Hugging Face's logo

duyphu
/
64d858fd-0ea9-bb1f-71f7-76dcd02f019f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
eb79532
·
verified ·
1 Parent(s): 5261d86

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
- "o_proj",
24
- "q_proj",
25
  "gate_proj",
26
- "v_proj",
27
- "down_proj",
28
  "k_proj",
29
- "up_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "gate_proj",
24
+ "up_proj",
25
+ "q_proj",
26
  "k_proj",
27
+ "o_proj",
28
+ "v_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:de80c4504d1046547f3429cb5f1c055a771159b30e077065340a63523cfeed76
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d459a0aea7c30cdd5b24b413c0474fb9242ef3b51745d27b00ca36583f0f86af
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d832bb3cc3345c7d1367a0a4e1d2c9b00577392abf18d7962a857bc4c37c0789
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae1a4013bfa6f5cd73b044f1cac13236ec595f2d83d14dc3fe283bf1293450e
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
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": 0.0015594541910331384,
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": 0.0015594541910331384,
13
  "eval_loss": 10.152922630310059,
14
- "eval_runtime": 3.2806,
15
- "eval_samples_per_second": 82.301,
16
- "eval_steps_per_second": 41.15,
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": 65558544384.0,
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": 0.0202729044834308,
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": 0.0015594541910331384,
13
  "eval_loss": 10.152922630310059,
14
+ "eval_runtime": 3.2878,
15
+ "eval_samples_per_second": 82.122,
16
+ "eval_steps_per_second": 41.061,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.007797270955165692,
21
+ "grad_norm": 2.428389549255371,
22
+ "learning_rate": 5e-05,
23
+ "loss": 10.1068,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.015594541910331383,
28
+ "grad_norm": 1.9053232669830322,
29
+ "learning_rate": 0.0001,
30
+ "loss": 10.1142,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.015594541910331383,
35
+ "eval_loss": 10.097267150878906,
36
+ "eval_runtime": 3.2915,
37
+ "eval_samples_per_second": 82.03,
38
+ "eval_steps_per_second": 41.015,
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": 852261076992.0,
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 sha256:3fe58f0e480f1016d6ab375860961b1880a9083e8107c14655529a4ff3736054
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddf1f426741b3bab3eb98e370541aebf785bc6915baaf21fda35bd8a09dea7d
3
  size 6776