Training in progress, step 300, checkpoint
Browse files- last-checkpoint/optimizer_0/.metadata +0 -0
- last-checkpoint/optimizer_0/__0_0.distcp +1 -1
- last-checkpoint/optimizer_0/__1_0.distcp +1 -1
- last-checkpoint/optimizer_0/__2_0.distcp +1 -1
- last-checkpoint/optimizer_0/__3_0.distcp +1 -1
- last-checkpoint/pytorch_model_fsdp_0/.metadata +0 -0
- last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp +1 -1
- last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp +1 -1
- last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp +1 -1
- last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +763 -3
last-checkpoint/optimizer_0/.metadata
CHANGED
|
Binary files a/last-checkpoint/optimizer_0/.metadata and b/last-checkpoint/optimizer_0/.metadata differ
|
|
|
last-checkpoint/optimizer_0/__0_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13934748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcabfd92be31b6499987f272f2e66282673bbf0f3477e3b95d3ea40fdce5a631
|
| 3 |
size 13934748
|
last-checkpoint/optimizer_0/__1_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13999412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45cb6bcfdabd08869c69097cfa5bee5aef04ef8c28f157d1f489ca78f5fe777b
|
| 3 |
size 13999412
|
last-checkpoint/optimizer_0/__2_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13990904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:596eeeb9c5038b414042e03c790c4d8a3ba4d45df7e2d23dd912b3398d87b3c1
|
| 3 |
size 13990904
|
last-checkpoint/optimizer_0/__3_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13990904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1034c58512d1793e1275c069dc6457aa4efaaf3eead8bde0452447a4e033790a
|
| 3 |
size 13990904
|
last-checkpoint/pytorch_model_fsdp_0/.metadata
CHANGED
|
Binary files a/last-checkpoint/pytorch_model_fsdp_0/.metadata and b/last-checkpoint/pytorch_model_fsdp_0/.metadata differ
|
|
|
last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6966784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4790eab0dde508fbf6099ce52ddbe518d5cf97627bbdf3949e06dde5e08e25fd
|
| 3 |
size 6966784
|
last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6966784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29186fb25040ec4572ae0b84469b79877a09d72bc3dfd7003bd296fc03a5510c
|
| 3 |
size 6966784
|
last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6966784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bd437dc3c0c22d9c434de5ec29821436fc23d3c711bd99c0f72ce1ee249cbd7
|
| 3 |
size 6966784
|
last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6966784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c1fbfb8b80209395e13448bf1015ddfce9474a48c7701f6ac933493628333aa
|
| 3 |
size 6966784
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0f8832d1e0a99012ddffa0912becb483c91f8a60016c8ffce71b49b64e355b
|
| 3 |
size 14960
|
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:f19c1c760c44b1d56e40c2b6486967adae47f40de9c950993205f9a2e7e66c38
|
| 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": 0.
|
| 5 |
"eval_steps": 20,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1539,6 +1539,766 @@
|
|
| 1539 |
"eval_samples_per_second": 6.626,
|
| 1540 |
"eval_steps_per_second": 0.207,
|
| 1541 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1542 |
}
|
| 1543 |
],
|
| 1544 |
"logging_steps": 1,
|
|
@@ -1558,7 +2318,7 @@
|
|
| 1558 |
"attributes": {}
|
| 1559 |
}
|
| 1560 |
},
|
| 1561 |
-
"total_flos":
|
| 1562 |
"train_batch_size": 8,
|
| 1563 |
"trial_name": null,
|
| 1564 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7978723404255319,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1539 |
