havinash-ai commited on
Commit
dc89a8c
·
verified ·
1 Parent(s): 6db4964

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:ccc5a89a83fd5f43e202d2057048a7482d623b385d2c02632fa5a473ed0cbdb6
3
  size 28350504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0910f52a3e188b9da426bb6031bbe2c51b3c2c0e4d879ec64f1f9cb21d0cad06
3
  size 28350504
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4f501a6ff6c070f6a759544d36756e6c6deb99c65c8061261cf2b1a82e7ced3
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e831aa4017482bf57b8ec93736e091d2d915eda972b60eeb56a105e7caa2a44
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:400a6d6a18fc16b638aeb824699e8e27e212104bd39097badfed36b500f6402a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1022d0341e89b05c8b4b19b5dc13f0dbef27d04eb03a1236b70fba46deea72a9
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": 0.021957913998170174,
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": 51.517,
74
  "eval_steps_per_second": 25.983,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 179237642305536.0,
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": 0.03293687099725526,
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": 51.517,
74
  "eval_steps_per_second": 25.983,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.025617566331198535,
79
+ "grad_norm": 26.675048828125,
80
+ "learning_rate": 0.00014,
81
+ "loss": 42.8055,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0292772186642269,
86
+ "grad_norm": 29.66798210144043,
87
+ "learning_rate": 0.00016,
88
+ "loss": 41.4285,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.03293687099725526,
93
+ "grad_norm": 33.63569641113281,
94
+ "learning_rate": 0.00018,
95
+ "loss": 37.7123,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.03293687099725526,
100
+ "eval_loss": 7.950884819030762,
101
+ "eval_runtime": 2.2054,
102
+ "eval_samples_per_second": 52.146,
103
+ "eval_steps_per_second": 26.3,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 268856463458304.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null