tuanna08go commited on
Commit
aaa87d9
·
verified ·
1 Parent(s): aabc294

Training in progress, step 13, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
  "up_proj",
25
- "v_proj",
26
- "k_proj",
27
  "o_proj",
 
28
  "down_proj",
29
- "gate_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
  "o_proj",
26
+ "v_proj",
27
  "down_proj",
28
+ "k_proj",
29
+ "q_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 sha256:5d3e13c9ab80cafa81a2e4fe2dccb2304ebc75a434666d5ad18c0fc597d56033
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d533d81dbfdcb2309dd5bef91e344e6bed96a99f6860d1eeac103dd73c45fa49
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae4bb3e2588a49373a006c5e0b129928d44b812b2dd5791ac4d897f232c261dd
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886a761dec666be830b95741b2dacd516d90cb6d27f81b7132bc5dc349dc6bfb
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:b2f2b1fe1ee433d0949425d85cbc1e7db562c93cb1fc4f9c675368fbffc7b15d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
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": 0.0036496350364963502,
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": 0.0036496350364963502,
13
  "eval_loss": 2.5532567501068115,
14
- "eval_runtime": 2.7578,
15
- "eval_samples_per_second": 42.062,
16
- "eval_steps_per_second": 21.031,
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": 25579197825024.0,
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": 0.04744525547445255,
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": 0.0036496350364963502,
13
  "eval_loss": 2.5532567501068115,
14
+ "eval_runtime": 3.8819,
15
+ "eval_samples_per_second": 29.882,
16
+ "eval_steps_per_second": 14.941,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.01824817518248175,
21
+ "grad_norm": 0.31805118918418884,
22
+ "learning_rate": 5e-05,
23
+ "loss": 2.5126,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0364963503649635,
28
+ "grad_norm": 0.43643781542778015,
29
+ "learning_rate": 0.0001,
30
+ "loss": 2.5551,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0364963503649635,
35
+ "eval_loss": 2.522387742996216,
36
+ "eval_runtime": 2.8014,
37
+ "eval_samples_per_second": 41.408,
38
+ "eval_steps_per_second": 20.704,
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": 332529571725312.0,
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:b4166bc5158f4425c615a0c9e4cf78e3986734199c84d68d0a5832d86ed37def
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5dcb0efb2ad43ed1017be9d035e3ce0c5cc80ee3989edbbea3607be96c0885
3
  size 6776