chauhoang commited on
Commit
f834c77
·
verified ·
1 Parent(s): bfb435e

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 sha256:2b7941b2a9cb61ac983217ab3e7d8f2bfe52a778f4486f9fc61ad0a73c6f04ec
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1000698e47d18cbde8251cb413a4a939ea5d19b02d6be2f3aa21835c6c98c4
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388618196a8bc01f7b9c3924edad037a902c6a67fbc668bb89573423be7d0825
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796d8c36d98a41d34e6f0de45d45ec0055666546d2789699721e36959feef64b
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a787192adbf84242f4b8cb401581e3a7836211ae22a109ec4de70e071b1870b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4d38c91461c8bd2b1846111e4953c1dc1e466ee07568e8fed1ad255d7379fd
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": 0.014225140199699084,
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": 0.7444,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4574419620986880.0,
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": 0.021337710299548625,
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": 0.7444,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.016413623307345096,
72
+ "grad_norm": 3.1235790252685547,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0391,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.016413623307345096,
79
+ "eval_loss": 0.6169207096099854,
80
+ "eval_runtime": 51.3498,
81
+ "eval_samples_per_second": 14.995,
82
+ "eval_steps_per_second": 7.498,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.019149227191902613,
87
+ "grad_norm": 4.052883148193359,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.4649,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7057675986665472.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null