vuongnhathien
commited on
Commit
•
b1aa8c6
1
Parent(s):
6d9297f
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May25_17-44-28_ab94a2ea8078/events.out.tfevents.1716685921.ab94a2ea8078.24.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1313 -0
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.942063492063492
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.3165
|
36 |
+
- Accuracy: 0.9421
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 6.140249030814106e+19,
|
4 |
+
"train_loss": 0.2272892904238228,
|
5 |
+
"train_runtime": 26538.9058,
|
6 |
+
"train_samples_per_second": 9.937,
|
7 |
+
"train_steps_per_second": 0.621
|
8 |
+
}
|
runs/May25_17-44-28_ab94a2ea8078/events.out.tfevents.1716685921.ab94a2ea8078.24.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a17a44e2431fee34471ad1a90a90c2668204132fc337afac6330e93e00a6b791
|
3 |
+
size 417
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 6.140249030814106e+19,
|
4 |
+
"train_loss": 0.2272892904238228,
|
5 |
+
"train_runtime": 26538.9058,
|
6 |
+
"train_samples_per_second": 9.937,
|
7 |
+
"train_steps_per_second": 0.621
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.31903526186943054,
|
3 |
+
"best_model_checkpoint": "./convnext-base-15ep/checkpoint-15386",
|
4 |
+
"epoch": 15.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 16485,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09,
|
13 |
+
"grad_norm": 12.268571853637695,
|
14 |
+
"learning_rate": 9.999092077649917e-05,
|
15 |
+
"loss": 1.8816,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.18,
|
20 |
+
"grad_norm": 16.745285034179688,
|
21 |
+
"learning_rate": 9.996368640328861e-05,
|
22 |
+
"loss": 0.9784,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.27,
|
27 |
+
"grad_norm": 15.278342247009277,
|
28 |
+
"learning_rate": 9.991830677104683e-05,
|
29 |
+
"loss": 0.8074,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.36,
|
34 |
+
"grad_norm": 12.999685287475586,
|
35 |
+
"learning_rate": 9.985479836024671e-05,
|
36 |
+
"loss": 0.6924,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.45,
|
41 |
+
"grad_norm": 15.637765884399414,
|
42 |
+
"learning_rate": 9.977318423517052e-05,
|
43 |
+
"loss": 0.6877,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.55,
|
48 |
+
"grad_norm": 8.964929580688477,
|
49 |
+
"learning_rate": 9.967349403553353e-05,
|
50 |
+
"loss": 0.6085,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.64,
|
55 |
+
"grad_norm": 20.98185157775879,
|
56 |
+
"learning_rate": 9.95557639657199e-05,
|
57 |
+
"loss": 0.6267,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.73,
|
62 |
+
"grad_norm": 17.35112953186035,
|
63 |
+
"learning_rate": 9.942003678163429e-05,
|
64 |
+
"loss": 0.6133,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.82,
|
69 |
+
"grad_norm": 4.6055192947387695,
|
70 |
+
"learning_rate": 9.926636177517427e-05,
|
71 |
+
"loss": 0.5813,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.91,
|
76 |
+
"grad_norm": 10.87624454498291,
|
77 |
+
"learning_rate": 9.909479475632904e-05,
|
78 |
+
"loss": 0.5717,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.0,
|
83 |
+
"eval_accuracy": 0.8572564612326043,
|
84 |
+
"eval_loss": 0.4616268575191498,
|
85 |
+
"eval_runtime": 111.9566,
|
86 |
+
"eval_samples_per_second": 22.464,
|
87 |
+
"eval_steps_per_second": 1.411,
|
88 |
+
"step": 1099
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.0,
|
92 |
+
"grad_norm": 12.744146347045898,
|
93 |
+
"learning_rate": 9.8905398032911e-05,
|
94 |
+
"loss": 0.5917,
|
95 |
+
"step": 1100
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.09,
|
99 |
+
"grad_norm": 7.046997547149658,
|
100 |
+
"learning_rate": 9.869824038792741e-05,
|
101 |
+
"loss": 0.4628,
|
102 |
+
"step": 1200
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.18,
|
106 |
+
"grad_norm": 14.269908905029297,
|
107 |
+
"learning_rate": 9.847339705460064e-05,
|
108 |
+
"loss": 0.4921,
|
109 |
+
"step": 1300
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.27,
|
113 |
+
"grad_norm": 13.306988716125488,
|
114 |
+
"learning_rate": 9.823094968904572e-05,
|
115 |
+
"loss": 0.474,
|
116 |
+
"step": 1400
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.36,
|
120 |
+
"grad_norm": 11.327611923217773,
|
121 |
+
"learning_rate": 9.797098634061542e-05,
|
122 |
+
"loss": 0.4723,
|
123 |
+
"step": 1500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.46,
|
127 |
+
"grad_norm": 10.74616813659668,
|
128 |
+
"learning_rate": 9.769360141992343e-05,
|
129 |
+
"loss": 0.4207,
|
130 |
+
"step": 1600
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.55,
|
134 |
+
"grad_norm": 12.389139175415039,
|
135 |
+
"learning_rate": 9.739889566455738e-05,
|
136 |
+
"loss": 0.492,
|
137 |
+
"step": 1700
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.64,
|
141 |
+
"grad_norm": 13.068366050720215,
|
142 |
+
"learning_rate": 9.708697610249406e-05,
|
143 |
+
"loss": 0.4583,
|
144 |
+
