kostiantynk-out commited on
Commit
a59a9e3
·
verified ·
1 Parent(s): b2ca386

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 sha256:49c94d33fb0b832708ba497b212de03fb0f046c564653ba1dbd9cff410157922
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a26c8e128c5dc26d8ff4ccf250f97980b651ba6864cb77b0079a96e63616a97
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdbac12b98442db665bb08215001b1ac5747386370657e8fd84f96e044512fe1
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90cea94123626b1ac41d3c9bce9b81fac42a8037904ff15f17c174b594a85ca8
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3dd893c207e3d1f2bc028be6b52b91d3d83dc4d2ada4afcc861658c1da027ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8533fae84b8bbe35ecff98d5d66a1e19344edfcde38ca202b781a73c8943ca
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": 0.0011597564511452595,
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": 20.773,
45
  "eval_steps_per_second": 10.387,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 615718085197824.0,
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": 0.002319512902290519,
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": 20.773,
45
  "eval_steps_per_second": 10.387,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.001546341934860346,
50
+ "grad_norm": 2.2434349060058594,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.9627,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0019329274185754324,
57
+ "grad_norm": 3.057121992111206,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.0058,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.002319512902290519,
64
+ "grad_norm": 3.5964255332946777,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.3888,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.002319512902290519,
71
+ "eval_loss": 1.9325042963027954,
72
+ "eval_runtime": 52.4509,
73
+ "eval_samples_per_second": 20.781,
74
+ "eval_steps_per_second": 10.391,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1231436170395648.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null