KajetanFrackowiak commited on
Commit
1a15c25
1 Parent(s): 151f926

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:e61dacee65d7563d42796ee90156a4c818d2d5b185a0bdd7adda79a5c9cd5604
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c85b42126896ca0a309e576edad67efd01ee7456c9094190b7090f8d41a2ef7
3
  size 268290900
run-1/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9babdd0e7820be9acca6aab028672af74ef1ed5b0ad723e9578c25013f9ed6b1
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c85b42126896ca0a309e576edad67efd01ee7456c9094190b7090f8d41a2ef7
3
  size 268290900
run-1/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eca0d7554df388c74d4cbe0ff9bac830adbf507fec66eee2ca09bf5063945e14
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceee4e6d26ac071575a4325cfbdb5bd8ca8b004453847f70bbd93c751f5b509
3
  size 536643898
run-1/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e1264523e958cf7990dc5f42d876cc12129475c4603804cf66868aaf25c2c24
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90dc4637e972cc69c745eebddd8a7560dca27d2318df3e23f8e145abbf236536
3
  size 1064
run-1/checkpoint-500/trainer_state.json CHANGED
@@ -12,23 +12,23 @@
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0064516129032258064,
14
  "eval_loss": NaN,
15
- "eval_runtime": 5.3104,
16
- "eval_samples_per_second": 583.757,
17
- "eval_steps_per_second": 12.24,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 94451.3046875,
23
- "learning_rate": 1.371069182389937e-05,
24
  "loss": 0.0,
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
  "stateful_callbacks": {
34
  "TrainerControl": {
@@ -46,8 +46,8 @@
46
  "train_batch_size": 48,
47
  "trial_name": null,
48
  "trial_params": {
49
- "alpha": 0.16176343022645268,
50
- "num_train_epochs": 5,
51
- "temperature": 12
52
  }
53
  }
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0064516129032258064,
14
  "eval_loss": NaN,
15
+ "eval_runtime": 5.354,
16
+ "eval_samples_per_second": 579.009,
17
+ "eval_steps_per_second": 12.141,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 143768.90625,
23
+ "learning_rate": 1.606918238993711e-05,
24
  "loss": 0.0,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 2544,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 8,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 48,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.41600283894248313,
50
+ "num_train_epochs": 8,
51
+ "temperature": 20
52
  }
53
  }
run-1/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:294e8e48bc1549edad3189588f706dce11934ea0b8d7c455022c6664ea0826eb
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6722fa4d4cd319ee6d313948dfb65a13aa608029a7cedd96bdd0a50d4d1c279
3
  size 5304
runs/Nov11_11-16-16_921d9136ef3a/events.out.tfevents.1731325170.921d9136ef3a.798.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33900cfb728310283b0f933b19d8d43fe2fd6a6518b00893ce90604c78d6c4d
3
+ size 13277
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43bd7cfd55720aa0e94faf0c4ced4f0bf32323b22dee95376cb1f23d04dc327c
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6722fa4d4cd319ee6d313948dfb65a13aa608029a7cedd96bdd0a50d4d1c279
3
  size 5304