kostiantynk commited on
Commit
5c65f9e
·
verified ·
1 Parent(s): e09d074

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 sha256:267d8b1ebfa2d150fbc8b0486f0c452f7a32aa49823636814ce411d327d814a3
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8977d57e78d7c0ac5f86abf60a6c2550bfbf115f2fb5f260922fc22e45dd9df5
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528c76132e80bd83990f741222370c0e55c52970cef0f8213d261f8ffdd85cda
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04302e83fe96d2882ca6dfc7f0b9f933970c9aa74a2e1ed51f828f0a45d0250
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bc810ded9a6553aa4ffc5e0c7dc10e42b829691498e07f15eb121c3db31fe36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecc3ffb2f15d93a45a27255b0eb1aeb7ab4841220e6a7b127189fc85f6acec1
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": 0.0003651557178469857,
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": 15.634,
46
  "eval_steps_per_second": 7.817,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4449637087838208.0,
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": 0.0005477335767704786,
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": 15.634,
46
  "eval_steps_per_second": 7.817,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0004213335205926758,
51
+ "grad_norm": 0.5551108717918396,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.3513,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0005477335767704786,
58
+ "eval_loss": 0.3726792335510254,
59
+ "eval_runtime": 958.9138,
60
+ "eval_samples_per_second": 15.632,
61
+ "eval_steps_per_second": 7.816,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 6886343112130560.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null