Hugging Face's logo

chauhoang
/
620be513-90da-06ab-a04f-bd410a8cf8d3

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
a18b4f9
·
verified ·
1 Parent(s): 7433870

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
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "dense_4h_to_h",
24
  "dense_h_to_4h",
 
25
  "query_key_value",
26
- "dense"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "dense_h_to_4h",
24
+ "dense",
25
  "query_key_value",
26
+ "dense_4h_to_h"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdfe74044799c2d681ddeb8f795fa19b7b298007751b096d62a1d240b818aeb
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00d8b2572c06729206ac0d5ffd9e3067507921142b1ee6a970cb44a8dee74e9
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:130b6d9b8600523f59d7b7c0ffafd7aa1f2bbb4bda6ea545b24188a174453250
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074e65caee7a885b06f613ecbdda741540666ec2e71262a1c1982162c41595cf
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e41786d93022ecb8c77c66c54399ef1b8e95dd48a633f70ac7335d6fde4af8f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1467d43e650401a3b512d395f9a9d91640b9c9a50e1c12bdce5220b151890407
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": 0.002793296089385475,
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": 0.002793296089385475,
13
  "eval_loss": 2.4049742221832275,
14
- "eval_runtime": 13.3264,
15
- "eval_samples_per_second": 11.331,
16
- "eval_steps_per_second": 5.703,
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": 285280535838720.0,
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": 0.036312849162011177,
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": 0.002793296089385475,
13
  "eval_loss": 2.4049742221832275,
14
+ "eval_runtime": 13.2901,
15
+ "eval_samples_per_second": 11.362,
16
+ "eval_steps_per_second": 5.719,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.013966480446927373,
21
+ "grad_norm": 2.8598062992095947,
22
+ "learning_rate": 5e-05,
23
+ "loss": 9.1267,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.027932960893854747,
28
+ "grad_norm": 4.437131881713867,
29
+ "learning_rate": 0.0001,
30
+ "loss": 8.7871,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.027932960893854747,
35
+ "eval_loss": 2.1106879711151123,
36
+ "eval_runtime": 12.4419,
37
+ "eval_samples_per_second": 12.136,
38
+ "eval_steps_per_second": 6.108,
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": 3708646965903360.0,
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 sha256:115376dd420f3056c40be76cdefe89e15ba8cd96b0c572ae21c3204e7eb59b24
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2da5b5df9750b789e8d32d33105fbbe059f3a5a7a2c0ad93921c3612cff93f8
3
  size 6776