Model save
Browse files- README.md +65 -0
- all_results.json +9 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
- runs/May07_01-10-03_illidan.cs.ucla.edu/events.out.tfevents.1715069421.illidan.cs.ucla.edu.3443160.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1137 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: tinyllama-sft-wizardlm_evol_instruct_v2-mix
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# tinyllama-sft-wizardlm_evol_instruct_v2-mix
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7211
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 4
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- total_eval_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 1
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.711 | 0.9994 | 781 | 0.7211 |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- Transformers 4.40.2
|
| 63 |
+
- Pytorch 2.3.0+cu121
|
| 64 |
+
- Datasets 2.19.1
|
| 65 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999360204734485,
|
| 3 |
+
"total_flos": 80545737277440.0,
|
| 4 |
+
"train_loss": 0.7457574072476386,
|
| 5 |
+
"train_runtime": 7303.4461,
|
| 6 |
+
"train_samples": 99999,
|
| 7 |
+
"train_samples_per_second": 13.692,
|
| 8 |
+
"train_steps_per_second": 0.107
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.40.2"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2200119864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0923348209ca0de45eb4c0c9a57e9c6ff56e532653300a9a1e5ad0e62176a5d
|
| 3 |
size 2200119864
|
runs/May07_01-10-03_illidan.cs.ucla.edu/events.out.tfevents.1715069421.illidan.cs.ucla.edu.3443160.0
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 sha256:0715d9c2e2e06dd164d6b0e6f88cac2b45dd8f76c740f68856ee57c71ca064cd
|
| 3 |
+
size 38606
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999360204734485,
|
| 3 |
+
"total_flos": 80545737277440.0,
|
| 4 |
+
"train_loss": 0.7457574072476386,
|
| 5 |
+
"train_runtime": 7303.4461,
|
| 6 |
+
"train_samples": 99999,
|
| 7 |
+
"train_samples_per_second": 13.692,
|
| 8 |
+
"train_steps_per_second": 0.107
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.999360204734485,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 781,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012795905310300703,
|
| 13 |
+
"grad_norm": 6.290177490440239,
|
| 14 |
+
"learning_rate": 2.5316455696202533e-07,
|
| 15 |
+
"loss": 1.0784,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006397952655150352,
|
| 20 |
+
"grad_norm": 6.702182800413163,
|
| 21 |
+
"learning_rate": 1.2658227848101267e-06,
|
| 22 |
+
"loss": 1.0415,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012795905310300703,
|
| 27 |
+
"grad_norm": 5.487859701594733,
|
| 28 |
+
"learning_rate": 2.5316455696202535e-06,
|
| 29 |
+
"loss": 1.0444,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.019193857965451054,
|
| 34 |
+
"grad_norm": 2.2091656111344116,
|
| 35 |
+
"learning_rate": 3.7974683544303802e-06,
|
| 36 |
+
"loss": 0.9625,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.025591810620601407,
|
| 41 |
+
"grad_norm": 1.3024745363944248,
|
| 42 |
+
"learning_rate": 5.063291139240507e-06,
|
| 43 |
+
"loss": 0.8519,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03198976327575176,
|
| 48 |
+
"grad_norm": 1.0696576308505852,
|
| 49 |
+
"learning_rate": 6.329113924050634e-06,
|
| 50 |
+
"loss": 0.8425,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03838771593090211,
|
| 55 |
+
"grad_norm": 0.9289972759140979,
|
| 56 |
+
"learning_rate": 7.5949367088607605e-06,
|
| 57 |
+
"loss": 0.8055,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.044785668586052464,
|
| 62 |
+
"grad_norm": 0.8881490776255759,
|
| 63 |
+
"learning_rate": 8.860759493670886e-06,
|
| 64 |
+
"loss": 0.8101,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05118362124120281,
|
| 69 |
+
"grad_norm": 1.003105745392554,
|
| 70 |
+
"learning_rate": 1.0126582278481014e-05,
|
| 71 |
+
"loss": 0.8034,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05758157389635317,
|
| 76 |
+
"grad_norm": 0.9061421007764652,
|
| 77 |
+
"learning_rate": 1.139240506329114e-05,
|
| 78 |
+
"loss": 0.8149,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06397952655150352,
|
| 83 |
+
