chauhoang commited on
Commit
dea4539
·
verified ·
1 Parent(s): 271fd0b

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:ddca857622e8c27f1d9324dd3fe0199f7c657b8990db04c7d39cae5b27d1b051
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb59ab53eed95e048a44b2925fc2333ffda1c96ba58aaac9172aa37b29793a67
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62b0531560d14359096182cbb60658ebacbd1e6cb8319d6c57b3b8c5b50ff45
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c1e6c104e1bdbe4651421baf71abd65a1c5b9b2e78d42cc747f73e5ff9e97c
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c363fc4792873829483e3b7bc2e930f4a294b39eed7cda2957acf45aeacdb1e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaadf4f547cd21543ad7ff107e2d09294cf6114de0af2a672ddac834a188b9ea
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.002240751513584556,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.0782,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3095683710320640.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003361127270376834,
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,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.0782,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0025854825156744875,
72
+ "grad_norm": 5.677429676055908,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.795,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0025854825156744875,
79
+ "eval_loss": NaN,
80
+ "eval_runtime": 247.7294,
81
+ "eval_samples_per_second": 19.723,
82
+ "eval_steps_per_second": 9.862,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0030163962682869024,
87
+ "grad_norm": 2.328920841217041,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.075,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4530768874045440.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null