"step": 1800
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.73,
|
148 |
+
"grad_norm": 6.97837495803833,
|
149 |
+
"learning_rate": 9.675795601323023e-05,
|
150 |
+
"loss": 0.4619,
|
151 |
+
"step": 1900
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.82,
|
155 |
+
"grad_norm": 11.903929710388184,
|
156 |
+
"learning_rate": 9.641195488664292e-05,
|
157 |
+
"loss": 0.4033,
|
158 |
+
"step": 2000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.91,
|
162 |
+
"grad_norm": 8.415858268737793,
|
163 |
+
"learning_rate": 9.604909837959455e-05,
|
164 |
+
"loss": 0.4653,
|
165 |
+
"step": 2100
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.0,
|
169 |
+
"eval_accuracy": 0.8970178926441352,
|
170 |
+
"eval_loss": 0.36072757840156555,
|
171 |
+
"eval_runtime": 111.9718,
|
172 |
+
"eval_samples_per_second": 22.461,
|
173 |
+
"eval_steps_per_second": 1.411,
|
174 |
+
"step": 2198
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.0,
|
178 |
+
"grad_norm": 19.435712814331055,
|
179 |
+
"learning_rate": 9.566951827029816e-05,
|
180 |
+
"loss": 0.442,
|
181 |
+
"step": 2200
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 2.09,
|
185 |
+
"grad_norm": 6.7451982498168945,
|
186 |
+
"learning_rate": 9.52733524104597e-05,
|
187 |
+
"loss": 0.3708,
|
188 |
+
"step": 2300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.18,
|
192 |
+
"grad_norm": 15.736494064331055,
|
193 |
+
"learning_rate": 9.486074467521456e-05,
|
194 |
+
"loss": 0.3583,
|
195 |
+
"step": 2400
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 2.27,
|
199 |
+
"grad_norm": 10.238139152526855,
|
200 |
+
"learning_rate": 9.44318449108766e-05,
|
201 |
+
"loss": 0.3513,
|
202 |
+
"step": 2500
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 2.37,
|
206 |
+
"grad_norm": 5.870657444000244,
|
207 |
+
"learning_rate": 9.398680888051863e-05,
|
208 |
+
"loss": 0.4243,
|
209 |
+
"step": 2600
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 2.46,
|
213 |
+
"grad_norm": 10.592901229858398,
|
214 |
+
"learning_rate": 9.352579820740405e-05,
|
215 |
+
"loss": 0.3681,
|
216 |
+
"step": 2700
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.55,
|
220 |
+
"grad_norm": 2.5265157222747803,
|
221 |
+
"learning_rate": 9.304898031629036e-05,
|
222 |
+
"loss": 0.3971,
|
223 |
+
"step": 2800
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 2.64,
|
227 |
+
"grad_norm": 20.8736572265625,
|
228 |
+
"learning_rate": 9.25565283726257e-05,
|
229 |
+
"loss": 0.4244,
|
230 |
+
"step": 2900
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.73,
|
234 |
+
"grad_norm": 2.61696457862854,
|
235 |
+
"learning_rate": 9.204862121966044e-05,
|
236 |
+
"loss": 0.3762,
|
237 |
+
"step": 3000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 2.82,
|
241 |
+
"grad_norm": 11.449930191040039,
|
242 |
+
"learning_rate": 9.152544331349694e-05,
|
243 |
+
"loss": 0.3584,
|
244 |
+
"step": 3100
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 2.91,
|
248 |
+
"grad_norm": 9.69878101348877,
|
249 |
+
"learning_rate": 9.098718465610088e-05,
|
250 |
+
"loss": 0.3449,
|
251 |
+
"step": 3200
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 3.0,
|
255 |
+
"eval_accuracy": 0.8950298210735587,
|
256 |
+
"eval_loss": 0.41042593121528625,
|
257 |
+
"eval_runtime": 111.0632,
|
258 |
+
"eval_samples_per_second": 22.645,
|
259 |
+
"eval_steps_per_second": 1.423,
|
260 |
+
"step": 3297
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.0,
|
264 |
+
"grad_norm": 2.2799901962280273,
|
265 |
+
"learning_rate": 9.043404072629829e-05,
|
266 |
+
"loss": 0.394,
|
267 |
+
"step": 3300
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 3.09,
|
271 |
+
"grad_norm": 11.792191505432129,
|
272 |
+
"learning_rate": 8.986621240878385e-05,
|
273 |
+
"loss": 0.2869,
|
274 |
+
"step": 3400
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 3.18,
|
278 |
+
"grad_norm": 1.5572706460952759,
|
279 |
+
"learning_rate": 8.928390592116575e-05,
|
280 |
+
"loss": 0.2879,
|
281 |
+
"step": 3500
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 3.28,
|
285 |
+
"grad_norm": 7.704630374908447,
|
286 |
+
"learning_rate": 8.86873327390739e-05,
|
287 |
+
"loss": 0.3059,
|
288 |
+
"step": 3600
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 3.37,
|
292 |
+
"grad_norm": 10.151177406311035,
|
293 |
+
"learning_rate": 8.807670951935846e-05,
|
294 |
+
"loss": 0.3329,
|
295 |
+
"step": 3700
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 3.46,
|
299 |
+
"grad_norm": 9.523168563842773,
|
300 |
+
"learning_rate": 8.745225802140691e-05,
|
301 |
+
"loss": 0.287,
|
302 |
+
"step": 3800
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.55,
|
306 |
+
"grad_norm": 9.30478572845459,
|
307 |
+
"learning_rate": 8.681420502660786e-05,
|
308 |
+
"loss": 0.2992,
|
309 |
+
"step": 3900
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 3.64,
|
313 |
+
"grad_norm": 7.661346912384033,
|
314 |
+
"learning_rate": 8.616278225599111e-05,