"grad_norm": 0.947301258001698,
|
| 84 |
+
"learning_rate": 1.2658227848101268e-05,
|
| 85 |
+
"loss": 0.8066,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07037747920665387,
|
| 90 |
+
"grad_norm": 0.9442508051067858,
|
| 91 |
+
"learning_rate": 1.3924050632911395e-05,
|
| 92 |
+
"loss": 0.7829,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07677543186180422,
|
| 97 |
+
"grad_norm": 0.9505498602464607,
|
| 98 |
+
"learning_rate": 1.5189873417721521e-05,
|
| 99 |
+
"loss": 0.789,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08317338451695458,
|
| 104 |
+
"grad_norm": 1.0294440611861784,
|
| 105 |
+
"learning_rate": 1.6455696202531647e-05,
|
| 106 |
+
"loss": 0.8047,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08957133717210493,
|
| 111 |
+
"grad_norm": 0.9037139700901843,
|
| 112 |
+
"learning_rate": 1.7721518987341772e-05,
|
| 113 |
+
"loss": 0.7808,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09596928982725528,
|
| 118 |
+
"grad_norm": 0.9155324723416859,
|
| 119 |
+
"learning_rate": 1.89873417721519e-05,
|
| 120 |
+
"loss": 0.7693,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10236724248240563,
|
| 125 |
+
"grad_norm": 1.01405799880107,
|
| 126 |
+
"learning_rate": 1.999989986294826e-05,
|
| 127 |
+
"loss": 0.7701,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.10876519513755598,
|
| 132 |
+
"grad_norm": 0.8936790580352,
|
| 133 |
+
"learning_rate": 1.9996395276708856e-05,
|
| 134 |
+
"loss": 0.7559,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11516314779270634,
|
| 139 |
+
"grad_norm": 0.9533062095051035,
|
| 140 |
+
"learning_rate": 1.9987885843187717e-05,
|
| 141 |
+
"loss": 0.7755,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12156110044785669,
|
| 146 |
+
"grad_norm": 0.8655719966380863,
|
| 147 |
+
"learning_rate": 1.9974375822762117e-05,
|
| 148 |
+
"loss": 0.7693,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.12795905310300704,
|
| 153 |
+
"grad_norm": 0.9292508995916059,
|
| 154 |
+
"learning_rate": 1.9955871979429188e-05,
|
| 155 |
+
"loss": 0.7672,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.1343570057581574,
|
| 160 |
+
"grad_norm": 0.8848494940071496,
|
| 161 |
+
"learning_rate": 1.9932383577419432e-05,
|
| 162 |
+
"loss": 0.7669,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.14075495841330773,
|
| 167 |
+
"grad_norm": 0.8492671125517353,
|
| 168 |
+
"learning_rate": 1.9903922376558432e-05,
|
| 169 |
+
"loss": 0.7807,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1471529110684581,
|
| 174 |
+
"grad_norm": 0.8680755550279518,
|
| 175 |
+
"learning_rate": 1.9870502626379127e-05,
|
| 176 |
+
"loss": 0.7884,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15355086372360843,
|
| 181 |
+
"grad_norm": 0.8715305157008323,
|
| 182 |
+
"learning_rate": 1.983214105898757e-05,
|
| 183 |
+
"loss": 0.7785,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1599488163787588,
|
| 188 |
+
"grad_norm": 0.920271623258983,
|
| 189 |
+
"learning_rate": 1.978885688068572e-05,
|
| 190 |
+
"loss": 0.7723,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.16634676903390916,
|
| 195 |
+
"grad_norm": 0.8601122413411659,
|
| 196 |
+
"learning_rate": 1.9740671762355548e-05,
|
| 197 |
+
"loss": 0.7548,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1727447216890595,
|
| 202 |
+
"grad_norm": 0.9508364162043275,
|
| 203 |
+
"learning_rate": 1.9687609828609156e-05,
|
| 204 |
+
"loss": 0.7782,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.17914267434420986,
|
| 209 |
+
"grad_norm": 0.9570098046333952,
|
| 210 |
+
"learning_rate": 1.9629697645710432e-05,
|
| 211 |
+
"loss": 0.7557,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1855406269993602,
|
| 216 |
+
"grad_norm": 0.9889078696060014,
|
| 217 |
+
"learning_rate": 1.9566964208274254e-05,
|
| 218 |
+
"loss": 0.777,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19193857965451055,
|
| 223 |
+
"grad_norm": 0.914516851971123,
|
| 224 |
+
"learning_rate": 1.9499440924749878e-05,
|
| 225 |
+
"loss": 0.7703,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.19833653230966092,
|
| 230 |
+
"grad_norm": 0.9666613857266174,
|
| 231 |
+
"learning_rate": 1.9427161601695833e-05,
|
| 232 |
+
