Model save
Browse files- README.md +62 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Jan10_01-09-48_f82d07273834/events.out.tfevents.1736500249.f82d07273834.562872.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2534 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: P1_baseline_without_retrieval
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# P1_baseline_without_retrieval
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.13.1
|
| 59 |
+
- Transformers 4.47.1
|
| 60 |
+
- Pytorch 2.5.1+cu124
|
| 61 |
+
- Datasets 2.19.0
|
| 62 |
+
- Tokenizers 0.21.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80836ec890b44552676d830eecbca8469f70b9870a890ee3ab10abbbd945da24
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9997185477061638,
|
| 3 |
+
"total_flos": 3.866808531592151e+17,
|
| 4 |
+
"train_loss": 0.5711438672759713,
|
| 5 |
+
"train_runtime": 4148.7499,
|
| 6 |
+
"train_samples": 14211,
|
| 7 |
+
"train_samples_per_second": 3.425,
|
| 8 |
+
"train_steps_per_second": 0.428
|
| 9 |
+
}
|
runs/Jan10_01-09-48_f82d07273834/events.out.tfevents.1736500249.f82d07273834.562872.0
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:f4eb45569336a6fc315172dd3ea5f38dd47999a533aee98e2f857d652d2e33f2
|
| 3 |
+
size 82108
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9997185477061638,
|
| 3 |
+
"total_flos": 3.866808531592151e+17,
|
| 4 |
+
"train_loss": 0.5711438672759713,
|
| 5 |
+
"train_runtime": 4148.7499,
|
| 6 |
+
"train_samples": 14211,
|
| 7 |
+
"train_samples_per_second": 3.425,
|
| 8 |
+
"train_steps_per_second": 0.428
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9997185477061638,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1776,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0005629045876723895,
|
| 13 |
+
"grad_norm": 0.8329170942306519,
|
| 14 |
+
"learning_rate": 1.1235955056179775e-06,
|
| 15 |
+
"loss": 0.8354,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0028145229383619475,
|
| 20 |
+
"grad_norm": 1.3410223722457886,
|
| 21 |
+
"learning_rate": 5.617977528089888e-06,
|
| 22 |
+
"loss": 1.725,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.005629045876723895,
|
| 27 |
+
"grad_norm": 3.013509511947632,
|
| 28 |
+
"learning_rate": 1.1235955056179776e-05,
|
| 29 |
+
"loss": 1.6574,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008443568815085843,
|
| 34 |
+
"grad_norm": 2.5674707889556885,
|
| 35 |
+
"learning_rate": 1.6853932584269665e-05,
|
| 36 |
+
"loss": 1.2345,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01125809175344779,
|
| 41 |
+
"grad_norm": 2.4031896591186523,
|
| 42 |
+
"learning_rate": 2.2471910112359552e-05,
|
| 43 |
+
"loss": 1.5218,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.014072614691809739,
|
| 48 |
+
"grad_norm": 1.1180998086929321,
|
| 49 |
+
"learning_rate": 2.8089887640449443e-05,
|
| 50 |
+
"loss": 1.2468,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.016887137630171686,
|
| 55 |
+
"grad_norm": 3.0892934799194336,
|
| 56 |
+
"learning_rate": 3.370786516853933e-05,
|
| 57 |
+
"loss": 1.2287,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.019701660568533633,
|
| 62 |
+
"grad_norm": 1.6239148378372192,
|
| 63 |
+
"learning_rate": 3.9325842696629214e-05,
|
| 64 |
+
"loss": 1.1948,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02251618350689558,
|
| 69 |
+
"grad_norm": 1.0267276763916016,
|
| 70 |
+
"learning_rate": 4.4943820224719104e-05,
|
| 71 |
+
"loss": 1.0779,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02533070644525753,
|
| 76 |
+
"grad_norm": 0.9497658610343933,
|
| 77 |
+
"learning_rate": 5.0561797752808995e-05,
|
| 78 |
+
"loss": 0.5863,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.028145229383619477,
|
| 83 |
+
"grad_norm": 1.321252703666687,
|
| 84 |
+
"learning_rate": 5.6179775280898885e-05,
|
| 85 |
+
"loss": 0.9368,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.030959752321981424,
|
| 90 |
+
"grad_norm": 1.583485722541809,
|
| 91 |
+
"learning_rate": 6.179775280898876e-05,
|
| 92 |
+
"loss": 0.7446,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03377427526034337,
|
| 97 |
+
"grad_norm": 1.6845484972000122,
|
| 98 |
+
"learning_rate": 6.741573033707866e-05,
|
| 99 |
+
"loss": 0.6362,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03658879819870532,
|
| 104 |
+
"grad_norm": 1.6922656297683716,
|
| 105 |
+
"learning_rate": 7.303370786516854e-05,
|
| 106 |
+
"loss": 0.6806,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.039403321137067265,
|
| 111 |
+
"grad_norm": 1.3192064762115479,
|
| 112 |
+
"learning_rate": 7.865168539325843e-05,
|
| 113 |
+
"loss": 0.6754,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.042217844075429216,
|
| 118 |
+
"grad_norm": 1.6908262968063354,
|
| 119 |
+
"learning_rate": 8.426966292134831e-05,
|
| 120 |
+
"loss": 0.7982,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04503236701379116,
|
| 125 |
+
"grad_norm": 1.8348135948181152,
|
| 126 |
+
"learning_rate": 8.988764044943821e-05,
|
| 127 |
+
"loss": 0.5052,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.04784688995215311,
|
| 132 |
+
"grad_norm": 1.3342186212539673,
|
| 133 |
+
"learning_rate": 9.550561797752809e-05,
|
| 134 |
+
"loss": 0.8893,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05066141289051506,
|
| 139 |
+
"grad_norm": 1.4185314178466797,
|
| 140 |
+
"learning_rate": 0.00010112359550561799,
|
| 141 |
+
"loss": 0.8553,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.053475935828877004,
|
| 146 |
+
"grad_norm": 2.145559310913086,
|
| 147 |
+
"learning_rate": 0.00010674157303370786,
|
| 148 |
+
"loss": 0.4912,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.056290458767238954,
|
| 153 |
+
"grad_norm": 0.9930405020713806,
|
| 154 |
+
"learning_rate": 0.00011235955056179777,
|
| 155 |
+
"loss": 0.5233,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0591049817056009,
|
| 160 |
+
"grad_norm": 1.733180046081543,
|
| 161 |
+
"learning_rate": 0.00011797752808988764,
|
| 162 |
+
"loss": 0.8077,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06191950464396285,
|
| 167 |
+
"grad_norm": 2.0119330883026123,
|
| 168 |
+
"learning_rate": 0.00012359550561797752,
|
| 169 |
+
"loss": 0.3477,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0647340275823248,
|
| 174 |
+
"grad_norm": 0.9684231281280518,
|
| 175 |
+
"learning_rate": 0.00012921348314606744,
|
| 176 |
+
"loss": 0.6151,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06754855052068674,
|
| 181 |
+
"grad_norm": 0.8802971839904785,
|
| 182 |
+
"learning_rate": 0.00013483146067415732,
|
| 183 |
+
"loss": 0.7356,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.07036307345904869,
|
| 188 |
+
"grad_norm": 1.386469841003418,
|
| 189 |
+
"learning_rate": 0.0001404494382022472,
|
| 190 |
+
"loss": 0.6414,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07317759639741064,
|
| 195 |
+
"grad_norm": 1.002143144607544,
|
| 196 |
+
"learning_rate": 0.0001460674157303371,
|
| 197 |
+
"loss": 0.5492,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07599211933577259,
|
| 202 |
+
"grad_norm": 1.686691164970398,
|
| 203 |
+
"learning_rate": 0.00015168539325842697,
|
| 204 |
+
"loss": 0.5085,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07880664227413453,
|
| 209 |
+
"grad_norm": 1.0069544315338135,
|
| 210 |
+
"learning_rate": 0.00015730337078651685,
|
| 211 |
+
"loss": 0.7826,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.08162116521249649,
|
| 216 |
+
"grad_norm": 1.2447969913482666,
|
| 217 |
+
"learning_rate": 0.00016292134831460674,
|
| 218 |
+
"loss": 0.648,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08443568815085843,
|
| 223 |
+
"grad_norm": 1.3154926300048828,
|
| 224 |
+
"learning_rate": 0.00016853932584269662,
|
| 225 |
+
"loss": 0.5664,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08725021108922038,
|
| 230 |
+
"grad_norm": 0.6880718469619751,
|
| 231 |
+
"learning_rate": 0.00017415730337078653,
|
| 232 |
+
"loss": 0.7669,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09006473402758232,
|
| 237 |
+
"grad_norm": 2.1054015159606934,
|
| 238 |
+
"learning_rate": 0.00017977528089887642,
|
| 239 |
+
"loss": 0.2233,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.09287925696594428,
|
| 244 |
+
"grad_norm": 2.41121506690979,
|
| 245 |
+
"learning_rate": 0.0001853932584269663,
|
| 246 |
+
"loss": 0.496,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09569377990430622,
|
| 251 |
+
"grad_norm": 1.5123809576034546,
|
| 252 |
+
"learning_rate": 0.00019101123595505618,
|
| 253 |
+
"loss": 0.834,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09850830284266816,
|
| 258 |
+
"grad_norm": 0.9215847849845886,
|
| 259 |
+
"learning_rate": 0.00019662921348314607,
|
| 260 |
+
"loss": 0.5,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.10132282578103012,
|
| 265 |
+
"grad_norm": 1.3919601440429688,
|
| 266 |
+
"learning_rate": 0.00019999922700687455,
|
| 267 |
+
"loss": 0.4441,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.10413734871939206,
|
| 272 |
+
"grad_norm": 0.9048366546630859,
|
| 273 |
+
"learning_rate": 0.00019999053097145492,
|
| 274 |
+