"eval_samples_per_second": 6.626,
|
| 1540 |
"eval_steps_per_second": 0.207,
|
| 1541 |
"step": 200
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.5345744680851063,
|
| 1545 |
+
"grad_norm": 6.333003044128418,
|
| 1546 |
+
"learning_rate": 1.0557390144892684e-05,
|
| 1547 |
+
"loss": 0.3334,
|
| 1548 |
+
"step": 201
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.5372340425531915,
|
| 1552 |
+
"grad_norm": 2.1432178020477295,
|
| 1553 |
+
"learning_rate": 1.0464565373634784e-05,
|
| 1554 |
+
"loss": 0.2513,
|
| 1555 |
+
"step": 202
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.5398936170212766,
|
| 1559 |
+
"grad_norm": 5.119022369384766,
|
| 1560 |
+
"learning_rate": 1.0371700468597886e-05,
|
| 1561 |
+
"loss": 0.2566,
|
| 1562 |
+
"step": 203
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.5425531914893617,
|
| 1566 |
+
"grad_norm": 3.5691733360290527,
|
| 1567 |
+
"learning_rate": 1.0278803452376416e-05,
|
| 1568 |
+
"loss": 0.3084,
|
| 1569 |
+
"step": 204
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.5452127659574468,
|
| 1573 |
+
"grad_norm": 3.0961036682128906,
|
| 1574 |
+
"learning_rate": 1.018588235033888e-05,
|
| 1575 |
+
"loss": 0.2085,
|
| 1576 |
+
"step": 205
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 0.5478723404255319,
|
| 1580 |
+
"grad_norm": 2.27486515045166,
|
| 1581 |
+
"learning_rate": 1.0092945189934558e-05,
|
| 1582 |
+
"loss": 0.2524,
|
| 1583 |
+
"step": 206
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.550531914893617,
|
| 1587 |
+
"grad_norm": 2.3716437816619873,
|
| 1588 |
+
"learning_rate": 1e-05,
|
| 1589 |
+
"loss": 0.2011,
|
| 1590 |
+
"step": 207
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 0.5531914893617021,
|
| 1594 |
+
"grad_norm": 2.6007697582244873,
|
| 1595 |
+
"learning_rate": 9.907054810065446e-06,
|
| 1596 |
+
"loss": 0.2451,
|
| 1597 |
+
"step": 208
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.5558510638297872,
|
| 1601 |
+
"grad_norm": 2.5963995456695557,
|
| 1602 |
+
"learning_rate": 9.81411764966112e-06,
|
| 1603 |
+
"loss": 0.2705,
|
| 1604 |
+
"step": 209
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 0.5585106382978723,
|
| 1608 |
+
"grad_norm": 2.1203646659851074,
|
| 1609 |
+
"learning_rate": 9.721196547623585e-06,
|
| 1610 |
+
"loss": 0.2101,
|
| 1611 |
+
"step": 210
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.5611702127659575,
|
| 1615 |
+
"grad_norm": 3.2986724376678467,
|
| 1616 |
+
"learning_rate": 9.628299531402118e-06,
|
| 1617 |
+
"loss": 0.2659,
|
| 1618 |
+
"step": 211
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 0.5638297872340425,
|
| 1622 |
+
"grad_norm": 2.127525568008423,
|
| 1623 |
+
"learning_rate": 9.535434626365221e-06,
|
| 1624 |
+
"loss": 0.251,
|
| 1625 |
+
"step": 212
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.5664893617021277,
|
| 1629 |
+
"grad_norm": 3.1327059268951416,
|
| 1630 |
+
"learning_rate": 9.442609855107317e-06,
|
| 1631 |
+
"loss": 0.2255,
|
| 1632 |
+
"step": 213
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 0.5691489361702128,
|
| 1636 |
+
"grad_norm": 2.0999770164489746,
|
| 1637 |
+
"learning_rate": 9.349833236755675e-06,
|
| 1638 |
+
"loss": 0.2549,
|
| 1639 |
+
"step": 214
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.5718085106382979,
|
| 1643 |
+
"grad_norm": 2.7766880989074707,
|
| 1644 |
+
"learning_rate": 9.257112786277631e-06,
|
| 1645 |
+
"loss": 0.2224,
|
| 1646 |
+
"step": 215
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 0.574468085106383,
|
