havinash-ai commited on
Commit
bee2a2b
·
verified ·
1 Parent(s): b0c6950

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:d1108f7fb395438a13c45c08f013b21c73f9673e136398d65a938b7d0f89226a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1f3297f155c45126a563fb04d87546a6e7663fcadd054ac7f0e72380185ff0
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd89b2f447c68cd7ec841b4c9d5e864bdddd6056bbc596881ce8680c77bca47
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb0d1fceefc062fb5941a9bedca22855e90c9c0282741b33699cfa86388707e
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:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df342e12f5c8177b234bccf3ed8fd60c478a1873dba9a7db1e26b1f1caf1d1fa
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": 0.00019865576267258218,
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": 28.676,
74
  "eval_steps_per_second": 14.339,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1202216761294848.0,
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": 0.0002979836440088733,
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": 28.676,
74
  "eval_steps_per_second": 14.339,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002317650564513459,
79
+ "grad_norm": 0.6438420414924622,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.2335,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0002648743502301096,
86
+ "grad_norm": 1.0555274486541748,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.0401,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002979836440088733,
93
+ "grad_norm": 0.9960046410560608,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.7068,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002979836440088733,
100
+ "eval_loss": 2.775230646133423,
101
+ "eval_runtime": 443.5677,
102
+ "eval_samples_per_second": 28.67,
103
+ "eval_steps_per_second": 14.336,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1757086035738624.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null