Instructions to use souging/1d2b505e-b9ed-47dd-9efa-613aa6ab044d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use souging/1d2b505e-b9ed-47dd-9efa-613aa6ab044d with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-0.5B-Chat") model = PeftModel.from_pretrained(base_model, "souging/1d2b505e-b9ed-47dd-9efa-613aa6ab044d") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 3, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +949 -4
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 60599872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a345fb2454d5f2f54887250d6032c4b6633afdeaa986fba71d5f0a3106aea8ca
|
| 3 |
size 60599872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31144340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b3486c0f692c537833f40177d52de03b126b368ac0126af6e6ab6863820be91
|
| 3 |
size 31144340
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6a6fc8618449cabfbf1e063fe41c12ca0842db9a8419827e0c9cfde85bacab3
|
| 3 |
size 15984
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a83fb5443e6fae9ad22e9de97d899739e369d667bc17abe33ef613fa902f3dd
|
| 3 |
size 15984
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad681ea63a107172cf444add37dbd472d0e249f67bcf7e7c89655cd219432a0c
|
| 3 |
size 15984
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:053f8af4554bcb93b467a7516e339230392426a19f66d9b9314277b600285b6f
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48419c5aeacafd1136d3fcf6d057c0d2eaf2e7aacf07faa28cc8521fba8b0e06
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af715130afab7a1adc071b04907dac34a4628ef2cfa2c9cd413234bfaf4ab7e
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05302bfd51493b9bfad3c0f36fe5b084e027f03053279c80969a26f3914a8765
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3e7f92866f23ee34826226442df5f6e7c5a4937930a2e5b5ee5df9fcef18407
|
| 3 |
size 15984
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ac31dcfba988823188c44099086577dd09e162577217892c3f4fd5ad8489c2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3962,6 +3962,951 @@
|
|
| 3962 |
"learning_rate": 2.4198997474396877e-05,
|
| 3963 |
"loss": 1.2761,
|
| 3964 |
"step": 565
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3965 |
}
|
| 3966 |
],
|
| 3967 |
"logging_steps": 1,
|
|
@@ -3976,12 +4921,12 @@
|
|
| 3976 |
"should_evaluate": false,
|
| 3977 |
"should_log": false,
|
| 3978 |
"should_save": true,
|
| 3979 |
-
"should_training_stop":
|
| 3980 |
},
|
| 3981 |
"attributes": {}
|
| 3982 |
}
|
| 3983 |
},
|
| 3984 |
-
"total_flos": 1.
|
| 3985 |
"train_batch_size": 4,
|
| 3986 |
"trial_name": null,
|
| 3987 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.713527851458886,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3962 |
"learning_rate": 2.4198997474396877e-05,
|
| 3963 |
"loss": 1.2761,
|
| 3964 |
"step": 565
|
| 3965 |
+
},
|
| 3966 |
+
{
|
| 3967 |
+
"epoch": 3.0026525198938994,
|
| 3968 |
+
"grad_norm": 0.7845560908317566,
|
| 3969 |
+
"learning_rate": 2.3856601107901166e-05,
|
| 3970 |
+
"loss": 1.5915,
|
| 3971 |
+
"step": 566
|
| 3972 |
+
},
|
| 3973 |
+
{
|
| 3974 |
+
"epoch": 3.0079575596816976,
|
| 3975 |
+
"grad_norm": 0.4286109209060669,
|
| 3976 |
+
"learning_rate": 2.351631966665476e-05,
|
| 3977 |
+
"loss": 1.0596,
|
| 3978 |
+
"step": 567
|
| 3979 |
+
},
|
| 3980 |
+
{
|
| 3981 |
+
"epoch": 3.013262599469496,
|
| 3982 |
+
"grad_norm": 0.42482790350914,
|
| 3983 |
+
"learning_rate": 2.31781624796453e-05,
|
| 3984 |
+
"loss": 1.0705,
|
| 3985 |
+
"step": 568
|
| 3986 |
+
},
|
| 3987 |
+
{
|
| 3988 |
+
"epoch": 3.018567639257294,
|
| 3989 |
+
"grad_norm": 0.40887096524238586,
|
| 3990 |
+
"learning_rate": 2.2842138817622883e-05,
|
| 3991 |
+
"loss": 0.8475,
|
| 3992 |
+
"step": 569
|
| 3993 |
+
},
|
| 3994 |
+
{
|
| 3995 |
+
"epoch": 3.023872679045093,
|
| 3996 |
+
"grad_norm": 0.4262137711048126,
|
| 3997 |
+
"learning_rate": 2.250825789284594e-05,
|
| 3998 |
+
"loss": 0.9428,
|
| 3999 |
+
"step": 570
|
| 4000 |
+
},
|
| 4001 |
+
{
|
| 4002 |
+
"epoch": 3.029177718832891,
|
| 4003 |
+
"grad_norm": 0.43155452609062195,
|
| 4004 |
+
"learning_rate": 2.217652885882869e-05,
|
| 4005 |
+
"loss": 1.0396,
|
| 4006 |
+
"step": 571
|
| 4007 |
+
},
|
| 4008 |
+
{
|
| 4009 |
