timewanderer commited on
Commit
a644663
1 Parent(s): 58bc6e1

Training in progress, step 1000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898cdf11d05981397287e11c7ef9415fbedfe915715e9c683335b09571b423e2
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef3d7b0babe94fa5166a9ac6f9db248a8c3aed522dd161e1d5841de8689beec
3
  size 268290900
run-0/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e0cab5051b745bbff2c6f300950be47171d04cd55ac0981e34e49b0a0ce0a8
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef3d7b0babe94fa5166a9ac6f9db248a8c3aed522dd161e1d5841de8689beec
3
  size 268290900
run-0/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c8049bb9511176abe9222ac241ddec6f82827513d445a59bd77224da171544d
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3846e1108a24cbd21e60e75fb69347d910affcbcc9e8b69193ba6cb0161346d7
3
  size 536643898
run-0/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:045cf4abe065257226fe11ac1a91dfd4c5b953cb2366365ef8bb18b4cf33e734
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9da1cbe846856af516cf037dd225e7f48e2737ef84c42a9bee0753b8c140ef
3
  size 1064
run-0/checkpoint-1000/trainer_state.json CHANGED
@@ -10,50 +10,50 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5796774193548387,
14
- "eval_loss": 0.19598601758480072,
15
- "eval_runtime": 5.7949,
16
- "eval_samples_per_second": 534.952,
17
- "eval_steps_per_second": 11.217,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5235025882720947,
23
- "learning_rate": 1.606918238993711e-05,
24
- "loss": 0.3143,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8158064516129032,
30
- "eval_loss": 0.096437968313694,
31
- "eval_runtime": 5.8632,
32
- "eval_samples_per_second": 528.722,
33
- "eval_steps_per_second": 11.086,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8754838709677419,
39
- "eval_loss": 0.06548532098531723,
40
- "eval_runtime": 5.6772,
41
- "eval_samples_per_second": 546.048,
42
- "eval_steps_per_second": 11.449,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.44506680965423584,
48
- "learning_rate": 1.2138364779874214e-05,
49
- "loss": 0.1116,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
- "max_steps": 2544,
55
  "num_input_tokens_seen": 0,
56
- "num_train_epochs": 8,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
@@ -71,8 +71,8 @@
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
- "alpha": 0.2580849577581932,
75
- "num_train_epochs": 8,
76
- "temperature": 14
77
  }
78
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.603225806451613,
14
+ "eval_loss": 0.23406817018985748,
15
+ "eval_runtime": 5.1784,
16
+ "eval_samples_per_second": 598.637,
17
+ "eval_steps_per_second": 12.552,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.57925945520401,
23
+ "learning_rate": 1.550763701707098e-05,
24
+ "loss": 0.3716,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8309677419354838,
30
+ "eval_loss": 0.1094982922077179,
31
+ "eval_runtime": 5.4255,
32
+ "eval_samples_per_second": 571.371,
33
+ "eval_steps_per_second": 11.98,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8819354838709678,
39
+ "eval_loss": 0.07135984301567078,
40
+ "eval_runtime": 5.3165,
41
+ "eval_samples_per_second": 583.086,
42
+ "eval_steps_per_second": 12.226,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5091490149497986,
48
+ "learning_rate": 1.101527403414196e-05,
49
+ "loss": 0.1274,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 2226,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 7,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
 
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
+ "alpha": 0.6968668210901579,
75
+ "num_train_epochs": 7,
76
+ "temperature": 5
77
  }
78
  }
run-0/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa272c0492b3901fc1a76322efd782d0609261ca66d80f909b4731c779116aae
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30bdc23a7d8fb386178e976baa34d55beb56c6ffba63fe636be670468d00efc1
3
  size 5240
runs/Oct12_05-09-37_f46fcd247c16/events.out.tfevents.1728710432.f46fcd247c16.522.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:741f204fdb387b746ca3c038a107c47fb4d4c620e16263f427edec93f80374d0
3
- size 12975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9146608885308ae52b893829ab25f389758fd06bd5b244595e0881410b759737
3
+ size 13832