Nexspear commited on
Commit
204a0fb
·
verified ·
1 Parent(s): 81e12e4

Training in progress, step 15, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55030b20caca048637fe1ea811707789c40bc170d01c0a47b083e79446548fc6
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f4e51bed17eb56869c2fc2d96a7f8e8b70aa63acaf71803357ce324b1d9b8e
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f6a3a45e24257d9848f134bd87b44baf6549dd9f11306859f571086ac246d2a
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbbdcd95cb688f6db2ee6f2752d625eaf67d6d2eaf9d7fea1708f3fc3161077f
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47ba7527fe6396c48f048eec5dbebbe83dd44cb9f375a7b9085d2380d5ce3551
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc6dab0f4dc4a00c15974f378193661a0a163003730e8304a27e1c7de229ff4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
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": 0.00701877522372346,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,28 @@
52
  "eval_samples_per_second": 458.451,
53
  "eval_steps_per_second": 57.306,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 1143394271232.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01052816283558519,
5
  "eval_steps": 5,
6
+ "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 458.451,
53
  "eval_steps_per_second": 57.306,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.008422530268468151,
58
+ "grad_norm": 0.05700007453560829,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 10.3739,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.01052816283558519,
65
+ "grad_norm": 0.07175807654857635,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 10.3717,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.01052816283558519,
72
+ "eval_loss": 10.374283790588379,
73
+ "eval_runtime": 5.229,
74
+ "eval_samples_per_second": 458.977,
75
+ "eval_steps_per_second": 57.372,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1729035239424.0,
97
  "train_batch_size": 8,
98
  "trial_name": null,
99
  "trial_params": null