AAA01101312 commited on
Commit
ccc96fb
1 Parent(s): 0ba41a9

Training in progress, step 500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a5725d33aa4b34947976af1599fa43b5eed4ad466fd87e83230ea23ec5ae5e
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0cc4778c604548cc03ed426cc23687a92f886997199dd2cf98d6ba3dcdbfe3b
3
  size 268290900
run-4/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34c58a50c849b52be08129cef2729104b91f5ebaf46457436ac0e5ddb0274590
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0cc4778c604548cc03ed426cc23687a92f886997199dd2cf98d6ba3dcdbfe3b
3
  size 268290900
run-4/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d28a1e8094eb6ab9663cd2fb830933ca60972e0ea885d2d509150b1efcbf6e84
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2219825dffd50ded2ac97c5ef392d5520e0cd579c8dac0addd5b05f923a40510
3
  size 536643898
run-4/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4f75fa3851d3548c8bbed0ee7c49e6a23f30f028b074a4398b38c7ecbd0f8e9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a61c60e2a1f354f14fb973803108ea16a9c8c66946147c407c26a5211c4f3d
3
  size 1064
run-4/checkpoint-500/trainer_state.json CHANGED
@@ -10,32 +10,32 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5770967741935484,
14
- "eval_loss": 0.21370309591293335,
15
- "eval_runtime": 12.8644,
16
- "eval_samples_per_second": 240.975,
17
- "eval_steps_per_second": 30.161,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.547938346862793,
23
- "learning_rate": 1.371069182389937e-05,
24
- "loss": 0.3338,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 1590,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 5,
32
  "save_steps": 500,
33
  "total_flos": 130072209152340.0,
34
  "train_batch_size": 48,
35
  "trial_name": null,
36
  "trial_params": {
37
- "alpha": 0.563778668706403,
38
- "num_train_epochs": 5,
39
- "temperature": 9
40
  }
41
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5816129032258065,
14
+ "eval_loss": 0.20736075937747955,
15
+ "eval_runtime": 16.608,
16
+ "eval_samples_per_second": 186.657,
17
+ "eval_steps_per_second": 23.362,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5436314940452576,
23
+ "learning_rate": 1.4758909853249476e-05,
24
+ "loss": 0.3269,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 1908,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 6,
32
  "save_steps": 500,
33
  "total_flos": 130072209152340.0,
34
  "train_batch_size": 48,
35
  "trial_name": null,
36
  "trial_params": {
37
+ "alpha": 0.29589437977264843,
38
+ "num_train_epochs": 6,
39
+ "temperature": 10
40
  }
41
  }
run-4/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d057a00a23fc67cb5b4ec3eb45359ad1e22d036d8b9c623bca41a72fc11b21f5
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e64020ddd316d64701082b74006fdab05b63fbcce34dfc1097dd97f3e6615f
3
  size 5048
runs/May20_10-50-20_MainPC/events.out.tfevents.1716171856.MainPC.254928.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504a135675f20478ae69ff889df2b6a743d1d7b8209b9e1c077969c414fb7b37
3
+ size 13062
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a215e5f7d5c2b9aa91e4a81eec8763769ad92dd6256812ac85d2fcf761390bd
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e64020ddd316d64701082b74006fdab05b63fbcce34dfc1097dd97f3e6615f
3
  size 5048