| 1650 |
+
"grad_norm": 2.451842784881592,
|
| 1651 |
+
"learning_rate": 9.164456513788186e-06,
|
| 1652 |
+
"loss": 0.2599,
|
| 1653 |
+
"step": 216
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.5771276595744681,
|
| 1657 |
+
"grad_norm": 2.7746975421905518,
|
| 1658 |
+
"learning_rate": 9.07187242385801e-06,
|
| 1659 |
+
"loss": 0.2601,
|
| 1660 |
+
"step": 217
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 0.5797872340425532,
|
| 1664 |
+
"grad_norm": 2.561441421508789,
|
| 1665 |
+
"learning_rate": 8.979368514821917e-06,
|
| 1666 |
+
"loss": 0.284,
|
| 1667 |
+
"step": 218
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.5824468085106383,
|
| 1671 |
+
"grad_norm": 2.425262928009033,
|
| 1672 |
+
"learning_rate": 8.88695277808791e-06,
|
| 1673 |
+
"loss": 0.2593,
|
| 1674 |
+
"step": 219
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.5851063829787234,
|
| 1678 |
+
"grad_norm": 3.180457830429077,
|
| 1679 |
+
"learning_rate": 8.79463319744677e-06,
|
| 1680 |
+
"loss": 0.2844,
|
| 1681 |
+
"step": 220
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.5851063829787234,
|
| 1685 |
+
"eval_accuracy": 0.8258823529411765,
|
| 1686 |
+
"eval_f1": 0.5163398692810458,
|
| 1687 |
+
"eval_loss": 0.41871950030326843,
|
| 1688 |
+
"eval_precision": 0.7523809523809524,
|
| 1689 |
+
"eval_recall": 0.39303482587064675,
|
| 1690 |
+
"eval_runtime": 34.0471,
|
| 1691 |
+
"eval_samples_per_second": 6.579,
|
| 1692 |
+
"eval_steps_per_second": 0.206,
|
| 1693 |
+
"step": 220
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.5877659574468085,
|
| 1697 |
+
"grad_norm": 2.8783645629882812,
|
| 1698 |
+
"learning_rate": 8.702417748382384e-06,
|
| 1699 |
+
"loss": 0.2458,
|
| 1700 |
+
"step": 221
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.5904255319148937,
|
| 1704 |
+
"grad_norm": 2.950291395187378,
|
| 1705 |
+
"learning_rate": 8.610314397382701e-06,
|
| 1706 |
+
"loss": 0.3062,
|
| 1707 |
+
"step": 222
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.5930851063829787,
|
| 1711 |
+
"grad_norm": 2.8430628776550293,
|
| 1712 |
+
"learning_rate": 8.51833110125153e-06,
|
| 1713 |
+
"loss": 0.2913,
|
| 1714 |
+
"step": 223
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.5957446808510638,
|
| 1718 |
+
"grad_norm": 6.691501617431641,
|
| 1719 |
+
"learning_rate": 8.426475806421139e-06,
|
| 1720 |
+
"loss": 0.3716,
|
| 1721 |
+
"step": 224
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.598404255319149,
|
| 1725 |
+
"grad_norm": 2.705397367477417,
|
| 1726 |
+
"learning_rate": 8.334756448265782e-06,
|
| 1727 |
+
"loss": 0.2692,
|
| 1728 |
+
"step": 225
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.601063829787234,
|
| 1732 |
+
"grad_norm": 2.276686429977417,
|
| 1733 |
+
"learning_rate": 8.243180950416142e-06,
|
| 1734 |
+
"loss": 0.214,
|
| 1735 |
+
"step": 226
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.6037234042553191,
|
| 1739 |
+
"grad_norm": 4.622035980224609,
|
| 1740 |
+
"learning_rate": 8.151757224074815e-06,
|
| 1741 |
+
"loss": 0.1863,
|
| 1742 |
+
"step": 227
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.6063829787234043,
|
| 1746 |
+
"grad_norm": 2.3402657508850098,
|
| 1747 |
+
"learning_rate": 8.060493167332874e-06,
|
| 1748 |
+
"loss": 0.2895,
|
| 1749 |
+
"step": 228
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.6090425531914894,
|
| 1753 |
+
"grad_norm": 4.533783912658691,
|
| 1754 |
+
"learning_rate": 7.969396664487534e-06,
|
| 1755 |
+
"loss": 0.256,
|
| 1756 |
+
"step": 229
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.6117021276595744,
|