|
315 |
+
"loss": 0.3259,
|
316 |
+
"step": 4000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 3.73,
|
320 |
+
"grad_norm": 5.623369216918945,
|
321 |
+
"learning_rate": 8.54982262860738e-05,
|
322 |
+
"loss": 0.334,
|
323 |
+
"step": 4100
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 3.82,
|
327 |
+
"grad_norm": 0.08087614178657532,
|
328 |
+
"learning_rate": 8.482077846294308e-05,
|
329 |
+
"loss": 0.3385,
|
330 |
+
"step": 4200
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 3.91,
|
334 |
+
"grad_norm": 12.912845611572266,
|
335 |
+
"learning_rate": 8.413068481460686e-05,
|
336 |
+
"loss": 0.3522,
|
337 |
+
"step": 4300
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 4.0,
|
341 |
+
"eval_accuracy": 0.9025844930417495,
|
342 |
+
"eval_loss": 0.37546443939208984,
|
343 |
+
"eval_runtime": 111.8065,
|
344 |
+
"eval_samples_per_second": 22.494,
|
345 |
+
"eval_steps_per_second": 1.413,
|
346 |
+
"step": 4396
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 4.0,
|
350 |
+
"grad_norm": 2.0130882263183594,
|
351 |
+
"learning_rate": 8.342819596164387e-05,
|
352 |
+
"loss": 0.2963,
|
353 |
+
"step": 4400
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 4.09,
|
357 |
+
"grad_norm": 9.422698020935059,
|
358 |
+
"learning_rate": 8.271356702618626e-05,
|
359 |
+
"loss": 0.263,
|
360 |
+
"step": 4500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 4.19,
|
364 |
+
"grad_norm": 4.466526985168457,
|
365 |
+
"learning_rate": 8.198705753926704e-05,
|
366 |
+
"loss": 0.2767,
|
367 |
+
"step": 4600
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 4.28,
|
371 |
+
"grad_norm": 8.486282348632812,
|
372 |
+
"learning_rate": 8.12489313465665e-05,
|
373 |
+
"loss": 0.2691,
|
374 |
+
"step": 4700
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.37,
|
378 |
+
"grad_norm": 1.178945541381836,
|
379 |
+
"learning_rate": 8.049945651259163e-05,
|
380 |
+
"loss": 0.2454,
|
381 |
+
"step": 4800
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 4.46,
|
385 |
+
"grad_norm": 8.335172653198242,
|
386 |
+
"learning_rate": 7.973890522332348e-05,
|
387 |
+
"loss": 0.2906,
|
388 |
+
"step": 4900
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 4.55,
|
392 |
+
"grad_norm": 3.436420440673828,
|
393 |
+
"learning_rate": 7.89675536873676e-05,
|
394 |
+
"loss": 0.2316,
|
395 |
+
"step": 5000
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 4.64,
|
399 |
+
"grad_norm": 7.467193603515625,
|
400 |
+
"learning_rate": 7.818568203564374e-05,
|
401 |
+
"loss": 0.2738,
|
402 |
+
"step": 5100
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 4.73,
|
406 |
+
"grad_norm": 10.7122163772583,
|
407 |
+
"learning_rate": 7.739357421965086e-05,
|
408 |
+
"loss": 0.281,
|
409 |
+
"step": 5200
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 4.82,
|
413 |
+
"grad_norm": 14.049674034118652,
|
414 |
+
"learning_rate": 7.65915179083449e-05,
|
415 |
+
"loss": 0.2782,
|
416 |
+
"step": 5300
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 4.91,
|
420 |
+
"grad_norm": 16.04802703857422,
|
421 |
+
"learning_rate": 7.577980438366628e-05,
|
422 |
+
"loss": 0.28,
|
423 |
+
"step": 5400
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 5.0,
|
427 |
+
"eval_accuracy": 0.9065606361829026,
|
428 |
+
"eval_loss": 0.3756468892097473,
|
429 |
+
"eval_runtime": 111.8227,
|
430 |
+
"eval_samples_per_second": 22.491,
|
431 |
+
"eval_steps_per_second": 1.413,
|
432 |
+
"step": 5495
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 5.0,
|
436 |
+
"grad_norm": 2.5667672157287598,
|
437 |
+
"learning_rate": 7.495872843475536e-05,
|
438 |
+
"loss": 0.2711,
|
439 |
+
"step": 5500
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 5.1,
|
443 |
+
"grad_norm": 5.182483673095703,
|
444 |
+
"learning_rate": 7.412858825089422e-05,
|
445 |
+
"loss": 0.1939,
|
446 |
+
"step": 5600
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 5.19,
|
450 |
+
"grad_norm": 13.568757057189941,
|
451 |
+
"learning_rate": 7.32896853132135e-05,
|
452 |
+
"loss": 0.2178,
|
453 |
+
"step": 5700
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 5.28,
|
457 |
+
"grad_norm": 10.223276138305664,
|
458 |
+
"learning_rate": 7.244232428520383e-05,
|
459 |
+
"loss": 0.2185,
|
460 |
+
"step": 5800
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 5.37,
|
464 |
+
"grad_norm": 0.07271099835634232,
|
465 |
+
"learning_rate": 7.158681290207163e-05,
|
466 |
+
"loss": 0.2218,
|
467 |
+
"step": 5900
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 5.46,
|
471 |
+
"grad_norm": 2.859640598297119,
|
472 |
+
"learning_rate": 7.07234618589791e-05,
|
473 |
+
"loss": 0.1974,
|
474 |
+
"step": 6000
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 5.55,
|
478 |
+
"grad_norm": 4.893543243408203,
|
479 |
+
"learning_rate": 6.985258469820939e-05,
|
480 |
+
"loss": 0.2201,
|
481 |
+
"step": 6100
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 5.64,
|
