Best000 commited on
Commit
107c27d
·
verified ·
1 Parent(s): 4ad019e

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 sha256:14989537dbff3c0736a657d50e22909e0cd30b24556bfb203766eb8c74cb2e01
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5e2f5f13084c419a12251d7392b9d4b1e4b8a507d3ab03ef7ffd2a6f7da90e
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e314abc50936800b969a408bf5f783d1b1e4148e714ebe1203d07a2f8c8e34ae
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f0f3848d2b58ceaaffcc3a7b9e5a965174d6d074cc5fb752c1dffb60d2cc17
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79e434457798f9692151fe018459b1bda48cd1e999a3dd276a4432fd1d9a599e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89aa540b8c3fabbcd74d788f9d4a71f3d52d803910db8076339022610c2b0f1f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
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": 0.34551495016611294,
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": 34.526,
46
  "eval_steps_per_second": 17.263,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1300253059842048.0,
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": 0.5182724252491694,
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": 34.526,
46
  "eval_steps_per_second": 17.263,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.39867109634551495,
51
+ "grad_norm": 1.948126196861267,
52
+ "learning_rate": 0.0001,
53
+ "loss": 1.1238,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.5182724252491694,
58
+ "eval_loss": 1.2024189233779907,
59
+ "eval_runtime": 0.9576,
60
+ "eval_samples_per_second": 33.419,
61
+ "eval_steps_per_second": 16.709,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1950379589763072.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null