Hugging Face's logo

phungkhaccuong
/
de74bd0b-dce0-bc47-f5d5-72322a9bef4f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
ad26f60
·
verified ·
1 Parent(s): 10e492c

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
- "v_proj",
25
  "gate_proj",
26
- "down_proj",
27
  "k_proj",
 
 
28
  "up_proj",
29
- "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "gate_proj",
24
+ "q_proj",
25
  "k_proj",
26
+ "o_proj",
27
+ "v_proj",
28
  "up_proj",
29
+ "down_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:c1f10764e251513b1f301d7f771f489b98e62c6754232e232bad0fa4a277e116
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfa1ea61d6d66b8c8ae1b60c79161d40aae29114cd7f0b36dfa73ed7b8a4797
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63c6749f19da8eb868c6548e758d42bb459d6457d505d56bd212c97ea90e8483
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64ed13e1239e7fb2dff3202fafa275bb988f2709fadcbc7f1f84734cf52f9ad
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:e64dc269c204efc2e9a4c4cbe20de7c7547b2a048bf7e9385229ea63d598fdfd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
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": 0.00021369804466289135,
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": 0.00021369804466289135,
13
  "eval_loss": 2.2744333744049072,
14
- "eval_runtime": 132.0623,
15
- "eval_samples_per_second": 14.925,
16
- "eval_steps_per_second": 7.466,
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": 184956424814592.0,
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": 0.002778074580617587,
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": 0.00021369804466289135,
13
  "eval_loss": 2.2744333744049072,
14
+ "eval_runtime": 130.9845,
15
+ "eval_samples_per_second": 15.048,
16
+ "eval_steps_per_second": 7.528,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0010684902233144566,
21
+ "grad_norm": 2.4032351970672607,
22
+ "learning_rate": 5e-05,
23
+ "loss": 2.3302,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0021369804466289132,
28
+ "grad_norm": 2.7247142791748047,
29
+ "learning_rate": 0.0001,
30
+ "loss": 2.1623,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0021369804466289132,
35
+ "eval_loss": 2.000274419784546,
36
+ "eval_runtime": 131.5784,
37
+ "eval_samples_per_second": 14.98,
38
+ "eval_steps_per_second": 7.494,
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": 2404433522589696.0,
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 sha256:0209ac49dd5466dcc9da58f89d7c6391b05ff1ef478651e2a60e1f8601f7716b
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1925ca82651d1c8f598744f98b24b1fc301513362eaf1b5af3203ccd16810a2c
3
  size 6776