"loss": 0.7609,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.20473448496481125,
|
| 237 |
+
"grad_norm": 0.8774756951541983,
|
| 238 |
+
"learning_rate": 1.9350162426854152e-05,
|
| 239 |
+
"loss": 0.7475,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.21113243761996162,
|
| 244 |
+
"grad_norm": 0.9670708841788205,
|
| 245 |
+
"learning_rate": 1.926848195103242e-05,
|
| 246 |
+
"loss": 0.76,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.21753039027511195,
|
| 251 |
+
"grad_norm": 0.8838923277068791,
|
| 252 |
+
"learning_rate": 1.9182161068802742e-05,
|
| 253 |
+
"loss": 0.7559,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.22392834293026231,
|
| 258 |
+
"grad_norm": 0.8979119023604246,
|
| 259 |
+
"learning_rate": 1.909124299802724e-05,
|
| 260 |
+
"loss": 0.7492,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.23032629558541268,
|
| 265 |
+
"grad_norm": 0.8267942600640766,
|
| 266 |
+
"learning_rate": 1.8995773258220374e-05,
|
| 267 |
+
"loss": 0.7498,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.236724248240563,
|
| 272 |
+
"grad_norm": 0.8110785643711048,
|
| 273 |
+
"learning_rate": 1.8895799647758912e-05,
|
| 274 |
+
"loss": 0.7397,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.24312220089571338,
|
| 279 |
+
"grad_norm": 0.8742502964910401,
|
| 280 |
+
"learning_rate": 1.879137221995095e-05,
|
| 281 |
+
"loss": 0.746,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.2495201535508637,
|
| 286 |
+
"grad_norm": 0.8560236399558296,
|
| 287 |
+
"learning_rate": 1.868254325797594e-05,
|
| 288 |
+
"loss": 0.7563,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2559181062060141,
|
| 293 |
+
"grad_norm": 0.8944327324689623,
|
| 294 |
+
"learning_rate": 1.8569367248708343e-05,
|
| 295 |
+
"loss": 0.7645,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.26231605886116444,
|
| 300 |
+
"grad_norm": 0.8621529624234945,
|
| 301 |
+
"learning_rate": 1.845190085543795e-05,
|
| 302 |
+
"loss": 0.7552,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2687140115163148,
|
| 307 |
+
"grad_norm": 0.8760942401693406,
|
| 308 |
+
"learning_rate": 1.8330202889500518e-05,
|
| 309 |
+
"loss": 0.7354,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2751119641714651,
|
| 314 |
+
"grad_norm": 0.8712951389244179,
|
| 315 |
+
"learning_rate": 1.8204334280833005e-05,
|
| 316 |
+
"loss": 0.7556,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.28150991682661547,
|
| 321 |
+
"grad_norm": 0.9117905123706684,
|
| 322 |
+
"learning_rate": 1.807435804746807e-05,
|
| 323 |
+
"loss": 0.7674,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.28790786948176583,
|
| 328 |
+
"grad_norm": 0.9659529366014488,
|
| 329 |
+
"learning_rate": 1.7940339263983112e-05,
|
| 330 |
+
"loss": 0.7705,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2943058221369162,
|
| 335 |
+
"grad_norm": 0.8392485914175913,
|
| 336 |
+
"learning_rate": 1.7802345028919728e-05,
|
| 337 |
+
"loss": 0.7522,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.30070377479206656,
|
| 342 |
+
"grad_norm": 0.9180964413930104,
|
| 343 |
+
"learning_rate": 1.766044443118978e-05,
|
| 344 |
+
"loss": 0.7658,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.30710172744721687,
|
| 349 |
+
"grad_norm": 0.8599442472058514,
|
| 350 |
+
"learning_rate": 1.7514708515485002e-05,
|
| 351 |
+
"loss": 0.7709,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.31349968010236723,
|
| 356 |
+
"grad_norm": 0.874820715756307,
|
| 357 |
+
"learning_rate": 1.736521024670737e-05,
|
| 358 |
+
"loss": 0.7298,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3198976327575176,
|
| 363 |
+
"grad_norm": 0.9507611932214313,
|
| 364 |
+
"learning_rate": 1.7212024473438145e-05,
|
| 365 |
+
"loss": 0.7829,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.32629558541266795,
|
| 370 |
+
"grad_norm": 0.8751685918941091,
|
| 371 |
+
"learning_rate": 1.705522789046377e-05,
|
| 372 |
+
"loss": 0.7519,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3326935380678183,
|
| 377 |
+
"grad_norm": 0.8011470314485565,
|
| 378 |
+
"learning_rate": 1.6894899000377462e-05,
|
| 379 |
+
"loss": 0.74,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3390914907229686,
|
| 384 |
+
"grad_norm": 0.8521229042194711,
|
| 385 |
+
