tuanna08go commited on
Commit
d9cdb4d
·
verified ·
1 Parent(s): b4ef6c0

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 sha256:7d29ac3f99014fc5a89ce38ab04f1dd7c9b1985e22a84e126a402d4bfa816dca
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1368f26d749c926a03092ec498deaf08a2ad54127599df47628f795f28e34632
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:757f1089063b0d9a3b0ad0f440f48fa0505a4b560a1bc4f8a7a7cccd30987d61
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3208704531c5f44dca6151413170d6a6df7e252d74a1689d88aebefe59e99a6d
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4f501a9b008bbdac942265279f859f2d9a1efce9fc3263e2d1364604049c85c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b49347475bc642ab719c98ac65f8cfd14867cc100c9208e704116b69aa264c7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.09985597695631301,
5
  "eval_steps": 10,
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": 48.591,
46
  "eval_steps_per_second": 6.091,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 6383420376612864.0,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1497839654344695,
5
  "eval_steps": 10,
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": 48.591,
46
  "eval_steps_per_second": 6.091,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.11521843494959194,
51
+ "grad_norm": 0.26952123641967773,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 1.5848,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.11521843494959194,
58
+ "eval_loss": 1.5333625078201294,
59
+ "eval_runtime": 36.4056,
60
+ "eval_samples_per_second": 48.207,
61
+ "eval_steps_per_second": 6.043,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 9575130564919296.0,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null