| 1760 |
+
"grad_norm": 4.254709243774414,
|
| 1761 |
+
"learning_rate": 7.878475585361045e-06,
|
| 1762 |
+
"loss": 0.2798,
|
| 1763 |
+
"step": 230
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.6143617021276596,
|
| 1767 |
+
"grad_norm": 2.4173777103424072,
|
| 1768 |
+
"learning_rate": 7.787737784620803e-06,
|
| 1769 |
+
"loss": 0.3046,
|
| 1770 |
+
"step": 231
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.6170212765957447,
|
| 1774 |
+
"grad_norm": 2.9640042781829834,
|
| 1775 |
+
"learning_rate": 7.697191101100802e-06,
|
| 1776 |
+
"loss": 0.2893,
|
| 1777 |
+
"step": 232
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.6196808510638298,
|
| 1781 |
+
"grad_norm": 2.9573986530303955,
|
| 1782 |
+
"learning_rate": 7.606843357124426e-06,
|
| 1783 |
+
"loss": 0.2764,
|
| 1784 |
+
"step": 233
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.6223404255319149,
|
| 1788 |
+
"grad_norm": 3.9960691928863525,
|
| 1789 |
+
"learning_rate": 7.516702357828672e-06,
|
| 1790 |
+
"loss": 0.3243,
|
| 1791 |
+
"step": 234
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.625,
|
| 1795 |
+
"grad_norm": 2.9117209911346436,
|
| 1796 |
+
"learning_rate": 7.42677589048989e-06,
|
| 1797 |
+
"loss": 0.2863,
|
| 1798 |
+
"step": 235
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 0.6276595744680851,
|
| 1802 |
+
"grad_norm": 2.57856822013855,
|
| 1803 |
+
"learning_rate": 7.337071723851018e-06,
|
| 1804 |
+
"loss": 0.2433,
|
| 1805 |
+
"step": 236
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 0.6303191489361702,
|
| 1809 |
+
"grad_norm": 3.1635406017303467,
|
| 1810 |
+
"learning_rate": 7.247597607450446e-06,
|
| 1811 |
+
"loss": 0.2622,
|
| 1812 |
+
"step": 237
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 0.6329787234042553,
|
| 1816 |
+
"grad_norm": 3.4039433002471924,
|
| 1817 |
+
"learning_rate": 7.1583612709525405e-06,
|
| 1818 |
+
"loss": 0.2313,
|
| 1819 |
+
"step": 238
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.6356382978723404,
|
| 1823 |
+
"grad_norm": 3.072800397872925,
|
| 1824 |
+
"learning_rate": 7.06937042347987e-06,
|
| 1825 |
+
"loss": 0.3117,
|
| 1826 |
+
"step": 239
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.6382978723404256,
|
| 1830 |
+
"grad_norm": 3.175246000289917,
|
| 1831 |
+
"learning_rate": 6.980632752947221e-06,
|
| 1832 |
+
"loss": 0.2632,
|
| 1833 |
+
"step": 240
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.6382978723404256,
|
| 1837 |
+
"eval_accuracy": 0.8235294117647058,
|
| 1838 |
+
"eval_f1": 0.5161290322580645,
|
| 1839 |
+
"eval_loss": 0.4037013053894043,
|
| 1840 |
+
"eval_precision": 0.7339449541284404,
|
| 1841 |
+
"eval_recall": 0.39800995024875624,
|
| 1842 |
+
"eval_runtime": 34.0215,
|
| 1843 |
+
"eval_samples_per_second": 6.584,
|
| 1844 |
+
"eval_steps_per_second": 0.206,
|
| 1845 |
+
"step": 240
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.6409574468085106,
|
| 1849 |
+
"grad_norm": 2.5714304447174072,
|
| 1850 |
+
"learning_rate": 6.892155925397437e-06,
|
| 1851 |
+
"loss": 0.2749,
|
| 1852 |
+
"step": 241
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 0.6436170212765957,
|
| 1856 |
+
"grad_norm": 3.128525733947754,
|
| 1857 |
+
"learning_rate": 6.803947584339148e-06,
|
| 1858 |
+
"loss": 0.3527,
|
| 1859 |
+
"step": 242
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 0.6462765957446809,
|
| 1863 |
+
"grad_norm": 3.6604840755462646,
|
| 1864 |
+
"learning_rate": 6.716015350086449e-06,
|
| 1865 |
+
"loss": 0.2686,
|
| 1866 |
+
"step": 243
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.648936170212766,
