
|
| 479 |
+
"loss": 1.7312,
|
| 480 |
+
"step": 380
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.96,
|
| 484 |
+
"learning_rate": 5.001712368734975e-07,
|
| 485 |
+
"loss": 2.0118,
|
| 486 |
+
"step": 385
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.0,
|
| 490 |
+
"learning_rate": 0.0,
|
| 491 |
+
"loss": 1.7726,
|
| 492 |
+
"step": 390
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.0,
|
| 496 |
+
"eval_loss": 1.8738644123077393,
|
| 497 |
+
"eval_runtime": 4.2323,
|
| 498 |
+
"eval_samples_per_second": 45.838,
|
| 499 |
+
"eval_steps_per_second": 5.907,
|
| 500 |
+
"step": 390
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.04,
|
| 504 |
+
"learning_rate": 5.001712368734899e-07,
|
| 505 |
+
"loss": 1.519,
|
| 506 |
+
"step": 395
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.08,
|
| 510 |
+
"learning_rate": 1.9933913245728396e-06,
|
| 511 |
+
"loss": 1.6714,
|
| 512 |
+
"step": 400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.12,
|
| 516 |
+
"learning_rate": 4.457885751780535e-06,
|
| 517 |
+
"loss": 1.6067,
|
| 518 |
+
"step": 405
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.15,
|
| 522 |
+
"learning_rate": 7.857716640189778e-06,
|
| 523 |
+
"loss": 1.4835,
|
| 524 |
+
"step": 410
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.19,
|
| 528 |
+
"learning_rate": 1.2143306799695189e-05,
|
| 529 |
+
"loss": 1.9692,
|
| 530 |
+
"step": 415
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.23,
|
| 534 |
+
"learning_rate": 1.725216267546246e-05,
|
| 535 |
+
"loss": 1.5852,
|
| 536 |
+
"step": 420
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.27,
|
| 540 |
+
"learning_rate": 2.310978564468141e-05,
|
| 541 |
+
"loss": 1.766,
|
| 542 |
+
"step": 425
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.31,
|
| 546 |
+
"learning_rate": 2.9630758374242642e-05,
|
| 547 |
+
"loss": 1.7481,
|
| 548 |
+
"step": 430
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.35,
|
| 552 |
+
"learning_rate": 3.671999039779748e-05,
|
| 553 |
+
"loss": 1.9411,
|
| 554 |
+
"step": 435
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.38,
|
| 558 |
+
"learning_rate": 4.427410474888202e-05,
|
| 559 |
+
"loss": 1.5399,
|
| 560 |
+
"step": 440
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.42,
|
| 564 |
+
"learning_rate": 5.218294542987346e-05,
|
| 565 |
+
"loss": 1.9887,
|
| 566 |
+
"step": 445
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.46,
|
| 570 |
+
"learning_rate": 6.033118373448485e-05,
|
| 571 |
+
"loss": 1.6023,
|
| 572 |
+
"step": 450
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.5,
|
| 576 |
+
"learning_rate": 6.859999999999997e-05,
|
| 577 |
+
"loss": 1.665,
|
| 578 |
+
"step": 455
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.54,
|
| 582 |
+
"learning_rate": 7.68688162655151e-05,
|
| 583 |
+
"loss": 1.6708,
|
| 584 |
+
"step": 460
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.58,
|
| 588 |
+
"learning_rate": 8.501705457012648e-05,
|
| 589 |
+
"loss": 1.7596,
|
| 590 |
+
"step": 465
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.62,
|
| 594 |
+
"learning_rate": 9.292589525111793e-05,
|
| 595 |
+
"loss": 2.0391,
|
| 596 |
+
"step": 470
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.65,
|
| 600 |
+
"learning_rate": 0.00010048000960220248,
|
| 601 |
+
"loss": 1.6346,
|
| 602 |
+
"step": 475
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.69,
|
| 606 |
+
"learning_rate": 0.00010756924162575731,
|
| 607 |
+
"loss": 1.5059,
|
| 608 |
+
"step": 480
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.73,
|
| 612 |
+
