tuanna08go commited on
Commit
0818559
·
verified ·
1 Parent(s): cd08167

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
- "v_proj",
25
- "k_proj",
26
  "down_proj",
 
 
27
  "gate_proj",
28
  "q_proj",
29
- "up_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
  "gate_proj",
27
  "q_proj",
28
+ "up_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:e7f286971a8b01ab9d27803001fa12a77e23315129c4bcd423be193703558891
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff81a78553230ee56817398ee6e35f2b3ddb6d6f0541158e2d4e75de79f2abcd
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9673d22f265ed23c9ac8fe3534732259b5ca12d0692ce0ea4ceef5963b1b4fd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beed8359fe142c0bd78cf5e499f7058c2c13c901dc109a35a05e5a60f3c080
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": 0.0005640953321111268,
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": 0.0005640953321111268,
13
  "eval_loss": NaN,
14
- "eval_runtime": 51.6818,
15
- "eval_samples_per_second": 14.454,
16
- "eval_steps_per_second": 7.237,
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": 174263604609024.0,
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": 0.007333239317444648,
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": 0.0005640953321111268,
13
  "eval_loss": NaN,
14
+ "eval_runtime": 51.6032,
15
+ "eval_samples_per_second": 14.476,
16
+ "eval_steps_per_second": 7.248,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0028204766605556338,
21
+ "grad_norm": NaN,
22
+ "learning_rate": 5e-05,
23
+ "loss": 0.0,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.0056409533211112676,
28
+ "grad_norm": NaN,
29
+ "learning_rate": 0.0001,
30
+ "loss": 0.0,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.0056409533211112676,
35
+ "eval_loss": NaN,
36
+ "eval_runtime": 52.8155,
37
+ "eval_samples_per_second": 14.144,
38
+ "eval_steps_per_second": 7.081,
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": 2265426859917312.0,
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 sha256:73422f35de60d7caa9a0026209dc8af67cf58b8d2a0de286721fddfab9a571bb
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c74248676b5a3a831ad01d0b16bf9549acb4a003b46180412e959d943eff3ea
3
  size 6776