|
| 1870 |
+
"grad_norm": 2.6133296489715576,
|
| 1871 |
+
"learning_rate": 6.628366819100586e-06,
|
| 1872 |
+
"loss": 0.2836,
|
| 1873 |
+
"step": 244
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.651595744680851,
|
| 1877 |
+
"grad_norm": 2.5161774158477783,
|
| 1878 |
+
"learning_rate": 6.54100956333369e-06,
|
| 1879 |
+
"loss": 0.2395,
|
| 1880 |
+
"step": 245
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.6542553191489362,
|
| 1884 |
+
"grad_norm": 2.824259042739868,
|
| 1885 |
+
"learning_rate": 6.453951129574644e-06,
|
| 1886 |
+
"loss": 0.2906,
|
| 1887 |
+
"step": 246
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.6569148936170213,
|
| 1891 |
+
"grad_norm": 2.747422456741333,
|
| 1892 |
+
"learning_rate": 6.3671990387971096e-06,
|
| 1893 |
+
"loss": 0.2368,
|
| 1894 |
+
"step": 247
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 0.6595744680851063,
|
| 1898 |
+
"grad_norm": 2.540599822998047,
|
| 1899 |
+
"learning_rate": 6.280760785509802e-06,
|
| 1900 |
+
"loss": 0.3036,
|
| 1901 |
+
"step": 248
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.6622340425531915,
|
| 1905 |
+
"grad_norm": 2.4649527072906494,
|
| 1906 |
+
"learning_rate": 6.194643837109015e-06,
|
| 1907 |
+
"loss": 0.2935,
|
| 1908 |
+
"step": 249
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.6648936170212766,
|
| 1912 |
+
"grad_norm": 2.2564632892608643,
|
| 1913 |
+
"learning_rate": 6.108855633233546e-06,
|
| 1914 |
+
"loss": 0.2276,
|
| 1915 |
+
"step": 250
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.6675531914893617,
|
| 1919 |
+
"grad_norm": 2.5052363872528076,
|
| 1920 |
+
"learning_rate": 6.0234035851219604e-06,
|
| 1921 |
+
"loss": 0.2464,
|
| 1922 |
+
"step": 251
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.6702127659574468,
|
| 1926 |
+
"grad_norm": 3.091642141342163,
|
| 1927 |
+
"learning_rate": 5.93829507497235e-06,
|
| 1928 |
+
"loss": 0.2766,
|
| 1929 |
+
"step": 252
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.6728723404255319,
|
| 1933 |
+
"grad_norm": 3.3672595024108887,
|
| 1934 |
+
"learning_rate": 5.853537455304575e-06,
|
| 1935 |
+
"loss": 0.2567,
|
| 1936 |
+
"step": 253
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.675531914893617,
|
| 1940 |
+
"grad_norm": 2.4779727458953857,
|
| 1941 |
+
"learning_rate": 5.769138048325087e-06,
|
| 1942 |
+
"loss": 0.2628,
|
| 1943 |
+
"step": 254
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 0.6781914893617021,
|
| 1947 |
+
"grad_norm": 2.5639469623565674,
|
| 1948 |
+
"learning_rate": 5.685104145294364e-06,
|
| 1949 |
+
"loss": 0.2204,
|
| 1950 |
+
"step": 255
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 0.6808510638297872,
|
| 1954 |
+
"grad_norm": 3.3351776599884033,
|
| 1955 |
+
"learning_rate": 5.601443005897012e-06,
|
| 1956 |
+
"loss": 0.2535,
|
| 1957 |
+
"step": 256
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 0.6835106382978723,
|
| 1961 |
+
"grad_norm": 2.3642754554748535,
|
| 1962 |
+
"learning_rate": 5.5181618576146e-06,
|
| 1963 |
+
"loss": 0.2234,
|
| 1964 |
+
"step": 257
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.6861702127659575,
|
| 1968 |
+
"grad_norm": 2.9997129440307617,
|
| 1969 |
+
"learning_rate": 5.435267895101303e-06,
|
| 1970 |
+
"loss": 0.2643,
|
| 1971 |
+
"step": 258
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.6888297872340425,
|
| 1975 |
+
"grad_norm": 2.4532787799835205,
|
| 1976 |
+
"learning_rate": 5.352768279562315e-06,
|
| 1977 |
+
"loss": 0.2621,
|
| 1978 |
+
"step": 259
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.6914893617021277,