"learning_rate": 0.00011409021435531856,
|
| 613 |
+
"loss": 1.7107,
|
| 614 |
+
"step": 485
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.77,
|
| 618 |
+
"learning_rate": 0.0001199478373245375,
|
| 619 |
+
"loss": 1.6263,
|
| 620 |
+
"step": 490
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.81,
|
| 624 |
+
"learning_rate": 0.0001250566932003048,
|
| 625 |
+
"loss": 1.7098,
|
| 626 |
+
"step": 495
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.85,
|
| 630 |
+
"learning_rate": 0.00012934228335981018,
|
| 631 |
+
"loss": 1.5807,
|
| 632 |
+
"step": 500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.88,
|
| 636 |
+
"learning_rate": 0.00013274211424821943,
|
| 637 |
+
"loss": 1.9171,
|
| 638 |
+
"step": 505
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.92,
|
| 642 |
+
"learning_rate": 0.00013520660867542716,
|
| 643 |
+
"loss": 1.6038,
|
| 644 |
+
"step": 510
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.96,
|
| 648 |
+
"learning_rate": 0.00013669982876312649,
|
| 649 |
+
"loss": 1.548,
|
| 650 |
+
"step": 515
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 4.0,
|
| 654 |
+
"learning_rate": 0.0001372,
|
| 655 |
+
"loss": 1.8101,
|
| 656 |
+
"step": 520
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.0,
|
| 660 |
+
"eval_loss": 1.8380614519119263,
|
| 661 |
+
"eval_runtime": 4.2339,
|
| 662 |
+
"eval_samples_per_second": 45.821,
|
| 663 |
+
"eval_steps_per_second": 5.905,
|
| 664 |
+
"step": 520
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 4.04,
|
| 668 |
+
"learning_rate": 0.0001366998287631265,
|
| 669 |
+
"loss": 1.7809,
|
| 670 |
+
"step": 525
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.08,
|
| 674 |
+
"learning_rate": 0.0001352066086754272,
|
| 675 |
+
"loss": 1.71,
|
| 676 |
+
"step": 530
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.12,
|
| 680 |
+
"learning_rate": 0.0001327421142482195,
|
| 681 |
+
"loss": 1.3283,
|
| 682 |
+
"step": 535
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.15,
|
| 686 |
+
"learning_rate": 0.00012934228335981015,
|
| 687 |
+
"loss": 1.4905,
|
| 688 |
+
"step": 540
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.19,
|
| 692 |
+
"learning_rate": 0.00012505669320030482,
|
| 693 |
+
"loss": 1.2511,
|
| 694 |
+
"step": 545
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.23,
|
| 698 |
+
"learning_rate": 0.00011994783732453755,
|
| 699 |
+
"loss": 1.6209,
|
| 700 |
+
"step": 550
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 4.27,
|
| 704 |
+
"learning_rate": 0.00011409021435531858,
|
| 705 |
+
"loss": 1.6988,
|
| 706 |
+
"step": 555
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 4.31,
|
| 710 |
+
"learning_rate": 0.00010756924162575738,
|
| 711 |
+
"loss": 1.2228,
|
| 712 |
+
"step": 560
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.35,
|
| 716 |
+
"learning_rate": 0.00010048000960220263,
|
| 717 |
+
"loss": 1.6827,
|
| 718 |
+
"step": 565
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.38,
|
| 722 |
+
"learning_rate": 9.292589525111788e-05,
|
| 723 |
+
"loss": 1.6977,
|
| 724 |
+
"step": 570
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 4.42,
|
| 728 |
+
"learning_rate": 8.501705457012643e-05,
|
| 729 |
+
"loss": 1.4269,
|
| 730 |
+
"step": 575
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.46,
|
| 734 |
+
"learning_rate": 7.686881626551516e-05,
|
| 735 |
+
"loss": 1.6831,
|
| 736 |
+
"step": 580
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.5,
|
| 740 |
+
"learning_rate": 6.860000000000003e-05,
|
| 741 |
+
"loss": 1.0505,
|
| 742 |
+
"step": 585