+
"epoch": 3.0344827586206895,
|
| 4010 |
+
"grad_norm": 0.428359717130661,
|
| 4011 |
+
"learning_rate": 2.1846960810090188e-05,
|
| 4012 |
+
"loss": 1.0105,
|
| 4013 |
+
"step": 572
|
| 4014 |
+
},
|
| 4015 |
+
{
|
| 4016 |
+
"epoch": 3.0397877984084882,
|
| 4017 |
+
"grad_norm": 0.43162691593170166,
|
| 4018 |
+
"learning_rate": 2.151956278190494e-05,
|
| 4019 |
+
"loss": 0.978,
|
| 4020 |
+
"step": 573
|
| 4021 |
+
},
|
| 4022 |
+
{
|
| 4023 |
+
"epoch": 3.0450928381962865,
|
| 4024 |
+
"grad_norm": 0.40628722310066223,
|
| 4025 |
+
"learning_rate": 2.119434375005527e-05,
|
| 4026 |
+
"loss": 0.8864,
|
| 4027 |
+
"step": 574
|
| 4028 |
+
},
|
| 4029 |
+
{
|
| 4030 |
+
"epoch": 3.050397877984085,
|
| 4031 |
+
"grad_norm": 0.46302545070648193,
|
| 4032 |
+
"learning_rate": 2.087131263058526e-05,
|
| 4033 |
+
"loss": 1.0971,
|
| 4034 |
+
"step": 575
|
| 4035 |
+
},
|
| 4036 |
+
{
|
| 4037 |
+
"epoch": 3.055702917771883,
|
| 4038 |
+
"grad_norm": 0.41567516326904297,
|
| 4039 |
+
"learning_rate": 2.055047827955618e-05,
|
| 4040 |
+
"loss": 0.8932,
|
| 4041 |
+
"step": 576
|
| 4042 |
+
},
|
| 4043 |
+
{
|
| 4044 |
+
"epoch": 3.061007957559682,
|
| 4045 |
+
"grad_norm": 0.4296072721481323,
|
| 4046 |
+
"learning_rate": 2.0231849492803852e-05,
|
| 4047 |
+
"loss": 0.9946,
|
| 4048 |
+
"step": 577
|
| 4049 |
+
},
|
| 4050 |
+
{
|
| 4051 |
+
"epoch": 3.06631299734748,
|
| 4052 |
+
"grad_norm": 0.4769238829612732,
|
| 4053 |
+
"learning_rate": 1.991543500569745e-05,
|
| 4054 |
+
"loss": 0.9136,
|
| 4055 |
+
"step": 578
|
| 4056 |
+
},
|
| 4057 |
+
{
|
| 4058 |
+
"epoch": 3.0716180371352784,
|
| 4059 |
+
"grad_norm": 0.41191771626472473,
|
| 4060 |
+
"learning_rate": 1.960124349289992e-05,
|
| 4061 |
+
"loss": 0.8407,
|
| 4062 |
+
"step": 579
|
| 4063 |
+
},
|
| 4064 |
+
{
|
| 4065 |
+
"epoch": 3.076923076923077,
|
| 4066 |
+
"grad_norm": 0.38414642214775085,
|
| 4067 |
+
"learning_rate": 1.928928356813032e-05,
|
| 4068 |
+
"loss": 0.8471,
|
| 4069 |
+
"step": 580
|
| 4070 |
+
},
|
| 4071 |
+
{
|
| 4072 |
+
"epoch": 3.0822281167108754,
|
| 4073 |
+
"grad_norm": 0.4157571792602539,
|
| 4074 |
+
"learning_rate": 1.8979563783927565e-05,
|
| 4075 |
+
"loss": 0.9727,
|
| 4076 |
+
"step": 581
|
| 4077 |
+
},
|
| 4078 |
+
{
|
| 4079 |
+
"epoch": 3.0875331564986737,
|
| 4080 |
+
"grad_norm": 0.4373985528945923,
|
| 4081 |
+
"learning_rate": 1.8672092631416013e-05,
|
| 4082 |
+
"loss": 1.0534,
|
| 4083 |
+
"step": 582
|
| 4084 |
+
},
|
| 4085 |
+
{
|
| 4086 |
+
"epoch": 3.092838196286472,
|
| 4087 |
+
"grad_norm": 0.3944924473762512,
|
| 4088 |
+
"learning_rate": 1.8366878540072614e-05,
|
| 4089 |
+
"loss": 0.9673,
|
| 4090 |
+
"step": 583
|
| 4091 |
+
},
|
| 4092 |
+
{
|
| 4093 |
+
"epoch": 3.0981432360742707,
|
| 4094 |
+
"grad_norm": 0.42874181270599365,
|
| 4095 |
+
"learning_rate": 1.8063929877495892e-05,
|
| 4096 |
+
"loss": 0.9854,
|
| 4097 |
+
"step": 584
|
| 4098 |
+
},
|
| 4099 |
+
{
|
| 4100 |
+
"epoch": 3.103448275862069,
|
| 4101 |
+
"grad_norm": 0.3736847937107086,
|
| 4102 |
+
"learning_rate": 1.7763254949176414e-05,
|
| 4103 |
+
"loss": 0.7645,
|
| 4104 |
+
"step": 585
|
| 4105 |
+
},
|
| 4106 |
+
{
|
| 4107 |
+
"epoch": 3.1087533156498672,
|
| 4108 |
+
"grad_norm": 0.4372352659702301,
|
| 4109 |
+
"learning_rate": 1.7464861998269243e-05,
|
| 4110 |
+
"loss": 1.1743,
|
| 4111 |
+
"step": 586
|
| 4112 |
+
},
|
| 4113 |
+
{
|
| 4114 |
+
"epoch": 3.114058355437666,
|
| 4115 |
+
"grad_norm": 0.4284694492816925,
|
| 4116 |
+
"learning_rate": 1.7168759205367893e-05,
|
| 4117 |
+
"loss": 1.0876,
|
| 4118 |
+
"step": 587
|
| 4119 |
+
},
|
| 4120 |
+
{
|
| 4121 |
+
"epoch": 3.1193633952254642,
|
| 4122 |
+
"grad_norm": 0.4218258261680603,
|
| 4123 |
+
"learning_rate": 1.6874954688279956e-05,
|
| 4124 |
+
"loss": 0.7981,
|
| 4125 |
+
"step": 588
|
| 4126 |
+
},
|
| 4127 |
+
{
|
| 4128 |
+
"epoch": 3.1246684350132625,
|
| 4129 |
+
"grad_norm": 0.4546039402484894,
|
| 4130 |
+
"learning_rate": 1.6583456501804725e-05,
|
| 4131 |
+
"loss": 1.0915,
|
| 4132 |
+
"step": 589
|
| 4133 |
+
},
|
| 4134 |
+
{
|
| 4135 |
+
"epoch": 3.129973474801061,
|
| 4136 |
+
"grad_norm": 0.420549601316452,
|
| 4137 |
+
"learning_rate": 1.6294272637512183e-05,
|
| 4138 |
+