"learning_rate": 1.67311180742757e-05,
|
| 386 |
+
"loss": 0.7543,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.345489443378119,
|
| 391 |
+
"grad_norm": 0.8130076328641188,
|
| 392 |
+
"learning_rate": 1.65639671115693e-05,
|
| 393 |
+
"loss": 0.7339,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.35188739603326935,
|
| 398 |
+
"grad_norm": 0.9621951058914813,
|
| 399 |
+
"learning_rate": 1.6393529798929103e-05,
|
| 400 |
+
"loss": 0.7411,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3582853486884197,
|
| 405 |
+
"grad_norm": 0.9254782095065907,
|
| 406 |
+
"learning_rate": 1.621989146838704e-05,
|
| 407 |
+
"loss": 0.7448,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3646833013435701,
|
| 412 |
+
"grad_norm": 0.8675888456425931,
|
| 413 |
+
"learning_rate": 1.6043139054613326e-05,
|
| 414 |
+
"loss": 0.7701,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3710812539987204,
|
| 419 |
+
"grad_norm": 0.8838846353868941,
|
| 420 |
+
"learning_rate": 1.586336105139127e-05,
|
| 421 |
+
"loss": 0.7365,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.37747920665387075,
|
| 426 |
+
"grad_norm": 0.9360739406132822,
|
| 427 |
+
"learning_rate": 1.568064746731156e-05,
|
| 428 |
+
"loss": 0.7334,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3838771593090211,
|
| 433 |
+
"grad_norm": 0.8975040372948366,
|
| 434 |
+
"learning_rate": 1.5495089780708062e-05,
|
| 435 |
+
"loss": 0.7294,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3902751119641715,
|
| 440 |
+
"grad_norm": 0.8204316809700783,
|
| 441 |
+
"learning_rate": 1.530678089385782e-05,
|
| 442 |
+
"loss": 0.7436,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.39667306461932184,
|
| 447 |
+
"grad_norm": 0.8979669622871939,
|
| 448 |
+
"learning_rate": 1.5115815086468103e-05,
|
| 449 |
+
"loss": 0.7596,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.40307101727447214,
|
| 454 |
+
"grad_norm": 0.87770927627433,
|
| 455 |
+
"learning_rate": 1.492228796847385e-05,
|
| 456 |
+
"loss": 0.7468,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.4094689699296225,
|
| 461 |
+
"grad_norm": 0.8479491304098338,
|
| 462 |
+
"learning_rate": 1.4726296432169095e-05,
|
| 463 |
+
"loss": 0.7556,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.41586692258477287,
|
| 468 |
+
"grad_norm": 0.8754654732089078,
|
| 469 |
+
"learning_rate": 1.4527938603696376e-05,
|
| 470 |
+
"loss": 0.7225,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.42226487523992323,
|
| 475 |
+
"grad_norm": 0.881596577987191,
|
| 476 |
+
"learning_rate": 1.4327313793918362e-05,
|
| 477 |
+
"loss": 0.7446,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.4286628278950736,
|
| 482 |
+
"grad_norm": 0.9352817977484518,
|
| 483 |
+
"learning_rate": 1.4124522448696407e-05,
|
| 484 |
+
"loss": 0.7216,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.4350607805502239,
|
| 489 |
+
"grad_norm": 0.8472386929218481,
|
| 490 |
+
"learning_rate": 1.3919666098600753e-05,
|
| 491 |
+
"loss": 0.7351,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.44145873320537427,
|
| 496 |
+
"grad_norm": 0.9626870416040649,
|
| 497 |
+
"learning_rate": 1.3712847308077737e-05,
|
| 498 |
+
"loss": 0.7335,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.44785668586052463,
|
| 503 |
+
"grad_norm": 0.8583773106564518,
|
| 504 |
+
"learning_rate": 1.350416962409934e-05,
|
| 505 |
+
"loss": 0.7472,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.454254638515675,
|
| 510 |
+
"grad_norm": 0.8162278696217269,
|
| 511 |
+
"learning_rate": 1.3293737524320798e-05,
|
| 512 |
+
"loss": 0.7425,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.46065259117082535,
|
| 517 |
+
"grad_norm": 0.8587065087391589,
|
| 518 |
+
"learning_rate": 1.3081656364772308e-05,
|
| 519 |
+
"loss": 0.721,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.46705054382597566,
|
| 524 |
+
"grad_norm": 0.9489656570168764,
|
| 525 |
+
"learning_rate": 1.2868032327110904e-05,
|
| 526 |
+
"loss": 0.7117,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.473448496481126,
|
| 531 |
+
"grad_norm": 0.8866065865142619,
|
| 532 |
+
"learning_rate": 1.2652972365459008e-05,
|
| 533 |
+
"loss": 0.7154,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4798464491362764,
