Model save
Browse files- README.md +9 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- runs/Feb07_16-20-06_r2d2-tom-003-8skr8/events.out.tfevents.1738945755.r2d2-tom-003-8skr8.115.0 +2 -2
- runs/Feb07_16-20-06_r2d2-tom-003-8skr8/events.out.tfevents.1738984959.r2d2-tom-003-8skr8.115.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +614 -0
README.md
CHANGED
|
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# robust_llm_r2d2_tom-003_Qwen2.5-7B-Instruct_full
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -45,6 +47,13 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- num_epochs: 1
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.37.2
|
|
|
|
| 14 |
# robust_llm_r2d2_tom-003_Qwen2.5-7B-Instruct_full
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.0885
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- num_epochs: 1
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 1.0835 | 0.59 | 478 | 1.0885 |
|
| 55 |
+
|
| 56 |
+
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.37.2
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.59,
|
| 3 |
+
"eval_loss": 1.0884811878204346,
|
| 4 |
+
"eval_runtime": 266.6098,
|
| 5 |
+
"eval_samples": 23110,
|
| 6 |
+
"eval_samples_per_second": 86.681,
|
| 7 |
+
"eval_steps_per_second": 10.836,
|
| 8 |
+
"train_loss": 1.1024827179050845,
|
| 9 |
+
"train_runtime": 38937.2818,
|
| 10 |
+
"train_samples": 207865,
|
| 11 |
+
"train_samples_per_second": 5.338,
|
| 12 |
+
"train_steps_per_second": 0.021
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.59,
|
| 3 |
+
"eval_loss": 1.0884811878204346,
|
| 4 |
+
"eval_runtime": 266.6098,
|
| 5 |
+
"eval_samples": 23110,
|
| 6 |
+
"eval_samples_per_second": 86.681,
|
| 7 |
+
"eval_steps_per_second": 10.836
|
| 8 |
+
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07a09f516052961cd44c68e9bb0029ceb0837c4e5e48e0362d9908208fd75243
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd59754f01258b5a505aac1b4459bd9c54e0fef2a67c2e8719d70714c53a8f59
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5576673ac34785071e82ab2b25136ed42c6eed46e8dffb67573aa400ce2e437
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81027beac8eccba06da3e2ac68c2d41b6eb239186ea24e3a0dbcc534de53c6d2
|
| 3 |
size 1089994880
|
runs/Feb07_16-20-06_r2d2-tom-003-8skr8/events.out.tfevents.1738945755.r2d2-tom-003-8skr8.115.0
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:b95c21b8ce8b2fac6d48ced05344052e54508407df641043ab8909f861c8a12d
|
| 3 |
+
size 20264
|
runs/Feb07_16-20-06_r2d2-tom-003-8skr8/events.out.tfevents.1738984959.r2d2-tom-003-8skr8.115.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783e835aad6d2ba29034ef38934729b8b7eef2ca03b8e32996e641c01f39da33
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.59,
|
| 3 |
+
"train_loss": 1.1024827179050845,
|
| 4 |
+
"train_runtime": 38937.2818,
|
| 5 |
+
"train_samples": 207865,
|
| 6 |
+
"train_samples_per_second": 5.338,
|
| 7 |
+
"train_steps_per_second": 0.021
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5886812785036658,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 478,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.999992497128677e-05,
|
| 14 |
+
"loss": 2.0742,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 1.9998124338461647e-05,
|
| 20 |
+
"loss": 1.2327,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 1.9992498057467824e-05,
|
| 26 |
+
"loss": 1.159,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.9983123267618306e-05,
|
| 32 |
+
"loss": 1.1495,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 1.997000348569964e-05,
|
| 38 |
+
"loss": 1.1277,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.99531436333659e-05,
|
| 44 |
+
"loss": 1.1321,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 1.9932550035292393e-05,
|
| 50 |
+
"loss": 1.1259,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 1.9908230416803093e-05,
|
| 56 |
+
"loss": 1.1427,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 1.98801939009726e-05,
|
| 62 |
+
"loss": 1.1101,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 1.9848451005203795e-05,
|
| 68 |
+