"loss": 1.1742,
|
| 4139 |
+
"step": 590
|
| 4140 |
+
},
|
| 4141 |
+
{
|
| 4142 |
+
"epoch": 3.1352785145888595,
|
| 4143 |
+
"grad_norm": 0.4172128140926361,
|
| 4144 |
+
"learning_rate": 1.600741102352409e-05,
|
| 4145 |
+
"loss": 0.993,
|
| 4146 |
+
"step": 591
|
| 4147 |
+
},
|
| 4148 |
+
{
|
| 4149 |
+
"epoch": 3.140583554376658,
|
| 4150 |
+
"grad_norm": 0.44922539591789246,
|
| 4151 |
+
"learning_rate": 1.57228795242965e-05,
|
| 4152 |
+
"loss": 1.0002,
|
| 4153 |
+
"step": 592
|
| 4154 |
+
},
|
| 4155 |
+
{
|
| 4156 |
+
"epoch": 3.145888594164456,
|
| 4157 |
+
"grad_norm": 0.4405660629272461,
|
| 4158 |
+
"learning_rate": 1.544068594040417e-05,
|
| 4159 |
+
"loss": 0.7937,
|
| 4160 |
+
"step": 593
|
| 4161 |
+
},
|
| 4162 |
+
{
|
| 4163 |
+
"epoch": 3.151193633952255,
|
| 4164 |
+
"grad_norm": 0.44561779499053955,
|
| 4165 |
+
"learning_rate": 1.516083800832676e-05,
|
| 4166 |
+
"loss": 1.1287,
|
| 4167 |
+
"step": 594
|
| 4168 |
+
},
|
| 4169 |
+
{
|
| 4170 |
+
"epoch": 3.156498673740053,
|
| 4171 |
+
"grad_norm": 0.42636775970458984,
|
| 4172 |
+
"learning_rate": 1.488334340023669e-05,
|
| 4173 |
+
"loss": 1.0461,
|
| 4174 |
+
"step": 595
|
| 4175 |
+
},
|
| 4176 |
+
{
|
| 4177 |
+
"epoch": 3.1618037135278514,
|
| 4178 |
+
"grad_norm": 0.41767892241477966,
|
| 4179 |
+
"learning_rate": 1.4608209723788835e-05,
|
| 4180 |
+
"loss": 0.9207,
|
| 4181 |
+
"step": 596
|
| 4182 |
+
},
|
| 4183 |
+
{
|
| 4184 |
+
"epoch": 3.1671087533156497,
|
| 4185 |
+
"grad_norm": 0.4501255452632904,
|
| 4186 |
+
"learning_rate": 1.4335444521911899e-05,
|
| 4187 |
+
"loss": 0.9065,
|
| 4188 |
+
"step": 597
|
| 4189 |
+
},
|
| 4190 |
+
{
|
| 4191 |
+
"epoch": 3.1724137931034484,
|
| 4192 |
+
"grad_norm": 0.42627593874931335,
|
| 4193 |
+
"learning_rate": 1.4065055272601703e-05,
|
| 4194 |
+
"loss": 1.0891,
|
| 4195 |
+
"step": 598
|
| 4196 |
+
},
|
| 4197 |
+
{
|
| 4198 |
+
"epoch": 3.1777188328912467,
|
| 4199 |
+
"grad_norm": 0.41368064284324646,
|
| 4200 |
+
"learning_rate": 1.3797049388716065e-05,
|
| 4201 |
+
"loss": 1.0053,
|
| 4202 |
+
"step": 599
|
| 4203 |
+
},
|
| 4204 |
+
{
|
| 4205 |
+
"epoch": 3.183023872679045,
|
| 4206 |
+
"grad_norm": 0.41634687781333923,
|
| 4207 |
+
"learning_rate": 1.3531434217771692e-05,
|
| 4208 |
+
"loss": 0.9862,
|
| 4209 |
+
"step": 600
|
| 4210 |
+
},
|
| 4211 |
+
{
|
| 4212 |
+
"epoch": 3.1883289124668437,
|
| 4213 |
+
"grad_norm": 0.4399423599243164,
|
| 4214 |
+
"learning_rate": 1.3268217041742701e-05,
|
| 4215 |
+
"loss": 1.1283,
|
| 4216 |
+
"step": 601
|
| 4217 |
+
},
|
| 4218 |
+
{
|
| 4219 |
+
"epoch": 3.193633952254642,
|
| 4220 |
+
"grad_norm": 0.4235760271549225,
|
| 4221 |
+
"learning_rate": 1.3007405076860875e-05,
|
| 4222 |
+
"loss": 0.8662,
|
| 4223 |
+
"step": 602
|
| 4224 |
+
},
|
| 4225 |
+
{
|
| 4226 |
+
"epoch": 3.1989389920424403,
|
| 4227 |
+
"grad_norm": 0.4228001832962036,
|
| 4228 |
+
"learning_rate": 1.2749005473418015e-05,
|
| 4229 |
+
"loss": 1.1027,
|
| 4230 |
+
"step": 603
|
| 4231 |
+
},
|
| 4232 |
+
{
|
| 4233 |
+
"epoch": 3.2042440318302385,
|
| 4234 |
+
"grad_norm": 0.4243561625480652,
|
| 4235 |
+
"learning_rate": 1.2493025315569801e-05,
|
| 4236 |
+
"loss": 1.1339,
|
| 4237 |
+
"step": 604
|
| 4238 |
+
},
|
| 4239 |
+
{
|
| 4240 |
+
"epoch": 3.2095490716180373,
|
| 4241 |
+
"grad_norm": 0.46745195984840393,
|
| 4242 |
+
"learning_rate": 1.2239471621141508e-05,
|
| 4243 |
+
"loss": 0.9855,
|
| 4244 |
+
"step": 605
|
| 4245 |
+
},
|
| 4246 |
+
{
|
| 4247 |
+
"epoch": 3.2148541114058355,
|
| 4248 |
+
"grad_norm": 0.41469866037368774,
|
| 4249 |
+
"learning_rate": 1.1988351341435792e-05,
|
| 4250 |
+
"loss": 0.8191,
|
| 4251 |
+
"step": 606
|
| 4252 |
+
},
|
| 4253 |
+
{
|
| 4254 |
+
"epoch": 3.220159151193634,
|
| 4255 |
+
"grad_norm": 0.4550921320915222,
|
| 4256 |
+
"learning_rate": 1.173967136104196e-05,
|
| 4257 |
+
"loss": 1.1261,
|
| 4258 |
+
"step": 607
|
| 4259 |
+
},
|
| 4260 |
+
{
|
| 4261 |
+
"epoch": 3.2254641909814326,
|
| 4262 |
+
"grad_norm": 0.4678977131843567,
|
| 4263 |
+
"learning_rate": 1.1493438497647313e-05,
|
| 4264 |
+
"loss": 1.1831,
|
| 4265 |
+
"step": 608
|
| 4266 |
+
},
|
| 4267 |
+
{
|
| 4268 |
+
"epoch": 3.230769230769231,
|
| 4269 |
+
