havinash-ai commited on
Commit
6b3fa03
·
verified ·
1 Parent(s): ff43a62

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 sha256:35ff6e996b906c18a2ba4e4215c41de305d53061820b1b6fa0bfe889b3644944
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949fa4e51e6e0bcfe5fe935c9979f5e0c2e798045feace14181cbe28c733247a
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080eaf89a3066cade79c2b266e821b4ba394d86a5cfd63b7a43426f57d011169
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63acaa5ca932ae4c3f035ef1ea6dd3541f3ac122cf2b60c524603ecc30095de
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb741a1b6c12fea007d9d6a85137f098d7e74d9ca251e354a6aa242a9cce0ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871f3f67e05823016dc8caa40ed97d5df9a85df2277a4171af37ea6a888e3518
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": 0.002548853016142736,
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": 28.333,
74
  "eval_steps_per_second": 14.167,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 550772026638336.0,
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": 0.0038232795242141037,
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": 28.333,
74
  "eval_steps_per_second": 14.167,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002973661852166525,
79
+ "grad_norm": 1.8160585165023804,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.3594,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0033984706881903144,
86
+ "grad_norm": 1.542261004447937,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.4013,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0038232795242141037,
93
+ "grad_norm": 1.645046353340149,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.373,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0038232795242141037,
100
+ "eval_loss": 1.691546082496643,
101
+ "eval_runtime": 68.0827,
102
+ "eval_samples_per_second": 14.571,
103
+ "eval_steps_per_second": 7.285,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 872055708844032.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null