chauhoang commited on
Commit
d417fa8
·
verified ·
1 Parent(s): a8b28ea

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
  "up_proj",
24
  "o_proj",
25
- "v_proj",
26
- "k_proj",
27
  "gate_proj",
28
- "q_proj",
29
- "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
+ "q_proj",
25
+ "k_proj",
26
  "up_proj",
27
  "o_proj",
 
 
28
  "gate_proj",
29
+ "v_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:ac56b08f0a692e44ce68cc980d1198585056b5f10ed6e431a2e2e2e9f2612bfc
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea9b4daf7ad162e71af90fb1b273d8a5cbb41c92528d88fecfd3e67023c97d8
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a82f8ab2e902c58fb75924a0451baa39229f2bfa544e411ab53c9f5645389172
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8dba158c00acea0c6ff7d2b5b2cce2e1e7c16f44a0c0e0b2dc6e722e3cab83
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
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": 0.00015335071308081582,
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": 0.00015335071308081582,
13
  "eval_loss": 10.366971015930176,
14
- "eval_runtime": 12.3861,
15
- "eval_samples_per_second": 221.699,
16
- "eval_steps_per_second": 110.85,
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": 12930908160.0,
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": 0.001993559270050606,
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": 0.00015335071308081582,
13
  "eval_loss": 10.366971015930176,
14
+ "eval_runtime": 12.3422,
15
+ "eval_samples_per_second": 222.488,
16
+ "eval_steps_per_second": 111.244,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0007667535654040791,
21
+ "grad_norm": 0.08022961020469666,
22
+ "learning_rate": 5e-05,
23
+ "loss": 10.3697,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0015335071308081583,
28
+ "grad_norm": 0.06305605173110962,
29
+ "learning_rate": 0.0001,
30
+ "loss": 10.3674,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0015335071308081583,
35
+ "eval_loss": 10.366765975952148,
36
+ "eval_runtime": 12.0611,
37
+ "eval_samples_per_second": 227.673,
38
+ "eval_steps_per_second": 113.837,
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": 168101806080.0,
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 sha256:21492ecf7793e01afeac404218bc3051057792eba6bd077cfceb0ba518ebf307
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4163f3ebb95d2f51719a41232c9f33e0890f526268dc5666ae0400f8e955e398
3
  size 6776