"grad_norm": 0.4221738576889038,
|
| 4270 |
+
"learning_rate": 1.1249659501850155e-05,
|
| 4271 |
+
"loss": 0.9385,
|
| 4272 |
+
"step": 609
|
| 4273 |
+
},
|
| 4274 |
+
{
|
| 4275 |
+
"epoch": 3.236074270557029,
|
| 4276 |
+
"grad_norm": 0.42360720038414,
|
| 4277 |
+
"learning_rate": 1.1008341056974854e-05,
|
| 4278 |
+
"loss": 1.0717,
|
| 4279 |
+
"step": 610
|
| 4280 |
+
},
|
| 4281 |
+
{
|
| 4282 |
+
"epoch": 3.2413793103448274,
|
| 4283 |
+
"grad_norm": 0.4413885474205017,
|
| 4284 |
+
"learning_rate": 1.0769489778888405e-05,
|
| 4285 |
+
"loss": 1.0303,
|
| 4286 |
+
"step": 611
|
| 4287 |
+
},
|
| 4288 |
+
{
|
| 4289 |
+
"epoch": 3.246684350132626,
|
| 4290 |
+
"grad_norm": 0.46732011437416077,
|
| 4291 |
+
"learning_rate": 1.0533112215819298e-05,
|
| 4292 |
+
"loss": 1.1025,
|
| 4293 |
+
"step": 612
|
| 4294 |
+
},
|
| 4295 |
+
{
|
| 4296 |
+
"epoch": 3.2519893899204244,
|
| 4297 |
+
"grad_norm": 0.4380669593811035,
|
| 4298 |
+
"learning_rate": 1.029921484817783e-05,
|
| 4299 |
+
"loss": 0.9418,
|
| 4300 |
+
"step": 613
|
| 4301 |
+
},
|
| 4302 |
+
{
|
| 4303 |
+
"epoch": 3.2572944297082227,
|
| 4304 |
+
"grad_norm": 0.4503823518753052,
|
| 4305 |
+
"learning_rate": 1.0067804088378455e-05,
|
| 4306 |
+
"loss": 0.8882,
|
| 4307 |
+
"step": 614
|
| 4308 |
+
},
|
| 4309 |
+
{
|
| 4310 |
+
"epoch": 3.2625994694960214,
|
| 4311 |
+
"grad_norm": 0.4514295756816864,
|
| 4312 |
+
"learning_rate": 9.8388862806641e-06,
|
| 4313 |
+
"loss": 0.971,
|
| 4314 |
+
"step": 615
|
| 4315 |
+
},
|
| 4316 |
+
{
|
| 4317 |
+
"epoch": 3.2679045092838197,
|
| 4318 |
+
"grad_norm": 0.4651792347431183,
|
| 4319 |
+
"learning_rate": 9.612467700932045e-06,
|
| 4320 |
+
"loss": 1.0794,
|
| 4321 |
+
"step": 616
|
| 4322 |
+
},
|
| 4323 |
+
{
|
| 4324 |
+
"epoch": 3.273209549071618,
|
| 4325 |
+
"grad_norm": 0.43075329065322876,
|
| 4326 |
+
"learning_rate": 9.388554556562049e-06,
|
| 4327 |
+
"loss": 0.826,
|
| 4328 |
+
"step": 617
|
| 4329 |
+
},
|
| 4330 |
+
{
|
| 4331 |
+
"epoch": 3.2785145888594163,
|
| 4332 |
+
"grad_norm": 0.44569700956344604,
|
| 4333 |
+
"learning_rate": 9.167152986246078e-06,
|
| 4334 |
+
"loss": 0.8903,
|
| 4335 |
+
"step": 618
|
| 4336 |
+
},
|
| 4337 |
+
{
|
| 4338 |
+
"epoch": 3.283819628647215,
|
| 4339 |
+
"grad_norm": 0.4716852903366089,
|
| 4340 |
+
"learning_rate": 8.948269059820025e-06,
|
| 4341 |
+
"loss": 1.2827,
|
| 4342 |
+
"step": 619
|
| 4343 |
+
},
|
| 4344 |
+
{
|
| 4345 |
+
"epoch": 3.2891246684350133,
|
| 4346 |
+
"grad_norm": 0.3898269236087799,
|
| 4347 |
+
"learning_rate": 8.731908778097302e-06,
|
| 4348 |
+
"loss": 0.7921,
|
| 4349 |
+
"step": 620
|
| 4350 |
+
},
|
| 4351 |
+
{
|
| 4352 |
+
"epoch": 3.2944297082228116,
|
| 4353 |
+
"grad_norm": 0.41322410106658936,
|
| 4354 |
+
"learning_rate": 8.518078072704338e-06,
|
| 4355 |
+
"loss": 0.8646,
|
| 4356 |
+
"step": 621
|
| 4357 |
+
},
|
| 4358 |
+
{
|
| 4359 |
+
"epoch": 3.29973474801061,
|
| 4360 |
+
"grad_norm": 0.46135348081588745,
|
| 4361 |
+
"learning_rate": 8.306782805917904e-06,
|
| 4362 |
+
"loss": 1.0674,
|
| 4363 |
+
"step": 622
|
| 4364 |
+
},
|
| 4365 |
+
{
|
| 4366 |
+
"epoch": 3.3050397877984086,
|
| 4367 |
+
"grad_norm": 0.4253339469432831,
|
| 4368 |
+
"learning_rate": 8.098028770504494e-06,
|
| 4369 |
+
"loss": 0.9122,
|
| 4370 |
+
"step": 623
|
| 4371 |
+
},
|
| 4372 |
+
{
|
| 4373 |
+
"epoch": 3.310344827586207,
|
| 4374 |
+
"grad_norm": 0.4982791841030121,
|
| 4375 |
+
"learning_rate": 7.891821689561459e-06,
|
| 4376 |
+
"loss": 1.0727,
|
| 4377 |
+
"step": 624
|
| 4378 |
+
},
|
| 4379 |
+
{
|
| 4380 |
+
"epoch": 3.315649867374005,
|
| 4381 |
+
"grad_norm": 0.44489818811416626,
|
| 4382 |
+
"learning_rate": 7.68816721636004e-06,
|
| 4383 |
+
"loss": 1.0117,
|
| 4384 |
+
"step": 625
|
| 4385 |
+
},
|
| 4386 |
+
{
|
| 4387 |
+
"epoch": 3.320954907161804,
|
| 4388 |
+
"grad_norm": 0.4277961254119873,
|
| 4389 |
+
"learning_rate": 7.487070934190532e-06,
|
| 4390 |
+
"loss": 1.0314,
|
| 4391 |
+
"step": 626
|
| 4392 |
+
},
|
| 4393 |
+
{
|
| 4394 |
+
"epoch": 3.326259946949602,
|
| 4395 |
+
"grad_norm": 0.4564836621284485,
|
| 4396 |
+
"learning_rate": 7.288538356209092e-06,
|
| 4397 |
+
"loss": 1.1363,
|
| 4398 |
+
"step": 627
|
| 4399 |
+
},
|
| 4400 |
