Aivesa commited on
Commit
b121647
·
verified ·
1 Parent(s): e1bb0c9

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 sha256:9a758ef4d0c5aca99ae3c470173c3b71e1347a2f193bf91b50a395c687f52baa
3
  size 604317736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13ed147644620729c239157741e06e052419dd5b42b3b75425e7037bed5fef8
3
  size 604317736
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:399b4ea02b6ef64c0100f1613ae32ab9c4a03e0ab0b049ca3cc6acc959865009
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c90e728e473ac8b80e35f25c41a90d578a157fe0b83850f190acc190a5d8c7
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b173ac9ab56406e53f02ac343bf22d13dc84cb35b451121151594928dcc2f4cd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
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": 3.8797785939682375e-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,
@@ -36,6 +36,35 @@
36
  "eval_samples_per_second": 17.984,
37
  "eval_steps_per_second": 8.992,
38
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 1,
@@ -55,7 +84,7 @@
55
  "attributes": {}
56
  }
57
  },
58
- "total_flos": 488620242763776.0,
59
  "train_batch_size": 2,
60
  "trial_name": null,
61
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.759557187936475e-05,
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,
 
36
  "eval_samples_per_second": 17.984,
37
  "eval_steps_per_second": 8.992,
38
  "step": 3
39
+ },
40
+ {
41
+ "epoch": 5.173038125290983e-05,
42
+ "grad_norm": 1.1495997905731201,
43
+ "learning_rate": 8e-05,
44
+ "loss": 1.4327,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 6.46629765661373e-05,
49
+ "grad_norm": 1.257749319076538,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.2136,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 7.759557187936475e-05,
56
+ "grad_norm": 1.423362135887146,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.3854,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 7.759557187936475e-05,
63
+ "eval_loss": 1.1243104934692383,
64
+ "eval_runtime": 1869.0389,
65
+ "eval_samples_per_second": 17.42,
66
+ "eval_steps_per_second": 8.71,
67
+ "step": 6
68
  }
69
  ],
70
  "logging_steps": 1,
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 977240485527552.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null