Aivesa commited on
Commit
312412b
·
verified ·
1 Parent(s): 2894c87

Training in progress, step 10, 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:b8f5aaf1323b06c7a2115e658947e4a9527903b885d45c171d1d55669485be15
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeedd722bcf9c553b29583ed89f09f09a3aa69c8174998ffe8c41400b79f35c8
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb5abb449d58e9b52950831cdbc95f48a963b067589244e1cf5e455722db93b
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bcea94baced0ba4c09a189f6e611c212074e012ed346bb849a6602905ff1db6
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b84c4d7aecf471df9c53c6191a11fb466bb6c04965a38b499e884c5f558f41e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ab434eb413c22dfe68751d23f523b350e713befd5789cab3e4721ae4a95e77
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.000898069151324652,
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,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 58.928,
95
  "eval_steps_per_second": 29.464,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 9967478243328.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009978546125829467,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 58.928,
95
  "eval_steps_per_second": 29.464,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009978546125829467,
100
+ "grad_norm": 2451.3212890625,
101
+ "learning_rate": 0.0002,
102
+ "loss": 776.4106,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 11074975825920.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null