tuanna08go commited on
Commit
7f5a2b5
·
verified ·
1 Parent(s): a584aa9

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 sha256:91094d08055e3e99fe094e0e373336458789e0997733b1ee0c88f128bc03ad3f
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d166edb66ecc6e96dac5a0d7aaef02a0d6938af07ac43d7aea25b7cbd34f8c9
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d2ed57d6081b7d4a1ceec7332cb3bdef216f421efd9a0a8676dfb75e5e234e2
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118357c000ea3ff7aad9795be734915c6def5b2651aae72386aa0f9e60a15f21
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:f4731a08616a258f51b82e9dd7d1ca90fe5909a76608a64af8bc3dc01ce461b8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef36bdc1b35a92e49ed00b8b3f1f22e99127b8d03f4084585183c1c83a3d7dc
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": 0.07396870554765292,
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": 10.3769,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 578658140160.0,
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": 0.11095305832147938,
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": 10.3769,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.08534850640113797,
72
+ "grad_norm": 0.024922257289290428,
73
+ "learning_rate": 5e-05,
74
+ "loss": 10.3789,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.08534850640113797,
79
+ "eval_loss": 10.373941421508789,
80
+ "eval_runtime": 0.8889,
81
+ "eval_samples_per_second": 166.498,
82
+ "eval_steps_per_second": 83.249,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.09957325746799431,
87
+ "grad_norm": 0.021093839779496193,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 10.3783,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 853439938560.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null