kostiantynk1205 commited on
Commit
5431bf8
·
verified ·
1 Parent(s): 72e6683

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:be6fac3179da944088bbb575d45563a852b99a1ffe22775655f6800d238fd1ce
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba2250b758359407691455c2ef67c90bd008984555267115950456a54fdaa05
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9ef28863310fac9fe2ad3f779f6693a34944e365f67657c9b03638c7e7ae6f6
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33da97eae43b8001922dda89659c28a8c12feabeb31d3aa6811c7fc34ba9944
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1097b6282e8c4a50e14783e29dad96846468dd1e20fb1487e6f416b722ae25d7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb5987ba29ffae1a6d1e2bcd10e38cb87eca775dd693e34444e8a0fbb9d1fbb
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": 15.575,
46
  "eval_steps_per_second": 7.787,
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": 15.575,
46
  "eval_steps_per_second": 7.787,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0008426670411853516,
51
+ "grad_norm": 0.37750139832496643,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.3475,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0010954671535409572,
58
+ "eval_loss": 0.3713858127593994,
59
+ "eval_runtime": 962.8376,
60
+ "eval_samples_per_second": 15.569,
61
+ "eval_steps_per_second": 7.784,
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