Best000 commited on
Commit
cc0bc98
·
verified ·
1 Parent(s): fd07190

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 sha256:3d5205d2963c538281a3a7580802ade78a3edd03757ea6a4dba75151686a4b5e
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20615588467f32d6a5727f99e866adc2dc7708db89d3739fdcc47c57452cbfba
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b641c0d61d91adfd4a0b677a75dda2d9b3b139245f3b55390ac576e03a76c54b
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14edfdaeed1673fe4318f69a563d2944f962b9a942f4726c0089c7febb3ab091
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d5081b267af95cf9f6203c3aaa67179c8d8bf336dbaefda7c27713282c1dbdc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
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": 0.007485963817841547,
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": 33.71,
45
  "eval_steps_per_second": 16.955,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 150029199212544.0,
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": 0.014971927635683094,
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": 33.71,
45
  "eval_steps_per_second": 16.955,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.009981285090455396,
50
+ "grad_norm": 2.6299636363983154,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.4253,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.012476606363069246,
57
+ "grad_norm": 2.9032979011535645,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.9614,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.014971927635683094,
64
+ "grad_norm": 2.814908266067505,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.3926,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.014971927635683094,
71
+ "eval_loss": 1.3469496965408325,
72
+ "eval_runtime": 5.1022,
73
+ "eval_samples_per_second": 33.123,
74
+ "eval_steps_per_second": 16.659,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 300058398425088.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null