+
{
|
| 4401 |
+
"epoch": 3.3315649867374004,
|
| 4402 |
+
"grad_norm": 0.4351053833961487,
|
| 4403 |
+
"learning_rate": 7.092574925286614e-06,
|
| 4404 |
+
"loss": 0.8532,
|
| 4405 |
+
"step": 628
|
| 4406 |
+
},
|
| 4407 |
+
{
|
| 4408 |
+
"epoch": 3.336870026525199,
|
| 4409 |
+
"grad_norm": 0.4466520845890045,
|
| 4410 |
+
"learning_rate": 6.899186013859561e-06,
|
| 4411 |
+
"loss": 1.0749,
|
| 4412 |
+
"step": 629
|
| 4413 |
+
},
|
| 4414 |
+
{
|
| 4415 |
+
"epoch": 3.3421750663129974,
|
| 4416 |
+
"grad_norm": 0.43360409140586853,
|
| 4417 |
+
"learning_rate": 6.708376923782635e-06,
|
| 4418 |
+
"loss": 1.1325,
|
| 4419 |
+
"step": 630
|
| 4420 |
+
},
|
| 4421 |
+
{
|
| 4422 |
+
"epoch": 3.3474801061007957,
|
| 4423 |
+
"grad_norm": 0.42665407061576843,
|
| 4424 |
+
"learning_rate": 6.520152886183406e-06,
|
| 4425 |
+
"loss": 0.9384,
|
| 4426 |
+
"step": 631
|
| 4427 |
+
},
|
| 4428 |
+
{
|
| 4429 |
+
"epoch": 3.352785145888594,
|
| 4430 |
+
"grad_norm": 0.4035145044326782,
|
| 4431 |
+
"learning_rate": 6.3345190613189635e-06,
|
| 4432 |
+
"loss": 0.888,
|
| 4433 |
+
"step": 632
|
| 4434 |
+
},
|
| 4435 |
+
{
|
| 4436 |
+
"epoch": 3.3580901856763927,
|
| 4437 |
+
"grad_norm": 0.42474696040153503,
|
| 4438 |
+
"learning_rate": 6.151480538434382e-06,
|
| 4439 |
+
"loss": 0.9458,
|
| 4440 |
+
"step": 633
|
| 4441 |
+
},
|
| 4442 |
+
{
|
| 4443 |
+
"epoch": 3.363395225464191,
|
| 4444 |
+
"grad_norm": 0.469412624835968,
|
| 4445 |
+
"learning_rate": 5.971042335623229e-06,
|
| 4446 |
+
"loss": 1.089,
|
| 4447 |
+
"step": 634
|
| 4448 |
+
},
|
| 4449 |
+
{
|
| 4450 |
+
"epoch": 3.3687002652519893,
|
| 4451 |
+
"grad_norm": 0.44619429111480713,
|
| 4452 |
+
"learning_rate": 5.793209399689978e-06,
|
| 4453 |
+
"loss": 1.1058,
|
| 4454 |
+
"step": 635
|
| 4455 |
+
},
|
| 4456 |
+
{
|
| 4457 |
+
"epoch": 3.3740053050397876,
|
| 4458 |
+
"grad_norm": 0.4655463695526123,
|
| 4459 |
+
"learning_rate": 5.617986606014419e-06,
|
| 4460 |
+
"loss": 1.0069,
|
| 4461 |
+
"step": 636
|
| 4462 |
+
},
|
| 4463 |
+
{
|
| 4464 |
+
"epoch": 3.3793103448275863,
|
| 4465 |
+
"grad_norm": 0.39096036553382874,
|
| 4466 |
+
"learning_rate": 5.445378758417925e-06,
|
| 4467 |
+
"loss": 0.8229,
|
| 4468 |
+
"step": 637
|
| 4469 |
+
},
|
| 4470 |
+
{
|
| 4471 |
+
"epoch": 3.3846153846153846,
|
| 4472 |
+
"grad_norm": 0.40619954466819763,
|
| 4473 |
+
"learning_rate": 5.275390589031859e-06,
|
| 4474 |
+
"loss": 0.8609,
|
| 4475 |
+
"step": 638
|
| 4476 |
+
},
|
| 4477 |
+
{
|
| 4478 |
+
"epoch": 3.389920424403183,
|
| 4479 |
+
"grad_norm": 0.41593998670578003,
|
| 4480 |
+
"learning_rate": 5.108026758167719e-06,
|
| 4481 |
+
"loss": 1.147,
|
| 4482 |
+
"step": 639
|
| 4483 |
+
},
|
| 4484 |
+
{
|
| 4485 |
+
"epoch": 3.3952254641909816,
|
| 4486 |
+
"grad_norm": 0.42704275250434875,
|
| 4487 |
+
"learning_rate": 4.943291854189493e-06,
|
| 4488 |
+
"loss": 0.9351,
|
| 4489 |
+
"step": 640
|
| 4490 |
+
},
|
| 4491 |
+
{
|
| 4492 |
+
"epoch": 3.40053050397878,
|
| 4493 |
+
"grad_norm": 0.4318499267101288,
|
| 4494 |
+
"learning_rate": 4.781190393387796e-06,
|
| 4495 |
+
"loss": 1.0269,
|
| 4496 |
+
"step": 641
|
| 4497 |
+
},
|
| 4498 |
+
{
|
| 4499 |
+
"epoch": 3.405835543766578,
|
| 4500 |
+
"grad_norm": 0.4125407636165619,
|
| 4501 |
+
"learning_rate": 4.6217268198560404e-06,
|
| 4502 |
+
"loss": 1.0724,
|
| 4503 |
+
"step": 642
|
| 4504 |
+
},
|
| 4505 |
+
{
|
| 4506 |
+
"epoch": 3.411140583554377,
|
| 4507 |
+
"grad_norm": 0.39712077379226685,
|
| 4508 |
+
"learning_rate": 4.464905505368658e-06,
|
| 4509 |
+
"loss": 0.8836,
|
| 4510 |
+
"step": 643
|
| 4511 |
+
},
|
| 4512 |
+
{
|
| 4513 |
+
"epoch": 3.416445623342175,
|
| 4514 |
+
"grad_norm": 0.4181307554244995,
|
| 4515 |
+
"learning_rate": 4.3107307492612086e-06,
|
| 4516 |
+
"loss": 1.0367,
|
| 4517 |
+
"step": 644
|
| 4518 |
+
},
|
| 4519 |
+
{
|
| 4520 |
+
"epoch": 3.4217506631299734,
|
| 4521 |
+
"grad_norm": 0.3876442611217499,
|
| 4522 |
+
"learning_rate": 4.1592067783125015e-06,
|
| 4523 |
+
"loss": 0.9397,
|
| 4524 |
+
"step": 645
|
| 4525 |
+
},
|
| 4526 |
+
{
|
| 4527 |
+
"epoch": 3.4270557029177717,
|
| 4528 |
+
"grad_norm": 0.39695391058921814,
|
| 4529 |
+
"learning_rate": 4.010337746628751e-06,
|
