nat-hunt commited on
Commit
913a79a
·
verified ·
1 Parent(s): e97dabf

Training in progress, step 42, 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:eb8a221c6135ceea351e87a19048ed3317af6f6f897c93fca714d149d9bfb9f4
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d7cdf226bad03dbef63e9b9f6505dcf65ef1b30da355ff5e8f3d8ae9d26bbf
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f06e9a6d6aaf16453fe8e391f706522a4c77be2366dbfec535ed44c3190df2b
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16204f53b210de3cbf2b4ceaca61d7cd5a00e5aeb96f90dfe60d22d513f86c9c
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c79f991d6cab3d774fa6aef4489d318512c29032b783d1f2d34eb0ee8e527747
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7435821fdd367275b38dd7f43b19cc2552d64f5a2461fe7a22bbd1ed764a7350
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cf140526b08395dbd0793ca343f0f70c5fb866a714c27208d9b9b1ce1a60172
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
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": 0.013164080865068171,
5
  "eval_steps": 14,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,28 @@
45
  "eval_samples_per_second": 393.301,
46
  "eval_steps_per_second": 196.65,
47
  "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +86,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 407323607040.0,
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": 0.019746121297602257,
5
  "eval_steps": 14,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 393.301,
46
  "eval_steps_per_second": 196.65,
47
  "step": 28
48
+ },
49
+ {
50
+ "epoch": 0.014104372355430184,
51
+ "grad_norm": 0.04112238809466362,
52
+ "learning_rate": 0.0001,
53
+ "loss": 10.3735,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.018805829807240243,
58
+ "grad_norm": 0.038700807839632034,
59
+ "learning_rate": 4.12214747707527e-05,
60
+ "loss": 10.3718,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.019746121297602257,
65
+ "eval_loss": 10.370706558227539,
66
+ "eval_runtime": 2.298,
67
+ "eval_samples_per_second": 389.905,
68
+ "eval_steps_per_second": 194.953,
69
+ "step": 42
70
  }
71
  ],
72
  "logging_steps": 10,
 
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 617450864640.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null