KajetanFrackowiak commited on
Commit
6c244bb
1 Parent(s): 002ed92

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 sha256:181452760f4889fb1745514a4de50facf35adde53641198d68d40c6fbe42eedd
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536a9ee9dbd08b8bea86c191c81974e31d8a0e16ae6bbd22d8d46671d81d979f
3
  size 268290900
run-0/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a194f282a8e26a82bdd7689de4ddd97047d74d6654d320f8165769f7cfc9e7e
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536a9ee9dbd08b8bea86c191c81974e31d8a0e16ae6bbd22d8d46671d81d979f
3
  size 268290900
run-0/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840b1da7c52d28aa7b4f6363df9c82058fd60b6d6f5e71f0fc59cf76d7a8a537
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca008170f003086187085e4b127eb79f43d1ad57ec964b34016be0a9d9a2d638
3
  size 536643898
run-0/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e744277c61f87520794334442fae36c5f9ff6e10cb79d4bfee5176ca7eafe2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98041bd7cae455426e290a1a0ee683bd5dd30893f7451fec3a464ae8995b17e4
3
  size 1064
run-0/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": 6.5628,
16
- "eval_samples_per_second": 472.357,
17
- "eval_steps_per_second": 9.904,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 98073.078125,
23
- "learning_rate": 1.550763701707098e-05,
24
  "loss": 0.0,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 2226,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 7,
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": 0.8432205176909278,
50
- "num_train_epochs": 7,
51
- "temperature": 11
52
  }
53
  }
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.0064516129032258064,
14
  "eval_loss": NaN,
15
+ "eval_runtime": 5.5627,
16
+ "eval_samples_per_second": 557.281,
17
+ "eval_steps_per_second": 11.685,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 107346.4609375,
23
+ "learning_rate": 1.650593990216632e-05,
24
  "loss": 0.0,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 2862,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 9,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 48,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.3670751935915354,
50
+ "num_train_epochs": 9,
51
+ "temperature": 12
52
  }
53
  }
run-0/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad31fffd4fa44dd29a691ca02fcda24b9b44f781e4b5cd32cce386bafd2786f9
3
- size 692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43bd7cfd55720aa0e94faf0c4ced4f0bf32323b22dee95376cb1f23d04dc327c
3
+ size 5304
runs/Nov11_11-16-16_921d9136ef3a/events.out.tfevents.1731324503.921d9136ef3a.798.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a33980fa02e25e4dda3fb46372a4e82d6e32e9f3f75b6e787811542cbd1683b
3
+ size 13314
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec6111867615c93bfb47766b6ed7ec39e891bc98f3bcc0627eaef3c0f74cc0e4
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43bd7cfd55720aa0e94faf0c4ced4f0bf32323b22dee95376cb1f23d04dc327c
3
  size 5304