phungkhaccuong commited on
Commit
7744ea8
·
verified ·
1 Parent(s): fdc16d6

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
- "down_proj",
24
- "o_proj",
25
  "k_proj",
26
- "gate_proj",
 
27
  "q_proj",
 
28
  "up_proj",
29
- "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
  "q_proj",
27
+ "down_proj",
28
  "up_proj",
29
+ "gate_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:b52f089b93ca06e8853abb0673099f93eca26ebb853cf31c5d357c42886fcb28
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9135b2b80fab9c3ca30d155afb05553241e3e57e216b9b9360e87666825b6d3
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9d1ad83a6a4c77a7e2e57abdc5cdeba36d34ea9eeaa0dbe6b3894721ee63c9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b75d0da7a1c8974a20b49ce81621e6e10cb5463a5dff0230771cbe30e7b5514
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33799e390fc551a91dceaf2550988dbd7c80389c682f07c9be0447bc39719a8a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d23ddc432877538e1482ac7028d4be4d6733be4d7e298176c8e6b45a4685c3
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": 0.00023149487817582037,
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": 0.00023149487817582037,
13
  "eval_loss": 1.8957964181900024,
14
- "eval_runtime": 213.5061,
15
- "eval_samples_per_second": 8.52,
16
- "eval_steps_per_second": 4.262,
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": 175270199820288.0,
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": 0.0030094334162856645,
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": 0.00023149487817582037,
13
  "eval_loss": 1.8957964181900024,
14
+ "eval_runtime": 213.5939,
15
+ "eval_samples_per_second": 8.516,
16
+ "eval_steps_per_second": 4.26,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0011574743908791018,
21
+ "grad_norm": 56.71136474609375,
22
+ "learning_rate": 5e-05,
23
+ "loss": 7.2579,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0023149487817582036,
28
+ "grad_norm": 65.8984603881836,
29
+ "learning_rate": 0.0001,
30
+ "loss": 6.12,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0023149487817582036,
35
+ "eval_loss": 1.417953610420227,
36
+ "eval_runtime": 215.2865,
37
+ "eval_samples_per_second": 8.449,
38
+ "eval_steps_per_second": 4.227,
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": 2278512597663744.0,
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:e5d8b7265fe7f35c0d7a8800e72915e2bf3de9a5c6b188e5f9608a1718b996f4
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9332d5064fe4a0455bf9925da7d2ee2584d4f6c985f095c85d3943b407ae55
3
  size 6776