tensor24 commited on
Commit
a64240f
·
verified ·
1 Parent(s): 0f05576

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 sha256:12cb2b2828a0d7ab9f209ff204be5cc47ea00fa0aa467eb0bc1816aca457f2c3
3
  size 100697728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f774f184c8184fa3623bf32dfec2c943f975ea15e8ef31323df32716261743
3
  size 100697728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6336c4868ef364cf215d70d867b7d4985da8e4fe0805fa3078704a38488bc00a
3
  size 51418196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1faca3e00d5dc62a81114ff201b4f127b10271954f6c4c22635066f7458884d
3
  size 51418196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1262f1ceabe7916769b7447217039f027c6f83a27e1c0141c16b2b148f9b0d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c357bfafab62ab14f0d4c4d9570ed28194b02613077cfb4fb793b2cb8e259cc2
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": 0.0021893814997263274,
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": 3.248,
45
  "eval_steps_per_second": 1.627,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 2210509810040832.0,
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": 0.004378762999452655,
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": 3.248,
45
  "eval_steps_per_second": 1.627,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0029191753329684362,
50
+ "grad_norm": 21.96184730529785,
51
+ "learning_rate": 8e-05,
52
+ "loss": 36.8291,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0036489691662105455,
57
+ "grad_norm": 23.605018615722656,
58
+ "learning_rate": 0.0001,
59
+ "loss": 35.7411,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.004378762999452655,
64
+ "grad_norm": 26.890573501586914,
65
+ "learning_rate": 0.00012,
66
+ "loss": 38.8873,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.004378762999452655,
71
+ "eval_loss": 8.529736518859863,
72
+ "eval_runtime": 177.7105,
73
+ "eval_samples_per_second": 3.247,
74
+ "eval_steps_per_second": 1.626,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 4421019620081664.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null