dimasik87 commited on
Commit
9c5dced
1 Parent(s): c39078c

Training in progress, step 8, 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:a75acaa9c0923b3ce2f86f82caa824047564e8e22cc0f07e2e83cf22ab78b9bb
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ffebc8520cfd036116ae46f6b2835a8e50eaa1d1c8088c4612a581676ee410
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23b869c79a588d911379bb179c2a336b972c3c2b2d49d9bfc4a97b9789a9774b
3
  size 194742714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cadcbd061e25e907e905d60404aa395a8802ca73261374aed9b94401f9381a1f
3
  size 194742714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ee2cd8c5c5beec086c14fd6869707b8b3d6d60db535cc5e7213498a9856b51
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 sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.0012134081601698772,
5
  "eval_steps": 2,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -81,6 +81,28 @@
81
  "eval_samples_per_second": 7.895,
82
  "eval_steps_per_second": 7.895,
83
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  }
85
  ],
86
  "logging_steps": 1,
@@ -100,7 +122,7 @@
100
  "attributes": {}
101
  }
102
  },
103
- "total_flos": 1676905757540352.0,
104
  "train_batch_size": 1,
105
  "trial_name": null,
106
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0016178775468931696,
5
  "eval_steps": 2,
6
+ "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
81
  "eval_samples_per_second": 7.895,
82
  "eval_steps_per_second": 7.895,
83
  "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.0014156428535315234,
87
+ "grad_norm": 0.4819552004337311,
88
+ "learning_rate": 0.00014,
89
+ "loss": 2.2254,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.0016178775468931696,
94
+ "grad_norm": 0.34892919659614563,
95
+ "learning_rate": 0.00016,
96
+ "loss": 2.3499,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.0016178775468931696,
101
+ "eval_loss": 2.0889296531677246,
102
+ "eval_runtime": 131.8555,
103
+ "eval_samples_per_second": 7.895,
104
+ "eval_steps_per_second": 7.895,
105
+ "step": 8
106
  }
107
  ],
108
  "logging_steps": 1,
 
122
  "attributes": {}
123
  }
124
  },
125
+ "total_flos": 2235874343387136.0,
126
  "train_batch_size": 1,
127
  "trial_name": null,
128
  "trial_params": null