lesso13 commited on
Commit
49c2255
·
verified ·
1 Parent(s): a6a9d70

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f73a8752f939eee3b0861d1274231b47eba85f91a1fac0885ed4aabc1971f81
3
  size 188784440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7395d78d40dc43b15bd8a531b0b277923697d43bf549cf4df97a436d5a81ea11
3
  size 188784440
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2245edf9dd2e8a6be6019f9ac4df59d450c62ba802df978d094999b00e9d755d
3
  size 377658554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e127f02d25d63d40f71581fa199bf2bfcf2c67e8a31e4b6f45edfc3e06360af
3
  size 377658554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22064a6ad321d076e149c2088e40e915a89692221e52177f897b1b55abd1bdaf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666da658b919333c192491b671083554125e623cc746a64fb7c027e5393167de
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.024891101431238332,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 0.00018,
45
  "loss": 3.9208,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 5717207128473600.0,
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": 0.049782202862476664,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 0.00018,
45
  "loss": 3.9208,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.029869321717486,
50
+ "grad_norm": 1.7839148044586182,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 3.8047,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.037336652146857496,
57
+ "grad_norm": 1.2594926357269287,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 3.5741,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.03982576228998133,
64
+ "eval_loss": 0.8886153101921082,
65
+ "eval_runtime": 50.8044,
66
+ "eval_samples_per_second": 3.346,
67
+ "eval_steps_per_second": 1.673,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.044803982576229,
72
+ "grad_norm": 1.2804442644119263,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 3.4823,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1.14344142569472e+16,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null