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.54,
|
| 746 |
+
"learning_rate": 6.033118373448492e-05,
|
| 747 |
+
"loss": 1.4459,
|
| 748 |
+
"step": 590
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.58,
|
| 752 |
+
"learning_rate": 5.218294542987365e-05,
|
| 753 |
+
"loss": 1.4365,
|
| 754 |
+
"step": 595
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.62,
|
| 758 |
+
"learning_rate": 4.42741047488822e-05,
|
| 759 |
+
"loss": 1.6545,
|
| 760 |
+
"step": 600
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.65,
|
| 764 |
+
"learning_rate": 3.671999039779743e-05,
|
| 765 |
+
"loss": 1.6826,
|
| 766 |
+
"step": 605
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 4.69,
|
| 770 |
+
"learning_rate": 2.9630758374242696e-05,
|
| 771 |
+
"loss": 1.6816,
|
| 772 |
+
"step": 610
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.73,
|
| 776 |
+
"learning_rate": 2.3109785644681465e-05,
|
| 777 |
+
"loss": 1.43,
|
| 778 |
+
"step": 615
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 4.77,
|
| 782 |
+
"learning_rate": 1.7252162675462504e-05,
|
| 783 |
+
"loss": 1.1238,
|
| 784 |
+
"step": 620
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 4.81,
|
| 788 |
+
"learning_rate": 1.2143306799695228e-05,
|
| 789 |
+
"loss": 1.1441,
|
| 790 |
+
"step": 625
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.85,
|
| 794 |
+
"learning_rate": 7.857716640189861e-06,
|
| 795 |
+
"loss": 1.5854,
|
| 796 |
+
"step": 630
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 4.88,
|
| 800 |
+
"learning_rate": 4.4578857517805195e-06,
|
| 801 |
+
"loss": 1.2825,
|
| 802 |
+
"step": 635
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.92,
|
| 806 |
+
"learning_rate": 1.9933913245728244e-06,
|
| 807 |
+
"loss": 1.3848,
|
| 808 |
+
"step": 640
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.96,
|
| 812 |
+
"learning_rate": 5.001712368734975e-07,
|
| 813 |
+
"loss": 1.4917,
|
| 814 |
+
"step": 645
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 5.0,
|
| 818 |
+
"learning_rate": 0.0,
|
| 819 |
+
"loss": 1.0341,
|
| 820 |
+
"step": 650
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 5.0,
|
| 824 |
+
"eval_loss": 1.7726789712905884,
|
| 825 |
+
"eval_runtime": 4.2405,
|
| 826 |
+
"eval_samples_per_second": 45.75,
|
| 827 |
+
"eval_steps_per_second": 5.896,
|
| 828 |
+
"step": 650
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 5.04,
|
| 832 |
+
"learning_rate": 5.001712368734899e-07,
|
| 833 |
+
"loss": 1.3946,
|
| 834 |
+
"step": 655
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 5.08,
|
| 838 |
+
"learning_rate": 1.9933913245728015e-06,
|
| 839 |
+
"loss": 1.1575,
|
| 840 |
+
"step": 660
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 5.12,
|
| 844 |
+
"learning_rate": 4.457885751780535e-06,
|
| 845 |
+
"loss": 1.2407,
|
| 846 |
+
"step": 665
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 5.15,
|
| 850 |
+
"learning_rate": 7.857716640189824e-06,
|
| 851 |
+
"loss": 1.299,
|
| 852 |
+
"step": 670
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 5.19,
|
| 856 |
+
"learning_rate": 1.2143306799695106e-05,
|
| 857 |
+
"loss": 1.4759,
|
| 858 |
+
"step": 675
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 5.23,
|
| 862 |
+
"learning_rate": 1.725216267546245e-05,
|
| 863 |
+
"loss": 1.2347,
|
| 864 |
+
"step": 680
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 5.27,
|
| 868 |
+
"learning_rate": 2.3109785644681495e-05,
|
| 869 |
+
"loss": 1.4233,
|
| 870 |
+
"step": 685
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 5.31,
|
| 874 |
+
"learning_rate": 2.963075837424263e-05,
