kk-aivio commited on
Commit
1cb9549
·
verified ·
1 Parent(s): 8390375

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 sha256:5abae79191be6b78b8961f9b230e56f289dc4eb02ca7e78880d4fd4f4e922460
3
  size 47235968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdac9f9130fcf36ece265280a5f5670e9dbf6823b89e877d84b0f6a30f1ec81
3
  size 47235968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aab36ed1daafd83e304cc46429c93dfb72984ecf7a0138fe84f1cb7bcf49898
3
  size 24410836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e499da8de79fad7bef33124a8e4abdfab1479bac4db436acbc6735c6b237c91
3
  size 24410836
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20fabbd3530b65abbae13570a3d6b6023989d569ba9d0b8340cc65b704944cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0576b700818dca016596489cc779fc592763d3d2be4d59097188efa34f62480
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": 0.0043876302577732776,
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": 44.012,
46
  "eval_steps_per_second": 22.015,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1699937066680320.0,
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": 0.006581445386659917,
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": 44.012,
46
  "eval_steps_per_second": 22.015,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.005062650297430705,
51
+ "grad_norm": 8.063873291015625,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 1.3195,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.006581445386659917,
58
+ "eval_loss": 1.2810492515563965,
59
+ "eval_runtime": 56.5925,
60
+ "eval_samples_per_second": 44.087,
61
+ "eval_steps_per_second": 22.052,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 2549905600020480.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null