timewanderer commited on
Commit
8493d01
1 Parent(s): 56831b2

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:db7b0ba484d365a8232c614da6b35c1ca8564e014b51324208c27b61981f817d
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
3
  size 268290900
run-3/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10caa747cc9b055b61da3a870005eb9854639faf1659a2954a7623865e788ced
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
3
  size 268290900
run-3/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9ccfb4b4789f10457afb99b1aabd35c5ff0b1a3606c647f48c026ef9e8352d6
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdf97ee43485482022c7936b134134b1d804f6bddceb5646e66726f0d638653
3
  size 536643898
run-3/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c794bc4c67ef18245dd516031ce405ab557e4d551d225d8dd1e1abc0f2be8e33
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
3
  size 1064
run-3/checkpoint-1000/trainer_state.json CHANGED
@@ -10,50 +10,50 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5803225806451613,
14
- "eval_loss": 0.19005867838859558,
15
- "eval_runtime": 5.674,
16
- "eval_samples_per_second": 546.354,
17
- "eval_steps_per_second": 11.456,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5149380564689636,
23
- "learning_rate": 1.685534591194969e-05,
24
- "loss": 0.3072,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.817741935483871,
30
- "eval_loss": 0.0924694836139679,
31
- "eval_runtime": 6.0294,
32
- "eval_samples_per_second": 514.15,
33
- "eval_steps_per_second": 10.781,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8770967741935484,
39
- "eval_loss": 0.06209348514676094,
40
- "eval_runtime": 5.7978,
41
- "eval_samples_per_second": 534.685,
42
- "eval_steps_per_second": 11.211,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.4281909167766571,
48
- "learning_rate": 1.371069182389937e-05,
49
- "loss": 0.1072,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
- "max_steps": 3180,
55
  "num_input_tokens_seen": 0,
56
- "num_train_epochs": 10,
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": 0.7637668053146042,
75
- "num_train_epochs": 10,
76
- "temperature": 18
77
  }
78
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6083870967741936,
14
+ "eval_loss": 0.26111724972724915,
15
+ "eval_runtime": 5.392,
16
+ "eval_samples_per_second": 574.924,
17
+ "eval_steps_per_second": 12.055,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.612690269947052,
23
+ "learning_rate": 1.371069182389937e-05,
24
+ "loss": 0.4067,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8261290322580646,
30
+ "eval_loss": 0.1251312643289566,
31
+ "eval_runtime": 5.4108,
32
+ "eval_samples_per_second": 572.929,
33
+ "eval_steps_per_second": 12.013,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8719354838709678,
39
+ "eval_loss": 0.08443494886159897,
40
+ "eval_runtime": 5.5128,
41
+ "eval_samples_per_second": 562.324,
42
+ "eval_steps_per_second": 11.791,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5761224031448364,
48
+ "learning_rate": 7.421383647798742e-06,
49
+ "loss": 0.1453,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 1590,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 5,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
 
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
+ "alpha": 0.4777308452793029,
75
+ "num_train_epochs": 5,
76
+ "temperature": 4
77
  }
78
  }
run-3/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ceb3fabcbf71cb66944e6d8ec61e55f12751f2e6805da39ec868f61cfabfda
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef5b259539127ef5ddc697d31b7e7180caca610f845f70ff2cba869a6149cf5
3
  size 5240
runs/Oct12_05-09-37_f46fcd247c16/events.out.tfevents.1728711874.f46fcd247c16.522.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ff40c380c71915c17772c8a71048733e75150efcceefff845f22247d3166e13
3
- size 13621
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d802ac01f6c2352b30e80ad15674bc6de269c70f80ea0a9a406db7e8587b62b
3
+ size 14366