Hugging Face's logo

tuanna08go
/
a45bc180-e906-4fa6-b3ca-f6bb98da93fb

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
48cf140
·
verified ·
1 Parent(s): 4fe962b

Training in progress, step 13, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +4 -4
  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
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "q_proj",
24
- "down_proj",
25
  "gate_proj",
26
- "v_proj",
27
- "up_proj",
28
  "o_proj",
29
- "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "up_proj",
24
  "q_proj",
 
25
  "gate_proj",
26
+ "k_proj",
27
+ "down_proj",
28
  "o_proj",
29
+ "v_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 sha256:59ea61344014a0373dc0ed189ea530fe586a9c796b2bb6dbebdab67b39df9535
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b0f5bed96cf00d049392da331cbca8684601406c41d238558718b75d1bd117
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d134e651da2fb926245009deb702e447c4e8a1938d59ef8d66f730da7a9393f9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f652dbd18930bab2d6588e7528276f064048e10abc10b227827f3d87c4f45f
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:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3efb11118abf3c106d4bd25c0e5f58b3ac02048b571233f339199d33571abd2
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": 4.74417060037479e-05,
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": 4.74417060037479e-05,
13
  "eval_loss": 1.785589575767517,
14
- "eval_runtime": 611.5762,
15
- "eval_samples_per_second": 14.513,
16
- "eval_steps_per_second": 7.257,
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": 175270199820288.0,
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": 0.0006167421780487227,
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": 4.74417060037479e-05,
13
  "eval_loss": 1.785589575767517,
14
+ "eval_runtime": 614.2354,
15
+ "eval_samples_per_second": 14.45,
16
+ "eval_steps_per_second": 7.225,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.00023720853001873946,
21
+ "grad_norm": 18.565052032470703,
22
+ "learning_rate": 5e-05,
23
+ "loss": 7.3014,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.00047441706003747893,
28
+ "grad_norm": 11.056122779846191,
29
+ "learning_rate": 0.0001,
30
+ "loss": 6.3042,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.00047441706003747893,
35
+ "eval_loss": 1.4843670129776,
36
+ "eval_runtime": 616.7874,
37
+ "eval_samples_per_second": 14.391,
38
+ "eval_steps_per_second": 7.195,
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": 2541417897394176.0,
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 sha256:0c2ae09ea5817d2cf48e15303dc40d7f66ac25e2bacaf2e1652d1e5bbbee3768
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd1b1b9519a418f55b9c0f9260090cf3b98b427e547e38f4b7b7f93ae8ee0a0
3
  size 6776