jwongTensora commited on
Commit
0edc420
·
verified ·
1 Parent(s): b8325af

Training in progress, step 3, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "down_proj",
 
24
  "v_proj",
25
  "q_proj",
26
- "up_proj",
27
  "o_proj",
28
- "k_proj",
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "up_proj",
24
+ "k_proj",
25
  "v_proj",
26
  "q_proj",
 
27
  "o_proj",
28
+ "down_proj",
29
  "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e80d12f3c994969faeab3befd1200b8057cd60bc4ddcbd923b89dd1428a4aef
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab35df2c6f42d94b1b765dd2d92defa45f055d1f9f3f69b3466f869f5b355ff
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0278c3b53e79f7d56f45467943a9f7b390c91a77ee38b1e0fa8f0abd44c7cfef
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9477a14fbbd471626d75553c2acab50cb49b130123579171cbc54ada9829819
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,114 +1,49 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.005608524957936063,
5
  "eval_steps": 3,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0005608524957936063,
13
- "grad_norm": 0.014158043079078197,
14
  "learning_rate": 2e-05,
15
  "loss": 11.9315,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0005608524957936063,
20
- "eval_loss": 11.931306838989258,
21
- "eval_runtime": 2.6792,
22
- "eval_samples_per_second": 280.305,
23
- "eval_steps_per_second": 140.339,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0011217049915872126,
28
- "grad_norm": 0.008724894374608994,
29
  "learning_rate": 4e-05,
30
  "loss": 11.9304,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0016825574873808188,
35
- "grad_norm": 0.012308093719184399,
36
  "learning_rate": 6e-05,
37
  "loss": 11.9319,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.0016825574873808188,
42
- "eval_loss": 11.931304931640625,
43
- "eval_runtime": 2.69,
44
- "eval_samples_per_second": 279.178,
45
- "eval_steps_per_second": 139.775,
46
  "step": 3
47
- },
48
- {
49
- "epoch": 0.002243409983174425,
50
- "grad_norm": 0.014784930273890495,
51
- "learning_rate": 8e-05,
52
- "loss": 11.9328,
53
- "step": 4
54
- },
55
- {
56
- "epoch": 0.0028042624789680315,
57
- "grad_norm": 0.018228236585855484,
58
- "learning_rate": 0.0001,
59
- "loss": 11.9248,
60
- "step": 5
61
- },
62
- {
63
- "epoch": 0.0033651149747616375,
64
- "grad_norm": 0.00944304559379816,
65
- "learning_rate": 0.00012,
66
- "loss": 11.926,
67
- "step": 6
68
- },
69
- {
70
- "epoch": 0.0033651149747616375,
71
- "eval_loss": 11.93128776550293,
72
- "eval_runtime": 2.737,
73
- "eval_samples_per_second": 274.384,
74
- "eval_steps_per_second": 137.374,
75
- "step": 6
76
- },
77
- {
78
- "epoch": 0.003925967470555244,
79
- "grad_norm": 0.010294442065060139,
80
- "learning_rate": 0.00014,
81
- "loss": 11.9324,
82
- "step": 7
83
- },
84
- {
85
- "epoch": 0.00448681996634885,
86
- "grad_norm": 0.006158821750432253,
87
- "learning_rate": 0.00016,
88
- "loss": 11.935,
89
- "step": 8
90
- },
91
- {
92
- "epoch": 0.005047672462142457,
93
- "grad_norm": 0.013304798863828182,
94
- "learning_rate": 0.00018,
95
- "loss": 11.9287,
96
- "step": 9
97
- },
98
- {
99
- "epoch": 0.005047672462142457,
100
- "eval_loss": 11.93126106262207,
101
- "eval_runtime": 2.6808,
102
- "eval_samples_per_second": 280.143,
103
- "eval_steps_per_second": 140.258,
104
- "step": 9
105
- },
106
- {
107
- "epoch": 0.005608524957936063,
108
- "grad_norm": 0.007890689186751842,
109
- "learning_rate": 0.0002,
110
- "loss": 11.9335,
111
- "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
@@ -123,12 +58,12 @@
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
- "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
- "total_flos": 1211154432.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0016825574873808188,
5
  "eval_steps": 3,
6
+ "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0005608524957936063,
13
+ "grad_norm": 0.016453281044960022,
14
  "learning_rate": 2e-05,
15
  "loss": 11.9315,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0005608524957936063,
20
+ "eval_loss": 11.931304931640625,
21
+ "eval_runtime": 2.7782,
22
+ "eval_samples_per_second": 270.314,
23
+ "eval_steps_per_second": 135.337,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0011217049915872126,
28
+ "grad_norm": 0.009702314622700214,
29
  "learning_rate": 4e-05,
30
  "loss": 11.9304,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0016825574873808188,
35
+ "grad_norm": 0.013587607070803642,
36
  "learning_rate": 6e-05,
37
  "loss": 11.9319,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.0016825574873808188,
42
+ "eval_loss": 11.931302070617676,
43
+ "eval_runtime": 2.7878,
44
+ "eval_samples_per_second": 269.386,
45
+ "eval_steps_per_second": 134.872,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
 
58
  "should_evaluate": false,
59
  "should_log": false,
60
  "should_save": true,
61
+ "should_training_stop": false
62
  },
63
  "attributes": {}
64
  }
65
  },
66
+ "total_flos": 384024576.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13c071afcb677798becdc51c2866c044c68ee8babfa41eab6cf9575fc41caa6d
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c057a083ef4657aa2451d0b6b5f1a22a6bca0f1f1706cd70ee0975139c91195c
3
  size 6776