maximuspowers commited on
Commit
5caff6d
·
verified ·
1 Parent(s): f7fd7e9

Training in progress, step 500

Browse files
all_results.json CHANGED
@@ -1,5 +1,17 @@
1
  {
2
  "epoch": 5.0,
 
 
 
 
 
 
 
 
 
 
 
 
3
  "total_flos": 0.0,
4
  "train_loss": 1.6828109741210937,
5
  "train_runtime": 29.5351,
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_exact_match_accuracy": 0.2,
4
+ "eval_hamming_loss": 0.075,
5
+ "eval_loss": 0.8420153856277466,
6
+ "eval_macro_f1": 0.09192664920219099,
7
+ "eval_macro_precision": 0.09243697478991597,
8
+ "eval_macro_recall": 0.09215686274509804,
9
+ "eval_micro_f1": 0.4,
10
+ "eval_micro_precision": 0.6071428571428571,
11
+ "eval_micro_recall": 0.2982456140350877,
12
+ "eval_runtime": 0.2221,
13
+ "eval_samples_per_second": 180.125,
14
+ "eval_steps_per_second": 13.509,
15
  "total_flos": 0.0,
16
  "train_loss": 1.6828109741210937,
17
  "train_runtime": 29.5351,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b28070514a109f4c6d0cc6bd89ef87ea76348c26aa37d820b2eae9f6195c9738
3
  size 441154988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d090d5e2966f2091768ffc79be690bc37433eae61a697aae158a43c8f2c1826
3
  size 441154988
runs/Jun15_00-38-20_92b2e0e6fb20/events.out.tfevents.1749947964.92b2e0e6fb20.2194.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c3147ab3f0cf9d900aafcf566f061e709215d31fd0c96edc7852d2af79588d
3
+ size 3776
runs/Jun15_00-40-18_92b2e0e6fb20/events.out.tfevents.1749948019.92b2e0e6fb20.2194.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88e4afb6c8a434d92c19def97557910319f634b24c709e67acb9de318f8594f
3
+ size 22648
test_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_exact_match_accuracy": 0.2,
4
+ "eval_hamming_loss": 0.075,
5
+ "eval_loss": 0.8420153856277466,
6
+ "eval_macro_f1": 0.09192664920219099,
7
+ "eval_macro_precision": 0.09243697478991597,
8
+ "eval_macro_recall": 0.09215686274509804,
9
+ "eval_micro_f1": 0.4,
10
+ "eval_micro_precision": 0.6071428571428571,
11
+ "eval_micro_recall": 0.2982456140350877,
12
+ "eval_runtime": 0.2221,
13
+ "eval_samples_per_second": 180.125,
14
+ "eval_steps_per_second": 13.509
15
+ }
trainer_state.json CHANGED
@@ -12,40 +12,40 @@
12
  {
13
  "epoch": 0,
14
  "step": 0,
15
- "train/classification_loss": 0.6832770109176636,
16
- "train/contrastive_loss": 7.157876014709473,
17
- "train/negative_loss": 7.157375812530518,
18
  "train/num_negatives": 190,
19
  "train/num_positives": 50,
20
- "train/positive_loss": 0.0005001117824576795,
21
- "train/total_loss": 2.1148521900177
22
  },
23
  {
24
  "epoch": 0,
25
  "step": 0,
26
- "train/classification_loss": 0.691846489906311,
27
- "train/contrastive_loss": 6.978695392608643,
28
- "train/negative_loss": 6.977847576141357,
29
  "train/num_negatives": 192,
30
  "train/num_positives": 48,
31
- "train/positive_loss": 0.0008476818911731243,
32
- "train/total_loss": 2.08758544921875
33
  },
34
  {
35
  "epoch": 5.0,
36
- "grad_norm": 9.853194236755371,
37
  "learning_rate": 9.800000000000001e-06,
38
- "loss": 2.9901,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 5.0,
43
  "step": 50,
44
  "total_flos": 0.0,
45
- "train_loss": 2.9900537109375,
46
- "train_runtime": 27.9302,
47
- "train_samples_per_second": 56.57,
48
- "train_steps_per_second": 1.79
49
  }
50
  ],
51
  "logging_steps": 50,
 
12
  {
13
  "epoch": 0,
14
  "step": 0,
15
+ "train/classification_loss": 0.6251798272132874,
16
+ "train/contrastive_loss": 1.386080265045166,
17
+ "train/negative_loss": 1.1070373058319092,
18
  "train/num_negatives": 190,
19
  "train/num_positives": 50,
20
+ "train/positive_loss": 0.27904292941093445,
21
+ "train/total_loss": 0.9023958444595337
22
  },
23
  {
24
  "epoch": 0,
25
  "step": 0,
26
+ "train/classification_loss": 0.6276130080223083,
27
+ "train/contrastive_loss": 1.6681630611419678,
28
+ "train/negative_loss": 1.269258737564087,
29
  "train/num_negatives": 192,
30
  "train/num_positives": 48,
31
+ "train/positive_loss": 0.39890438318252563,
32
+ "train/total_loss": 0.9612456560134888
33
  },
34
  {
35
  "epoch": 5.0,
36
+ "grad_norm": 10.065888404846191,
37
  "learning_rate": 9.800000000000001e-06,
38
+ "loss": 1.6828,
39
  "step": 50
40
  },
41
  {
42
  "epoch": 5.0,
43
  "step": 50,
44
  "total_flos": 0.0,
45
+ "train_loss": 1.6828109741210937,
46
+ "train_runtime": 29.5351,
47
+ "train_samples_per_second": 53.496,
48
+ "train_steps_per_second": 1.693
49
  }
50
  ],
51
  "logging_steps": 50,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02a3dbfbd9db3f1e4a919c78948efb8eb944344dc26585f19fc5dded995095b
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e2d330b9dd8fe925b85bea0db478c22579b7da080ec4cac0c4183a4c7358e0
3
  size 5368