"loss": 1.1267,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 1.9813013637282426e-05,
|
| 74 |
+
"loss": 1.1185,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.07,
|
| 79 |
+
"learning_rate": 1.9773895090910098e-05,
|
| 80 |
+
"loss": 1.1049,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 1.9731110040717384e-05,
|
| 86 |
+
"loss": 1.1232,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"learning_rate": 1.9684674536758894e-05,
|
| 92 |
+
"loss": 1.1158,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 1.9634605998492386e-05,
|
| 98 |
+
"loss": 1.0992,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"learning_rate": 1.958092320824417e-05,
|
| 104 |
+
"loss": 1.118,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 1.952364630416322e-05,
|
| 110 |
+
"loss": 1.1062,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 1.9462796772666746e-05,
|
| 116 |
+
"loss": 1.1213,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"learning_rate": 1.9398397440379923e-05,
|
| 122 |
+
"loss": 1.0936,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 1.9330472465572883e-05,
|
| 128 |
+
"loss": 1.1248,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.12,
|
| 133 |
+
"learning_rate": 1.9259047329098173e-05,
|
| 134 |
+
"loss": 1.1104,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 1.918414882483206e-05,
|
| 140 |
+
"loss": 1.1026,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.14,
|
| 145 |
+
"learning_rate": 1.91058050496233e-05,
|
| 146 |
+
"loss": 1.1049,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.14,
|
| 151 |
+
"learning_rate": 1.902404539275307e-05,
|
| 152 |
+
"loss": 1.0877,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.15,
|
| 157 |
+
"learning_rate": 1.8938900524910128e-05,
|
| 158 |
+
"loss": 1.1035,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.15,
|
| 163 |
+
"learning_rate": 1.8850402386685235e-05,
|
| 164 |
+
"loss": 1.0895,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 1.875858417658921e-05,
|
| 170 |
+
"loss": 1.0995,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"learning_rate": 1.866348033859909e-05,
|
| 176 |
+
"loss": 1.1066,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 1.8565126549237092e-05,
|
| 182 |
+
"loss": 1.1129,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.18,
|
| 187 |
+
"learning_rate": 1.846355970418718e-05,
|
| 188 |
+
"loss": 1.0883,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.18,
|
| 193 |
+
"learning_rate": 1.8358817904454328e-05,
|
| 194 |
+
"loss": 1.1067,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.19,
|
| 199 |
+
"learning_rate": 1.825094044207158e-05,
|
| 200 |
+
"loss": 1.0965,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.2,
|
| 205 |
+
"learning_rate": 1.8139967785360338e-05,
|
| 206 |
+
"loss": 1.0957,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.2,
|
| 211 |
+
"learning_rate": 1.8025941563749407e-05,
|
| 212 |
+
"loss": 1.0956,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.21,
|
| 217 |
+
"learning_rate": 1.7908904552158435e-05,
|
| 218 |
+
"loss": 1.0859,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.22,
|
| 223 |
+
"learning_rate": 1.7788900654951664e-05,
|
| 224 |
+
"loss": 1.1044,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.22,
|
| 229 |
+
"learning_rate": 1.766597488946798e-05,
|
| 230 |
+
"loss": 1.1113,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.23,
|
| 235 |
+
"learning_rate": 1.7540173369133463e-05,
|
| 236 |
+
"loss": 1.1069,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.23,
|
| 241 |
+
"learning_rate": 1.741154328616274e-05,
|
| 242 |
+
"loss": 1.1087,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.24,
|
| 247 |
+
"learning_rate": 1.728013289385568e-05,
|
| 248 |
+
"loss": 1.0956,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.25,
|
| 253 |
+
"learning_rate": 1.7145991488495997e-05,
|
| 254 |
+
"loss": 1.0832,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25,
|
| 259 |
+
"learning_rate": 1.7009169390858635e-05,
|
| 260 |
+
"loss": 1.1101,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26,
|
| 265 |
+