|
| 538 |
+
"grad_norm": 0.9315838159542567,
|
| 539 |
+
"learning_rate": 1.243658415285622e-05,
|
| 540 |
+
"loss": 0.7684,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.48624440179142675,
|
| 545 |
+
"grad_norm": 0.8553566142004,
|
| 546 |
+
"learning_rate": 1.2218976027351177e-05,
|
| 547 |
+
"loss": 0.7246,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4926423544465771,
|
| 552 |
+
"grad_norm": 0.9294553052999376,
|
| 553 |
+
"learning_rate": 1.2000256937760446e-05,
|
| 554 |
+
"loss": 0.7312,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4990403071017274,
|
| 559 |
+
"grad_norm": 0.8632512793370595,
|
| 560 |
+
"learning_rate": 1.1780536389121668e-05,
|
| 561 |
+
"loss": 0.7414,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5054382597568778,
|
| 566 |
+
"grad_norm": 0.8379396676665268,
|
| 567 |
+
"learning_rate": 1.155992438786818e-05,
|
| 568 |
+
"loss": 0.7264,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5118362124120281,
|
| 573 |
+
"grad_norm": 0.9222125293365617,
|
| 574 |
+
"learning_rate": 1.1338531386752618e-05,
|
| 575 |
+
"loss": 0.7685,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5182341650671785,
|
| 580 |
+
"grad_norm": 0.8293885569783266,
|
| 581 |
+
"learning_rate": 1.1116468229547079e-05,
|
| 582 |
+
"loss": 0.7315,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5246321177223289,
|
| 587 |
+
"grad_norm": 0.8181032830246795,
|
| 588 |
+
"learning_rate": 1.0893846095547493e-05,
|
| 589 |
+
"loss": 0.7124,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5310300703774792,
|
| 594 |
+
"grad_norm": 0.8952645487752635,
|
| 595 |
+
"learning_rate": 1.0670776443910024e-05,
|
| 596 |
+
"loss": 0.7371,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5374280230326296,
|
| 601 |
+
"grad_norm": 0.8781812680428416,
|
| 602 |
+
"learning_rate": 1.0447370957847343e-05,
|
| 603 |
+
"loss": 0.7374,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5438259756877799,
|
| 608 |
+
"grad_norm": 0.8047369438911633,
|
| 609 |
+
"learning_rate": 1.0223741488712732e-05,
|
| 610 |
+
"loss": 0.727,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5502239283429302,
|
| 615 |
+
"grad_norm": 0.859407154090335,
|
| 616 |
+
"learning_rate": 1e-05,
|
| 617 |
+
"loss": 0.7421,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5566218809980806,
|
| 622 |
+
"grad_norm": 0.8893479868039521,
|
| 623 |
+
"learning_rate": 9.776258511287271e-06,
|
| 624 |
+
"loss": 0.732,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5630198336532309,
|
| 629 |
+
"grad_norm": 0.949546721569847,
|
| 630 |
+
"learning_rate": 9.55262904215266e-06,
|
| 631 |
+
"loss": 0.7332,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5694177863083814,
|
| 636 |
+
"grad_norm": 0.8485580508908309,
|
| 637 |
+
"learning_rate": 9.329223556089976e-06,
|
| 638 |
+
"loss": 0.7412,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5758157389635317,
|
| 643 |
+
"grad_norm": 0.8283004065969708,
|
| 644 |
+
"learning_rate": 9.10615390445251e-06,
|
| 645 |
+
"loss": 0.7211,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.582213691618682,
|
| 650 |
+
"grad_norm": 0.8817929492946212,
|
| 651 |
+
"learning_rate": 8.883531770452924e-06,
|
| 652 |
+
"loss": 0.7341,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5886116442738324,
|
| 657 |
+
"grad_norm": 0.8900670681272643,
|
| 658 |
+
"learning_rate": 8.661468613247387e-06,
|
| 659 |
+
"loss": 0.7441,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5950095969289827,
|
| 664 |
+
"grad_norm": 0.8174845932665962,
|
| 665 |
+
"learning_rate": 8.440075612131823e-06,
|
| 666 |
+
"loss": 0.7265,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6014075495841331,
|
| 671 |
+
"grad_norm": 0.8390159513525518,
|
| 672 |
+
"learning_rate": 8.219463610878336e-06,
|
| 673 |
+
"loss": 0.7052,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6078055022392834,
|
| 678 |
+
"grad_norm": 0.8412199328086044,
|
| 679 |
+
"learning_rate": 7.999743062239557e-06,
|
| 680 |
+
"loss": 0.7249,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6142034548944337,
|
| 685 |
+
"grad_norm": 0.8369817069040336,
|
| 686 |
+
"learning_rate": 7.781023972648826e-06,
|
| 687 |
+
