ClarenceDan commited on
Commit
1ca1e47
·
verified ·
1 Parent(s): ec7c97b

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:439e39539b86dabe60eaa8b349ae4d0b07d76393c413791617fb469d3911e95e
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c859fabd663769c7b10d77d36d57653c22c805cf9f3ef6af5c13efcc0255a2a9
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:785e4326789083199c007f703e4de5b4280ad9727be251c8033d15edbab51509
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d6913dd7b48c0ed25fae0b53787ac8aee7453b37f65799d521d39364c064c0
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 8.595065000179063e-05,
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,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 20.86,
45
  "eval_steps_per_second": 10.431,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 949861251809280.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00017190130000358127,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 20.86,
45
  "eval_steps_per_second": 10.431,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00011460086666905418,
50
+ "grad_norm": 0.3155519962310791,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.3463,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00014325108333631772,
57
+ "grad_norm": 0.47635114192962646,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.3387,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00017190130000358127,
64
+ "grad_norm": 0.43341612815856934,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.4044,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00017190130000358127,
71
+ "eval_loss": 0.4110422134399414,
72
+ "eval_runtime": 743.8877,
73
+ "eval_samples_per_second": 19.757,
74
+ "eval_steps_per_second": 9.879,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1899722503618560.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null