"loss": 0.6331,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.10695187165775401,
|
| 279 |
+
"grad_norm": 0.9864197969436646,
|
| 280 |
+
"learning_rate": 0.000199972173502251,
|
| 281 |
+
"loss": 0.7634,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.10976639459611595,
|
| 286 |
+
"grad_norm": 1.0270127058029175,
|
| 287 |
+
"learning_rate": 0.00019994415637302547,
|
| 288 |
+
"loss": 0.5543,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11258091753447791,
|
| 293 |
+
"grad_norm": 1.1281390190124512,
|
| 294 |
+
"learning_rate": 0.00019990648229089103,
|
| 295 |
+
"loss": 0.7303,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.11539544047283985,
|
| 300 |
+
"grad_norm": 0.7723137140274048,
|
| 301 |
+
"learning_rate": 0.0001998591548960489,
|
| 302 |
+
"loss": 0.5619,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1182099634112018,
|
| 307 |
+
"grad_norm": 0.5689103603363037,
|
| 308 |
+
"learning_rate": 0.00019980217876143698,
|
| 309 |
+
"loss": 0.6684,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.12102448634956375,
|
| 314 |
+
"grad_norm": 2.17149019241333,
|
| 315 |
+
"learning_rate": 0.0001997355593922881,
|
| 316 |
+
"loss": 0.6625,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1238390092879257,
|
| 321 |
+
"grad_norm": 1.15530526638031,
|
| 322 |
+
"learning_rate": 0.000199659303225598,
|
| 323 |
+
"loss": 0.5027,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.12665353222628764,
|
| 328 |
+
"grad_norm": 0.933122456073761,
|
| 329 |
+
"learning_rate": 0.00019957341762950344,
|
| 330 |
+
"loss": 0.4687,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1294680551646496,
|
| 335 |
+
"grad_norm": 0.9144341945648193,
|
| 336 |
+
"learning_rate": 0.0001994779109025702,
|
| 337 |
+
"loss": 0.855,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.13228257810301153,
|
| 342 |
+
"grad_norm": 0.7820045351982117,
|
| 343 |
+
"learning_rate": 0.00019937279227299131,
|
| 344 |
+
"loss": 0.5393,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13509710104137349,
|
| 349 |
+
"grad_norm": 1.2164809703826904,
|
| 350 |
+
"learning_rate": 0.00019925807189769533,
|
| 351 |
+
"loss": 0.8503,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.13791162397973544,
|
| 356 |
+
"grad_norm": 0.8118152022361755,
|
| 357 |
+
"learning_rate": 0.0001991337608613649,
|
| 358 |
+
"loss": 0.6439,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.14072614691809737,
|
| 363 |
+
"grad_norm": 1.0747621059417725,
|
| 364 |
+
"learning_rate": 0.00019899987117536587,
|
| 365 |
+
"loss": 0.5872,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.14354066985645933,
|
| 370 |
+
"grad_norm": 2.370304822921753,
|
| 371 |
+
"learning_rate": 0.00019885641577658666,
|
| 372 |
+
"loss": 0.5854,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1463551927948213,
|
| 377 |
+
"grad_norm": 0.8851784467697144,
|
| 378 |
+
"learning_rate": 0.00019870340852618803,
|
| 379 |
+
"loss": 0.6521,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.14916971573318322,
|
| 384 |
+
"grad_norm": 1.0250051021575928,
|
| 385 |
+
"learning_rate": 0.00019854086420826418,
|
| 386 |
+
"loss": 0.7139,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.15198423867154517,
|
| 391 |
+
"grad_norm": 0.45537930727005005,
|
| 392 |
+
"learning_rate": 0.00019836879852841387,
|
| 393 |
+
"loss": 0.5634,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.15479876160990713,
|
| 398 |
+
"grad_norm": 0.8726896047592163,
|
| 399 |
+
"learning_rate": 0.0001981872281122231,
|
| 400 |
+
"loss": 0.4579,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15761328454826906,
|
| 405 |
+
"grad_norm": 1.0558394193649292,
|
| 406 |
+
"learning_rate": 0.0001979961705036587,
|
| 407 |
+
"loss": 0.7129,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.16042780748663102,
|
| 412 |
+
"grad_norm": 0.9016023874282837,
|
| 413 |
+
"learning_rate": 0.000197795644163373,
|
| 414 |
+
"loss": 0.67,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.16324233042499298,
|
| 419 |
+
"grad_norm": 1.2795695066452026,
|
| 420 |
+
"learning_rate": 0.00019758566846692029,
|
| 421 |
+
"loss": 0.6221,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.1660568533633549,
|
| 426 |
+
"grad_norm": 0.9220066666603088,
|
| 427 |
+
"learning_rate": 0.00019736626370288457,
|
| 428 |
+
"loss": 0.6101,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16887137630171686,
|
| 433 |
+
"grad_norm": 0.8552654385566711,
|
| 434 |
+
"learning_rate": 0.00019713745107091923,
|
| 435 |
+
"loss": 0.5985,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1716858992400788,
|
| 440 |
+
"grad_norm": 0.9308118224143982,
|
| 441 |
+
"learning_rate": 0.0001968992526796987,
|
| 442 |
+
"loss": 0.7646,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17450042217844075,
|
| 447 |
+
"grad_norm": 1.162402868270874,
|
| 448 |
+
"learning_rate": 0.00019665169154478213,
|
| 449 |
+
"loss": 0.8352,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1773149451168027,
|
| 454 |
+
"grad_norm": 0.7268826961517334,
|
| 455 |
+
"learning_rate": 0.00019639479158638972,
|
| 456 |
+
"loss": 0.5086,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.18012946805516464,
|
| 461 |
+
"grad_norm": 0.9068782329559326,
|
| 462 |
+
"learning_rate": 0.00019612857762709124,
|
| 463 |
+
"loss": 0.7053,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.1829439909935266,
|
| 468 |
+
"grad_norm": 1.0525766611099243,
|
| 469 |
+
"learning_rate": 0.0001958530753894078,
|
| 470 |
+
"loss": 0.8175,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.18575851393188855,
|
| 475 |
+
"grad_norm": 0.8571164608001709,
|
| 476 |
+
"learning_rate": 0.0001955683114933263,
|
| 477 |
+
"loss": 0.6137,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.18857303687025048,
|
| 482 |
+
"grad_norm": 1.1700630187988281,
|
| 483 |
+
"learning_rate": 0.00019527431345372738,
|
| 484 |
+
"loss": 0.4982,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.19138755980861244,
|
| 489 |
+
"grad_norm": 0.9724971055984497,
|
| 490 |
+
"learning_rate": 0.00019497110967772692,
|
| 491 |
+
"loss": 0.603,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.1942020827469744,
|
| 496 |
+
"grad_norm": 1.852655053138733,
|
| 497 |
+
"learning_rate": 0.000194658729461931,
|
| 498 |
+
"loss": 0.5137,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.19701660568533633,
|
| 503 |
+
"grad_norm": 1.018691062927246,
|
| 504 |
+
"learning_rate": 0.00019433720298960537,
|
| 505 |
+
"loss": 0.7321,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.19983112862369828,
|
| 510 |
+
"grad_norm": 1.1386247873306274,
|
| 511 |
+
"learning_rate": 0.00019400656132775908,
|
| 512 |
+
"loss": 0.6923,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.20264565156206024,
|
| 517 |
+
"grad_norm": 0.7724803686141968,
|
| 518 |
+
"learning_rate": 0.0001936668364241424,
|
| 519 |
+
"loss": 0.4945,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.20546017450042217,
|
| 524 |
+
"grad_norm": 0.49107155203819275,
|
| 525 |
+
"learning_rate": 0.00019331806110416027,
|
| 526 |
+
"loss": 0.6003,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.20827469743878413,
|
| 531 |
+
"grad_norm": 0.6642640829086304,
|
| 532 |
+
"learning_rate": 0.00019296026906770027,
|
| 533 |
+
"loss": 0.2862,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.2110892203771461,
|
| 538 |
+
"grad_norm": 1.6255823373794556,
|
| 539 |
+
"learning_rate": 0.0001925934948858767,
|
| 540 |
+
"loss": 0.6002,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.21390374331550802,
|
| 545 |
+
"grad_norm": 1.1237847805023193,
|
| 546 |
+
"learning_rate": 0.00019221777399768998,
|
| 547 |
+
"loss": 0.6876,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.21671826625386997,
|
| 552 |
+
"grad_norm": 1.4545127153396606,
|
| 553 |
+
"learning_rate": 0.00019183314270660248,
|
| 554 |
+
"loss": 0.648,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2195327891922319,
|
| 559 |
+
"grad_norm": 1.7229652404785156,
|
| 560 |
+
"learning_rate": 0.00019143963817703087,
|
| 561 |
+
"loss": 0.4523,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.22234731213059386,
|
| 566 |
+
"grad_norm": 1.0194050073623657,
|
| 567 |
+
"learning_rate": 0.00019103729843075498,
|
| 568 |
+
"loss": 0.5688,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.22516183506895582,
|
| 573 |
+
"grad_norm": 1.1462711095809937,
|
| 574 |
+
"learning_rate": 0.0001906261623432441,
|
| 575 |
+
"loss": 0.608,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.22797635800731775,
|
| 580 |
+
"grad_norm": 0.7898936867713928,
|
| 581 |
+
"learning_rate": 0.00019020626963990074,
|
| 582 |
+
"loss": 0.5458,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.2307908809456797,
|
| 587 |
+
"grad_norm": 3.30757474899292,
|
| 588 |
+
"learning_rate": 0.00018977766089222208,
|
| 589 |
+
"loss": 0.491,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.23360540388404166,
|
| 594 |
+
"grad_norm": 1.2833960056304932,
|
| 595 |
+
"learning_rate": 0.00018934037751387997,
|
| 596 |
+
"loss": 0.5706,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2364199268224036,
|
| 601 |
+
"grad_norm": 1.2525941133499146,