"loss": 0.732,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6206014075495841,
|
| 692 |
+
"grad_norm": 0.8837012458062626,
|
| 693 |
+
"learning_rate": 7.563415847143782e-06,
|
| 694 |
+
"loss": 0.7203,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6269993602047345,
|
| 699 |
+
"grad_norm": 0.8540794083066343,
|
| 700 |
+
"learning_rate": 7.347027634540993e-06,
|
| 701 |
+
"loss": 0.7135,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6333973128598849,
|
| 706 |
+
"grad_norm": 0.8525705119650993,
|
| 707 |
+
"learning_rate": 7.131967672889101e-06,
|
| 708 |
+
"loss": 0.7195,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6397952655150352,
|
| 713 |
+
"grad_norm": 0.8786823273169972,
|
| 714 |
+
"learning_rate": 6.918343635227694e-06,
|
| 715 |
+
"loss": 0.7339,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6461932181701855,
|
| 720 |
+
"grad_norm": 1.0560174180349937,
|
| 721 |
+
"learning_rate": 6.706262475679205e-06,
|
| 722 |
+
"loss": 0.7187,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6525911708253359,
|
| 727 |
+
"grad_norm": 0.8749872839659149,
|
| 728 |
+
"learning_rate": 6.495830375900665e-06,
|
| 729 |
+
"loss": 0.7354,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6589891234804862,
|
| 734 |
+
"grad_norm": 0.8972887639537709,
|
| 735 |
+
"learning_rate": 6.287152691922264e-06,
|
| 736 |
+
"loss": 0.7352,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.6653870761356366,
|
| 741 |
+
"grad_norm": 0.758512097349371,
|
| 742 |
+
"learning_rate": 6.080333901399252e-06,
|
| 743 |
+
"loss": 0.7247,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6717850287907869,
|
| 748 |
+
"grad_norm": 0.8424258585380499,
|
| 749 |
+
"learning_rate": 5.875477551303596e-06,
|
| 750 |
+
"loss": 0.7299,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6781829814459372,
|
| 755 |
+
"grad_norm": 0.8587554713063377,
|
| 756 |
+
"learning_rate": 5.672686206081638e-06,
|
| 757 |
+
"loss": 0.7456,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6845809341010877,
|
| 762 |
+
"grad_norm": 0.8220663211697773,
|
| 763 |
+
"learning_rate": 5.47206139630363e-06,
|
| 764 |
+
"loss": 0.7255,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.690978886756238,
|
| 769 |
+
"grad_norm": 0.764989841037643,
|
| 770 |
+
"learning_rate": 5.273703567830908e-06,
|
| 771 |
+
"loss": 0.6999,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6973768394113884,
|
| 776 |
+
"grad_norm": 0.841679038026195,
|
| 777 |
+
"learning_rate": 5.077712031526153e-06,
|
| 778 |
+
"loss": 0.7216,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7037747920665387,
|
| 783 |
+
"grad_norm": 0.9158140652111489,
|
| 784 |
+
"learning_rate": 4.8841849135319015e-06,
|
| 785 |
+
"loss": 0.7197,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.710172744721689,
|
| 790 |
+
"grad_norm": 0.7720710563951564,
|
| 791 |
+
"learning_rate": 4.693219106142186e-06,
|
| 792 |
+
"loss": 0.7101,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7165706973768394,
|
| 797 |
+
"grad_norm": 0.9540569720579076,
|
| 798 |
+
"learning_rate": 4.504910219291941e-06,
|
| 799 |
+
"loss": 0.7292,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7229686500319897,
|
| 804 |
+
"grad_norm": 0.8573826120101363,
|
| 805 |
+
"learning_rate": 4.319352532688444e-06,
|
| 806 |
+
"loss": 0.7105,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7293666026871402,
|
| 811 |
+
"grad_norm": 0.8106292253940656,
|
| 812 |
+
"learning_rate": 4.13663894860873e-06,
|
| 813 |
+
"loss": 0.7084,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7357645553422905,
|
| 818 |
+
"grad_norm": 0.8820590050867799,
|
| 819 |
+
"learning_rate": 3.956860945386677e-06,
|
| 820 |
+
"loss": 0.713,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.7421625079974408,
|
| 825 |
+
"grad_norm": 0.8091830896370955,
|
| 826 |
+
"learning_rate": 3.7801085316129615e-06,
|
| 827 |
+
"loss": 0.6979,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7485604606525912,
|
| 832 |
+
"grad_norm": 0.9215560782786927,
|
| 833 |
+
"learning_rate": 3.606470201070904e-06,
|
| 834 |
+
"loss": 0.7238,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.7549584133077415,
|
| 839 |
+
"grad_norm": 0.8256761378699967,
|
| 840 |
+
"learning_rate": 3.4360328884307058e-06,