|
| 1982 |
+
"grad_norm": 2.572538137435913,
|
| 1983 |
+
"learning_rate": 5.270670138135234e-06,
|
| 1984 |
+
"loss": 0.2499,
|
| 1985 |
+
"step": 260
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 0.6914893617021277,
|
| 1989 |
+
"eval_accuracy": 0.8247058823529412,
|
| 1990 |
+
"eval_f1": 0.5299684542586751,
|
| 1991 |
+
"eval_loss": 0.3885125517845154,
|
| 1992 |
+
"eval_precision": 0.7241379310344828,
|
| 1993 |
+
"eval_recall": 0.417910447761194,
|
| 1994 |
+
"eval_runtime": 33.8843,
|
| 1995 |
+
"eval_samples_per_second": 6.611,
|
| 1996 |
+
"eval_steps_per_second": 0.207,
|
| 1997 |
+
"step": 260
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.6941489361702128,
|
| 2001 |
+
"grad_norm": 2.906144618988037,
|
| 2002 |
+
"learning_rate": 5.188980563274315e-06,
|
| 2003 |
+
"loss": 0.3095,
|
| 2004 |
+
"step": 261
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.6968085106382979,
|
| 2008 |
+
"grad_norm": 2.319133996963501,
|
| 2009 |
+
"learning_rate": 5.107706612137776e-06,
|
| 2010 |
+
"loss": 0.2388,
|
| 2011 |
+
"step": 262
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.699468085106383,
|
| 2015 |
+
"grad_norm": 3.162642478942871,
|
| 2016 |
+
"learning_rate": 5.026855305978129e-06,
|
| 2017 |
+
"loss": 0.2462,
|
| 2018 |
+
"step": 263
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.7021276595744681,
|
| 2022 |
+
"grad_norm": 2.749540090560913,
|
| 2023 |
+
"learning_rate": 4.946433629535585e-06,
|
| 2024 |
+
"loss": 0.2659,
|
| 2025 |
+
"step": 264
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.7047872340425532,
|
| 2029 |
+
"grad_norm": 2.891836643218994,
|
| 2030 |
+
"learning_rate": 4.866448530434692e-06,
|
| 2031 |
+
"loss": 0.2332,
|
| 2032 |
+
"step": 265
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.7074468085106383,
|
| 2036 |
+
"grad_norm": 2.4717514514923096,
|
| 2037 |
+
"learning_rate": 4.786906918584083e-06,
|
| 2038 |
+
"loss": 0.2136,
|
| 2039 |
+
"step": 266
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.7101063829787234,
|
| 2043 |
+
"grad_norm": 2.679591655731201,
|
| 2044 |
+
"learning_rate": 4.707815665579569e-06,
|
| 2045 |
+
"loss": 0.3036,
|
| 2046 |
+
"step": 267
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.7127659574468085,
|
| 2050 |
+
"grad_norm": 2.3344614505767822,
|
| 2051 |
+
"learning_rate": 4.629181604110464e-06,
|
| 2052 |
+
"loss": 0.2853,
|
| 2053 |
+
"step": 268
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.7154255319148937,
|
| 2057 |
+
"grad_norm": 2.839320182800293,
|
| 2058 |
+
"learning_rate": 4.551011527369348e-06,
|
| 2059 |
+
"loss": 0.2394,
|
| 2060 |
+
"step": 269
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.7180851063829787,
|
| 2064 |
+
"grad_norm": 2.27245831489563,
|
| 2065 |
+
"learning_rate": 4.4733121884651665e-06,
|
| 2066 |
+
"loss": 0.2496,
|
| 2067 |
+
"step": 270
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.7207446808510638,
|
| 2071 |
+
"grad_norm": 3.038536548614502,
|
| 2072 |
+
"learning_rate": 4.3960902998398524e-06,
|
| 2073 |
+
"loss": 0.2787,
|
| 2074 |
+
"step": 271
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.723404255319149,
|
| 2078 |
+
"grad_norm": 3.1204025745391846,
|
| 2079 |
+
"learning_rate": 4.319352532688444e-06,
|
| 2080 |
+
"loss": 0.2678,
|
| 2081 |
+
"step": 272
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.726063829787234,
|
| 2085 |
+
"grad_norm": 3.8436288833618164,
|
| 2086 |
+
"learning_rate": 4.243105516382732e-06,
|
| 2087 |
+
"loss": 0.2405,
|
| 2088 |
+
"step": 273
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.7287234042553191,