|
| 602 |
+
"learning_rate": 0.00018889446175671926,
|
| 603 |
+
"loss": 0.7208,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.23923444976076555,
|
| 608 |
+
"grad_norm": 0.9608438014984131,
|
| 609 |
+
"learning_rate": 0.00018843995670667543,
|
| 610 |
+
"loss": 0.5394,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2420489726991275,
|
| 615 |
+
"grad_norm": 0.8090662360191345,
|
| 616 |
+
"learning_rate": 0.00018797690627961132,
|
| 617 |
+
"loss": 0.4402,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.24486349563748944,
|
| 622 |
+
"grad_norm": 0.8819811344146729,
|
| 623 |
+
"learning_rate": 0.00018750535521707396,
|
| 624 |
+
"loss": 0.4728,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2476780185758514,
|
| 629 |
+
"grad_norm": 0.9342750906944275,
|
| 630 |
+
"learning_rate": 0.0001870253490819713,
|
| 631 |
+
"loss": 0.5013,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.25049254151421335,
|
| 636 |
+
"grad_norm": 0.7526805400848389,
|
| 637 |
+
"learning_rate": 0.00018653693425417002,
|
| 638 |
+
"loss": 0.4606,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2533070644525753,
|
| 643 |
+
"grad_norm": 1.2073928117752075,
|
| 644 |
+
"learning_rate": 0.00018604015792601396,
|
| 645 |
+
"loss": 0.7602,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.2561215873909372,
|
| 650 |
+
"grad_norm": 0.48888304829597473,
|
| 651 |
+
"learning_rate": 0.00018553506809776424,
|
| 652 |
+
"loss": 0.8642,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.2589361103292992,
|
| 657 |
+
"grad_norm": 1.424832820892334,
|
| 658 |
+
"learning_rate": 0.00018502171357296144,
|
| 659 |
+
"loss": 0.7515,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.2617506332676611,
|
| 664 |
+
"grad_norm": 0.4335147738456726,
|
| 665 |
+
"learning_rate": 0.00018450014395370983,
|
| 666 |
+
"loss": 0.6242,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.26456515620602306,
|
| 671 |
+
"grad_norm": 1.4052842855453491,
|
| 672 |
+
"learning_rate": 0.00018397040963588488,
|
| 673 |
+
"loss": 0.405,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.26737967914438504,
|
| 678 |
+
"grad_norm": 0.8757149577140808,
|
| 679 |
+
"learning_rate": 0.0001834325618042636,
|
| 680 |
+
"loss": 0.6849,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.27019420208274697,
|
| 685 |
+
"grad_norm": 2.241838216781616,
|
| 686 |
+
"learning_rate": 0.00018288665242757903,
|
| 687 |
+
"loss": 0.5653,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.2730087250211089,
|
| 692 |
+
"grad_norm": 1.2316606044769287,
|
| 693 |
+
"learning_rate": 0.00018233273425349885,
|
| 694 |
+
"loss": 0.3658,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.2758232479594709,
|
| 699 |
+
"grad_norm": 1.174371361732483,
|
| 700 |
+
"learning_rate": 0.0001817708608035286,
|
| 701 |
+
"loss": 0.6299,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.2786377708978328,
|
| 706 |
+
"grad_norm": 0.7687806487083435,
|
| 707 |
+
"learning_rate": 0.00018120108636784034,
|
| 708 |
+
"loss": 0.4896,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.28145229383619474,
|
| 713 |
+
"grad_norm": 1.2060645818710327,
|
| 714 |
+
"learning_rate": 0.00018062346600002699,
|
| 715 |
+
"loss": 0.6195,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.28426681677455673,
|
| 720 |
+
"grad_norm": 0.9059650897979736,
|
| 721 |
+
"learning_rate": 0.0001800380555117827,
|
| 722 |
+
"loss": 0.7028,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.28708133971291866,
|
| 727 |
+
"grad_norm": 1.1394221782684326,
|
| 728 |
+
"learning_rate": 0.00017944491146751026,
|
| 729 |
+
"loss": 0.5942,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2898958626512806,
|
| 734 |
+
"grad_norm": 0.8699471354484558,
|
| 735 |
+
"learning_rate": 0.0001788440911788556,
|
| 736 |
+
"loss": 0.336,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2927103855896426,
|
| 741 |
+
"grad_norm": 1.5057145357131958,
|
| 742 |
+
"learning_rate": 0.0001782356526991702,
|
| 743 |
+
"loss": 0.5421,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.2955249085280045,
|
| 748 |
+
"grad_norm": 1.7533260583877563,
|
| 749 |
+
"learning_rate": 0.00017761965481790162,
|
| 750 |
+
"loss": 0.5161,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.29833943146636643,
|
| 755 |
+
"grad_norm": 0.7779251933097839,
|
| 756 |
+
"learning_rate": 0.00017699615705491325,
|
| 757 |
+
"loss": 0.7673,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.3011539544047284,
|
| 762 |
+
"grad_norm": 1.0537793636322021,
|
| 763 |
+
"learning_rate": 0.00017636521965473323,
|
| 764 |
+
"loss": 0.5704,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.30396847734309035,
|
| 769 |
+
"grad_norm": 1.4870874881744385,
|
| 770 |
+
"learning_rate": 0.00017572690358073326,
|
| 771 |
+
"loss": 0.5846,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.3067830002814523,
|
| 776 |
+
"grad_norm": 0.5922363996505737,
|
| 777 |
+
"learning_rate": 0.00017508127050923835,
|
| 778 |
+
"loss": 0.7014,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.30959752321981426,
|
| 783 |
+
"grad_norm": 0.8268614411354065,
|
| 784 |
+
"learning_rate": 0.00017442838282356727,
|
| 785 |
+
"loss": 0.7332,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.3124120461581762,
|
| 790 |
+
"grad_norm": 0.6626672148704529,
|
| 791 |
+
"learning_rate": 0.00017376830360800498,
|
| 792 |
+
"loss": 0.6285,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3152265690965381,
|
| 797 |
+
"grad_norm": 0.7634074091911316,
|
| 798 |
+
"learning_rate": 0.00017310109664170703,
|
| 799 |
+
"loss": 0.5794,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.3180410920349001,
|
| 804 |
+
"grad_norm": 0.6927458047866821,
|
| 805 |
+
"learning_rate": 0.00017242682639253718,
|
| 806 |
+
"loss": 0.3854,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.32085561497326204,
|
| 811 |
+
"grad_norm": 0.7036980390548706,
|
| 812 |
+
"learning_rate": 0.00017174555801083814,
|
| 813 |
+
"loss": 0.4077,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.32367013791162397,
|
| 818 |
+
"grad_norm": 0.5988078117370605,
|
| 819 |
+
"learning_rate": 0.00017105735732313667,
|
| 820 |
+
"loss": 0.4527,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.32648466084998595,
|
| 825 |
+
"grad_norm": 1.1813197135925293,
|
| 826 |
+
"learning_rate": 0.00017036229082578307,
|
| 827 |
+
"loss": 0.8273,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.3292991837883479,
|
| 832 |
+
"grad_norm": 0.7539934515953064,
|
| 833 |
+
"learning_rate": 0.00016966042567852615,
|
| 834 |
+
"loss": 0.6084,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3321137067267098,
|
| 839 |
+
"grad_norm": 1.3654534816741943,
|
| 840 |
+
"learning_rate": 0.00016895182969802386,
|
| 841 |
+
"loss": 0.8049,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.3349282296650718,
|
| 846 |
+
"grad_norm": 1.3293468952178955,
|
| 847 |
+
"learning_rate": 0.00016823657135129087,
|
| 848 |
+
"loss": 0.5769,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.3377427526034337,
|
| 853 |
+
"grad_norm": 0.7219970226287842,
|
| 854 |
+
"learning_rate": 0.00016751471974908288,
|
| 855 |
+
"loss": 0.6883,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.34055727554179566,
|
| 860 |
+
"grad_norm": 0.3910175561904907,
|
| 861 |
+
"learning_rate": 0.00016678634463921884,
|
| 862 |
+
"loss": 0.4406,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3433717984801576,
|
| 867 |
+
"grad_norm": 0.6810513138771057,
|
| 868 |
+
"learning_rate": 0.00016605151639984187,
|
| 869 |
+
"loss": 0.532,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.34618632141851957,
|
| 874 |
+
"grad_norm": 1.6218785047531128,
|
| 875 |
+
"learning_rate": 0.00016531030603261884,
|
| 876 |
+
"loss": 0.8189,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.3490008443568815,
|
| 881 |
+
"grad_norm": 1.138554334640503,
|
| 882 |
+
"learning_rate": 0.00016456278515588024,
|
| 883 |
+
"loss": 0.5942,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.35181536729524343,
|
| 888 |
+
"grad_norm": 0.9244788289070129,
|
| 889 |
+
"learning_rate": 0.00016380902599769982,
|
| 890 |
+
"loss": 0.7253,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.3546298902336054,
|
| 895 |
+
"grad_norm": 1.2546799182891846,
|
| 896 |
+
"learning_rate": 0.00016304910138891597,
|
| 897 |
+
"loss": 0.6356,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.35744441317196735,
|
| 902 |
+
"grad_norm": 0.9498732089996338,
|
| 903 |
+
"learning_rate": 0.00016228308475609433,
|
| 904 |
+
"loss": 0.6773,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.3602589361103293,
|
| 909 |
+
"grad_norm": 0.605629026889801,
|
| 910 |
+
"learning_rate": 0.00016151105011443314,
|
| 911 |
+
"loss": 0.5681,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.36307345904869126,
|
| 916 |
+
"grad_norm": 0.8649378418922424,
|
| 917 |
+
"learning_rate": 0.00016073307206061177,
|
| 918 |
+
"loss": 0.657,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3658879819870532,
|
| 923 |
+
"grad_norm": 0.9192129969596863,
|
| 924 |
+
"learning_rate": 0.00015994922576558263,
|
| 925 |
+