| 4530 |
+
"loss": 0.9293,
|
| 4531 |
+
"step": 646
|
| 4532 |
+
},
|
| 4533 |
+
{
|
| 4534 |
+
"epoch": 3.4323607427055705,
|
| 4535 |
+
"grad_norm": 0.4199883043766022,
|
| 4536 |
+
"learning_rate": 3.864127735529656e-06,
|
| 4537 |
+
"loss": 0.9296,
|
| 4538 |
+
"step": 647
|
| 4539 |
+
},
|
| 4540 |
+
{
|
| 4541 |
+
"epoch": 3.4376657824933687,
|
| 4542 |
+
"grad_norm": 0.3985312581062317,
|
| 4543 |
+
"learning_rate": 3.7205807534365315e-06,
|
| 4544 |
+
"loss": 0.9955,
|
| 4545 |
+
"step": 648
|
| 4546 |
+
},
|
| 4547 |
+
{
|
| 4548 |
+
"epoch": 3.442970822281167,
|
| 4549 |
+
"grad_norm": 0.4070163667201996,
|
| 4550 |
+
"learning_rate": 3.5797007357623945e-06,
|
| 4551 |
+
"loss": 1.1499,
|
| 4552 |
+
"step": 649
|
| 4553 |
+
},
|
| 4554 |
+
{
|
| 4555 |
+
"epoch": 3.4482758620689653,
|
| 4556 |
+
"grad_norm": 0.4120256304740906,
|
| 4557 |
+
"learning_rate": 3.441491544804112e-06,
|
| 4558 |
+
"loss": 1.0506,
|
| 4559 |
+
"step": 650
|
| 4560 |
+
},
|
| 4561 |
+
{
|
| 4562 |
+
"epoch": 3.453580901856764,
|
| 4563 |
+
"grad_norm": 0.4328514337539673,
|
| 4564 |
+
"learning_rate": 3.3059569696364502e-06,
|
| 4565 |
+
"loss": 1.02,
|
| 4566 |
+
"step": 651
|
| 4567 |
+
},
|
| 4568 |
+
{
|
| 4569 |
+
"epoch": 3.4588859416445623,
|
| 4570 |
+
"grad_norm": 0.386901319026947,
|
| 4571 |
+
"learning_rate": 3.1731007260082616e-06,
|
| 4572 |
+
"loss": 0.9069,
|
| 4573 |
+
"step": 652
|
| 4574 |
+
},
|
| 4575 |
+
{
|
| 4576 |
+
"epoch": 3.4641909814323606,
|
| 4577 |
+
"grad_norm": 0.41177234053611755,
|
| 4578 |
+
"learning_rate": 3.0429264562405776e-06,
|
| 4579 |
+
"loss": 0.9475,
|
| 4580 |
+
"step": 653
|
| 4581 |
+
},
|
| 4582 |
+
{
|
| 4583 |
+
"epoch": 3.4694960212201593,
|
| 4584 |
+
"grad_norm": 0.4173250198364258,
|
| 4585 |
+
"learning_rate": 2.9154377291267674e-06,
|
| 4586 |
+
"loss": 1.0873,
|
| 4587 |
+
"step": 654
|
| 4588 |
+
},
|
| 4589 |
+
{
|
| 4590 |
+
"epoch": 3.4748010610079576,
|
| 4591 |
+
"grad_norm": 0.4708622097969055,
|
| 4592 |
+
"learning_rate": 2.790638039834668e-06,
|
| 4593 |
+
"loss": 1.043,
|
| 4594 |
+
"step": 655
|
| 4595 |
+
},
|
| 4596 |
+
{
|
| 4597 |
+
"epoch": 3.480106100795756,
|
| 4598 |
+
"grad_norm": 0.4121977686882019,
|
| 4599 |
+
"learning_rate": 2.6685308098108106e-06,
|
| 4600 |
+
"loss": 0.8853,
|
| 4601 |
+
"step": 656
|
| 4602 |
+
},
|
| 4603 |
+
{
|
| 4604 |
+
"epoch": 3.4854111405835546,
|
| 4605 |
+
"grad_norm": 0.41821739077568054,
|
| 4606 |
+
"learning_rate": 2.5491193866866025e-06,
|
| 4607 |
+
"loss": 1.1232,
|
| 4608 |
+
"step": 657
|
| 4609 |
+
},
|
| 4610 |
+
{
|
| 4611 |
+
"epoch": 3.490716180371353,
|
| 4612 |
+
"grad_norm": 0.6239829659461975,
|
| 4613 |
+
"learning_rate": 2.432407044186509e-06,
|
| 4614 |
+
"loss": 0.9521,
|
| 4615 |
+
"step": 658
|
| 4616 |
+
},
|
| 4617 |
+
{
|
| 4618 |
+
"epoch": 3.496021220159151,
|
| 4619 |
+
"grad_norm": 0.42042478919029236,
|
| 4620 |
+
"learning_rate": 2.3183969820383735e-06,
|
| 4621 |
+
"loss": 1.0479,
|
| 4622 |
+
"step": 659
|
| 4623 |
+
},
|
| 4624 |
+
{
|
| 4625 |
+
"epoch": 3.5013262599469495,
|
| 4626 |
+
"grad_norm": 0.43602442741394043,
|
| 4627 |
+
"learning_rate": 2.2070923258856255e-06,
|
| 4628 |
+
"loss": 1.0141,
|
| 4629 |
+
"step": 660
|
| 4630 |
+
},
|
| 4631 |
+
{
|
| 4632 |
+
"epoch": 3.5066312997347477,
|
| 4633 |
+
"grad_norm": 0.42365264892578125,
|
| 4634 |
+
"learning_rate": 2.098496127201648e-06,
|
| 4635 |
+
"loss": 0.9022,
|
| 4636 |
+
"step": 661
|
| 4637 |
+
},
|
| 4638 |
+
{
|
| 4639 |
+
"epoch": 3.5119363395225465,
|
| 4640 |
+
"grad_norm": 0.4319221079349518,
|
| 4641 |
+
"learning_rate": 1.992611363206103e-06,
|
| 4642 |
+
"loss": 1.1883,
|
| 4643 |
+
"step": 662
|
| 4644 |
+
},
|
| 4645 |
+
{
|
| 4646 |
+
"epoch": 3.5172413793103448,
|
| 4647 |
+
"grad_norm": 0.38604557514190674,
|
| 4648 |
+
"learning_rate": 1.889440936783242e-06,
|
| 4649 |
+
"loss": 0.8162,
|
| 4650 |
+
"step": 663
|
| 4651 |
+
},
|
| 4652 |
+
{
|
| 4653 |
+
"epoch": 3.522546419098143,
|
| 4654 |
+
"grad_norm": 0.4492553770542145,
|
| 4655 |
+
"learning_rate": 1.7889876764024505e-06,
|
| 4656 |
+
"loss": 0.9154,
|
| 4657 |
+
"step": 664
|
| 4658 |
+
},
|
| 4659 |
+
{
|
| 4660 |
+
"epoch": 3.5278514588859418,
|
| 4661 |
+