|
| 841 |
+
"loss": 0.7377,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.7613563659628919,
|
| 846 |
+
"grad_norm": 0.8664264779515329,
|
| 847 |
+
"learning_rate": 3.2688819257242963e-06,
|
| 848 |
+
"loss": 0.7419,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7677543186180422,
|
| 853 |
+
"grad_norm": 0.8896365508552663,
|
| 854 |
+
"learning_rate": 3.1051009996225434e-06,
|
| 855 |
+
"loss": 0.7021,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.7741522712731925,
|
| 860 |
+
"grad_norm": 0.8877160233939523,
|
| 861 |
+
"learning_rate": 2.9447721095362325e-06,
|
| 862 |
+
"loss": 0.7194,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.780550223928343,
|
| 867 |
+
"grad_norm": 0.87887437602247,
|
| 868 |
+
"learning_rate": 2.7879755265618558e-06,
|
| 869 |
+
"loss": 0.6994,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.7869481765834933,
|
| 874 |
+
"grad_norm": 0.9105056631876884,
|
| 875 |
+
"learning_rate": 2.6347897532926293e-06,
|
| 876 |
+
"loss": 0.7178,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.7933461292386437,
|
| 881 |
+
"grad_norm": 0.8372924489670353,
|
| 882 |
+
"learning_rate": 2.485291484515e-06,
|
| 883 |
+
"loss": 0.7033,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.799744081893794,
|
| 888 |
+
"grad_norm": 0.8723730239208861,
|
| 889 |
+
"learning_rate": 2.339555568810221e-06,
|
| 890 |
+
"loss": 0.7276,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8061420345489443,
|
| 895 |
+
"grad_norm": 0.8150967413326101,
|
| 896 |
+
"learning_rate": 2.1976549710802754e-06,
|
| 897 |
+
"loss": 0.7364,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8125399872040947,
|
| 902 |
+
"grad_norm": 0.9104498719001516,
|
| 903 |
+
"learning_rate": 2.0596607360168897e-06,
|
| 904 |
+
"loss": 0.721,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.818937939859245,
|
| 909 |
+
"grad_norm": 0.8059019041226441,
|
| 910 |
+
"learning_rate": 1.9256419525319316e-06,
|
| 911 |
+
"loss": 0.7003,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.8253358925143954,
|
| 916 |
+
"grad_norm": 0.8016220960820958,
|
| 917 |
+
"learning_rate": 1.7956657191669969e-06,
|
| 918 |
+
"loss": 0.7405,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8317338451695457,
|
| 923 |
+
"grad_norm": 0.8296186304272232,
|
| 924 |
+
"learning_rate": 1.6697971104994847e-06,
|
| 925 |
+
"loss": 0.7237,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.838131797824696,
|
| 930 |
+
"grad_norm": 0.8575579265825671,
|
| 931 |
+
"learning_rate": 1.5480991445620541e-06,
|
| 932 |
+
"loss": 0.7252,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.8445297504798465,
|
| 937 |
+
"grad_norm": 0.8443927649243143,
|
| 938 |
+
"learning_rate": 1.4306327512916574e-06,
|
| 939 |
+
"loss": 0.7178,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.8509277031349968,
|
| 944 |
+
"grad_norm": 0.7908279914848837,
|
| 945 |
+
"learning_rate": 1.3174567420240647e-06,
|
| 946 |
+
"loss": 0.6936,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.8573256557901472,
|
| 951 |
+
"grad_norm": 0.8218483754182432,
|
| 952 |
+
"learning_rate": 1.2086277800490554e-06,
|
| 953 |
+
"loss": 0.7007,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.8637236084452975,
|
| 958 |
+
"grad_norm": 0.8256511379428485,
|
| 959 |
+
"learning_rate": 1.1042003522410882e-06,
|
| 960 |
+
"loss": 0.6889,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.8701215611004478,
|
| 965 |
+
"grad_norm": 0.8968851185464259,
|
| 966 |
+
"learning_rate": 1.0042267417796292e-06,
|
| 967 |
+
"loss": 0.7123,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.8765195137555982,
|
| 972 |
+
"grad_norm": 0.8823080752196552,
|
| 973 |
+
"learning_rate": 9.08757001972762e-07,
|
| 974 |
+
"loss": 0.7021,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.8829174664107485,
|
| 979 |
+
"grad_norm": 0.8466732079799328,
|
| 980 |
+
"learning_rate": 8.178389311972612e-07,
|
| 981 |
+
"loss": 0.6956,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.889315419065899,
|
| 986 |
+
"grad_norm": 0.8760114826953183,
|
| 987 |
+
"learning_rate": 7.315180489675822e-07,
|
| 988 |
+
"loss": 0.6976,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.8957133717210493,
|
| 993 |
+
