Hugging Face's logo

pyamy
/
llama2-7b-backward-lora

Text Generation
PEFT
Safetensors
Transformers
lora
Model card Files
xet
Community
pyamy commited on
Commit
2e1ceba
·
verified ·
1 Parent(s): 7b47490

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. checkpoint-50/adapter_config.json +3 -3
  4. checkpoint-50/adapter_model.safetensors +1 -1
  5. checkpoint-50/optimizer.pt +1 -1
  6. checkpoint-50/scaler.pt +1 -1
  7. checkpoint-50/scheduler.pt +1 -1
  8. checkpoint-50/trainer_state.json +14 -14
  9. checkpoint-50/training_args.bin +1 -1
  10. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -25,10 +25,10 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "o_proj",
30
  "q_proj",
31
- "k_proj"
 
 
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
28
  "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616d027fb005edff9745e7c771538e7da2b03596707bad0242163b2fc606ad11
3
  size 33588528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bc3ecfc964e633b395cf812586870c7cc362c3ed21ac4c7b593874543c7975
3
  size 33588528
checkpoint-50/adapter_config.json CHANGED
@@ -25,10 +25,10 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "o_proj",
30
  "q_proj",
31
- "k_proj"
 
 
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
 
 
28
  "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "trainable_token_indices": null,
checkpoint-50/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616d027fb005edff9745e7c771538e7da2b03596707bad0242163b2fc606ad11
3
  size 33588528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bc3ecfc964e633b395cf812586870c7cc362c3ed21ac4c7b593874543c7975
3
  size 33588528
checkpoint-50/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a580fd932e1b65d83e870d30e92e823e851317b9f942cefdcc0d34b4aac5f263
3
  size 17338708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38322fa67c0cd9b4bea2f8ed1ea3fa702cf1c76a8e623fe2b4b4468e581047b2
3
  size 17338708
checkpoint-50/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4a0e99f2cd8a3b5675a350b3b4e3d065c31530d1da439f4d4e2562f4cf72cd2
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16548743276424cd66e7996bdcfd2223400028fb58a78b40458f14aa4250dd8
3
  size 988
checkpoint-50/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc546be0326b4a0b2e6a212bb8589b29ecc3eb77870dc69fdc4706bbcece8bf2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55a3b0f2ba55e355a29b19063f461fa9b5392d5c673dcc7784da8b9c5691fb1f
3
  size 1064
checkpoint-50/trainer_state.json CHANGED
@@ -11,37 +11,37 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.16,
14
- "grad_norm": 41.431053161621094,
15
  "learning_rate": 0.00012,
16
- "loss": 33.6557,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.32,
21
- "grad_norm": 7.633413314819336,
22
- "learning_rate": 0.00017,
23
- "loss": 13.5995,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.48,
28
- "grad_norm": 0.17992551624774933,
29
- "learning_rate": 0.00012,
30
- "loss": 0.1692,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 0.64,
35
- "grad_norm": 0.11148593574762344,
36
- "learning_rate": 7e-05,
37
- "loss": 0.1384,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 0.8,
42
- "grad_norm": 0.11761105805635452,
43
- "learning_rate": 2e-05,
44
- "loss": 0.115,
45
  "step": 50
46
  }
47
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.16,
14
+ "grad_norm": NaN,
15
  "learning_rate": 0.00012,
16
+ "loss": 33.5024,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.32,
21
+ "grad_norm": 8.700640678405762,
22
+ "learning_rate": 0.000175,
23
+ "loss": 16.2186,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.48,
28
+ "grad_norm": 0.22131234407424927,
29
+ "learning_rate": 0.000125,
30
+ "loss": 0.1905,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 0.64,
35
+ "grad_norm": 0.11870493739843369,
36
+ "learning_rate": 7.500000000000001e-05,
37
+ "loss": 0.1386,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 0.8,
42
+ "grad_norm": 0.1110013872385025,
43
+ "learning_rate": 2.5e-05,
44
+ "loss": 0.1143,
45
  "step": 50
46
  }
47
  ],
checkpoint-50/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f0bc7579225e5bda2d02e3f9ab438477eceb2e35462a762b5f86825bd52af8
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f60acf5fc471590e2b4ac63d9c481ed856618b1b406e6a68b2ac2ff182d6d1
3
  size 5304
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f0bc7579225e5bda2d02e3f9ab438477eceb2e35462a762b5f86825bd52af8
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f60acf5fc471590e2b4ac63d9c481ed856618b1b406e6a68b2ac2ff182d6d1
3
  size 5304