jssky commited on
Commit
df26f52
·
verified ·
1 Parent(s): 4cbccbd

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 sha256:1b2b0fc56d1413c01870d6c498f4cefbd16531eddec5cd7ec62429784de6645d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48fcf70db53587e2a12a599258d0e60abb259291aee67345f5efa917508b553
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:405d243ce8b437a037dd53cddd2026b63cc0535c5729f84ef6b276a5705b110f
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1b2d7325c10616dea312a42adda649dcff329d6e970d1bfed4c76ad751cd14
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
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": 0.00015746378332983415,
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": 4.959,
45
  "eval_steps_per_second": 4.959,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 2225661850681344.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0003149275666596683,
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": 4.959,
45
  "eval_steps_per_second": 4.959,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0002099517111064455,
50
+ "grad_norm": 1.3818600177764893,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.0932,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0002624396388830569,
57
+ "grad_norm": 1.3986132144927979,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.1926,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0003149275666596683,
64
+ "grad_norm": 1.6934878826141357,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2556,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0003149275666596683,
71
+ "eval_loss": 1.2398279905319214,
72
+ "eval_runtime": 808.9202,
73
+ "eval_samples_per_second": 4.958,
74
+ "eval_steps_per_second": 4.958,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 4451323701362688.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null