485 |
+
"grad_norm": 9.013633728027344,
|
486 |
+
"learning_rate": 6.897449769529792e-05,
|
487 |
+
"loss": 0.2031,
|
488 |
+
"step": 6200
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 5.73,
|
492 |
+
"grad_norm": 8.197441101074219,
|
493 |
+
"learning_rate": 6.808951974417078e-05,
|
494 |
+
"loss": 0.2532,
|
495 |
+
"step": 6300
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 5.82,
|
499 |
+
"grad_norm": 0.8769248127937317,
|
500 |
+
"learning_rate": 6.719797224133242e-05,
|
501 |
+
"loss": 0.2399,
|
502 |
+
"step": 6400
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 5.91,
|
506 |
+
"grad_norm": 9.442893981933594,
|
507 |
+
"learning_rate": 6.630017896914446e-05,
|
508 |
+
"loss": 0.2456,
|
509 |
+
"step": 6500
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 6.0,
|
513 |
+
"eval_accuracy": 0.9172962226640159,
|
514 |
+
"eval_loss": 0.349565327167511,
|
515 |
+
"eval_runtime": 110.6537,
|
516 |
+
"eval_samples_per_second": 22.729,
|
517 |
+
"eval_steps_per_second": 1.428,
|
518 |
+
"step": 6594
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 6.01,
|
522 |
+
"grad_norm": 9.589459419250488,
|
523 |
+
"learning_rate": 6.539646597823791e-05,
|
524 |
+
"loss": 0.2373,
|
525 |
+
"step": 6600
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 6.1,
|
529 |
+
"grad_norm": 11.073722839355469,
|
530 |
+
"learning_rate": 6.44871614691018e-05,
|
531 |
+
"loss": 0.1756,
|
532 |
+
"step": 6700
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 6.19,
|
536 |
+
"grad_norm": 15.033493995666504,
|
537 |
+
"learning_rate": 6.357259567289082e-05,
|
538 |
+
"loss": 0.1883,
|
539 |
+
"step": 6800
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 6.28,
|
543 |
+
"grad_norm": 2.1004364490509033,
|
544 |
+
"learning_rate": 6.265310073149584e-05,
|
545 |
+
"loss": 0.1599,
|
546 |
+
"step": 6900
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 6.37,
|
550 |
+
"grad_norm": 2.42246675491333,
|
551 |
+
"learning_rate": 6.172901057692007e-05,
|
552 |
+
"loss": 0.2066,
|
553 |
+
"step": 7000
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 6.46,
|
557 |
+
"grad_norm": 5.9083147048950195,
|
558 |
+
"learning_rate": 6.0800660810005416e-05,
|
559 |
+
"loss": 0.1966,
|
560 |
+
"step": 7100
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 6.55,
|
564 |
+
"grad_norm": 2.3564085960388184,
|
565 |
+
"learning_rate": 5.9868388578552734e-05,
|
566 |
+
"loss": 0.1641,
|
567 |
+
"step": 7200
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 6.64,
|
571 |
+
"grad_norm": 0.16256462037563324,
|
572 |
+
"learning_rate": 5.893253245488015e-05,
|
573 |
+
"loss": 0.1643,
|
574 |
+
"step": 7300
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 6.73,
|
578 |
+
"grad_norm": 6.537099838256836,
|
579 |
+
"learning_rate": 5.79934323128641e-05,
|
580 |
+
"loss": 0.1932,
|
581 |
+
"step": 7400
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 6.82,
|
585 |
+
"grad_norm": 9.104645729064941,
|
586 |
+
"learning_rate": 5.705142920450777e-05,
|
587 |
+
"loss": 0.1993,
|
588 |
+
"step": 7500
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 6.92,
|
592 |
+
"grad_norm": 13.837006568908691,
|
593 |
+
"learning_rate": 5.610686523608151e-05,
|
594 |
+
"loss": 0.2141,
|
595 |
+
"step": 7600
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 7.0,
|
599 |
+
"eval_accuracy": 0.920079522862823,
|
600 |
+
"eval_loss": 0.3611968457698822,
|
601 |
+
"eval_runtime": 111.0708,
|
602 |
+
"eval_samples_per_second": 22.643,
|
603 |
+
"eval_steps_per_second": 1.423,
|
604 |
+
"step": 7693
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 7.01,
|
608 |
+
"grad_norm": 13.015904426574707,
|
609 |
+
"learning_rate": 5.516008344388053e-05,
|
610 |
+
"loss": 0.1581,
|
611 |
+
"step": 7700
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 7.1,
|
615 |
+
"grad_norm": 5.245505332946777,
|
616 |
+
"learning_rate": 5.421142766964474e-05,
|
617 |
+
"loss": 0.1366,
|
618 |
+
"step": 7800
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 7.19,
|
622 |
+
"grad_norm": 1.4385249614715576,
|
623 |
+
"learning_rate": 5.326124243568617e-05,
|
624 |
+
"loss": 0.1867,
|
625 |
+
"step": 7900
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 7.28,
|
629 |
+
"grad_norm": 1.0775200128555298,
|
630 |
+
"learning_rate": 5.230987281976901e-05,
|
631 |
+
"loss": 0.1415,
|
632 |
+
"step": 8000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 7.37,
|
636 |
+
"grad_norm": 1.4409250020980835,
|
637 |
+
"learning_rate": 5.135766432978829e-05,
|
638 |
+
"loss": 0.2004,
|
639 |
+
"step": 8100
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 7.46,
|
643 |
+
"grad_norm": 0.05134790390729904,
|
644 |
+
"learning_rate": 5.0404962778292e-05,
|
645 |
+
"loss": 0.159,
|
646 |
+
"step": 8200
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 7.55,
|
650 |
+
"grad_norm": 7.336070537567139,
|
651 |
+
"learning_rate": 4.945211415689278e-05,
|
652 |
+
"loss": 0.1578,
