kostiantynk commited on
Commit
bd0c683
·
verified ·
1 Parent(s): a74767f

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 sha256:4f3980d852eb312dd39cd171fd22e25798d9004ce52bf12240104d571a8e6112
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3356e0dcb295fc68a038b4193109f01aa6af480c55d4449910331f6b42ad4059
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7ee0340d1be204920c09c58f5e4ce095eae9a6ca2decc76ff42ad29001825a9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d6b9b1528d5be01b613da0eceb5ab6fe94959eff9f875850ddeeeedaee293c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32134ae54983fa5ef5140991dc2cfb9fe710ddfbb9422d1124fd05a3c750b848
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36b079fde0d50a71846e4012b55dbfb2dd9d8c0de22b0a59c006da6f057b01b
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": 0.006876790830945559,
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": 17.769,
45
  "eval_steps_per_second": 8.885,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1051603079528448.0,
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": 0.013753581661891117,
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": 17.769,
45
  "eval_steps_per_second": 8.885,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.009169054441260744,
50
+ "grad_norm": 8.345035552978516,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.4904,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.011461318051575931,
57
+ "grad_norm": 7.962756633758545,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.3341,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.013753581661891117,
64
+ "grad_norm": 6.0530219078063965,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.4597,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.013753581661891117,
71
+ "eval_loss": 0.5594660043716431,
72
+ "eval_runtime": 10.3706,
73
+ "eval_samples_per_second": 17.742,
74
+ "eval_steps_per_second": 8.871,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2103206159056896.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null