trenden commited on
Commit
12796ca
·
verified ·
1 Parent(s): 05a5714

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32f7bfc6cf8992379ed257c4e3f200046e818c7fd8bb702e36cff2366b5d7f9c
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04ebe5c84c8b3262633d34efc299ef4a84992880d5c41a439103022f69535e3
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26be9a0dd1aa463b700fbb45d805aac59733a74eda796ca73aa2d80fa7068ad3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbbcb23d25c544f81a8c2543a41d190bbb16acc1fc25cf12788c539eeb42cda
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e0cecd4fa0b346dabc60917e1b3ca1c91ce878034ad78d001aa7d9a1f75d88e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af9dcf2fb5ed0d697f9edd141933429239d504a5421e3ad9ffe3f66c8eb063a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0018709073900841909,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 24.199,
74
  "eval_steps_per_second": 12.109,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1618368717127680.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002806361085126286,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 24.199,
74
  "eval_steps_per_second": 12.109,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002182725288431556,
79
+ "grad_norm": 0.8463139533996582,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8157,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002494543186778921,
86
+ "grad_norm": 0.6177520155906677,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7816,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002806361085126286,
93
+ "grad_norm": 1.193546175956726,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.626,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002806361085126286,
100
+ "eval_loss": 1.691176414489746,
101
+ "eval_runtime": 55.8437,
102
+ "eval_samples_per_second": 24.193,
103
+ "eval_steps_per_second": 12.105,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2496911734996992.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null