|
653 |
+
"step": 8300
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 7.64,
|
657 |
+
"grad_norm": 0.08769059181213379,
|
658 |
+
"learning_rate": 4.849946451061443e-05,
|
659 |
+
"loss": 0.1883,
|
660 |
+
"step": 8400
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 7.73,
|
664 |
+
"grad_norm": 12.924542427062988,
|
665 |
+
"learning_rate": 4.754735981221927e-05,
|
666 |
+
"loss": 0.1717,
|
667 |
+
"step": 8500
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 7.83,
|
671 |
+
"grad_norm": 6.11922025680542,
|
672 |
+
"learning_rate": 4.659614583656138e-05,
|
673 |
+
"loss": 0.1557,
|
674 |
+
"step": 8600
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 7.92,
|
678 |
+
"grad_norm": 20.91149139404297,
|
679 |
+
"learning_rate": 4.564616803501205e-05,
|
680 |
+
"loss": 0.1458,
|
681 |
+
"step": 8700
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 8.0,
|
685 |
+
"eval_accuracy": 0.9304174950298211,
|
686 |
+
"eval_loss": 0.33909356594085693,
|
687 |
+
"eval_runtime": 111.9164,
|
688 |
+
"eval_samples_per_second": 22.472,
|
689 |
+
"eval_steps_per_second": 1.412,
|
690 |
+
"step": 8792
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 8.01,
|
694 |
+
"grad_norm": 2.7522988319396973,
|
695 |
+
"learning_rate": 4.469777141000255e-05,
|
696 |
+
"loss": 0.1309,
|
697 |
+
"step": 8800
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 8.1,
|
701 |
+
"grad_norm": 8.19546890258789,
|
702 |
+
"learning_rate": 4.375130038972988e-05,
|
703 |
+
"loss": 0.1502,
|
704 |
+
"step": 8900
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 8.19,
|
708 |
+
"grad_norm": 3.5378799438476562,
|
709 |
+
"learning_rate": 4.2807098703071255e-05,
|
710 |
+
"loss": 0.1528,
|
711 |
+
"step": 9000
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 8.28,
|
715 |
+
"grad_norm": 8.663042068481445,
|
716 |
+
"learning_rate": 4.18655092547524e-05,
|
717 |
+
"loss": 0.0897,
|
718 |
+
"step": 9100
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 8.37,
|
722 |
+
"grad_norm": 0.019041290506720543,
|
723 |
+
"learning_rate": 4.092687400081522e-05,
|
724 |
+
"loss": 0.16,
|
725 |
+
"step": 9200
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 8.46,
|
729 |
+
"grad_norm": 0.053332068026065826,
|
730 |
+
"learning_rate": 3.999153382442995e-05,
|
731 |
+
"loss": 0.1378,
|
732 |
+
"step": 9300
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 8.55,
|
736 |
+
"grad_norm": 5.864047050476074,
|
737 |
+
"learning_rate": 3.9059828412097024e-05,
|
738 |
+
"loss": 0.1176,
|
739 |
+
"step": 9400
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 8.64,
|
743 |
+
"grad_norm": 11.58228588104248,
|
744 |
+
"learning_rate": 3.8132096130283455e-05,
|
745 |
+
"loss": 0.1336,
|
746 |
+
"step": 9500
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 8.74,
|
750 |
+
"grad_norm": 0.3950587511062622,
|
751 |
+
"learning_rate": 3.7208673902538706e-05,
|
752 |
+
"loss": 0.1525,
|
753 |
+
"step": 9600
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 8.83,
|
757 |
+
"grad_norm": 9.62333869934082,
|
758 |
+
"learning_rate": 3.628989708713436e-05,
|
759 |
+
"loss": 0.1565,
|
760 |
+
"step": 9700
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 8.92,
|
764 |
+
"grad_norm": 12.212615966796875,
|
765 |
+
"learning_rate": 3.537609935527264e-05,
|
766 |
+
"loss": 0.1842,
|
767 |
+
"step": 9800
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 9.0,
|
771 |
+
"eval_accuracy": 0.932803180914513,
|
772 |
+
"eval_loss": 0.33526965975761414,
|
773 |
+
"eval_runtime": 111.0268,
|
774 |
+
"eval_samples_per_second": 22.652,
|
775 |
+
"eval_steps_per_second": 1.423,
|
776 |
+
"step": 9891
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 9.01,
|
780 |
+
"grad_norm": 2.527280807495117,
|
781 |
+
"learning_rate": 3.446761256990723e-05,
|
782 |
+
"loss": 0.1074,
|
783 |
+
"step": 9900
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 9.1,
|
787 |
+
"grad_norm": 0.02450253628194332,
|
788 |
+
"learning_rate": 3.356476666522099e-05,
|
789 |
+
"loss": 0.1001,
|
790 |
+
"step": 10000
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 9.19,
|
794 |
+
"grad_norm": 0.32657700777053833,
|
795 |
+
"learning_rate": 3.266788952680414e-05,
|
796 |
+
"loss": 0.1094,
|
797 |
+
"step": 10100
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 9.28,
|
801 |
+
"grad_norm": 2.115306854248047,
|
802 |
+
"learning_rate": 3.177730687257639e-05,
|
803 |
+
"loss": 0.1069,
|
804 |
+
"step": 10200
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 9.37,
|
808 |
+
"grad_norm": 0.252822607755661,
|
809 |
+
"learning_rate": 3.0893342134496295e-05,
|
810 |
+
"loss": 0.1074,
|
811 |
+
"step": 10300
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 9.46,
|
815 |
+
"grad_norm": 10.717082023620605,
|
816 |
+
"learning_rate": 3.0016316341100808e-05,
|
817 |
+
"loss": 0.1075,
|
818 |
+
"step": 10400
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 9.55,
|
822 |
+
