great0001 commited on
Commit
3c58f7a
·
verified ·
1 Parent(s): 50430c3

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d8ab291c926e4e002d093a3f19591cbfa0db12ba6f4f39d48310e27af79f2
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fbbd3758ca728b013e1c238d0add48620a637527fbffe50b1516c915228810
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4202aed9ccfb7057d653eb2be36922f49e6fcc0af716385a6997bec6f563d51a
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb05b8c3f2ceb28969a1c7e84a4d5eb2a3c146aa7d950bdeae122576c85a6c51
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c013662eb3d2cf5fd75b84bce4f03835c6a78f724775d1abe2fb6d699b6aa4ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bceb7de99ff7b17d6ec7d794e86c7f9fba87fb5bd36c827c120924e029007a1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.31137724550898205,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 56.919,
46
  "eval_steps_per_second": 28.459,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 645719660691456.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.46706586826347307,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 56.919,
46
  "eval_steps_per_second": 28.459,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.3592814371257485,
51
+ "grad_norm": 0.0009263353422284126,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.0,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.46706586826347307,
58
+ "eval_loss": 1.6689746189513244e-05,
59
+ "eval_runtime": 0.308,
60
+ "eval_samples_per_second": 58.433,
61
+ "eval_steps_per_second": 29.217,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 968579491037184.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null