"loss": 0.501,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3687025049254151,
|
| 930 |
+
"grad_norm": 0.9517626166343689,
|
| 931 |
+
"learning_rate": 0.00015915958696730814,
|
| 932 |
+
"loss": 0.4914,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.3715170278637771,
|
| 937 |
+
"grad_norm": 0.7139463424682617,
|
| 938 |
+
"learning_rate": 0.0001583642319634426,
|
| 939 |
+
"loss": 0.6748,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.37433155080213903,
|
| 944 |
+
"grad_norm": 0.7017699480056763,
|
| 945 |
+
"learning_rate": 0.00015756323760396002,
|
| 946 |
+
"loss": 0.4724,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.37714607374050096,
|
| 951 |
+
"grad_norm": 0.69412761926651,
|
| 952 |
+
"learning_rate": 0.00015675668128372854,
|
| 953 |
+
"loss": 0.3082,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.37996059667886295,
|
| 958 |
+
"grad_norm": 0.9961652755737305,
|
| 959 |
+
"learning_rate": 0.00015594464093503246,
|
| 960 |
+
"loss": 0.5198,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.3827751196172249,
|
| 965 |
+
"grad_norm": 0.8897234797477722,
|
| 966 |
+
"learning_rate": 0.00015512719502004197,
|
| 967 |
+
"loss": 0.6707,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.3855896425555868,
|
| 972 |
+
"grad_norm": 1.5628478527069092,
|
| 973 |
+
"learning_rate": 0.0001543044225232319,
|
| 974 |
+
"loss": 0.7418,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.3884041654939488,
|
| 979 |
+
"grad_norm": 0.98553866147995,
|
| 980 |
+
"learning_rate": 0.00015347640294375005,
|
| 981 |
+
"loss": 0.6553,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.3912186884323107,
|
| 986 |
+
"grad_norm": 1.6320457458496094,
|
| 987 |
+
"learning_rate": 0.0001526432162877356,
|
| 988 |
+
"loss": 0.7794,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.39403321137067265,
|
| 993 |
+
"grad_norm": 0.7922711372375488,
|
| 994 |
+
"learning_rate": 0.0001518049430605887,
|
| 995 |
+
"loss": 0.4737,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.39684773430903464,
|
| 1000 |
+
"grad_norm": 2.2716257572174072,
|
| 1001 |
+
"learning_rate": 0.00015096166425919175,
|
| 1002 |
+
"loss": 0.6215,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.39966225724739657,
|
| 1007 |
+
"grad_norm": 0.6248972415924072,
|
| 1008 |
+
"learning_rate": 0.0001501134613640832,
|
| 1009 |
+
"loss": 0.431,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4024767801857585,
|
| 1014 |
+
"grad_norm": 0.7897845506668091,
|
| 1015 |
+
"learning_rate": 0.00014926041633158454,
|
| 1016 |
+
"loss": 0.6622,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.4052913031241205,
|
| 1021 |
+
"grad_norm": 0.35586240887641907,
|
| 1022 |
+
"learning_rate": 0.0001484026115858815,
|
| 1023 |
+
"loss": 0.2137,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.4081058260624824,
|
| 1028 |
+
"grad_norm": 1.1606733798980713,
|
| 1029 |
+
"learning_rate": 0.00014754013001105998,
|
| 1030 |
+
"loss": 0.5948,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.41092034900084434,
|
| 1035 |
+
"grad_norm": 1.2706083059310913,
|
| 1036 |
+
"learning_rate": 0.00014667305494309727,
|
| 1037 |
+
"loss": 0.9048,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.41373487193920633,
|
| 1042 |
+
"grad_norm": 0.4990655779838562,
|
| 1043 |
+
"learning_rate": 0.00014580147016181005,
|
| 1044 |
+
"loss": 0.6926,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.41654939487756826,
|
| 1049 |
+
"grad_norm": 0.9936563968658447,
|
| 1050 |
+
"learning_rate": 0.00014492545988275933,
|
| 1051 |
+
"loss": 0.8315,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.4193639178159302,
|
| 1056 |
+
"grad_norm": 0.9066222906112671,
|
| 1057 |
+
"learning_rate": 0.0001440451087491129,
|
| 1058 |
+
"loss": 0.4171,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4221784407542922,
|
| 1063 |
+
"grad_norm": 1.0959652662277222,
|
| 1064 |
+
"learning_rate": 0.00014316050182346733,
|
| 1065 |
+
"loss": 0.586,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4249929636926541,
|
| 1070 |
+
"grad_norm": 0.726209819316864,
|
| 1071 |
+
"learning_rate": 0.0001422717245796285,
|
| 1072 |
+
"loss": 0.485,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.42780748663101603,
|
| 1077 |
+
"grad_norm": 1.6239256858825684,
|
| 1078 |
+
"learning_rate": 0.00014137886289435295,
|
| 1079 |
+
"loss": 0.4708,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.430622009569378,
|
| 1084 |
+
"grad_norm": 1.3807324171066284,
|
| 1085 |
+
"learning_rate": 0.00014048200303905034,
|
| 1086 |
+
"loss": 0.4916,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.43343653250773995,
|
| 1091 |
+
"grad_norm": 0.9176377654075623,
|
| 1092 |
+
"learning_rate": 0.00013958123167144733,
|
| 1093 |
+
"loss": 0.5487,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.4362510554461019,
|
| 1098 |
+
"grad_norm": 1.0780225992202759,
|
| 1099 |
+
"learning_rate": 0.0001386766358272146,
|
| 1100 |
+
"loss": 0.6175,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.4390655783844638,
|
| 1105 |
+
"grad_norm": 2.6700491905212402,
|
| 1106 |
+
"learning_rate": 0.00013776830291155703,
|
| 1107 |
+
"loss": 0.7033,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.4418801013228258,
|
| 1112 |
+
"grad_norm": 0.9618711471557617,
|
| 1113 |
+
"learning_rate": 0.00013685632069076846,
|
| 1114 |
+
"loss": 0.6698,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.4446946242611877,
|
| 1119 |
+
"grad_norm": 1.3910859823226929,
|
| 1120 |
+
"learning_rate": 0.00013594077728375128,
|
| 1121 |
+
"loss": 0.8375,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.44750914719954965,
|
| 1126 |
+
"grad_norm": 0.755133867263794,
|
| 1127 |
+
"learning_rate": 0.00013502176115350213,
|
| 1128 |
+
"loss": 0.3719,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.45032367013791164,
|
| 1133 |
+
"grad_norm": 0.5240243077278137,
|
| 1134 |
+
"learning_rate": 0.00013409936109856424,
|
| 1135 |
+
"loss": 0.3539,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.45313819307627357,
|
| 1140 |
+
"grad_norm": 1.1372967958450317,
|
| 1141 |
+
"learning_rate": 0.00013317366624444744,
|
| 1142 |
+
"loss": 0.7051,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4559527160146355,
|
| 1147 |
+
"grad_norm": 1.4525517225265503,
|
| 1148 |
+
"learning_rate": 0.00013224476603501662,
|
| 1149 |
+
"loss": 0.6504,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.4587672389529975,
|
| 1154 |
+
"grad_norm": 0.658799946308136,
|
| 1155 |
+
"learning_rate": 0.00013131275022384918,
|
| 1156 |
+
"loss": 0.4961,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4615817618913594,
|
| 1161 |
+
"grad_norm": 0.8785876631736755,
|
| 1162 |
+
"learning_rate": 0.00013037770886556294,
|
| 1163 |
+
"loss": 0.4614,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.46439628482972134,
|
| 1168 |
+
"grad_norm": 1.465197205543518,
|
| 1169 |
+
"learning_rate": 0.0001294397323071145,
|
| 1170 |
+
"loss": 0.4032,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4672108077680833,
|
| 1175 |
+
"grad_norm": 1.070615291595459,
|
| 1176 |
+
"learning_rate": 0.00012849891117906978,
|
| 1177 |
+
"loss": 0.9079,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.47002533070644525,
|
| 1182 |
+
"grad_norm": 0.5417959690093994,
|
| 1183 |
+
"learning_rate": 0.00012755533638684704,
|
| 1184 |
+
"loss": 0.33,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.4728398536448072,
|
| 1189 |
+
"grad_norm": 0.9827715754508972,
|
| 1190 |
+
"learning_rate": 0.00012660909910193303,
|
| 1191 |
+
"loss": 0.5105,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.47565437658316917,
|
| 1196 |
+
"grad_norm": 0.5091266632080078,
|
| 1197 |
+
"learning_rate": 0.0001256602907530739,
|
| 1198 |
+
"loss": 0.2981,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.4784688995215311,
|
| 1203 |
+
"grad_norm": 0.7054405212402344,
|
| 1204 |
+
"learning_rate": 0.000124709003017441,
|
| 1205 |
+
"loss": 0.3981,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.48128342245989303,
|
| 1210 |
+
"grad_norm": 0.7525174617767334,
|
| 1211 |
+
"learning_rate": 0.00012375532781177257,
|
| 1212 |
+
"loss": 0.6399,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.484097945398255,
|
| 1217 |
+
"grad_norm": 1.1248599290847778,
|
| 1218 |
+
"learning_rate": 0.0001227993572834926,
|
| 1219 |
+
"loss": 0.624,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.48691246833661694,
|
| 1224 |
+
"grad_norm": 0.6768050193786621,
|
| 1225 |
+
"learning_rate": 0.00012184118380180716,
|
| 1226 |
+
"loss": 0.6998,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.4897269912749789,
|
| 1231 |
+
"grad_norm": 0.8580127954483032,
|
| 1232 |
+
"learning_rate": 0.0001208808999487793,
|
| 1233 |
+
"loss": 0.6036,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.49254151421334086,
|
| 1238 |
+
"grad_norm": 1.0916856527328491,
|
| 1239 |
+
"learning_rate": 0.0001199185985103836,
|
| 1240 |
+
"loss": 0.6118,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.4953560371517028,
|
| 1245 |
+
"grad_norm": 0.9223160147666931,
|
| 1246 |
+
"learning_rate": 0.00011895437246754074,
|
| 1247 |
+