"grad_norm": 0.030081748962402344,
|
823 |
+
"learning_rate": 2.914654800091768e-05,
|
824 |
+
"loss": 0.1344,
|
825 |
+
"step": 10500
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 9.65,
|
829 |
+
"grad_norm": 13.859551429748535,
|
830 |
+
"learning_rate": 2.8284352986793094e-05,
|
831 |
+
"loss": 0.1205,
|
832 |
+
"step": 10600
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 9.74,
|
836 |
+
"grad_norm": 1.8139934539794922,
|
837 |
+
"learning_rate": 2.7430044421176447e-05,
|
838 |
+
"loss": 0.1253,
|
839 |
+
"step": 10700
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 9.83,
|
843 |
+
"grad_norm": 1.271942377090454,
|
844 |
+
"learning_rate": 2.6583932562403957e-05,
|
845 |
+
"loss": 0.1226,
|
846 |
+
"step": 10800
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 9.92,
|
850 |
+
"grad_norm": 0.060803137719631195,
|
851 |
+
"learning_rate": 2.5746324692022527e-05,
|
852 |
+
"loss": 0.1037,
|
853 |
+
"step": 10900
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 10.0,
|
857 |
+
"eval_accuracy": 0.9355864811133201,
|
858 |
+
"eval_loss": 0.33833950757980347,
|
859 |
+
"eval_runtime": 111.2929,
|
860 |
+
"eval_samples_per_second": 22.598,
|
861 |
+
"eval_steps_per_second": 1.42,
|
862 |
+
"step": 10990
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 10.01,
|
866 |
+
"grad_norm": 0.0546095035970211,
|
867 |
+
"learning_rate": 2.4917525003194624e-05,
|
868 |
+
"loss": 0.1162,
|
869 |
+
"step": 11000
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 10.1,
|
873 |
+
"grad_norm": 6.095231533050537,
|
874 |
+
"learning_rate": 2.409783449022475e-05,
|
875 |
+
"loss": 0.0934,
|
876 |
+
"step": 11100
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 10.19,
|
880 |
+
"grad_norm": 0.6238592267036438,
|
881 |
+
"learning_rate": 2.3287550839247624e-05,
|
882 |
+
"loss": 0.087,
|
883 |
+
"step": 11200
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 10.28,
|
887 |
+
"grad_norm": 24.5279598236084,
|
888 |
+
"learning_rate": 2.2486968320117907e-05,
|
889 |
+
"loss": 0.0873,
|
890 |
+
"step": 11300
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 10.37,
|
894 |
+
"grad_norm": 2.309201240539551,
|
895 |
+
"learning_rate": 2.169637767954048e-05,
|
896 |
+
"loss": 0.0853,
|
897 |
+
"step": 11400
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 10.46,
|
901 |
+
"grad_norm": 0.10698918998241425,
|
902 |
+
"learning_rate": 2.091606603548029e-05,
|
903 |
+
"loss": 0.0994,
|
904 |
+
"step": 11500
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 10.56,
|
908 |
+
"grad_norm": 0.09092956781387329,
|
909 |
+
"learning_rate": 2.0146316772889983e-05,
|
910 |
+
"loss": 0.0704,
|
911 |
+
"step": 11600
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 10.65,
|
915 |
+
"grad_norm": 10.446697235107422,
|
916 |
+
"learning_rate": 1.9387409440793386e-05,
|
917 |
+
"loss": 0.0918,
|
918 |
+
"step": 11700
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 10.74,
|
922 |
+
"grad_norm": 8.398408889770508,
|
923 |
+
"learning_rate": 1.863961965076186e-05,
|
924 |
+
"loss": 0.096,
|
925 |
+
"step": 11800
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 10.83,
|
929 |
+
"grad_norm": 0.9171711802482605,
|
930 |
+
"learning_rate": 1.790321897682083e-05,
|
931 |
+
"loss": 0.1025,
|
932 |
+
"step": 11900
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 10.92,
|
936 |
+
"grad_norm": 0.2961582839488983,
|
937 |
+
"learning_rate": 1.7178474856822456e-05,
|
938 |
+
"loss": 0.0747,
|
939 |
+
"step": 12000
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 11.0,
|
943 |
+
"eval_accuracy": 0.936779324055666,
|
944 |
+
"eval_loss": 0.33453264832496643,
|
945 |
+
"eval_runtime": 109.702,
|
946 |
+
"eval_samples_per_second": 22.926,
|
947 |
+
"eval_steps_per_second": 1.44,
|
948 |
+
"step": 12089
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 11.01,
|
952 |
+
"grad_norm": 0.05641782283782959,
|
953 |
+
"learning_rate": 1.646565049532063e-05,
|
954 |
+
"loss": 0.0575,
|
955 |
+
"step": 12100
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 11.1,
|
959 |
+
"grad_norm": 0.008614973165094852,
|
960 |
+
"learning_rate": 1.576500476798311e-05,
|
961 |
+
"loss": 0.0942,
|
962 |
+
"step": 12200
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 11.19,
|
966 |
+
"grad_norm": 0.0614984966814518,
|
967 |
+
"learning_rate": 1.5076792127576073e-05,
|
968 |
+
"loss": 0.0737,
|
969 |
+
"step": 12300
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 11.28,
|
973 |
+
"grad_norm": 0.6600818037986755,
|
974 |
+
"learning_rate": 1.4401262511554642e-05,
|
975 |
+
"loss": 0.0601,
|
976 |
+
"step": 12400
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 11.37,
|
980 |
+
"grad_norm": 7.176374435424805,
|
981 |
+
"learning_rate": 1.3738661251293423e-05,
|
982 |
+
"loss": 0.0739,
|
983 |
+
"step": 12500
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 11.46,
|
987 |
+
"grad_norm": 0.5290641784667969,
|
988 |
+