"learning_rate": 1.6869717927332825e-05,
|
| 266 |
+
"loss": 1.0885,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 1.6727689410667887e-05,
|
| 272 |
+
"loss": 1.0907,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.27,
|
| 277 |
+
"learning_rate": 1.6583137120349028e-05,
|
| 278 |
+
"loss": 1.1001,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.28,
|
| 283 |
+
"learning_rate": 1.64361152826105e-05,
|
| 284 |
+
"loss": 1.1047,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.28,
|
| 289 |
+
"learning_rate": 1.6286679050093573e-05,
|
| 290 |
+
"loss": 1.0976,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.29,
|
| 295 |
+
"learning_rate": 1.6134884481156994e-05,
|
| 296 |
+
"loss": 1.1082,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3,
|
| 301 |
+
"learning_rate": 1.5980788518847706e-05,
|
| 302 |
+
"loss": 1.0839,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3,
|
| 307 |
+
"learning_rate": 1.5824448969539653e-05,
|
| 308 |
+
"loss": 1.0892,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.31,
|
| 313 |
+
"learning_rate": 1.566592448124874e-05,
|
| 314 |
+
"loss": 1.1104,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.31,
|
| 319 |
+
"learning_rate": 1.550527452163209e-05,
|
| 320 |
+
"loss": 1.0929,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.32,
|
| 325 |
+
"learning_rate": 1.5342559355679776e-05,
|
| 326 |
+
"loss": 1.0888,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.33,
|
| 331 |
+
"learning_rate": 1.5177840023107498e-05,
|
| 332 |
+
"loss": 1.0824,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.33,
|
| 337 |
+
"learning_rate": 1.5011178315458601e-05,
|
| 338 |
+
"loss": 1.0953,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.34,
|
| 343 |
+
"learning_rate": 1.4842636752924073e-05,
|
| 344 |
+
"loss": 1.079,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.34,
|
| 349 |
+
"learning_rate": 1.467227856088921e-05,
|
| 350 |
+
"loss": 1.0762,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.35,
|
| 355 |
+
"learning_rate": 1.4500167646215722e-05,
|
| 356 |
+
"loss": 1.0995,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.36,
|
| 361 |
+
"learning_rate": 1.4326368573268199e-05,
|
| 362 |
+
"loss": 1.0934,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.36,
|
| 367 |
+
"learning_rate": 1.415094653969395e-05,
|
| 368 |
+
"loss": 1.0889,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.37,
|
| 373 |
+
"learning_rate": 1.397396735196525e-05,
|
| 374 |
+
"loss": 1.0913,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.38,
|
| 379 |
+
"learning_rate": 1.3795497400693198e-05,
|
| 380 |
+
"loss": 1.0786,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.38,
|
| 385 |
+
"learning_rate": 1.3615603635722463e-05,
|
| 386 |
+
"loss": 1.0863,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.39,
|
| 391 |
+
"learning_rate": 1.3434353541016238e-05,
|
| 392 |
+
"loss": 1.0904,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.39,
|
| 397 |
+
"learning_rate": 1.3251815109340813e-05,
|
| 398 |
+
"loss": 1.0932,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.4,
|
| 403 |
+
"learning_rate": 1.3068056816759303e-05,
|
| 404 |
+
"loss": 1.1046,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.41,
|
| 409 |
+
"learning_rate": 1.2883147596944054e-05,
|
| 410 |
+
"loss": 1.0881,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.41,
|
| 415 |
+
"learning_rate": 1.2697156815317409e-05,
|
| 416 |
+
"loss": 1.0994,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.42,
|
| 421 |
+
"learning_rate": 1.2510154243030482e-05,
|
| 422 |
+
"loss": 1.0975,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.42,
|
| 427 |
+
"learning_rate": 1.2322210030789759e-05,
|
| 428 |
+
"loss": 1.0813,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.43,
|
| 433 |
+
"learning_rate": 1.2133394682541287e-05,
|
| 434 |
+
"loss": 1.091,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.44,
|
| 439 |
+
"learning_rate": 1.194377902902238e-05,
|
| 440 |
+
"loss": 1.0777,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.44,
|
| 445 |
+
"learning_rate": 1.1753434201190716e-05,
