daniel40 commited on
Commit
01d8722
·
verified ·
1 Parent(s): 662475f

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 sha256:4efc025c7f52e778d036e9922a1d395da6fcbc5d6012e408aecb8d846c3e6c3c
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc708f488c87dfacc58b27754e2a0a109cc8b6726e6ffef955af585a65e6b416
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14bea7038ce26cb702f9480082584b20e01a8a33f40ddce09f221f6293429a6f
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bebd7d96c7a506c0caf17d4f11d635dba6bd1bc6996f9ff80c877c79386927
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f30a67427262f36b8dc8e78cd118c45a4ced87393a58db0b71b4f804d1ee1c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62708c636bc8cc7b15d22a9dcde570698e82a0c4bc55a7697cb5721a614ef94f
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": 0.0456140350877193,
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": 58.139,
46
  "eval_steps_per_second": 29.07,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1697668241817600.0,
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": 0.06842105263157895,
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": 58.139,
46
  "eval_steps_per_second": 29.07,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.05263157894736842,
51
+ "grad_norm": 6.468547821044922,
52
+ "learning_rate": 0.0001,
53
+ "loss": 6.8025,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.06842105263157895,
58
+ "eval_loss": 1.6305490732192993,
59
+ "eval_runtime": 4.0462,
60
+ "eval_samples_per_second": 59.315,
61
+ "eval_steps_per_second": 29.658,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 2546502362726400.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null