"learning_rate": 1.308922898298977e-05,
|
989 |
+
"loss": 0.069,
|
990 |
+
"step": 12600
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 11.56,
|
994 |
+
"grad_norm": 0.010565654374659061,
|
995 |
+
"learning_rate": 1.2453201560272204e-05,
|
996 |
+
"loss": 0.0818,
|
997 |
+
"step": 12700
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 11.65,
|
1001 |
+
"grad_norm": 0.48881271481513977,
|
1002 |
+
"learning_rate": 1.183080996854562e-05,
|
1003 |
+
"loss": 0.0751,
|
1004 |
+
"step": 12800
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 11.74,
|
1008 |
+
"grad_norm": 0.5463552474975586,
|
1009 |
+
"learning_rate": 1.1222280241104716e-05,
|
1010 |
+
"loss": 0.0684,
|
1011 |
+
"step": 12900
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 11.83,
|
1015 |
+
"grad_norm": 5.191521167755127,
|
1016 |
+
"learning_rate": 1.062783337704557e-05,
|
1017 |
+
"loss": 0.1047,
|
1018 |
+
"step": 13000
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 11.92,
|
1022 |
+
"grad_norm": 0.0762176662683487,
|
1023 |
+
"learning_rate": 1.0047685261005707e-05,
|
1024 |
+
"loss": 0.0912,
|
1025 |
+
"step": 13100
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 12.0,
|
1029 |
+
"eval_accuracy": 0.9391650099403579,
|
1030 |
+
"eval_loss": 0.3244304656982422,
|
1031 |
+
"eval_runtime": 112.1314,
|
1032 |
+
"eval_samples_per_second": 22.429,
|
1033 |
+
"eval_steps_per_second": 1.409,
|
1034 |
+
"step": 13188
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 12.01,
|
1038 |
+
"grad_norm": 0.017082059755921364,
|
1039 |
+
"learning_rate": 9.482046584761495e-06,
|
1040 |
+
"loss": 0.0909,
|
1041 |
+
"step": 13200
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 12.1,
|
1045 |
+
"grad_norm": 16.901845932006836,
|
1046 |
+
"learning_rate": 8.931122770711425e-06,
|
1047 |
+
"loss": 0.0827,
|
1048 |
+
"step": 13300
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 12.19,
|
1052 |
+
"grad_norm": 0.1826079934835434,
|
1053 |
+
"learning_rate": 8.395113897273105e-06,
|
1054 |
+
"loss": 0.086,
|
1055 |
+
"step": 13400
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 12.28,
|
1059 |
+
"grad_norm": 0.14454180002212524,
|
1060 |
+
"learning_rate": 7.874214626220899e-06,
|
1061 |
+
"loss": 0.0624,
|
1062 |
+
"step": 13500
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 12.37,
|
1066 |
+
"grad_norm": 3.5157103538513184,
|
1067 |
+
"learning_rate": 7.368614131990986e-06,
|
1068 |
+
"loss": 0.1045,
|
1069 |
+
"step": 13600
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 12.47,
|
1073 |
+
"grad_norm": 0.0011518648825585842,
|
1074 |
+
"learning_rate": 6.8784960329789264e-06,
|
1075 |
+
"loss": 0.0802,
|
1076 |
+
"step": 13700
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 12.56,
|
1080 |
+
"grad_norm": 1.2086189985275269,
|
1081 |
+
"learning_rate": 6.404038324855222e-06,
|
1082 |
+
"loss": 0.0515,
|
1083 |
+
"step": 13800
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 12.65,
|
1087 |
+
"grad_norm": 5.540249824523926,
|
1088 |
+
"learning_rate": 5.945413315922826e-06,
|
1089 |
+
"loss": 0.0687,
|
1090 |
+
"step": 13900
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 12.74,
|
1094 |
+
"grad_norm": 9.239886283874512,
|
1095 |
+
"learning_rate": 5.5027875645401015e-06,
|
1096 |
+
"loss": 0.0625,
|
1097 |
+
"step": 14000
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 12.83,
|
1101 |
+
"grad_norm": 0.017092958092689514,
|
1102 |
+
"learning_rate": 5.076321818632018e-06,
|
1103 |
+
"loss": 0.1087,
|
1104 |
+
"step": 14100
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 12.92,
|
1108 |
+
"grad_norm": 9.08121109008789,
|
1109 |
+
"learning_rate": 4.666170957311472e-06,
|
1110 |
+
"loss": 0.0733,
|
1111 |
+
"step": 14200
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 13.0,
|
1115 |
+
"eval_accuracy": 0.9407554671968191,
|
1116 |
+
"eval_loss": 0.32192325592041016,
|
1117 |
+
"eval_runtime": 110.2447,
|
1118 |
+
"eval_samples_per_second": 22.813,
|
1119 |
+
"eval_steps_per_second": 1.433,
|
1120 |
+
"step": 14287
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 13.01,
|
1124 |
+
"grad_norm": 0.021881932392716408,
|
1125 |
+
"learning_rate": 4.272483934632021e-06,
|
1126 |
+
"loss": 0.0548,
|
1127 |
+
"step": 14300
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 13.1,
|
1131 |
+
"grad_norm": 0.6576229929924011,
|
1132 |
+
"learning_rate": 3.895403725492402e-06,
|
1133 |
+
"loss": 0.059,
|
1134 |
+
"step": 14400
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 13.19,
|
1138 |
+
"grad_norm": 5.590795516967773,
|
1139 |
+
"learning_rate": 3.5350672737124725e-06,
|
1140 |
+
"loss": 0.092,
|
1141 |
+
"step": 14500
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 13.28,
|
1145 |
+
"grad_norm": 0.2879085838794708,
|
1146 |
+
"learning_rate": 3.1916054422994834e-06,
|
1147 |
+
"loss": 0.0642,
|
1148 |
+
"step": 14600
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 13.38,
|
1152 |
+
