ninagroot commited on
Commit
37dea36
·
verified ·
1 Parent(s): a4a9d15

ninagroot/Llama-360Mtest

Browse files
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 5.8561
17
 
18
  ## Model description
19
 
@@ -36,24 +36,21 @@ The following hyperparameters were used during training:
36
  - train_batch_size: 16
37
  - eval_batch_size: 8
38
  - seed: 42
39
- - gradient_accumulation_steps: 2
40
- - total_train_batch_size: 32
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 100
44
- - num_epochs: 6
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 1.0 | 7 | 9.1363 |
52
- | No log | 2.0 | 14 | 7.9096 |
53
- | 8.079 | 3.0 | 21 | 7.2609 |
54
- | 8.079 | 4.0 | 28 | 6.7298 |
55
- | 8.079 | 5.0 | 35 | 6.3046 |
56
- | 5.3833 | 6.0 | 42 | 5.8561 |
57
 
58
 
59
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 9.4293
17
 
18
  ## Model description
19
 
 
36
  - train_batch_size: 16
37
  - eval_batch_size: 8
38
  - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 128
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 100
44
+ - num_epochs: 4
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.57 | 1 | 9.6426 |
52
+ | No log | 1.71 | 3 | 9.5332 |
53
+ | No log | 2.29 | 4 | 9.4293 |
 
 
 
54
 
55
 
56
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5314de0e6bae78b3e90a94d54ab98a610b929655649ce1c000ac275ddfeb18b3
3
  size 1408774432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a3367f2f2c17f2b23c5fdc4c8cfd7f784410e25e40151b285fbaea9e5b607c
3
  size 1408774432
runs/Apr16_10-43-51_gcn8.local.snellius.surf.nl/events.out.tfevents.1713257040.gcn8.local.snellius.surf.nl.2086007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1579d42ec94a320564337e755525b5e7bc43d8075121c6db34b877c4eef1e52
3
+ size 5708
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bcf0dc28dac8adfaff8556279cd6e376bd5cd0b28004cded240c3c22f00164d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabbb15f87119364a944aca12e21e49592f86b20f544a151141eb7c96a6a0714
3
  size 4984