"loss": 0.5047,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.4981705600900647,
|
| 1252 |
+
"grad_norm": 2.015151262283325,
|
| 1253 |
+
"learning_rate": 0.00011798831498713334,
|
| 1254 |
+
"loss": 0.4731,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5009850830284267,
|
| 1259 |
+
"grad_norm": 1.1331337690353394,
|
| 1260 |
+
"learning_rate": 0.00011702051941300396,
|
| 1261 |
+
"loss": 0.5136,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.5037996059667886,
|
| 1266 |
+
"grad_norm": 1.0576162338256836,
|
| 1267 |
+
"learning_rate": 0.00011605107925693582,
|
| 1268 |
+
"loss": 0.4992,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5066141289051506,
|
| 1273 |
+
"grad_norm": 0.8101834654808044,
|
| 1274 |
+
"learning_rate": 0.00011508008818961731,
|
| 1275 |
+
"loss": 0.4718,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.5094286518435125,
|
| 1280 |
+
"grad_norm": 0.922261655330658,
|
| 1281 |
+
"learning_rate": 0.00011410764003159147,
|
| 1282 |
+
"loss": 0.3622,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5122431747818744,
|
| 1287 |
+
"grad_norm": 0.6725795865058899,
|
| 1288 |
+
"learning_rate": 0.00011313382874419031,
|
| 1289 |
+
"loss": 0.4803,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5150576977202365,
|
| 1294 |
+
"grad_norm": 1.7679307460784912,
|
| 1295 |
+
"learning_rate": 0.00011215874842045631,
|
| 1296 |
+
"loss": 0.4316,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.5178722206585984,
|
| 1301 |
+
"grad_norm": 0.7769971489906311,
|
| 1302 |
+
"learning_rate": 0.00011118249327605055,
|
| 1303 |
+
"loss": 0.3043,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.5206867435969603,
|
| 1308 |
+
"grad_norm": 1.3879740238189697,
|
| 1309 |
+
"learning_rate": 0.00011020515764014942,
|
| 1310 |
+
"loss": 0.4857,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5235012665353223,
|
| 1315 |
+
"grad_norm": 0.9753875136375427,
|
| 1316 |
+
"learning_rate": 0.00010922683594633021,
|
| 1317 |
+
"loss": 0.5712,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5263157894736842,
|
| 1322 |
+
"grad_norm": 1.2720959186553955,
|
| 1323 |
+
"learning_rate": 0.00010824762272344651,
|
| 1324 |
+
"loss": 0.509,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5291303124120461,
|
| 1329 |
+
"grad_norm": 0.8127233386039734,
|
| 1330 |
+
"learning_rate": 0.00010726761258649461,
|
| 1331 |
+
"loss": 0.57,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.5319448353504082,
|
| 1336 |
+
"grad_norm": 1.2257153987884521,
|
| 1337 |
+
"learning_rate": 0.00010628690022747132,
|
| 1338 |
+
"loss": 0.5516,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5347593582887701,
|
| 1343 |
+
"grad_norm": 0.7144739627838135,
|
| 1344 |
+
"learning_rate": 0.00010530558040622472,
|
| 1345 |
+
"loss": 0.6066,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.537573881227132,
|
| 1350 |
+
"grad_norm": 0.7518823146820068,
|
| 1351 |
+
"learning_rate": 0.00010432374794129791,
|
| 1352 |
+
"loss": 0.6092,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5403884041654939,
|
| 1357 |
+
"grad_norm": 0.9559532403945923,
|
| 1358 |
+
"learning_rate": 0.00010334149770076747,
|
| 1359 |
+
"loss": 0.5019,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.5432029271038559,
|
| 1364 |
+
"grad_norm": 1.0719863176345825,
|
| 1365 |
+
"learning_rate": 0.00010235892459307688,
|
| 1366 |
+
"loss": 0.4403,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.5460174500422178,
|
| 1371 |
+
"grad_norm": 0.7807120084762573,
|
| 1372 |
+
"learning_rate": 0.00010137612355786618,
|
| 1373 |
+
"loss": 0.5249,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.5488319729805798,
|
| 1378 |
+
"grad_norm": 1.4584418535232544,
|
| 1379 |
+
"learning_rate": 0.00010039318955679857,
|
| 1380 |
+
"loss": 0.475,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.5516464959189418,
|
| 1385 |
+
"grad_norm": 0.7352472543716431,
|
| 1386 |
+
"learning_rate": 9.941021756438488e-05,
|
| 1387 |
+
"loss": 0.64,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.5544610188573037,
|
| 1392 |
+
"grad_norm": 1.0791490077972412,
|
| 1393 |
+
"learning_rate": 9.842730255880678e-05,
|
| 1394 |
+
"loss": 0.5755,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5572755417956656,
|
| 1399 |
+
"grad_norm": 0.9303123354911804,
|
| 1400 |
+
"learning_rate": 9.744453951273968e-05,
|
| 1401 |
+
"loss": 0.6485,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5600900647340276,
|
| 1406 |
+
"grad_norm": 0.6764497756958008,
|
| 1407 |
+
"learning_rate": 9.646202338417613e-05,
|
| 1408 |
+
"loss": 0.4572,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.5629045876723895,
|
| 1413 |
+
"grad_norm": 0.9425994157791138,
|
| 1414 |
+
"learning_rate": 9.547984910725064e-05,
|
| 1415 |
+
"loss": 0.733,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5657191106107515,
|
| 1420 |
+
"grad_norm": 0.9432514905929565,
|
| 1421 |
+
"learning_rate": 9.449811158306684e-05,
|
| 1422 |
+
"loss": 0.4557,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.5685336335491135,
|
| 1427 |
+
"grad_norm": 0.999247133731842,
|
| 1428 |
+
"learning_rate": 9.35169056705278e-05,
|
| 1429 |
+
"loss": 0.6724,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.5713481564874754,
|
| 1434 |
+
"grad_norm": 1.0435142517089844,
|
| 1435 |
+
"learning_rate": 9.253632617717038e-05,
|
| 1436 |
+
"loss": 0.5394,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.5741626794258373,
|
| 1441 |
+
"grad_norm": 1.8879817724227905,
|
| 1442 |
+
"learning_rate": 9.155646785000467e-05,
|
| 1443 |
+
"loss": 0.5066,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.5769772023641992,
|
| 1448 |
+
"grad_norm": 0.7503070831298828,
|
| 1449 |
+
"learning_rate": 9.057742536635913e-05,
|
| 1450 |
+
"loss": 0.6197,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.5797917253025612,
|
| 1455 |
+
"grad_norm": 0.9366083741188049,
|
| 1456 |
+
"learning_rate": 8.959929332473262e-05,
|
| 1457 |
+
"loss": 0.5373,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5826062482409231,
|
| 1462 |
+
"grad_norm": 0.5995301008224487,
|
| 1463 |
+
"learning_rate": 8.86221662356539e-05,
|
| 1464 |
+
"loss": 0.4054,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.5854207711792851,
|
| 1469 |
+
"grad_norm": 0.5817670226097107,
|
| 1470 |
+
"learning_rate": 8.764613851254968e-05,
|
| 1471 |
+
"loss": 0.5262,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5882352941176471,
|
| 1476 |
+
"grad_norm": 0.5300823450088501,
|
| 1477 |
+
"learning_rate": 8.667130446262214e-05,
|
| 1478 |
+
"loss": 0.678,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.591049817056009,
|
| 1483 |
+
"grad_norm": 0.9397202134132385,
|
| 1484 |
+
"learning_rate": 8.569775827773656e-05,
|
| 1485 |
+
"loss": 0.6118,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.5938643399943709,
|
| 1490 |
+
"grad_norm": 0.8151072859764099,
|
| 1491 |
+
"learning_rate": 8.472559402532021e-05,
|
| 1492 |
+
"loss": 0.5034,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.5966788629327329,
|
| 1497 |
+
"grad_norm": 0.7164279818534851,
|
| 1498 |
+
"learning_rate": 8.375490563927328e-05,
|
| 1499 |
+
"loss": 0.2909,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5994933858710948,
|
| 1504 |
+
"grad_norm": 0.7771260738372803,
|
| 1505 |
+
"learning_rate": 8.278578691089249e-05,
|
| 1506 |
+
"loss": 0.5102,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.6023079088094568,
|
| 1511 |
+
"grad_norm": 0.5859299302101135,
|
| 1512 |
+
"learning_rate": 8.181833147980894e-05,
|
| 1513 |
+
"loss": 0.3361,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6051224317478188,
|
| 1518 |
+
"grad_norm": 1.3162269592285156,
|
| 1519 |
+
"learning_rate": 8.085263282493998e-05,
|
| 1520 |
+
"loss": 0.5598,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.6079369546861807,
|
| 1525 |
+
"grad_norm": 1.9372239112854004,
|
| 1526 |
+
"learning_rate": 7.98887842554572e-05,
|
| 1527 |
+
"loss": 0.5755,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.6107514776245426,
|
| 1532 |
+
"grad_norm": 1.0530599355697632,
|
| 1533 |
+
"learning_rate": 7.892687890177044e-05,
|
| 1534 |
+
"loss": 0.6622,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.6135660005629046,
|
| 1539 |
+
"grad_norm": 0.8324519991874695,
|
| 1540 |
+
"learning_rate": 7.796700970652932e-05,
|
| 1541 |
+
"loss": 0.4768,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.6163805235012665,
|
| 1546 |
+
"grad_norm": 1.280251145362854,
|
| 1547 |
+
"learning_rate": 7.700926941564262e-05,
|
| 1548 |
+
"loss": 0.3465,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.6191950464396285,
|
| 1553 |
+
"grad_norm": 1.4136282205581665,
|
| 1554 |
+
"learning_rate": 7.605375056931712e-05,
|
| 1555 |
+
"loss": 0.4388,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.6220095693779905,
|
| 1560 |
+
"grad_norm": 0.9467165470123291,
|
| 1561 |
+
"learning_rate": 7.510054549311573e-05,
|
| 1562 |
+
"loss": 0.4631,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.6248240923163524,
|
| 1567 |
+
"grad_norm": 0.4942507743835449,
|
| 1568 |
+
"learning_rate": 7.41497462890369e-05,
|
| 1569 |
+
"loss": 0.5125,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.6276386152547143,
