tuanna08go commited on
Commit
cd22032
·
verified ·
1 Parent(s): e6ca8f0

Training in progress, step 11, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -21,9 +21,9 @@
21
  "revision": null,
22
  "target_modules": [
23
  "dense",
 
24
  "dense_4h_to_h",
25
- "dense_h_to_4h",
26
- "query_key_value"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "dense",
24
+ "query_key_value",
25
  "dense_4h_to_h",
26
+ "dense_h_to_4h"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d5a4c61df04e1bd6d99c7d9cf45fc0e2df8c69d07c1d0204c8a04038e57d1e1
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0d34daa653cc4bbf179297ff452cf8497dd860a87d859ceaa58cbd5f9b91fb
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f41e71feeb79e98493b739b2d314d99cd08c65d69bf0f6256f6b0574cd3fa69
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a63875dc55d86a3c4c111467e1aa918a8dde4f6319abb10d2aaae6375a00fc
3
  size 162868
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a6a849e107fa2528c91f9807c59dfd07fa371d054b02baa13faf760bf66528a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b534877ba1f0b48dec1fc63df154003dca34fc8076dd09eab46f1a2c707f9a
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 sha256:6bfa0bb279f2101788d08b0135f42a939bc4867be11fd447a266649f4c2aa9b2
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": 0.02359882005899705,
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 +11,32 @@
11
  {
12
  "epoch": 0.02359882005899705,
13
  "eval_loss": 11.216988563537598,
14
- "eval_runtime": 1.6363,
15
- "eval_samples_per_second": 174.787,
16
- "eval_steps_per_second": 22.001,
17
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 10,
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 +44,12 @@
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": 308633665536.0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.25958702064896755,
5
+ "eval_steps": 9,
6
+ "global_step": 11,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.02359882005899705,
13
  "eval_loss": 11.216988563537598,
14
+ "eval_runtime": 1.8833,
15
+ "eval_samples_per_second": 151.859,
16
+ "eval_steps_per_second": 19.115,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.21238938053097345,
21
+ "eval_loss": 11.165812492370605,
22
+ "eval_runtime": 0.9078,
23
+ "eval_samples_per_second": 315.047,
24
+ "eval_steps_per_second": 39.656,
25
+ "step": 9
26
+ },
27
+ {
28
+ "epoch": 0.2359882005899705,
29
+ "grad_norm": 15.300642967224121,
30
+ "learning_rate": 9.089646803833589e-05,
31
+ "loss": 179.1345,
32
+ "step": 10
33
  }
34
  ],
35
  "logging_steps": 10,
36
+ "max_steps": 43,
37
  "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 2,
39
+ "save_steps": 11,
40
  "stateful_callbacks": {
41
  "TrainerControl": {
42
  "args": {
 
44
  "should_evaluate": false,
45
  "should_log": false,
46
  "should_save": true,
47
+ "should_training_stop": false
48
  },
49
  "attributes": {}
50
  }
51
  },
52
+ "total_flos": 3394970320896.0,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d880d637c6cc54b3d6f5cf1f927a0c0f30ed24b4a65a8baf2b655f90100ae4e
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9460c14ef70df0752b1cb0dc4faf7e59316dbcc782d6c021a2b93b14ba0471
3
  size 6776