ClarenceDan commited on
Commit
bfe61eb
·
verified ·
1 Parent(s): 2f118af

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 sha256:408386eb456e3ed844d19cd8745dda23af4cbfcb09ed4b07913251ae4299f6bc
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b3c0b11caeb6fc62a18593d8ebaa21368a7e637f3a4487aa05e05bf41524e8
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dade08edc5a7c462132bca4bfb626733379ed5f860c0478a555b16ebe38bd2a7
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb8212600331bcd9d0514b37face03806f019c76ebf4f6a2164994a3ff07960
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722fbfbb6eef10843027f96a5aa6e1568d6f2eccd5c7f794541dd6908d397450
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
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": 0.0004491690372810301,
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": 10.145,
45
  "eval_steps_per_second": 5.074,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 529343503663104.0,
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": 0.0008983380745620602,
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": 10.145,
45
  "eval_steps_per_second": 5.074,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0005988920497080402,
50
+ "grad_norm": 3.7658534049987793,
51
+ "learning_rate": 8e-05,
52
+ "loss": 13.3329,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0007486150621350501,
57
+ "grad_norm": 3.601372241973877,
58
+ "learning_rate": 0.0001,
59
+ "loss": 12.3815,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0008983380745620602,
64
+ "grad_norm": 4.870517730712891,
65
+ "learning_rate": 0.00012,
66
+ "loss": 13.1262,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0008983380745620602,
71
+ "eval_loss": 3.0220553874969482,
72
+ "eval_runtime": 277.2274,
73
+ "eval_samples_per_second": 10.147,
74
+ "eval_steps_per_second": 5.075,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1099405738377216.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null