Hugging Face's logo

chauhoang
/
6dc5c693-bd8b-469b-8884-71b4941f4e88

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
3769a5b
·
verified ·
1 Parent(s): 231e7b5

Training in progress, step 13, checkpoint

Browse files
Files changed (7) hide show
  1. last-checkpoint/adapter_config.json +5 -5
  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
- "v_proj",
24
- "q_proj",
25
- "k_proj",
26
  "o_proj",
 
 
27
  "gate_proj",
28
- "up_proj",
29
- "down_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "o_proj",
24
+ "k_proj",
25
+ "q_proj",
26
  "gate_proj",
27
+ "v_proj",
28
+ "down_proj",
29
+ "up_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:e0ba41007ea06161ccd7f845e5d184a074a53a7c7a3f734c7e89590f005d012e
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fe3439283869835102253292681b5d21925c75a62e6bb88f7bea4cea90d417
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ca20accb7f6defc91c896e7318cb8cf1e90c6cd8554a07a200006153efec117
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7df2ad93809b6bc1feccee5a266c961f1d1ed1d07d59b2b8c69607dbb756d1
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
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": 0.0036496350364963502,
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": 0.0036496350364963502,
13
  "eval_loss": 8.032208442687988,
14
- "eval_runtime": 6.4289,
15
- "eval_samples_per_second": 18.044,
16
- "eval_steps_per_second": 9.022,
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": 50009733070848.0,
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": 0.04744525547445255,
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": 0.0036496350364963502,
13
  "eval_loss": 8.032208442687988,
14
+ "eval_runtime": 6.3647,
15
+ "eval_samples_per_second": 18.225,
16
+ "eval_steps_per_second": 9.113,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.01824817518248175,
21
+ "grad_norm": 11.895684242248535,
22
+ "learning_rate": 5e-05,
23
+ "loss": 7.7326,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0364963503649635,
28
+ "grad_norm": 12.489108085632324,
29
+ "learning_rate": 0.0001,
30
+ "loss": 6.1782,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0364963503649635,
35
+ "eval_loss": 4.179005146026611,
36
+ "eval_runtime": 6.3854,
37
+ "eval_samples_per_second": 18.166,
38
+ "eval_steps_per_second": 9.083,
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": 650126529921024.0,
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 sha256:7faa01bf5e42a704fbe0f14b14a5126256b3525a31b9d29d45527114a8dedcf3
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c75ace39d51aa01260eabcf89455a8393ca57bbcb4cbc8f2893bbba5818431
3
  size 6776