"grad_norm": 0.48259761929512024,
|
| 4662 |
+
"learning_rate": 1.691254336040595e-06,
|
| 4663 |
+
"loss": 1.1543,
|
| 4664 |
+
"step": 665
|
| 4665 |
+
},
|
| 4666 |
+
{
|
| 4667 |
+
"epoch": 3.53315649867374,
|
| 4668 |
+
"grad_norm": 0.42067569494247437,
|
| 4669 |
+
"learning_rate": 1.59624359510657e-06,
|
| 4670 |
+
"loss": 0.9555,
|
| 4671 |
+
"step": 666
|
| 4672 |
+
},
|
| 4673 |
+
{
|
| 4674 |
+
"epoch": 3.5384615384615383,
|
| 4675 |
+
"grad_norm": 0.4336354434490204,
|
| 4676 |
+
"learning_rate": 1.5039580583678393e-06,
|
| 4677 |
+
"loss": 1.0775,
|
| 4678 |
+
"step": 667
|
| 4679 |
+
},
|
| 4680 |
+
{
|
| 4681 |
+
"epoch": 3.543766578249337,
|
| 4682 |
+
"grad_norm": 0.4591228663921356,
|
| 4683 |
+
"learning_rate": 1.414400255879008e-06,
|
| 4684 |
+
"loss": 0.9744,
|
| 4685 |
+
"step": 668
|
| 4686 |
+
},
|
| 4687 |
+
{
|
| 4688 |
+
"epoch": 3.5490716180371353,
|
| 4689 |
+
"grad_norm": 0.42854616045951843,
|
| 4690 |
+
"learning_rate": 1.327572642912468e-06,
|
| 4691 |
+
"loss": 1.0535,
|
| 4692 |
+
"step": 669
|
| 4693 |
+
},
|
| 4694 |
+
{
|
| 4695 |
+
"epoch": 3.5543766578249336,
|
| 4696 |
+
"grad_norm": 0.42818158864974976,
|
| 4697 |
+
"learning_rate": 1.2434775998910964e-06,
|
| 4698 |
+
"loss": 1.1064,
|
| 4699 |
+
"step": 670
|
| 4700 |
+
},
|
| 4701 |
+
{
|
| 4702 |
+
"epoch": 3.5596816976127323,
|
| 4703 |
+
"grad_norm": 0.4128066897392273,
|
| 4704 |
+
"learning_rate": 1.1621174323229612e-06,
|
| 4705 |
+
"loss": 1.0044,
|
| 4706 |
+
"step": 671
|
| 4707 |
+
},
|
| 4708 |
+
{
|
| 4709 |
+
"epoch": 3.5649867374005306,
|
| 4710 |
+
"grad_norm": 0.445983350276947,
|
| 4711 |
+
"learning_rate": 1.0834943707381784e-06,
|
| 4712 |
+
"loss": 1.0046,
|
| 4713 |
+
"step": 672
|
| 4714 |
+
},
|
| 4715 |
+
{
|
| 4716 |
+
"epoch": 3.570291777188329,
|
| 4717 |
+
"grad_norm": 0.38624265789985657,
|
| 4718 |
+
"learning_rate": 1.0076105706276888e-06,
|
| 4719 |
+
"loss": 0.8713,
|
| 4720 |
+
"step": 673
|
| 4721 |
+
},
|
| 4722 |
+
{
|
| 4723 |
+
"epoch": 3.575596816976127,
|
| 4724 |
+
"grad_norm": 0.4329744279384613,
|
| 4725 |
+
"learning_rate": 9.344681123841967e-07,
|
| 4726 |
+
"loss": 1.1048,
|
| 4727 |
+
"step": 674
|
| 4728 |
+
},
|
| 4729 |
+
{
|
| 4730 |
+
"epoch": 3.5809018567639255,
|
| 4731 |
+
"grad_norm": 0.44485026597976685,
|
| 4732 |
+
"learning_rate": 8.640690012451515e-07,
|
| 4733 |
+
"loss": 0.879,
|
| 4734 |
+
"step": 675
|
| 4735 |
+
},
|
| 4736 |
+
{
|
| 4737 |
+
"epoch": 3.586206896551724,
|
| 4738 |
+
"grad_norm": 0.4935271143913269,
|
| 4739 |
+
"learning_rate": 7.964151672377458e-07,
|
| 4740 |
+
"loss": 0.9697,
|
| 4741 |
+
"step": 676
|
| 4742 |
+
},
|
| 4743 |
+
{
|
| 4744 |
+
"epoch": 3.5915119363395225,
|
| 4745 |
+
"grad_norm": 0.4287927746772766,
|
| 4746 |
+
"learning_rate": 7.315084651260009e-07,
|
| 4747 |
+
"loss": 0.8972,
|
| 4748 |
+
"step": 677
|
| 4749 |
+
},
|
| 4750 |
+
{
|
| 4751 |
+
"epoch": 3.5968169761273208,
|
| 4752 |
+
"grad_norm": 0.3863944411277771,
|
| 4753 |
+
"learning_rate": 6.69350674359959e-07,
|
| 4754 |
+
"loss": 0.8455,
|
| 4755 |
+
"step": 678
|
| 4756 |
+
},
|
| 4757 |
+
{
|
| 4758 |
+
"epoch": 3.6021220159151195,
|
| 4759 |
+
"grad_norm": 0.4372875988483429,
|
| 4760 |
+
"learning_rate": 6.099434990268609e-07,
|
| 4761 |
+
"loss": 1.0293,
|
| 4762 |
+
"step": 679
|
| 4763 |
+
},
|
| 4764 |
+
{
|
| 4765 |
+
"epoch": 3.6074270557029178,
|
| 4766 |
+
"grad_norm": 0.44932833313941956,
|
| 4767 |
+
"learning_rate": 5.532885678043977e-07,
|
| 4768 |
+
"loss": 1.0488,
|
| 4769 |
+
"step": 680
|
| 4770 |
+
},
|
| 4771 |
+
{
|
| 4772 |
+
"epoch": 3.612732095490716,
|
| 4773 |
+
"grad_norm": 0.440734326839447,
|
| 4774 |
+
"learning_rate": 4.9938743391615e-07,
|
| 4775 |
+
"loss": 1.1057,
|
| 4776 |
+
"step": 681
|
| 4777 |
+
},
|
| 4778 |
+
{
|
| 4779 |
+
"epoch": 3.618037135278515,
|
| 4780 |
+
"grad_norm": 0.4488030672073364,
|
| 4781 |
+
"learning_rate": 4.482415750889204e-07,
|
| 4782 |
+
"loss": 0.8689,
|
| 4783 |
+
"step": 682
|
| 4784 |
+
},
|
| 4785 |
+
{
|
| 4786 |
+
"epoch": 3.623342175066313,
|
| 4787 |
+
"grad_norm": 0.4091316759586334,
|
| 4788 |
+
"learning_rate": 3.998523935122772e-07,
|
| 4789 |
+
"loss": 0.8172,
|
| 4790 |
+
"step": 683
|
| 4791 |
+
},
|