|
| 1574 |
+
"grad_norm": 0.5631272196769714,
|
| 1575 |
+
"learning_rate": 7.320144482661533e-05,
|
| 1576 |
+
"loss": 0.5205,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6304531381930762,
|
| 1581 |
+
"grad_norm": 1.3057935237884521,
|
| 1582 |
+
"learning_rate": 7.225573273404513e-05,
|
| 1583 |
+
"loss": 0.7294,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.6332676611314382,
|
| 1588 |
+
"grad_norm": 0.9623622298240662,
|
| 1589 |
+
"learning_rate": 7.131270138932655e-05,
|
| 1590 |
+
"loss": 0.5844,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6360821840698002,
|
| 1595 |
+
"grad_norm": 1.0017409324645996,
|
| 1596 |
+
"learning_rate": 7.037244191143661e-05,
|
| 1597 |
+
"loss": 0.3777,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6388967070081621,
|
| 1602 |
+
"grad_norm": 0.9390413165092468,
|
| 1603 |
+
"learning_rate": 6.943504515152491e-05,
|
| 1604 |
+
"loss": 0.6049,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6417112299465241,
|
| 1609 |
+
"grad_norm": 0.5731076598167419,
|
| 1610 |
+
"learning_rate": 6.850060168413518e-05,
|
| 1611 |
+
"loss": 0.4316,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.644525752884886,
|
| 1616 |
+
"grad_norm": 0.42738592624664307,
|
| 1617 |
+
"learning_rate": 6.756920179845383e-05,
|
| 1618 |
+
"loss": 0.4463,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6473402758232479,
|
| 1623 |
+
"grad_norm": 1.3607089519500732,
|
| 1624 |
+
"learning_rate": 6.66409354895857e-05,
|
| 1625 |
+
"loss": 0.5199,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6501547987616099,
|
| 1630 |
+
"grad_norm": 0.9413872361183167,
|
| 1631 |
+
"learning_rate": 6.57158924498586e-05,
|
| 1632 |
+
"loss": 0.37,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.6529693216999719,
|
| 1637 |
+
"grad_norm": 0.8918866515159607,
|
| 1638 |
+
"learning_rate": 6.479416206015679e-05,
|
| 1639 |
+
"loss": 0.595,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.6557838446383338,
|
| 1644 |
+
"grad_norm": 1.254056453704834,
|
| 1645 |
+
"learning_rate": 6.387583338128471e-05,
|
| 1646 |
+
"loss": 0.7506,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.6585983675766958,
|
| 1651 |
+
"grad_norm": 0.7493451833724976,
|
| 1652 |
+
"learning_rate": 6.296099514536167e-05,
|
| 1653 |
+
"loss": 0.4956,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.6614128905150577,
|
| 1658 |
+
"grad_norm": 0.6410611271858215,
|
| 1659 |
+
"learning_rate": 6.20497357472482e-05,
|
| 1660 |
+
"loss": 0.5979,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.6642274134534196,
|
| 1665 |
+
"grad_norm": 0.6682597994804382,
|
| 1666 |
+
"learning_rate": 6.114214323600504e-05,
|
| 1667 |
+
"loss": 0.4579,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.6670419363917816,
|
| 1672 |
+
"grad_norm": 1.117984652519226,
|
| 1673 |
+
"learning_rate": 6.023830530638559e-05,
|
| 1674 |
+
"loss": 0.4828,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6698564593301436,
|
| 1679 |
+
"grad_norm": 0.8667401075363159,
|
| 1680 |
+
"learning_rate": 5.9338309290362324e-05,
|
| 1681 |
+
"loss": 0.6108,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6726709822685055,
|
| 1686 |
+
"grad_norm": 0.5072731971740723,
|
| 1687 |
+
"learning_rate": 5.844224214868881e-05,
|
| 1688 |
+
"loss": 0.4543,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.6754855052068675,
|
| 1693 |
+
"grad_norm": 1.5477889776229858,
|
| 1694 |
+
"learning_rate": 5.7550190462496946e-05,
|
| 1695 |
+
"loss": 0.4118,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.6783000281452294,
|
| 1700 |
+
"grad_norm": 1.0128791332244873,
|
| 1701 |
+
"learning_rate": 5.66622404249314e-05,
|
| 1702 |
+
"loss": 0.5121,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.6811145510835913,
|
| 1707 |
+
"grad_norm": 0.8333756327629089,
|
| 1708 |
+
"learning_rate": 5.577847783282122e-05,
|
| 1709 |
+
"loss": 0.3744,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.6839290740219532,
|
| 1714 |
+
"grad_norm": 0.6459574103355408,
|
| 1715 |
+
"learning_rate": 5.48989880783898e-05,
|
| 1716 |
+
"loss": 0.5707,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.6867435969603152,
|
| 1721 |
+
"grad_norm": 1.1848655939102173,
|
| 1722 |
+
"learning_rate": 5.4023856141004236e-05,
|
| 1723 |
+
"loss": 0.6197,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.6895581198986772,
|
| 1728 |
+
"grad_norm": 1.0240199565887451,
|
| 1729 |
+
"learning_rate": 5.3153166578963965e-05,
|
| 1730 |
+
"loss": 0.544,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.6923726428370391,
|
| 1735 |
+
"grad_norm": 0.6922760605812073,
|
| 1736 |
+
"learning_rate": 5.228700352133071e-05,
|
| 1737 |
+
"loss": 0.4769,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.6951871657754011,
|
| 1742 |
+
"grad_norm": 0.7377022504806519,
|
| 1743 |
+
"learning_rate": 5.142545065979955e-05,
|
| 1744 |
+
"loss": 0.5942,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.698001688713763,
|
| 1749 |
+
"grad_norm": 0.8629385828971863,
|
| 1750 |
+
"learning_rate": 5.05685912406123e-05,
|
| 1751 |
+
"loss": 0.7816,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.7008162116521249,
|
| 1756 |
+
"grad_norm": 0.9569929242134094,
|
| 1757 |
+
"learning_rate": 4.971650805651406e-05,
|
| 1758 |
+
"loss": 0.6106,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.7036307345904869,
|
| 1763 |
+
"grad_norm": 0.49353519082069397,
|
| 1764 |
+
"learning_rate": 4.886928343875341e-05,
|
| 1765 |
+
"loss": 0.4153,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.7064452575288489,
|
| 1770 |
+
"grad_norm": 0.9434248805046082,
|
| 1771 |
+
"learning_rate": 4.8026999249127315e-05,
|
| 1772 |
+
"loss": 0.4643,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.7092597804672108,
|
| 1777 |
+
"grad_norm": 0.5096941590309143,
|
| 1778 |
+
"learning_rate": 4.71897368720714e-05,
|
| 1779 |
+
"loss": 0.9337,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.7120743034055728,
|
| 1784 |
+
"grad_norm": 0.9566155672073364,
|
| 1785 |
+
"learning_rate": 4.6357577206796096e-05,
|
| 1786 |
+
"loss": 0.7062,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.7148888263439347,
|
| 1791 |
+
"grad_norm": 0.6990448832511902,
|
| 1792 |
+
"learning_rate": 4.553060065947013e-05,
|
| 1793 |
+
"loss": 0.4033,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.7177033492822966,
|
| 1798 |
+
"grad_norm": 0.9153978228569031,
|
| 1799 |
+
"learning_rate": 4.4708887135451396e-05,
|
| 1800 |
+
"loss": 0.5575,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.7205178722206586,
|
| 1805 |
+
"grad_norm": 1.2567604780197144,
|
| 1806 |
+
"learning_rate": 4.3892516031565954e-05,
|
| 1807 |
+
"loss": 0.45,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.7233323951590206,
|
| 1812 |
+
"grad_norm": 1.2241476774215698,
|
| 1813 |
+
"learning_rate": 4.3081566228436686e-05,
|
| 1814 |
+
"loss": 0.7022,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.7261469180973825,
|
| 1819 |
+
"grad_norm": 1.0247058868408203,
|
| 1820 |
+
"learning_rate": 4.227611608286147e-05,
|
| 1821 |
+
"loss": 0.5987,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.7289614410357445,
|
| 1826 |
+
"grad_norm": 0.9229673147201538,
|
| 1827 |
+
"learning_rate": 4.147624342024209e-05,
|
| 1828 |
+
"loss": 0.5189,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.7317759639741064,
|
| 1833 |
+
"grad_norm": 0.6648756861686707,
|
| 1834 |
+
"learning_rate": 4.0682025527064486e-05,
|
| 1835 |
+
"loss": 0.4758,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.7345904869124683,
|
| 1840 |
+
"grad_norm": 0.40781381726264954,
|
| 1841 |
+
"learning_rate": 3.9893539143431044e-05,
|
| 1842 |
+
"loss": 0.451,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7374050098508302,
|
| 1847 |
+
"grad_norm": 0.7853880524635315,
|
| 1848 |
+
"learning_rate": 3.911086045564575e-05,
|
| 1849 |
+
"loss": 0.6077,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.7402195327891923,
|
| 1854 |
+
"grad_norm": 0.7318276166915894,
|
| 1855 |
+
"learning_rate": 3.83340650888527e-05,
|
| 1856 |
+
"loss": 0.4472,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7430340557275542,
|
| 1861 |
+
"grad_norm": 1.5267870426177979,
|
| 1862 |
+
"learning_rate": 3.756322809972905e-05,
|
| 1863 |
+
"loss": 0.8982,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7458485786659161,
|
| 1868 |
+
"grad_norm": 0.5616324543952942,
|
| 1869 |
+
"learning_rate": 3.679842396923271e-05,
|
| 1870 |
+
"loss": 0.5635,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7486631016042781,
|
| 1875 |
+
"grad_norm": 0.7878595590591431,
|
| 1876 |
+
"learning_rate": 3.6039726595405755e-05,
|
| 1877 |
+
"loss": 0.5973,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.75147762454264,
|
| 1882 |
+
"grad_norm": 0.3910659849643707,
|
| 1883 |
+
"learning_rate": 3.528720928623414e-05,
|
| 1884 |
+
"loss": 0.462,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.7542921474810019,
|
| 1889 |
+
"grad_norm": 0.7616758346557617,
|
| 1890 |
+
"learning_rate": 3.4540944752564406e-05,
|
| 1891 |
+
"loss": 0.4222,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.757106670419364,