|
| 875 |
+
"loss": 1.4062,
|
| 876 |
+
"step": 690
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 5.35,
|
| 880 |
+
"learning_rate": 3.6719990397797463e-05,
|
| 881 |
+
"loss": 1.2485,
|
| 882 |
+
"step": 695
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 5.38,
|
| 886 |
+
"learning_rate": 4.4274104748882125e-05,
|
| 887 |
+
"loss": 1.4536,
|
| 888 |
+
"step": 700
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 5.42,
|
| 892 |
+
"learning_rate": 5.2182945429873444e-05,
|
| 893 |
+
"loss": 1.2116,
|
| 894 |
+
"step": 705
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 5.46,
|
| 898 |
+
"learning_rate": 6.033118373448483e-05,
|
| 899 |
+
"loss": 1.1743,
|
| 900 |
+
"step": 710
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 5.5,
|
| 904 |
+
"learning_rate": 6.859999999999984e-05,
|
| 905 |
+
"loss": 1.2798,
|
| 906 |
+
"step": 715
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 5.54,
|
| 910 |
+
"learning_rate": 7.686881626551508e-05,
|
| 911 |
+
"loss": 1.1637,
|
| 912 |
+
"step": 720
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.58,
|
| 916 |
+
"learning_rate": 8.501705457012647e-05,
|
| 917 |
+
"loss": 1.4529,
|
| 918 |
+
"step": 725
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 5.62,
|
| 922 |
+
"learning_rate": 9.292589525111778e-05,
|
| 923 |
+
"loss": 1.1575,
|
| 924 |
+
"step": 730
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 5.65,
|
| 928 |
+
"learning_rate": 0.00010048000960220244,
|
| 929 |
+
"loss": 1.4035,
|
| 930 |
+
"step": 735
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.69,
|
| 934 |
+
"learning_rate": 0.0001075692416257573,
|
| 935 |
+
"loss": 1.2311,
|
| 936 |
+
"step": 740
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.73,
|
| 940 |
+
"learning_rate": 0.00011409021435531843,
|
| 941 |
+
"loss": 1.3514,
|
| 942 |
+
"step": 745
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.77,
|
| 946 |
+
"learning_rate": 0.00011994783732453749,
|
| 947 |
+
"loss": 1.0519,
|
| 948 |
+
"step": 750
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 5.81,
|
| 952 |
+
"learning_rate": 0.00012505669320030485,
|
| 953 |
+
"loss": 1.39,
|
| 954 |
+
"step": 755
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 5.85,
|
| 958 |
+
"learning_rate": 0.00012934228335981013,
|
| 959 |
+
"loss": 1.2267,
|
| 960 |
+
"step": 760
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.88,
|
| 964 |
+
"learning_rate": 0.00013274211424821943,
|
| 965 |
+
"loss": 1.431,
|
| 966 |
+
"step": 765
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.92,
|
| 970 |
+
"learning_rate": 0.00013520660867542716,
|
| 971 |
+
"loss": 1.5557,
|
| 972 |
+
"step": 770
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 5.96,
|
| 976 |
+
"learning_rate": 0.00013669982876312649,
|
| 977 |
+
"loss": 1.2241,
|
| 978 |
+
"step": 775
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 6.0,
|
| 982 |
+
"learning_rate": 0.0001372,
|
| 983 |
+
"loss": 1.1435,
|
| 984 |
+
"step": 780
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 6.0,
|
| 988 |
+
"eval_loss": 1.752521276473999,
|
| 989 |
+
"eval_runtime": 4.2466,
|
| 990 |
+
"eval_samples_per_second": 45.684,
|
| 991 |
+
"eval_steps_per_second": 5.887,
|
| 992 |
+
"step": 780
|
| 993 |
}
|
| 994 |
],
|
| 995 |
+
"max_steps": 910,
|
| 996 |
+
"num_train_epochs": 7,
|
| 997 |
+
"total_flos": 811181113344000.0,
|
| 998 |
"trial_name": null,
|
| 999 |
"trial_params": null
|
| 1000 |
}
|
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 sha256:1bf17e5c0319daac4eb8decc923d42c574d61cb10c1cc3267a038b27c7c37d44
|
| 3 |
+
size 3311
|