| 4792 |
+
{
|
| 4793 |
+
"epoch": 3.6286472148541113,
|
| 4794 |
+
"grad_norm": 0.44093477725982666,
|
| 4795 |
+
"learning_rate": 3.5422121580005864e-07,
|
| 4796 |
+
"loss": 1.0464,
|
| 4797 |
+
"step": 684
|
| 4798 |
+
},
|
| 4799 |
+
{
|
| 4800 |
+
"epoch": 3.63395225464191,
|
| 4801 |
+
"grad_norm": 0.4517577886581421,
|
| 4802 |
+
"learning_rate": 3.1134929295407564e-07,
|
| 4803 |
+
"loss": 1.3728,
|
| 4804 |
+
"step": 685
|
| 4805 |
+
},
|
| 4806 |
+
{
|
| 4807 |
+
"epoch": 3.6392572944297084,
|
| 4808 |
+
"grad_norm": 0.4129403531551361,
|
| 4809 |
+
"learning_rate": 2.7123780032973235e-07,
|
| 4810 |
+
"loss": 0.8975,
|
| 4811 |
+
"step": 686
|
| 4812 |
+
},
|
| 4813 |
+
{
|
| 4814 |
+
"epoch": 3.6445623342175066,
|
| 4815 |
+
"grad_norm": 0.44569700956344604,
|
| 4816 |
+
"learning_rate": 2.3388783760386601e-07,
|
| 4817 |
+
"loss": 1.0423,
|
| 4818 |
+
"step": 687
|
| 4819 |
+
},
|
| 4820 |
+
{
|
| 4821 |
+
"epoch": 3.649867374005305,
|
| 4822 |
+
"grad_norm": 0.388634592294693,
|
| 4823 |
+
"learning_rate": 1.9930042874457254e-07,
|
| 4824 |
+
"loss": 0.8275,
|
| 4825 |
+
"step": 688
|
| 4826 |
+
},
|
| 4827 |
+
{
|
| 4828 |
+
"epoch": 3.655172413793103,
|
| 4829 |
+
"grad_norm": 0.4346824586391449,
|
| 4830 |
+
"learning_rate": 1.6747652198313957e-07,
|
| 4831 |
+
"loss": 1.106,
|
| 4832 |
+
"step": 689
|
| 4833 |
+
},
|
| 4834 |
+
{
|
| 4835 |
+
"epoch": 3.660477453580902,
|
| 4836 |
+
"grad_norm": 0.4045989215373993,
|
| 4837 |
+
"learning_rate": 1.3841698978804285e-07,
|
| 4838 |
+
"loss": 0.7959,
|
| 4839 |
+
"step": 690
|
| 4840 |
+
},
|
| 4841 |
+
{
|
| 4842 |
+
"epoch": 3.6657824933687,
|
| 4843 |
+
"grad_norm": 0.4275589883327484,
|
| 4844 |
+
"learning_rate": 1.1212262884103974e-07,
|
| 4845 |
+
"loss": 1.1,
|
| 4846 |
+
"step": 691
|
| 4847 |
+
},
|
| 4848 |
+
{
|
| 4849 |
+
"epoch": 3.6710875331564985,
|
| 4850 |
+
"grad_norm": 0.4341103136539459,
|
| 4851 |
+
"learning_rate": 8.85941600153033e-08,
|
| 4852 |
+
"loss": 1.0429,
|
| 4853 |
+
"step": 692
|
| 4854 |
+
},
|
| 4855 |
+
{
|
| 4856 |
+
"epoch": 3.676392572944297,
|
| 4857 |
+
"grad_norm": 0.3971407413482666,
|
| 4858 |
+
"learning_rate": 6.783222835572055e-08,
|
| 4859 |
+
"loss": 0.8308,
|
| 4860 |
+
"step": 693
|
| 4861 |
+
},
|
| 4862 |
+
{
|
| 4863 |
+
"epoch": 3.6816976127320955,
|
| 4864 |
+
"grad_norm": 0.4377444386482239,
|
| 4865 |
+
"learning_rate": 4.98374030611084e-08,
|
| 4866 |
+
"loss": 1.0022,
|
| 4867 |
+
"step": 694
|
| 4868 |
+
},
|
| 4869 |
+
{
|
| 4870 |
+
"epoch": 3.687002652519894,
|
| 4871 |
+
"grad_norm": 0.39874109625816345,
|
| 4872 |
+
"learning_rate": 3.461017746871675e-08,
|
| 4873 |
+
"loss": 0.9231,
|
| 4874 |
+
"step": 695
|
| 4875 |
+
},
|
| 4876 |
+
{
|
| 4877 |
+
"epoch": 3.6923076923076925,
|
| 4878 |
+
"grad_norm": 0.40262848138809204,
|
| 4879 |
+
"learning_rate": 2.215096904060454e-08,
|
| 4880 |
+
"loss": 0.9854,
|
| 4881 |
+
"step": 696
|
| 4882 |
+
},
|
| 4883 |
+
{
|
| 4884 |
+
"epoch": 3.697612732095491,
|
| 4885 |
+
"grad_norm": 0.3901890218257904,
|
| 4886 |
+
"learning_rate": 1.246011935228064e-08,
|
| 4887 |
+
"loss": 0.9308,
|
| 4888 |
+
"step": 697
|
| 4889 |
+
},
|
| 4890 |
+
{
|
| 4891 |
+
"epoch": 3.702917771883289,
|
| 4892 |
+
"grad_norm": 0.3963816165924072,
|
| 4893 |
+
"learning_rate": 5.537894083273543e-09,
|
| 4894 |
+
"loss": 1.0706,
|
| 4895 |
+
"step": 698
|
| 4896 |
+
},
|
| 4897 |
+
{
|
| 4898 |
+
"epoch": 3.708222811671088,
|
| 4899 |
+
"grad_norm": 0.4288328289985657,
|
| 4900 |
+
"learning_rate": 1.384483009898796e-09,
|
| 4901 |
+
"loss": 0.975,
|
| 4902 |
+
"step": 699
|
| 4903 |
+
},
|
| 4904 |
+
{
|
| 4905 |
+
"epoch": 3.713527851458886,
|
| 4906 |
+
"grad_norm": 0.42579135298728943,
|
| 4907 |
+
"learning_rate": 0.0,
|
| 4908 |
+
"loss": 1.0967,
|
| 4909 |
+
"step": 700
|
| 4910 |
}
|
| 4911 |
],
|
| 4912 |
"logging_steps": 1,
|
|
|
|
| 4921 |
"should_evaluate": false,
|
| 4922 |
"should_log": false,
|
| 4923 |
"should_save": true,
|
| 4924 |
+
"should_training_stop": true
|
| 4925 |
},
|
| 4926 |
"attributes": {}
|
| 4927 |
}
|
| 4928 |
},
|
| 4929 |
+
"total_flos": 1.4097816028708864e+17,
|
| 4930 |
"train_batch_size": 4,
|
| 4931 |
"trial_name": null,
|
| 4932 |
"trial_params": null
|