|
| 446 |
+
"loss": 1.0904,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.45,
|
| 451 |
+
"learning_rate": 1.1562431603540807e-05,
|
| 452 |
+
"loss": 1.0827,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.46,
|
| 457 |
+
"learning_rate": 1.1370842887317888e-05,
|
| 458 |
+
"loss": 1.0922,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.46,
|
| 463 |
+
"learning_rate": 1.117873992363919e-05,
|
| 464 |
+
"loss": 1.1067,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.47,
|
| 469 |
+
"learning_rate": 1.09861947765328e-05,
|
| 470 |
+
"loss": 1.1017,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.47,
|
| 475 |
+
"learning_rate": 1.0793279675904072e-05,
|
| 476 |
+
"loss": 1.0762,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.48,
|
| 481 |
+
"learning_rate": 1.0600066990439895e-05,
|
| 482 |
+
"loss": 1.0908,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.49,
|
| 487 |
+
"learning_rate": 1.0406629200460836e-05,
|
| 488 |
+
"loss": 1.0848,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.49,
|
| 493 |
+
"learning_rate": 1.0213038870731443e-05,
|
| 494 |
+
"loss": 1.088,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.5,
|
| 499 |
+
"learning_rate": 1.0019368623238845e-05,
|
| 500 |
+
"loss": 1.088,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5,
|
| 505 |
+
"learning_rate": 9.82569110994992e-06,
|
| 506 |
+
"loss": 1.0889,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.51,
|
| 511 |
+
"learning_rate": 9.632078985557163e-06,
|
| 512 |
+
"loss": 1.0811,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.52,
|
| 517 |
+
"learning_rate": 9.438604880223595e-06,
|
| 518 |
+
"loss": 1.1001,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.52,
|
| 523 |
+
"learning_rate": 9.245341372336829e-06,
|
| 524 |
+
"loss": 1.092,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.53,
|
| 529 |
+
"learning_rate": 9.052360961282558e-06,
|
| 530 |
+
"loss": 1.1029,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.54,
|
| 535 |
+
"learning_rate": 8.859736040247719e-06,
|
| 536 |
+
"loss": 1.0768,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.54,
|
| 541 |
+
"learning_rate": 8.667538869063456e-06,
|
| 542 |
+
"loss": 1.0811,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.55,
|
| 547 |
+
"learning_rate": 8.475841547098128e-06,
|
| 548 |
+
"loss": 1.0795,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.55,
|
| 553 |
+
"learning_rate": 8.28471598621049e-06,
|
| 554 |
+
"loss": 1.0765,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.56,
|
| 559 |
+
"learning_rate": 8.094233883773255e-06,
|
| 560 |
+
"loss": 1.0957,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.57,
|
| 565 |
+
"learning_rate": 7.904466695777082e-06,
|
| 566 |
+
"loss": 1.0678,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.57,
|
| 571 |
+
"learning_rate": 7.715485610025124e-06,
|
| 572 |
+
"loss": 1.1001,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.58,
|
| 577 |
+
"learning_rate": 7.5273615194281845e-06,
|
| 578 |
+
"loss": 1.0732,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.58,
|
| 583 |
+
"learning_rate": 7.340164995410497e-06,
|
| 584 |
+
"loss": 1.0835,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.59,
|
| 589 |
+
"eval_loss": 1.0884634256362915,
|
| 590 |
+
"eval_runtime": 268.6576,
|
| 591 |
+
"eval_samples_per_second": 86.02,
|
| 592 |
+
"eval_steps_per_second": 10.753,
|
| 593 |
+
"step": 478
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.59,
|
| 597 |
+
"step": 478,
|
| 598 |
+
"total_flos": 1.0640133502713987e+19,
|
| 599 |
+
"train_loss": 1.1024827179050845,
|
| 600 |
+
"train_runtime": 38937.2818,
|
| 601 |
+
"train_samples_per_second": 5.338,
|
| 602 |
+
"train_steps_per_second": 0.021
|
| 603 |
+
}
|
| 604 |
+
],
|
| 605 |
+
"logging_steps": 5,
|
| 606 |
+
"max_steps": 811,
|
| 607 |
+
"num_input_tokens_seen": 0,
|
| 608 |
+
"num_train_epochs": 1,
|
| 609 |
+
"save_steps": 500,
|
| 610 |
+
"total_flos": 1.0640133502713987e+19,
|
| 611 |
+
"train_batch_size": null,
|
| 612 |
+
"trial_name": null,
|
| 613 |
+
"trial_params": null
|
| 614 |
+
}
|