ccore commited on
Commit
9736a13
·
verified ·
1 Parent(s): efb9cd9

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:622ceda914025a3cb6c3aea861afbd414ca14e4ada07549a490403bb60ed436e
3
  size 1447317080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eeef6ea82868fed037096afaae75138d366fdd8a948a478a6d39da41c0320cc
3
  size 1447317080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e7ab6da7bbcf285ba92b6a319955403be98c63cb8e5f808e2fac2b858c00b04
3
  size 2894813242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e307af0d3d8da03f1b9c643b876554b892185b2c269d203e47abe5885b91daa
3
  size 2894813242
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:230edc29c7f4d0d371abd36f9f7bae2a11f65b418f970748364cb37008e3f3ef
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9b5be710a7d11d99443218152501810ac7e04613867545dd1469d3cfd97c06
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,86 +1,27 @@
1
  {
2
- "best_metric": 0.37884894013404846,
3
- "best_model_checkpoint": "./opt_trained2/checkpoint-3212",
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 3212,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.6226650062266501,
13
- "grad_norm": 0.7334734201431274,
14
- "learning_rate": 0.0003875716064757161,
15
- "loss": 3.2343,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_loss": 0.4036673307418823,
21
- "eval_runtime": 273.6748,
22
- "eval_samples_per_second": 10.436,
23
- "eval_steps_per_second": 2.609,
24
  "step": 803
25
- },
26
- {
27
- "epoch": 1.2453300124533002,
28
- "grad_norm": 1.277639627456665,
29
- "learning_rate": 0.0003751183063511831,
30
- "loss": 3.2109,
31
- "step": 1000
32
- },
33
- {
34
- "epoch": 1.86799501867995,
35
- "grad_norm": 1.1930288076400757,
36
- "learning_rate": 0.00036273972602739727,
37
- "loss": 3.4898,
38
- "step": 1500
39
- },
40
- {
41
- "epoch": 2.0,
42
- "eval_loss": 0.3986678719520569,
43
- "eval_runtime": 273.4619,
44
- "eval_samples_per_second": 10.444,
45
- "eval_steps_per_second": 2.611,
46
- "step": 1606
47
- },
48
- {
49
- "epoch": 2.4906600249066004,
50
- "grad_norm": 0.363370418548584,
51
- "learning_rate": 0.0003502864259028643,
52
- "loss": 3.1553,
53
- "step": 2000
54
- },
55
- {
56
- "epoch": 3.0,
57
- "eval_loss": 0.3892712891101837,
58
- "eval_runtime": 273.5885,
59
- "eval_samples_per_second": 10.439,
60
- "eval_steps_per_second": 2.61,
61
- "step": 2409
62
- },
63
- {
64
- "epoch": 3.1133250311332503,
65
- "grad_norm": 0.4317278563976288,
66
- "learning_rate": 0.0003378331257783313,
67
- "loss": 3.0505,
68
- "step": 2500
69
- },
70
- {
71
- "epoch": 3.7359900373599,
72
- "grad_norm": 0.3730609118938446,
73
- "learning_rate": 0.00032537982565379825,
74
- "loss": 2.9785,
75
- "step": 3000
76
- },
77
- {
78
- "epoch": 4.0,
79
- "eval_loss": 0.37884894013404846,
80
- "eval_runtime": 273.844,
81
- "eval_samples_per_second": 10.429,
82
- "eval_steps_per_second": 2.607,
83
- "step": 3212
84
  }
85
  ],
86
  "logging_steps": 500,
@@ -100,7 +41,7 @@
100
  "attributes": {}
101
  }
102
  },
103
- "total_flos": 1.2514885666272e+17,
104
  "train_batch_size": 4,
105
  "trial_name": null,
106
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.344450980424881,
3
+ "best_model_checkpoint": "./opt_trained2/checkpoint-803",
4
+ "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 803,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.6226650062266501,
13
+ "grad_norm": 1.3505125045776367,
14
+ "learning_rate": 0.000387546699875467,
15
+ "loss": 2.7763,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_loss": 0.344450980424881,
21
+ "eval_runtime": 273.127,
22
+ "eval_samples_per_second": 10.457,
23
+ "eval_steps_per_second": 2.614,
24
  "step": 803
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 500,
 
41
  "attributes": {}
42
  }
43
  },
44
+ "total_flos": 3.128721416568e+16,
45
  "train_batch_size": 4,
46
  "trial_name": null,
47
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69d0a29f401b9a755904f81ae972cbb11a5cf5b18ec1bf43f3d071d452c37c88
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ebdc8e79af6a5c9fa4062f9f21aa548e32853f463a515333ea4cf561b7abfc
3
  size 5368