"grad_norm": 0.8384622643848926,
|
| 994 |
+
"learning_rate": 6.498375731458529e-07,
|
| 995 |
+
"loss": 0.7103,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9021113243761996,
|
| 1000 |
+
"grad_norm": 0.8194072342460205,
|
| 1001 |
+
"learning_rate": 5.728383983041696e-07,
|
| 1002 |
+
"loss": 0.7157,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.90850927703135,
|
| 1007 |
+
"grad_norm": 0.9294398002536329,
|
| 1008 |
+
"learning_rate": 5.005590752501244e-07,
|
| 1009 |
+
"loss": 0.7248,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9149072296865003,
|
| 1014 |
+
"grad_norm": 0.8943875627138937,
|
| 1015 |
+
"learning_rate": 4.3303579172574884e-07,
|
| 1016 |
+
"loss": 0.7171,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9213051823416507,
|
| 1021 |
+
"grad_norm": 0.8691772678725829,
|
| 1022 |
+
"learning_rate": 3.7030235428956895e-07,
|
| 1023 |
+
"loss": 0.7317,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.927703134996801,
|
| 1028 |
+
"grad_norm": 0.9150925426459633,
|
| 1029 |
+
"learning_rate": 3.1239017139084725e-07,
|
| 1030 |
+
"loss": 0.7459,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.9341010876519513,
|
| 1035 |
+
"grad_norm": 0.8226066365805443,
|
| 1036 |
+
"learning_rate": 2.593282376444539e-07,
|
| 1037 |
+
"loss": 0.7004,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.9404990403071017,
|
| 1042 |
+
"grad_norm": 0.827122609753977,
|
| 1043 |
+
"learning_rate": 2.11143119314281e-07,
|
| 1044 |
+
"loss": 0.7353,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.946896992962252,
|
| 1049 |
+
"grad_norm": 0.928354448329939,
|
| 1050 |
+
"learning_rate": 1.6785894101243205e-07,
|
| 1051 |
+
"loss": 0.7494,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.9532949456174025,
|
| 1056 |
+
"grad_norm": 0.8296013670372103,
|
| 1057 |
+
"learning_rate": 1.2949737362087156e-07,
|
| 1058 |
+
"loss": 0.7057,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9596928982725528,
|
| 1063 |
+
"grad_norm": 0.8790221772454616,
|
| 1064 |
+
"learning_rate": 9.607762344156946e-08,
|
| 1065 |
+
"loss": 0.725,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.9660908509277031,
|
| 1070 |
+
"grad_norm": 0.8987832603853396,
|
| 1071 |
+
"learning_rate": 6.761642258056977e-08,
|
| 1072 |
+
"loss": 0.7245,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.9724888035828535,
|
| 1077 |
+
"grad_norm": 0.7657247344848286,
|
| 1078 |
+
"learning_rate": 4.412802057081278e-08,
|
| 1079 |
+
"loss": 0.7057,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.9788867562380038,
|
| 1084 |
+
"grad_norm": 0.7827327625691514,
|
| 1085 |
+
"learning_rate": 2.5624177237884017e-08,
|
| 1086 |
+
"loss": 0.72,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.9852847088931542,
|
| 1091 |
+
"grad_norm": 0.8361648349847708,
|
| 1092 |
+
"learning_rate": 1.2114156812284006e-08,
|
| 1093 |
+
"loss": 0.7083,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.9916826615483045,
|
| 1098 |
+
"grad_norm": 0.8873989576007488,
|
| 1099 |
+
"learning_rate": 3.6047232911462506e-09,
|
| 1100 |
+
"loss": 0.6976,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.9980806142034548,
|
| 1105 |
+
"grad_norm": 0.873748350676312,
|
| 1106 |
+
"learning_rate": 1.0013705174061195e-10,
|
| 1107 |
+
"loss": 0.711,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.999360204734485,
|
| 1112 |
+
"eval_loss": 0.7211461067199707,
|
| 1113 |
+
"eval_runtime": 620.1493,
|
| 1114 |
+
"eval_samples_per_second": 69.338,
|
| 1115 |
+
"eval_steps_per_second": 2.167,
|
| 1116 |
+
"step": 781
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.999360204734485,
|
| 1120 |
+
"step": 781,
|
| 1121 |
+
"total_flos": 80545737277440.0,
|
| 1122 |
+
"train_loss": 0.7457574072476386,
|
| 1123 |
+
"train_runtime": 7303.4461,
|
| 1124 |
+
"train_samples_per_second": 13.692,
|
| 1125 |
+
"train_steps_per_second": 0.107
|
| 1126 |
+
}
|
| 1127 |
+
],
|
| 1128 |
+
"logging_steps": 5,
|
| 1129 |
+
"max_steps": 781,
|
| 1130 |
+
"num_input_tokens_seen": 0,
|
| 1131 |
+
"num_train_epochs": 1,
|
| 1132 |
+
"save_steps": 100,
|
| 1133 |
+
"total_flos": 80545737277440.0,
|
| 1134 |
+
"train_batch_size": 16,
|
| 1135 |
+
"trial_name": null,
|
| 1136 |
+
"trial_params": null
|
| 1137 |
+
}
|