chauhoang commited on
Commit
1fd3330
·
verified ·
1 Parent(s): b8e73b1

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
- "q_proj",
24
- "k_proj",
25
- "down_proj",
26
  "up_proj",
 
27
  "v_proj",
 
28
  "o_proj",
29
- "gate_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "up_proj",
24
+ "down_proj",
25
  "v_proj",
26
+ "k_proj",
27
  "o_proj",
28
+ "gate_proj",
29
+ "q_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:b53273726c5bcc03d4bf18061840adc040be2d44073c509311710ac0400762a4
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c27d1de0bff83d1d678bf9679ff04dd5ae08ee291db1d05297c43d5c66cd3f
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5301eefa2ca0533565f41f3d9220f1a8ebf9d05db6bc77fc5c0af6ac80f5220a
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d493bce3d1d2ffb7932a993af053ef9c6f9d5149141e27cf12e80b968064af0c
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:fcecbcc564666edf6af81b027426d9673e892a66966056d8334ef5d45a66687e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c29849c270e30e3c343a211f23de14083950f8d99ea329e8fff4d42bc8e200
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": 0.004210526315789474,
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": 0.004210526315789474,
13
  "eval_loss": 2.6562552452087402,
14
- "eval_runtime": 4.4099,
15
- "eval_samples_per_second": 22.676,
16
- "eval_steps_per_second": 11.338,
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": 32429825851392.0,
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": 0.05473684210526316,
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": 0.004210526315789474,
13
  "eval_loss": 2.6562552452087402,
14
+ "eval_runtime": 4.4287,
15
+ "eval_samples_per_second": 22.58,
16
+ "eval_steps_per_second": 11.29,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.021052631578947368,
21
+ "grad_norm": 0.8043078184127808,
22
+ "learning_rate": 5e-05,
23
+ "loss": 2.8372,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.042105263157894736,
28
+ "grad_norm": 0.45552536845207214,
29
+ "learning_rate": 0.0001,
30
+ "loss": 2.2991,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 0.042105263157894736,
35
+ "eval_loss": 2.550579786300659,
36
+ "eval_runtime": 3.9155,
37
+ "eval_samples_per_second": 25.54,
38
+ "eval_steps_per_second": 12.77,
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": 445910105456640.0,
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 sha256:901693ea3f10dd45e479f7107d4a5fc7cc914ada2afade2acaab60d6ec8812b9
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef159b29b63bd338f642a319fdd06f63f51fa9c4450117d464320c95f8bc0383
3
  size 6776