Hugging Face's logo

duyphu
/
2c4bec72-b234-4f54-9315-a44be468a024

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
d2244f3
·
verified ·
1 Parent(s): 2c95e33

Training in progress, step 13, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +2 -2
  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
@@ -21,11 +21,11 @@
21
  "revision": null,
22
  "target_modules": [
23
  "v_proj",
24
- "up_proj",
25
- "down_proj",
26
  "q_proj",
 
27
  "k_proj",
28
  "gate_proj",
 
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
21
  "revision": null,
22
  "target_modules": [
23
  "v_proj",
 
 
24
  "q_proj",
25
+ "up_proj",
26
  "k_proj",
27
  "gate_proj",
28
+ "down_proj",
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ab88f621229288ca6a54ad30b9fc94489abcccb5b8b08ae668350936ce5908
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1aad19b5d49a9866dc0c9a53950982df6aaf4bdd385ff67266d4f7c02cbd89
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91ca086d3d55ed13afffcdf74afef91b778bf3fbb27034490bc5b9ce38eb7be7
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0903a358b479588deae139482268c6735086a05a3e1a0180957df368d2ce5b1
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
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": 0.00011327914814080598,
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": 0.00011327914814080598,
13
  "eval_loss": 10.371950149536133,
14
- "eval_runtime": 23.8998,
15
- "eval_samples_per_second": 155.524,
16
- "eval_steps_per_second": 77.783,
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": 22629089280.0,
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": 0.0014726289258304777,
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": 0.00011327914814080598,
13
  "eval_loss": 10.371950149536133,
14
+ "eval_runtime": 23.6823,
15
+ "eval_samples_per_second": 156.953,
16
+ "eval_steps_per_second": 78.498,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0005663957407040299,
21
+ "grad_norm": 0.03484996780753136,
22
+ "learning_rate": 5e-05,
23
+ "loss": 10.3711,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0011327914814080599,
28
+ "grad_norm": 0.03236381709575653,
29
+ "learning_rate": 0.0001,
30
+ "loss": 10.3752,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0011327914814080599,
35
+ "eval_loss": 10.371683120727539,
36
+ "eval_runtime": 23.7061,
37
+ "eval_samples_per_second": 156.795,
38
+ "eval_steps_per_second": 78.419,
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": 300643614720.0,
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 sha256:0c97483435c7ab10484c3ca6faa8a5c6d6d8d4f20b487b8282c7cc87235be4fc
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e800d2d7b2e89082fbacfe6dae17becb71257bbe015e2619e98f27d7545ee7
3
  size 6776