shibajustfor commited on
Commit
ee1f1bd
·
verified ·
1 Parent(s): f4c956e

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 sha256:56a7143eb127d2a8c89687af5d55981cb801945ec29a1e7c68370da5884a1e19
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88485fe7793dcaecb2478a2f90a99d689cdecac72693372f782c62086a0608d
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f70c44a4a5f4f7a5325baa9bc5602044187d7ba256cd06840336c01ff0fb773b
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbf7b276b74f997dad00f30133b1d37f13fca0d19160ceb9f2437d8519bf272
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d44674e2e3b9f7554311b4e60eca4d2c20155a8871289e702a9e642015db6204
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59644a58893e50212ccc11d836aae9e81423261edd2c8244dc8fc0cd5ce0151
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": 0.0007303114356939714,
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": 15.65,
46
  "eval_steps_per_second": 7.825,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 9135190211297280.0,
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": 0.0010954671535409572,
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": 15.65,
46
  "eval_steps_per_second": 7.825,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0008426670411853516,
51
+ "grad_norm": 0.38002777099609375,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.3478,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0010954671535409572,
58
+ "eval_loss": 0.3715435862541199,
59
+ "eval_runtime": 958.5409,
60
+ "eval_samples_per_second": 15.638,
61
+ "eval_steps_per_second": 7.819,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.394040587157504e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null