alejndrojavier commited on
Commit
f6a6baa
1 Parent(s): 93e3837

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d41b44a19076dc963906f74db5bad9a0f3a2ed0db603e4434ff773e5c7c7af45
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6352a74e314452393f2a2fcf071c68c935c571007dfbcc47e746cf616a7246a1
3
  size 267832560
tmp-checkpoint-175/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d41b44a19076dc963906f74db5bad9a0f3a2ed0db603e4434ff773e5c7c7af45
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6352a74e314452393f2a2fcf071c68c935c571007dfbcc47e746cf616a7246a1
3
  size 267832560
tmp-checkpoint-175/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0562a8ac51a11d62a677f3eb1664a85a4938de97bf08ee6e3d1263c467d6af0d
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:467810065677088ea64b1a84b5d3872a1458ff620639aee59220366634b1d3ea
3
  size 535727290
tmp-checkpoint-175/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edbd1fa69b76fd64e56c6d8bade26ed0ac2df01ea03ddec54594de558a79cbc0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58ef9a709639d15ce823cbab1c94a327f84302849ffa232663b1d79c1fa4e24
3
  size 14244
tmp-checkpoint-175/trainer_state.json CHANGED
@@ -11,29 +11,29 @@
11
  {
12
  "epoch": 0.29,
13
  "learning_rate": 1.0000000000000002e-06,
14
- "loss": 1.1289,
15
  "step": 50
16
  },
17
  {
18
  "epoch": 0.57,
19
  "learning_rate": 2.0000000000000003e-06,
20
- "loss": 0.9944,
21
  "step": 100
22
  },
23
  {
24
  "epoch": 0.86,
25
  "learning_rate": 3e-06,
26
- "loss": 0.7327,
27
  "step": 150
28
  },
29
  {
30
  "epoch": 1.0,
31
- "eval_accuracy": 0.7728571428571429,
32
- "eval_f1": 0.8712550607287449,
33
- "eval_loss": 0.449686199426651,
34
- "eval_runtime": 10.5768,
35
- "eval_samples_per_second": 66.182,
36
- "eval_steps_per_second": 4.16,
37
  "step": 175
38
  }
39
  ],
 
11
  {
12
  "epoch": 0.29,
13
  "learning_rate": 1.0000000000000002e-06,
14
+ "loss": 0.5522,
15
  "step": 50
16
  },
17
  {
18
  "epoch": 0.57,
19
  "learning_rate": 2.0000000000000003e-06,
20
+ "loss": 0.553,
21
  "step": 100
22
  },
23
  {
24
  "epoch": 0.86,
25
  "learning_rate": 3e-06,
26
+ "loss": 0.5327,
27
  "step": 150
28
  },
29
  {
30
  "epoch": 1.0,
31
+ "eval_accuracy": 0.7685714285714286,
32
+ "eval_f1": 0.8691437802907915,
33
+ "eval_loss": 0.5155649185180664,
34
+ "eval_runtime": 10.9449,
35
+ "eval_samples_per_second": 63.957,
36
+ "eval_steps_per_second": 4.02,
37
  "step": 175
38
  }
39
  ],