adammandic87 commited on
Commit
ec56bc9
·
verified ·
1 Parent(s): e3fdf91

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 sha256:2fb969da3c3dccf3a7c2dabf1720a09b93427c74776527ba92892736c41925e1
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573c39f7406c8ac6367b76446a94469f1c2cadf6b4247d9eb4eb338f94276539
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7b60e53e13a7f0615704ac9bd1fadde1134c9655c4bdf78f1ba4f98517e4ae
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c7413d3a33443aed5e53856d5da511d44a80620f3f8fa47e3958c8ea8b2e414
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f5a597df541a953761770aa099d34e8b7f2ef4a2b3a4e48555ba4a369718753
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347eca5a8330a3b6f76e113dfe8a5bfd152db6621bafb09c29d2965a0ece0a4b
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": 0.05741626794258373,
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": 17.889,
45
  "eval_steps_per_second": 9.333,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 492029198991360.0,
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": 0.11483253588516747,
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": 17.889,
45
  "eval_steps_per_second": 9.333,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.07655502392344497,
50
+ "grad_norm": 0.3195428252220154,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.5062,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.09569377990430622,
57
+ "grad_norm": 0.3404718041419983,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.537,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.11483253588516747,
64
+ "grad_norm": 0.3823797106742859,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.4345,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.11483253588516747,
71
+ "eval_loss": 1.4316757917404175,
72
+ "eval_runtime": 1.2951,
73
+ "eval_samples_per_second": 17.759,
74
+ "eval_steps_per_second": 9.265,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 984058397982720.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null