Hugging Face's logo

duyphu
/
226aab2f-efc7-745f-3ff1-5dc599d63b39

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
e851977
·
verified ·
1 Parent(s): b3bb411

Training in progress, step 13, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +3 -3
  2. last-checkpoint/adapter_model.safetensors +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +32 -10
  7. last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "gate_proj",
24
- "o_proj",
 
25
  "down_proj",
26
  "v_proj",
27
  "up_proj",
28
- "q_proj",
29
- "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "gate_proj",
24
+ "k_proj",
25
+ "q_proj",
26
  "down_proj",
27
  "v_proj",
28
  "up_proj",
29
+ "o_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0093aea21c9e3c9365b75a1416e59ff350c6d394a362ea2723d0ccd29dd227b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44ceb0136c9fb0050e50b3a8fa358caebdfcd433272d0f1d0124d594f48e725
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21dc7d8e0e51055cdc8f9352d8dca9b7d88a22e970523b6e05b349ef611ad23a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fc2d0d02471945483c14ae550677f016d9e8c6a8106ef187edabc89b67e1df
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e4a030d5f2a011fddc5fea81bb79de52b6e53d28e163c3a1aa9f9ecc15a84d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.00014304616815077065,
5
- "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,17 +11,39 @@
11
  {
12
  "epoch": 0.00014304616815077065,
13
  "eval_loss": 0.6253636479377747,
14
- "eval_runtime": 324.9172,
15
- "eval_samples_per_second": 9.061,
16
- "eval_steps_per_second": 4.53,
17
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 5,
21
- "max_steps": 1,
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
- "save_steps": 1,
25
  "stateful_callbacks": {
26
  "TrainerControl": {
27
  "args": {
@@ -29,12 +51,12 @@
29
  "should_evaluate": false,
30
  "should_log": false,
31
  "should_save": true,
32
- "should_training_stop": true
33
  },
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 369912849629184.0,
38
  "train_batch_size": 2,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0018596001859600185,
5
+ "eval_steps": 10,
6
+ "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.00014304616815077065,
13
  "eval_loss": 0.6253636479377747,
14
+ "eval_runtime": 324.4199,
15
+ "eval_samples_per_second": 9.075,
16
+ "eval_steps_per_second": 4.537,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0007152308407538533,
21
+ "grad_norm": 0.3303487300872803,
22
+ "learning_rate": 5e-05,
23
+ "loss": 0.6582,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0014304616815077067,
28
+ "grad_norm": 0.3911873698234558,
29
+ "learning_rate": 0.0001,
30
+ "loss": 0.5993,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0014304616815077067,
35
+ "eval_loss": 0.6021842360496521,
36
+ "eval_runtime": 326.4286,
37
+ "eval_samples_per_second": 9.019,
38
+ "eval_steps_per_second": 4.509,
39
+ "step": 10
40
  }
41
  ],
42
  "logging_steps": 5,
43
+ "max_steps": 50,
44
  "num_input_tokens_seen": 0,
45
  "num_train_epochs": 1,
46
+ "save_steps": 13,
47
  "stateful_callbacks": {
48
  "TrainerControl": {
49
  "args": {
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": false
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 4115280452124672.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:867c18c5fd92f7824a558e462f8e2af6586399e20e27e9f5fb5ee685d77041e5
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbabf14d64cabaaba277772c0488f57f6ff57505994b75cc9f3f7307cfc075a6
3
  size 6776