Hugging Face's logo

Adanato
/
llama_finetuned_diverseset-base-entropy

PEFT
Safetensors
Model card Files Community
Adanato commited on
Commit
5482179
·
1 Parent(s): 90f4a6f

2 epochs

Browse files
Files changed (11) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. optimizer.bin +1 -1
  4. pytorch_model_fsdp.bin +1 -1
  5. rng_state_0.pth +1 -1
  6. rng_state_1.pth +1 -1
  7. rng_state_2.pth +3 -0
  8. rng_state_3.pth +3 -0
  9. scheduler.pt +1 -1
  10. trainer_state.json +6 -31
  11. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "down_proj",
27
  "gate_proj",
 
28
  "q_proj",
29
  "k_proj",
30
- "v_proj",
31
  "up_proj",
32
- "o_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "gate_proj",
27
+ "o_proj",
28
  "q_proj",
29
  "k_proj",
 
30
  "up_proj",
31
+ "v_proj",
32
+ "down_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18f8196935ffa730d7beab425af09839e2f3a37ea0ab54586a37a05abbc055e4
3
  size 828526568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3e2df3bd5c9ac678c0a760d452f1539fc543b7595ac5e86475ad9f8743f714
3
  size 828526568
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab3454aec70d93534cbaef6d45e8eac954431896fa370c8b7aebe140463cc1a4
3
  size 1657755122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514a514ef78516aa57bf0b7790ee8ee7e731c8efb406bee2d1941151352f7fa1
3
  size 1657755122
pytorch_model_fsdp.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:392cfc6f2fbaf927236b942eeb00f510a4b001e0e186148d37cb48989a1d756c
3
  size 828793718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbdcdd6228e084a487fb92e7a8755c3c34709cd8ab73a438d366685aa4e231b
3
  size 828793718
rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b502bbb8f5bb58cc253485137025eb50baf1d0517cd1ee00cd28c40e1a9cddef
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a4a9cd007b8617763f9005c6e22738380d8b580b52101a1bf9c59664e8d993
3
  size 15024
rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80bf41dc4fdd47ffef5c685e789dec2e18b0176b51fe864faba61bb61375c5b4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48286aef07e9bb6579f9f3e39a4fbfb7902ec9833db787e6611bdd49f08045ad
3
  size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bdb2bf9730ba493051e3d3fef0f436afd714d8119060ca1006d1fcb5101826
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd55eb9c5a8767f6f9bf7184e9cb4afb5ad8d6d5680d74f62ae398098bd0611f
3
+ size 15024
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4c4bf030a043b5793570ddca57982299259411348cfc6ad2d7ebf9e0e03c45
3
  size 1064
trainer_state.json CHANGED
@@ -1,42 +1,17 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 7.533333333333333,
5
  "eval_steps": 500,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 2.533333333333333,
13
- "grad_norm": 0.13746494054794312,
14
- "learning_rate": 0.00015000000000000001,
15
- "loss": 1.2377,
16
- "mean_token_accuracy": 0.7695108048225704,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 5.0,
21
- "grad_norm": 0.09443415701389313,
22
- "learning_rate": 5.000000000000002e-05,
23
- "loss": 0.9059,
24
- "mean_token_accuracy": 0.8102362244515806,
25
- "step": 20
26
- },
27
- {
28
- "epoch": 7.533333333333333,
29
- "grad_norm": 0.06916765123605728,
30
- "learning_rate": 0.0,
31
- "loss": 0.8402,
32
- "mean_token_accuracy": 0.8208924665262824,
33
- "step": 30
34
- }
35
- ],
36
  "logging_steps": 10,
37
- "max_steps": 30,
38
  "num_input_tokens_seen": 0,
39
- "num_train_epochs": 10,
40
  "save_steps": 500,
41
  "stateful_callbacks": {
42
  "TrainerControl": {
@@ -50,7 +25,7 @@
50
  "attributes": {}
51
  }
52
  },
53
- "total_flos": 1.5998749419503616e+17,
54
  "train_batch_size": 2,
55
  "trial_name": null,
56
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
+ "log_history": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "logging_steps": 10,
12
+ "max_steps": 2,
13
  "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 2,
15
  "save_steps": 500,
16
  "stateful_callbacks": {
17
  "TrainerControl": {
 
25
  "attributes": {}
26
  }
27
  },
28
+ "total_flos": 1.0764220983410688e+16,
29
  "train_batch_size": 2,
30
  "trial_name": null,
31
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:154a667582f87fb846fb692f77282d08c6276f02ecd8bc2ad0a76014e4c454a9
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c4aaa4c52101559ee2c28555e99779038d7f4bf172ebabf5f25d22208cbc1c
3
  size 5816