|
| 1896 |
+
"grad_norm": 1.3086707592010498,
|
| 1897 |
+
"learning_rate": 3.380100510107814e-05,
|
| 1898 |
+
"loss": 0.6267,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.7599211933577259,
|
| 1903 |
+
"grad_norm": 0.7841249108314514,
|
| 1904 |
+
"learning_rate": 3.3067461827324755e-05,
|
| 1905 |
+
"loss": 0.4136,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.7627357162960878,
|
| 1910 |
+
"grad_norm": 0.47329601645469666,
|
| 1911 |
+
"learning_rate": 3.2340385808813315e-05,
|
| 1912 |
+
"loss": 0.485,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.7655502392344498,
|
| 1917 |
+
"grad_norm": 0.719576895236969,
|
| 1918 |
+
"learning_rate": 3.161984729816415e-05,
|
| 1919 |
+
"loss": 0.4311,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.7683647621728117,
|
| 1924 |
+
"grad_norm": 1.036814570426941,
|
| 1925 |
+
"learning_rate": 3.090591591632082e-05,
|
| 1926 |
+
"loss": 0.4341,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.7711792851111736,
|
| 1931 |
+
"grad_norm": 1.327804684638977,
|
| 1932 |
+
"learning_rate": 3.0198660645822985e-05,
|
| 1933 |
+
"loss": 0.4251,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.7739938080495357,
|
| 1938 |
+
"grad_norm": 0.880226731300354,
|
| 1939 |
+
"learning_rate": 2.9498149824141196e-05,
|
| 1940 |
+
"loss": 0.3617,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.7768083309878976,
|
| 1945 |
+
"grad_norm": 0.7395775318145752,
|
| 1946 |
+
"learning_rate": 2.880445113707384e-05,
|
| 1947 |
+
"loss": 0.6637,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.7796228539262595,
|
| 1952 |
+
"grad_norm": 1.0488626956939697,
|
| 1953 |
+
"learning_rate": 2.8117631612207084e-05,
|
| 1954 |
+
"loss": 0.4081,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.7824373768646214,
|
| 1959 |
+
"grad_norm": 0.8878235220909119,
|
| 1960 |
+
"learning_rate": 2.743775761243843e-05,
|
| 1961 |
+
"loss": 0.5031,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7852518998029834,
|
| 1966 |
+
"grad_norm": 0.6816940903663635,
|
| 1967 |
+
"learning_rate": 2.6764894829564613e-05,
|
| 1968 |
+
"loss": 0.4063,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.7880664227413453,
|
| 1973 |
+
"grad_norm": 0.4741825759410858,
|
| 1974 |
+
"learning_rate": 2.6099108277934103e-05,
|
| 1975 |
+
"loss": 0.3073,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.7908809456797072,
|
| 1980 |
+
"grad_norm": 0.8777612447738647,
|
| 1981 |
+
"learning_rate": 2.5440462288165146e-05,
|
| 1982 |
+
"loss": 0.6016,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.7936954686180693,
|
| 1987 |
+
"grad_norm": 0.6074641346931458,
|
| 1988 |
+
"learning_rate": 2.4789020500930095e-05,
|
| 1989 |
+
"loss": 0.5282,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.7965099915564312,
|
| 1994 |
+
"grad_norm": 0.8305478692054749,
|
| 1995 |
+
"learning_rate": 2.414484586080612e-05,
|
| 1996 |
+
"loss": 0.6746,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.7993245144947931,
|
| 2001 |
+
"grad_norm": 1.8334358930587769,
|
| 2002 |
+
"learning_rate": 2.3508000610193258e-05,
|
| 2003 |
+
"loss": 0.3076,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.8021390374331551,
|
| 2008 |
+
"grad_norm": 0.8415083885192871,
|
| 2009 |
+
"learning_rate": 2.287854628330043e-05,
|
| 2010 |
+
"loss": 0.4482,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.804953560371517,
|
| 2015 |
+
"grad_norm": 1.1256593465805054,
|
| 2016 |
+
"learning_rate": 2.2256543700199685e-05,
|
| 2017 |
+
"loss": 0.4828,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.8077680833098789,
|
| 2022 |
+
"grad_norm": 0.6625217795372009,
|
| 2023 |
+
"learning_rate": 2.164205296094961e-05,
|
| 2024 |
+
"loss": 0.2526,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.810582606248241,
|
| 2029 |
+
"grad_norm": 1.2664328813552856,
|
| 2030 |
+
"learning_rate": 2.1035133439788236e-05,
|
| 2031 |
+
"loss": 0.5837,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.8133971291866029,
|
| 2036 |
+
"grad_norm": 0.6024655699729919,
|
| 2037 |
+
"learning_rate": 2.0435843779396156e-05,
|
| 2038 |
+
"loss": 0.5919,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.8162116521249648,
|
| 2043 |
+
"grad_norm": 0.660294234752655,
|
| 2044 |
+
"learning_rate": 1.9844241885230163e-05,
|
| 2045 |
+
"loss": 0.4167,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.8190261750633268,
|
| 2050 |
+
"grad_norm": 0.7786351442337036,
|
| 2051 |
+
"learning_rate": 1.9260384919928266e-05,
|
| 2052 |
+
"loss": 0.5695,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.8218406980016887,
|
| 2057 |
+
"grad_norm": 0.7518659830093384,
|
| 2058 |
+
"learning_rate": 1.8684329297786453e-05,
|
| 2059 |
+
"loss": 0.7747,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.8246552209400506,
|
| 2064 |
+
"grad_norm": 0.7769446969032288,
|
| 2065 |
+
"learning_rate": 1.8116130679307708e-05,
|
| 2066 |
+
"loss": 0.6442,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.8274697438784127,
|
| 2071 |
+
"grad_norm": 0.49770888686180115,
|
| 2072 |
+
"learning_rate": 1.7555843965823992e-05,
|
| 2073 |
+
"loss": 0.4515,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.8302842668167746,
|
| 2078 |
+
"grad_norm": 0.9085186719894409,
|
| 2079 |
+
"learning_rate": 1.7003523294191294e-05,
|
| 2080 |
+
"loss": 0.419,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.8330987897551365,
|
| 2085 |
+
"grad_norm": 1.536907434463501,
|
| 2086 |
+
"learning_rate": 1.6459222031558974e-05,
|
| 2087 |
+
"loss": 0.5198,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.8359133126934984,
|
| 2092 |
+
"grad_norm": 0.6355032920837402,
|
| 2093 |
+
"learning_rate": 1.5922992770213064e-05,
|
| 2094 |
+
"loss": 0.524,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.8387278356318604,
|
| 2099 |
+
"grad_norm": 0.7401185631752014,
|
| 2100 |
+
"learning_rate": 1.5394887322494732e-05,
|
| 2101 |
+
"loss": 0.362,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.8415423585702223,
|
| 2106 |
+
"grad_norm": 0.7638711333274841,
|
| 2107 |
+
"learning_rate": 1.4874956715793886e-05,
|
| 2108 |
+
"loss": 0.363,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8443568815085843,
|
| 2113 |
+
"grad_norm": 1.4240124225616455,
|
| 2114 |
+
"learning_rate": 1.4363251187618854e-05,
|
| 2115 |
+
"loss": 0.7827,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.8471714044469463,
|
| 2120 |
+
"grad_norm": 0.8892093896865845,
|
| 2121 |
+
"learning_rate": 1.3859820180742156e-05,
|
| 2122 |
+
"loss": 0.3835,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8499859273853082,
|
| 2127 |
+
"grad_norm": 0.8796232342720032,
|
| 2128 |
+
"learning_rate": 1.3364712338423214e-05,
|
| 2129 |
+
"loss": 0.6749,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.8528004503236701,
|
| 2134 |
+
"grad_norm": 0.7944719195365906,
|
| 2135 |
+
"learning_rate": 1.287797549970826e-05,
|
| 2136 |
+
"loss": 0.5354,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.8556149732620321,
|
| 2141 |
+
"grad_norm": 0.6994941830635071,
|
| 2142 |
+
"learning_rate": 1.2399656694807971e-05,
|
| 2143 |
+
"loss": 0.5961,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.858429496200394,
|
| 2148 |
+
"grad_norm": 0.8955370187759399,
|
| 2149 |
+
"learning_rate": 1.1929802140553258e-05,
|
| 2150 |
+
"loss": 0.2639,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.861244019138756,
|
| 2155 |
+
"grad_norm": 0.9208924174308777,
|
| 2156 |
+
"learning_rate": 1.1468457235929597e-05,
|
| 2157 |
+
"loss": 0.5161,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.864058542077118,
|
| 2162 |
+
"grad_norm": 1.6513868570327759,
|
| 2163 |
+
"learning_rate": 1.1015666557690452e-05,
|
| 2164 |
+
"loss": 0.3097,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8668730650154799,
|
| 2169 |
+
"grad_norm": 0.9617025256156921,
|
| 2170 |
+
"learning_rate": 1.0571473856050107e-05,
|
| 2171 |
+
"loss": 0.5886,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.8696875879538418,
|
| 2176 |
+
"grad_norm": 1.428849458694458,
|
| 2177 |
+
"learning_rate": 1.0135922050456347e-05,
|
| 2178 |
+
"loss": 0.5518,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8725021108922038,
|
| 2183 |
+
"grad_norm": 0.9242206811904907,
|
| 2184 |
+
"learning_rate": 9.709053225443487e-06,
|
| 2185 |
+
"loss": 0.6922,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.8753166338305657,
|
| 2190 |
+
"grad_norm": 0.9717757701873779,
|
| 2191 |
+
"learning_rate": 9.29090862656593e-06,
|
| 2192 |
+
"loss": 0.3653,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.8781311567689276,
|
| 2197 |
+
"grad_norm": 0.48359620571136475,
|
| 2198 |
+
"learning_rate": 8.881528656412963e-06,
|
| 2199 |
+
"loss": 0.2516,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.8809456797072897,
|
| 2204 |
+
"grad_norm": 1.1804348230361938,
|
| 2205 |
+
"learning_rate": 8.480952870704873e-06,
|
| 2206 |
+
"loss": 0.3171,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.8837602026456516,
|
| 2211 |
+
"grad_norm": 0.8391767740249634,
|
| 2212 |
+
"learning_rate": 8.08921997447094e-06,
|
| 2213 |
+
"loss": 0.4603,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.8865747255840135,