|
| 2092 |
+
"grad_norm": 3.1559836864471436,
|
| 2093 |
+
"learning_rate": 4.167355837898585e-06,
|
| 2094 |
+
"loss": 0.2881,
|
| 2095 |
+
"step": 274
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.7313829787234043,
|
| 2099 |
+
"grad_norm": 2.5084681510925293,
|
| 2100 |
+
"learning_rate": 4.092110041246865e-06,
|
| 2101 |
+
"loss": 0.2365,
|
| 2102 |
+
"step": 275
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.7340425531914894,
|
| 2106 |
+
"grad_norm": 3.0584487915039062,
|
| 2107 |
+
"learning_rate": 4.017374626908125e-06,
|
| 2108 |
+
"loss": 0.2808,
|
| 2109 |
+
"step": 276
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.7367021276595744,
|
| 2113 |
+
"grad_norm": 3.6234519481658936,
|
| 2114 |
+
"learning_rate": 3.943156051271003e-06,
|
| 2115 |
+
"loss": 0.2993,
|
| 2116 |
+
"step": 277
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.7393617021276596,
|
| 2120 |
+
"grad_norm": 1.8584307432174683,
|
| 2121 |
+
"learning_rate": 3.8694607260744745e-06,
|
| 2122 |
+
"loss": 0.2012,
|
| 2123 |
+
"step": 278
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.7420212765957447,
|
| 2127 |
+
"grad_norm": 2.4248085021972656,
|
| 2128 |
+
"learning_rate": 3.7962950178539282e-06,
|
| 2129 |
+
"loss": 0.2352,
|
| 2130 |
+
"step": 279
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.7446808510638298,
|
| 2134 |
+
"grad_norm": 2.5359675884246826,
|
| 2135 |
+
"learning_rate": 3.7236652473911817e-06,
|
| 2136 |
+
"loss": 0.2121,
|
| 2137 |
+
"step": 280
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.7446808510638298,
|
| 2141 |
+
"eval_accuracy": 0.8223529411764706,
|
| 2142 |
+
"eval_f1": 0.5175718849840255,
|
| 2143 |
+
"eval_loss": 0.3953240215778351,
|
| 2144 |
+
"eval_precision": 0.7232142857142857,
|
| 2145 |
+
"eval_recall": 0.40298507462686567,
|
| 2146 |
+
"eval_runtime": 34.1139,
|
| 2147 |
+
"eval_samples_per_second": 6.566,
|
| 2148 |
+
"eval_steps_per_second": 0.205,
|
| 2149 |
+
"step": 280
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.7473404255319149,
|
| 2153 |
+
"grad_norm": 2.3844354152679443,
|
| 2154 |
+
"learning_rate": 3.651577689168405e-06,
|
| 2155 |
+
"loss": 0.2212,
|
| 2156 |
+
"step": 281
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.75,
|
| 2160 |
+
"grad_norm": 2.8635263442993164,
|
| 2161 |
+
"learning_rate": 3.580038570826093e-06,
|
| 2162 |
+
"loss": 0.2259,
|
| 2163 |
+
"step": 282
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.7526595744680851,
|
| 2167 |
+
"grad_norm": 3.1672933101654053,
|
| 2168 |
+
"learning_rate": 3.509054072625031e-06,
|
| 2169 |
+
"loss": 0.2691,
|
| 2170 |
+
"step": 283
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.7553191489361702,
|
| 2174 |
+
"grad_norm": 3.298377752304077,
|
| 2175 |
+
"learning_rate": 3.4386303269124142e-06,
|
| 2176 |
+
"loss": 0.261,
|
| 2177 |
+
"step": 284
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 0.7579787234042553,
|
| 2181 |
+
"grad_norm": 3.3718481063842773,
|
| 2182 |
+
"learning_rate": 3.3687734175920505e-06,
|
| 2183 |
+
"loss": 0.2842,
|
| 2184 |
+
"step": 285
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.7606382978723404,
|
| 2188 |
+
"grad_norm": 2.822702646255493,
|
| 2189 |
+
"learning_rate": 3.299489379598777e-06,
|
| 2190 |
+
"loss": 0.2416,
|
| 2191 |
+
"step": 286
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.7632978723404256,
|
| 2195 |
+
"grad_norm": 3.209895372390747,
|
| 2196 |
+
"learning_rate": 3.2307841983771182e-06,
|
| 2197 |
+
"loss": 0.2706,
|
| 2198 |
+
"step": 287
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.7659574468085106,
