havinash-ai commited on
Commit
f9705d0
·
verified ·
1 Parent(s): 1e8fa5d

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:c3815d64981c91867d521c7050fbad75c200643c8e4750e9db52a0f0c8d6ae66
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c3f545168d9796ebce05fc9ffff0ab0ef52ada4d375b9b67178a365c9acc19
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:274f8e8a60999a59fe31e87c3b8a84d162de4ab77b7cf5c61cee9461a92f8ecb
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a250e08bb30683ad16c743eb8ab58dd6bf7c4163fad3ac79ee54ca13c33d1c3
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 sha256:19394caac0370dc5eb8bb3d271a9b6d245fc10d68ceffd549459fcf4f2e70bc9
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": 0.0002393823934249636,
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": 19.719,
74
  "eval_steps_per_second": 9.86,
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": 0.0003590735901374454,
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": 19.719,
74
  "eval_steps_per_second": 9.86,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00027927945899579087,
79
+ "grad_norm": 40.676212310791016,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.6105,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003191765245666181,
86
+ "grad_norm": 16.026796340942383,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.5054,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003590735901374454,
93
+ "grad_norm": 8.725200653076172,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.0238,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003590735901374454,
100
+ "eval_loss": 3.485398054122925,
101
+ "eval_runtime": 476.979,
102
+ "eval_samples_per_second": 22.127,
103
+ "eval_steps_per_second": 11.063,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2450672628793344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null