Hugging Face's logo

chauhoang
/
854dc53b-b1f3-b04f-e4ab-de5f708c2dd7

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
1521e65
·
verified ·
1 Parent(s): 9241109

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
- "q_proj",
24
- "o_proj",
25
- "gate_proj",
26
- "up_proj",
27
  "k_proj",
 
28
  "v_proj",
29
- "down_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
 
23
  "k_proj",
24
+ "up_proj",
25
  "v_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_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 sha256:968837bc91b90453e60c170c8786c53982e40571cbc9ef3d937b20ab2482a434
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89e3a034f310eb0d92851d6924f49a4f1a81338aa571c53a2777fb6d75ae471
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cac1812017eb86840ce993d98ef9cb4b2e44dd87a6203278cac11bd3b957de7f
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0ae09bfadae0e60f855fed328c41558222c03eda29cc3e63e6c211b3b3ffd2
3
  size 39398
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": 1.6223823874168022e-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": 1.6223823874168022e-05,
13
  "eval_loss": 11.932548522949219,
14
- "eval_runtime": 232.7314,
15
- "eval_samples_per_second": 111.515,
16
- "eval_steps_per_second": 55.76,
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": 118161408.0,
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": 0.0002109097103641843,
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": 1.6223823874168022e-05,
13
  "eval_loss": 11.932548522949219,
14
+ "eval_runtime": 232.3563,
15
+ "eval_samples_per_second": 111.695,
16
+ "eval_steps_per_second": 55.85,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 8.111911937084011e-05,
21
+ "grad_norm": 0.016159748658537865,
22
+ "learning_rate": 5e-05,
23
+ "loss": 11.9312,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.00016223823874168022,
28
+ "grad_norm": 0.013233560137450695,
29
+ "learning_rate": 0.0001,
30
+ "loss": 11.9326,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.00016223823874168022,
35
+ "eval_loss": 11.932516098022461,
36
+ "eval_runtime": 236.8859,
37
+ "eval_samples_per_second": 109.559,
38
+ "eval_steps_per_second": 54.782,
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": 1536098304.0,
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 sha256:780cd0db8d569828dc9a08cf8f50e37aec63968c8a33a270c9cc94189a72c032
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee42275aacb45addd6e3e1293037306c5c9eb50d6b6d9af9449adb3ca399d1a
3
  size 6776