Hugging Face's logo

chauhoang
/
43c5e90a-91f9-d2b4-19f3-6ca01351db92

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
0009019
·
verified ·
1 Parent(s): 9303d8d

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
@@ -22,11 +22,11 @@
22
  "target_modules": [
23
  "k_proj",
24
  "down_proj",
25
- "o_proj",
26
  "gate_proj",
27
  "up_proj",
 
28
  "q_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
22
  "target_modules": [
23
  "k_proj",
24
  "down_proj",
 
25
  "gate_proj",
26
  "up_proj",
27
+ "v_proj",
28
  "q_proj",
29
+ "o_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 sha256:79e553933af6b5129e7b70e72e26a7c3d6fb14168fa66ab6280ea4d52df44322
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd097df2187a1ae2538f50619bd3796856a0e74a56bddf78430f113d35bae13
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c450678c3390772893f2002dcf236e3305d39cb29e84065707078617b075577c
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ef77ab090dbdf3c2e1ca57736ab93da98cbc3031d3deca5011178e6b2d5bf1
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d20938fdf180abcaa5fb4311a1433c95811c7ad7a2a935c0fa2fec209987e03
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7c5a707a1669fe1f7e9aa7ebbce4572676dd691ca2acdd528004951920e448
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": 0.00036088054853843375,
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": 0.00036088054853843375,
13
  "eval_loss": 2.2970988750457764,
14
- "eval_runtime": 40.0649,
15
- "eval_samples_per_second": 29.128,
16
- "eval_steps_per_second": 14.576,
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": 51158395650048.0,
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": 0.004691447130999639,
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": 0.00036088054853843375,
13
  "eval_loss": 2.2970988750457764,
14
+ "eval_runtime": 40.8928,
15
+ "eval_samples_per_second": 28.538,
16
+ "eval_steps_per_second": 14.281,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.001804402742692169,
21
+ "grad_norm": 1.4550670385360718,
22
+ "learning_rate": 5e-05,
23
+ "loss": 2.0658,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.003608805485384338,
28
+ "grad_norm": 1.1833549737930298,
29
+ "learning_rate": 0.0001,
30
+ "loss": 2.0273,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.003608805485384338,
35
+ "eval_loss": 1.8604884147644043,
36
+ "eval_runtime": 40.0345,
37
+ "eval_samples_per_second": 29.15,
38
+ "eval_steps_per_second": 14.587,
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": 665059143450624.0,
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 sha256:412b6ef2927a599fdc6d886fadee0a2651bc037242da7e14dd2ddda29884fad8
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50725a811099cc953c692444240f695cc543e40a7e213fd43ea2ecf5328126b8
3
  size 6776