"grad_norm": 0.1755078285932541,
|
1153 |
+
"learning_rate": 2.86514296592269e-06,
|
1154 |
+
"loss": 0.069,
|
1155 |
+
"step": 14700
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 13.47,
|
1159 |
+
"grad_norm": 11.491580963134766,
|
1160 |
+
"learning_rate": 2.5557984056135964e-06,
|
1161 |
+
"loss": 0.0692,
|
1162 |
+
"step": 14800
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 13.56,
|
1166 |
+
"grad_norm": 0.22245600819587708,
|
1167 |
+
"learning_rate": 2.263684105708275e-06,
|
1168 |
+
"loss": 0.0843,
|
1169 |
+
"step": 14900
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 13.65,
|
1173 |
+
"grad_norm": 19.67642593383789,
|
1174 |
+
"learning_rate": 1.9889061530473986e-06,
|
1175 |
+
"loss": 0.058,
|
1176 |
+
"step": 15000
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 13.74,
|
1180 |
+
"grad_norm": 6.375917434692383,
|
1181 |
+
"learning_rate": 1.7315643384487713e-06,
|
1182 |
+
"loss": 0.0828,
|
1183 |
+
"step": 15100
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 13.83,
|
1187 |
+
"grad_norm": 0.5529243350028992,
|
1188 |
+
"learning_rate": 1.4917521204664331e-06,
|
1189 |
+
"loss": 0.0743,
|
1190 |
+
"step": 15200
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 13.92,
|
1194 |
+
"grad_norm": 6.179434299468994,
|
1195 |
+
"learning_rate": 1.269556591449389e-06,
|
1196 |
+
"loss": 0.0667,
|
1197 |
+
"step": 15300
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 14.0,
|
1201 |
+
"eval_accuracy": 0.9435387673956263,
|
1202 |
+
"eval_loss": 0.31903526186943054,
|
1203 |
+
"eval_runtime": 110.0813,
|
1204 |
+
"eval_samples_per_second": 22.847,
|
1205 |
+
"eval_steps_per_second": 1.435,
|
1206 |
+
"step": 15386
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 14.01,
|
1210 |
+
"grad_norm": 2.8753578662872314,
|
1211 |
+
"learning_rate": 1.065058445912398e-06,
|
1212 |
+
"loss": 0.0588,
|
1213 |
+
"step": 15400
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 14.1,
|
1217 |
+
"grad_norm": 0.04811515659093857,
|
1218 |
+
"learning_rate": 8.783319512302102e-07,
|
1219 |
+
"loss": 0.0608,
|
1220 |
+
"step": 15500
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 14.19,
|
1224 |
+
"grad_norm": 7.1183762550354,
|
1225 |
+
"learning_rate": 7.094449206659748e-07,
|
1226 |
+
"loss": 0.0768,
|
1227 |
+
"step": 15600
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 14.29,
|
1231 |
+
"grad_norm": 0.26764577627182007,
|
1232 |
+
"learning_rate": 5.584586887435739e-07,
|
1233 |
+
"loss": 0.0713,
|
1234 |
+
"step": 15700
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 14.38,
|
1238 |
+
"grad_norm": 5.16556978225708,
|
1239 |
+
"learning_rate": 4.254280889728068e-07,
|
1240 |
+
"loss": 0.0687,
|
1241 |
+
"step": 15800
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 14.47,
|
1245 |
+
"grad_norm": 0.2050618976354599,
|
1246 |
+
"learning_rate": 3.104014339355921e-07,
|
1247 |
+
"loss": 0.0591,
|
1248 |
+
"step": 15900
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 14.56,
|
1252 |
+
"grad_norm": 5.02229642868042,
|
1253 |
+
"learning_rate": 2.1342049774030758e-07,
|
1254 |
+
"loss": 0.0687,
|
1255 |
+
"step": 16000
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 14.65,
|
1259 |
+
"grad_norm": 0.027897778898477554,
|
1260 |
+
"learning_rate": 1.3452050085075442e-07,
|
1261 |
+
"loss": 0.0534,
|
1262 |
+
"step": 16100
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 14.74,
|
1266 |
+
"grad_norm": 14.302966117858887,
|
1267 |
+
"learning_rate": 7.37300972951771e-08,
|
1268 |
+
"loss": 0.0811,
|
1269 |
+
"step": 16200
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 14.83,
|
1273 |
+
"grad_norm": 0.017526021227240562,
|
1274 |
+
"learning_rate": 3.107136425999912e-08,
|
1275 |
+
"loss": 0.0723,
|
1276 |
+
"step": 16300
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 14.92,
|
1280 |
+
"grad_norm": 4.576681137084961,
|
1281 |
+
"learning_rate": 6.559794072080738e-09,
|
1282 |
+
"loss": 0.0694,
|
1283 |
+
"step": 16400
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 15.0,
|
1287 |
+
"eval_accuracy": 0.9431411530815109,
|
1288 |
+
"eval_loss": 0.31916290521621704,
|
1289 |
+
"eval_runtime": 106.1086,
|
1290 |
+
"eval_samples_per_second": 23.702,
|
1291 |
+
"eval_steps_per_second": 1.489,
|
1292 |
+
"step": 16485
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 15.0,
|
1296 |
+
"step": 16485,
|
1297 |
+
"total_flos": 6.140249030814106e+19,
|
1298 |
+
"train_loss": 0.2272892904238228,
|
1299 |
+
"train_runtime": 26538.9058,
|
1300 |
+
"train_samples_per_second": 9.937,
|
1301 |
+
"train_steps_per_second": 0.621
|
1302 |
+
}
|
1303 |
+
],
|
1304 |
+
"logging_steps": 100,
|
1305 |
+
"max_steps": 16485,
|
1306 |
+
"num_input_tokens_seen": 0,
|
1307 |
+
"num_train_epochs": 15,
|
1308 |
+
"save_steps": 500,
|
1309 |
+
"total_flos": 6.140249030814106e+19,
|
1310 |
+
"train_batch_size": 16,
|
1311 |
+
"trial_name": null,
|
1312 |
+
"trial_params": null
|
1313 |
+
}
|