|
| 2218 |
+
"grad_norm": 0.37848615646362305,
|
| 2219 |
+
"learning_rate": 7.706367818309624e-06,
|
| 2220 |
+
"loss": 0.3601,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8893892485223754,
|
| 2225 |
+
"grad_norm": 0.328762412071228,
|
| 2226 |
+
"learning_rate": 7.332433394731331e-06,
|
| 2227 |
+
"loss": 0.4663,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8922037714607374,
|
| 2232 |
+
"grad_norm": 1.1124379634857178,
|
| 2233 |
+
"learning_rate": 6.967452834584009e-06,
|
| 2234 |
+
"loss": 0.7712,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8950182943990993,
|
| 2239 |
+
"grad_norm": 0.946675181388855,
|
| 2240 |
+
"learning_rate": 6.611461403562147e-06,
|
| 2241 |
+
"loss": 0.5769,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.8978328173374613,
|
| 2246 |
+
"grad_norm": 1.3897684812545776,
|
| 2247 |
+
"learning_rate": 6.264493498799185e-06,
|
| 2248 |
+
"loss": 0.4381,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.9006473402758233,
|
| 2253 |
+
"grad_norm": 0.5598315596580505,
|
| 2254 |
+
"learning_rate": 5.92658264554401e-06,
|
| 2255 |
+
"loss": 0.4289,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.9034618632141852,
|
| 2260 |
+
"grad_norm": 0.6429581046104431,
|
| 2261 |
+
"learning_rate": 5.597761493921627e-06,
|
| 2262 |
+
"loss": 0.7875,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.9062763861525471,
|
| 2267 |
+
"grad_norm": 0.8496813178062439,
|
| 2268 |
+
"learning_rate": 5.278061815778313e-06,
|
| 2269 |
+
"loss": 0.4269,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.9090909090909091,
|
| 2274 |
+
"grad_norm": 0.9900699257850647,
|
| 2275 |
+
"learning_rate": 4.967514501611881e-06,
|
| 2276 |
+
"loss": 0.2818,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.911905432029271,
|
| 2281 |
+
"grad_norm": 0.8361634016036987,
|
| 2282 |
+
"learning_rate": 4.666149557586697e-06,
|
| 2283 |
+
"loss": 0.4749,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.914719954967633,
|
| 2288 |
+
"grad_norm": 0.5384243130683899,
|
| 2289 |
+
"learning_rate": 4.3739961026345586e-06,
|
| 2290 |
+
"loss": 0.5043,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.917534477905995,
|
| 2295 |
+
"grad_norm": 0.8283894658088684,
|
| 2296 |
+
"learning_rate": 4.091082365641085e-06,
|
| 2297 |
+
"loss": 0.7093,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.9203490008443569,
|
| 2302 |
+
"grad_norm": 0.5737767219543457,
|
| 2303 |
+
"learning_rate": 3.817435682718096e-06,
|
| 2304 |
+
"loss": 0.4823,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.9231635237827188,
|
| 2309 |
+
"grad_norm": 0.4942363500595093,
|
| 2310 |
+
"learning_rate": 3.5530824945623542e-06,
|
| 2311 |
+
"loss": 0.6501,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.9259780467210807,
|
| 2316 |
+
"grad_norm": 0.9362422823905945,
|
| 2317 |
+
"learning_rate": 3.298048343900717e-06,
|
| 2318 |
+
"loss": 0.2883,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.9287925696594427,
|
| 2323 |
+
"grad_norm": 0.9241194725036621,
|
| 2324 |
+
"learning_rate": 3.0523578730221713e-06,
|
| 2325 |
+
"loss": 0.6112,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.9316070925978047,
|
| 2330 |
+
"grad_norm": 1.3847359418869019,
|
| 2331 |
+
"learning_rate": 2.8160348213967848e-06,
|
| 2332 |
+
"loss": 0.5209,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.9344216155361666,
|
| 2337 |
+
"grad_norm": 1.0031473636627197,
|
| 2338 |
+
"learning_rate": 2.589102023381895e-06,
|
| 2339 |
+
"loss": 0.3663,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.9372361384745286,
|
| 2344 |
+
"grad_norm": 0.616346538066864,
|
| 2345 |
+
"learning_rate": 2.3715814060157772e-06,
|
| 2346 |
+
"loss": 0.4261,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.9400506614128905,
|
| 2351 |
+
"grad_norm": 0.8073914647102356,
|
| 2352 |
+
"learning_rate": 2.1634939868990235e-06,
|
| 2353 |
+
"loss": 0.3541,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9428651843512524,
|
| 2358 |
+
"grad_norm": 0.64414381980896,
|
| 2359 |
+
"learning_rate": 1.9648598721637045e-06,
|
| 2360 |
+
"loss": 0.5996,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9456797072896144,
|
| 2365 |
+
"grad_norm": 0.7799990177154541,
|
| 2366 |
+
"learning_rate": 1.7756982545306443e-06,
|
| 2367 |
+
"loss": 0.4095,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.9484942302279764,
|
| 2372 |
+
"grad_norm": 0.6466760039329529,
|
| 2373 |
+
"learning_rate": 1.596027411454981e-06,
|
| 2374 |
+
"loss": 0.3666,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9513087531663383,
|
| 2379 |
+
"grad_norm": 0.728364884853363,
|
| 2380 |
+
"learning_rate": 1.4258647033601024e-06,
|
| 2381 |
+
"loss": 0.6216,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.9541232761047003,
|
| 2386 |
+
"grad_norm": 0.9482190012931824,
|
| 2387 |
+
"learning_rate": 1.265226571960254e-06,
|
| 2388 |
+
"loss": 0.5574,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.9569377990430622,
|
| 2393 |
+
"grad_norm": 0.9594746232032776,
|
| 2394 |
+
"learning_rate": 1.1141285386718437e-06,
|
| 2395 |
+
"loss": 0.6466,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.9597523219814241,
|
| 2400 |
+
"grad_norm": 1.3607548475265503,
|
| 2401 |
+
"learning_rate": 9.72585203113774e-07,
|
| 2402 |
+
"loss": 0.5807,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.9625668449197861,
|
| 2407 |
+
"grad_norm": 2.761012554168701,
|
| 2408 |
+
"learning_rate": 8.406102416967043e-07,
|
| 2409 |
+
"loss": 0.4588,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9653813678581481,
|
| 2414 |
+
"grad_norm": 0.7540304660797119,
|
| 2415 |
+
"learning_rate": 7.182164063015973e-07,
|
| 2416 |
+
"loss": 0.5414,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.96819589079651,
|
| 2421 |
+
"grad_norm": 1.1836090087890625,
|
| 2422 |
+
"learning_rate": 6.054155230476699e-07,
|
| 2423 |
+
"loss": 0.4274,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.971010413734872,
|
| 2428 |
+
"grad_norm": 0.6484697461128235,
|
| 2429 |
+
"learning_rate": 5.022184911495864e-07,
|
| 2430 |
+
"loss": 0.4756,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.9738249366732339,
|
| 2435 |
+
"grad_norm": 0.72726970911026,
|
| 2436 |
+
"learning_rate": 4.0863528186445564e-07,
|
| 2437 |
+
"loss": 0.5541,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.9766394596115958,
|
| 2442 |
+
"grad_norm": 0.7867249846458435,
|
| 2443 |
+
"learning_rate": 3.246749375282909e-07,
|
| 2444 |
+
"loss": 0.4513,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.9794539825499577,
|
| 2449 |
+
"grad_norm": 0.7862501740455627,
|
| 2450 |
+
"learning_rate": 2.50345570682331e-07,
|
| 2451 |
+
"loss": 0.4277,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.9822685054883197,
|
| 2456 |
+
"grad_norm": 0.9948648810386658,
|
| 2457 |
+
"learning_rate": 1.856543632892116e-07,
|
| 2458 |
+
"loss": 0.5665,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.9850830284266817,
|
| 2463 |
+
"grad_norm": 0.7089385390281677,
|
| 2464 |
+
"learning_rate": 1.3060756603897605e-07,
|
| 2465 |
+
"loss": 0.4658,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.9878975513650436,
|
| 2470 |
+
"grad_norm": 0.5250968933105469,
|
| 2471 |
+
"learning_rate": 8.521049774512513e-08,
|
| 2472 |
+
"loss": 0.4507,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.9907120743034056,
|
| 2477 |
+
"grad_norm": 0.6175426244735718,
|
| 2478 |
+
"learning_rate": 4.946754483071692e-08,
|
| 2479 |
+
"loss": 0.3314,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.9935265972417675,
|
| 2484 |
+
"grad_norm": 0.6678758263587952,
|
| 2485 |
+
"learning_rate": 2.3382160904483753e-08,
|
| 2486 |
+
"loss": 0.3931,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9963411201801294,
|
| 2491 |
+
"grad_norm": 0.7605099081993103,
|
| 2492 |
+
"learning_rate": 6.95686642719906e-09,
|
| 2493 |
+
"loss": 0.3326,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9991556431184914,
|
| 2498 |
+
"grad_norm": 0.5569049119949341,
|
| 2499 |
+
"learning_rate": 1.932484680944313e-10,
|
| 2500 |
+
"loss": 0.4035,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.9997185477061638,
|
| 2505 |
+
"step": 1776,
|
| 2506 |
+
"total_flos": 3.866808531592151e+17,
|
| 2507 |
+
"train_loss": 0.5711438672759713,
|
| 2508 |
+
"train_runtime": 4148.7499,
|
| 2509 |
+
"train_samples_per_second": 3.425,
|
| 2510 |
+
"train_steps_per_second": 0.428
|
| 2511 |
+
}
|
| 2512 |
+
],
|
| 2513 |
+
"logging_steps": 5,
|
| 2514 |
+
"max_steps": 1776,
|
| 2515 |
+
"num_input_tokens_seen": 0,
|
| 2516 |
+
"num_train_epochs": 1,
|
| 2517 |
+
"save_steps": 20,
|
| 2518 |
+
"stateful_callbacks": {
|
| 2519 |
+
"TrainerControl": {
|
| 2520 |
+
"args": {
|
| 2521 |
+
"should_epoch_stop": false,
|
| 2522 |
+
"should_evaluate": false,
|
| 2523 |
+
"should_log": false,
|
| 2524 |
+
"should_save": true,
|
| 2525 |
+
"should_training_stop": true
|
| 2526 |
+
},
|
| 2527 |
+
"attributes": {}
|
| 2528 |
+
}
|
| 2529 |
+
},
|
| 2530 |
+
"total_flos": 3.866808531592151e+17,
|
| 2531 |
+
"train_batch_size": 2,
|
| 2532 |
+
"trial_name": null,
|
| 2533 |
+
"trial_params": null
|
| 2534 |
+
}
|