|
| 2202 |
+
"grad_norm": 2.953824996948242,
|
| 2203 |
+
"learning_rate": 3.162663809364178e-06,
|
| 2204 |
+
"loss": 0.2629,
|
| 2205 |
+
"step": 288
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.7686170212765957,
|
| 2209 |
+
"grad_norm": 4.190698623657227,
|
| 2210 |
+
"learning_rate": 3.095134097476904e-06,
|
| 2211 |
+
"loss": 0.2609,
|
| 2212 |
+
"step": 289
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 0.7712765957446809,
|
| 2216 |
+
"grad_norm": 4.36337423324585,
|
| 2217 |
+
"learning_rate": 3.0282008966036647e-06,
|
| 2218 |
+
"loss": 0.2549,
|
| 2219 |
+
"step": 290
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 0.773936170212766,
|
| 2223 |
+
"grad_norm": 2.8681600093841553,
|
| 2224 |
+
"learning_rate": 2.9618699891002843e-06,
|
| 2225 |
+
"loss": 0.2464,
|
| 2226 |
+
"step": 291
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 0.776595744680851,
|
| 2230 |
+
"grad_norm": 3.781843900680542,
|
| 2231 |
+
"learning_rate": 2.8961471052904855e-06,
|
| 2232 |
+
"loss": 0.3261,
|
| 2233 |
+
"step": 292
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 0.7792553191489362,
|
| 2237 |
+
"grad_norm": 3.1815481185913086,
|
| 2238 |
+
"learning_rate": 2.831037922970855e-06,
|
| 2239 |
+
"loss": 0.2659,
|
| 2240 |
+
"step": 293
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.7819148936170213,
|
| 2244 |
+
"grad_norm": 3.2825517654418945,
|
| 2245 |
+
"learning_rate": 2.7665480669203383e-06,
|
| 2246 |
+
"loss": 0.2239,
|
| 2247 |
+
"step": 294
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 0.7845744680851063,
|
| 2251 |
+
"grad_norm": 2.418006420135498,
|
| 2252 |
+
"learning_rate": 2.702683108414326e-06,
|
| 2253 |
+
"loss": 0.2476,
|
| 2254 |
+
"step": 295
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 0.7872340425531915,
|
| 2258 |
+
"grad_norm": 3.483743906021118,
|
| 2259 |
+
"learning_rate": 2.639448564743328e-06,
|
| 2260 |
+
"loss": 0.2306,
|
| 2261 |
+
"step": 296
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 0.7898936170212766,
|
| 2265 |
+
"grad_norm": 3.201629638671875,
|
| 2266 |
+
"learning_rate": 2.57684989873636e-06,
|
| 2267 |
+
"loss": 0.2562,
|
| 2268 |
+
"step": 297
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 0.7925531914893617,
|
| 2272 |
+
"grad_norm": 2.7855303287506104,
|
| 2273 |
+
"learning_rate": 2.514892518288988e-06,
|
| 2274 |
+
"loss": 0.2245,
|
| 2275 |
+
"step": 298
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 0.7952127659574468,
|
| 2279 |
+
"grad_norm": 3.742940664291382,
|
| 2280 |
+
"learning_rate": 2.4535817758961644e-06,
|
| 2281 |
+
"loss": 0.3192,
|
| 2282 |
+
"step": 299
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.7978723404255319,
|
| 2286 |
+
"grad_norm": 2.966266393661499,
|
| 2287 |
+
"learning_rate": 2.3929229681898005e-06,
|
| 2288 |
+
"loss": 0.2704,
|
| 2289 |
+
"step": 300
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.7978723404255319,
|
| 2293 |
+
"eval_accuracy": 0.8329411764705882,
|
| 2294 |
+
"eval_f1": 0.5644171779141104,
|
| 2295 |
+
"eval_loss": 0.38487711548805237,
|
| 2296 |
+
"eval_precision": 0.736,
|
| 2297 |
+
"eval_recall": 0.4577114427860697,
|
| 2298 |
+
"eval_runtime": 33.5166,
|
| 2299 |
+
"eval_samples_per_second": 6.683,
|
| 2300 |
+
"eval_steps_per_second": 0.209,
|
| 2301 |
+
"step": 300
|
| 2302 |
}
|
| 2303 |
],
|
| 2304 |
"logging_steps": 1,
|
|
|
|
| 2318 |
"attributes": {}
|
| 2319 |
}
|
| 2320 |
},
|
| 2321 |
+
"total_flos": 9.717414664287027e+16,
|
| 2322 |
"train_batch_size": 8,
|
| 2323 |
"trial_name": null,
|
| 2324 |
"trial_params": null
|