duyphu commited on
Commit
1ce19a4
·
verified ·
1 Parent(s): e3d0f52

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
  "o_proj",
24
- "q_proj",
25
  "gate_proj",
26
- "v_proj",
27
  "up_proj",
28
- "k_proj",
29
- "down_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "k_proj",
24
  "o_proj",
 
25
  "gate_proj",
 
26
  "up_proj",
27
+ "down_proj",
28
+ "q_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:a8c9b313793ee9dce1a112689c47f0b75a07534cb2e5e6db18c9818a0f543ad9
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b284aa7e2463fa0621634ebb1a3d7717573518cf0abe2fd3a8d674d7c2b6b8f
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6d5cf199e7dd33a4935dd29796c2c2f22b8314f52e8f256877bc06ede0e795
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b0c32404be77ee7788148e112d211d5db35e7c7ba396d8173ef9a4e3295810
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed413ffc1f3bedbef14e57f493d3e8611649fb25a4d11d4dded6eabfeeb78de
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13faeb7c07b6eac60a31399e246f468d54a7d2e489790228eeba86d58d6477e2
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": 2.6892564205997043e-05,
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": 2.6892564205997043e-05,
13
  "eval_loss": 1.3629132509231567,
14
- "eval_runtime": 647.4241,
15
- "eval_samples_per_second": 24.184,
16
- "eval_steps_per_second": 12.093,
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": 40537282314240.0,
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": 0.00034960333467796154,
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": 2.6892564205997043e-05,
13
  "eval_loss": 1.3629132509231567,
14
+ "eval_runtime": 651.4742,
15
+ "eval_samples_per_second": 24.033,
16
+ "eval_steps_per_second": 12.017,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0001344628210299852,
21
+ "grad_norm": 0.958237886428833,
22
+ "learning_rate": 5e-05,
23
+ "loss": 1.3946,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0002689256420599704,
28
+ "grad_norm": 0.49982360005378723,
29
+ "learning_rate": 0.0001,
30
+ "loss": 1.2357,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0002689256420599704,
35
+ "eval_loss": 1.3428665399551392,
36
+ "eval_runtime": 647.8287,
37
+ "eval_samples_per_second": 24.168,
38
+ "eval_steps_per_second": 12.085,
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": 559414495936512.0,
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 sha256:8df29ee90f1ce713d766d28c84acfb9b79e51778f95f3c88129a0a80ab85f956
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d24a7bb1d0079717ad04b13a50f31253936a2b527bd7fdf63ead37dd9c9185
3
  size 6776