philip-hightech commited on
Commit
ef1dc97
·
verified ·
1 Parent(s): 5ae9cdd

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 sha256:6f9dea8cebe1141bc6997efd26a85adb49ba96068853a2ea382fb3af053097ff
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34d0ab3f769eb6f131d2298b19c9f685f4d19880278c28b99fb6a994e43ffad
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eda7ffb60687703c60aed51975da5062941c3225fb70a861c0960c48c1135f81
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e323229fe93089232fc9e8715f4398c40070624f90d498f431d53ad45f923fa3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f005639ce0865eae9775065c9fed38932da15f22f9e96d8e1fc81a298bdf6ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
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": 0.0004662004662004662,
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": 23.075,
45
  "eval_steps_per_second": 11.538,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 786064805462016.0,
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": 0.0009324009324009324,
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": 23.075,
45
  "eval_steps_per_second": 11.538,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0006216006216006216,
50
+ "grad_norm": 2.470583200454712,
51
+ "learning_rate": 8e-05,
52
+ "loss": 6.3336,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.000777000777000777,
57
+ "grad_norm": 1.9067507982254028,
58
+ "learning_rate": 0.0001,
59
+ "loss": 4.3592,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0009324009324009324,
64
+ "grad_norm": 3.4067890644073486,
65
+ "learning_rate": 0.00012,
66
+ "loss": 5.8512,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0009324009324009324,
71
+ "eval_loss": 5.809554576873779,
72
+ "eval_runtime": 117.4521,
73
+ "eval_samples_per_second": 23.073,
74
+ "eval_steps_per_second": 11.537,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1664607823331328.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null