Best000 commited on
Commit
bcda640
·
verified ·
1 Parent(s): 4b22319

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 sha256:2799d6a06be1587fd050ef7a7ce4d722b63016eb8f5230a0d715cd4d0d86a343
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30a688057c80d1476e2b7c0457f500ba62dd58b7bfc8747b6bca3a2b4b4572c
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05be5469a1d6735879bd906cedefd99736c28bd177f4a323378a41090048c16e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af88a2e133501e2ed5d82e56be40c8e485de7f8b48bda06b82e6623f861b500
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": 0.000143448012049633,
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": 19.491,
74
  "eval_steps_per_second": 9.746,
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": 0.0002151720180744495,
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": 19.491,
74
  "eval_steps_per_second": 9.746,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001673560140579052,
79
+ "grad_norm": 1.1959559917449951,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.7878,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00019126401606617735,
86
+ "grad_norm": 0.7699796557426453,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.144,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002151720180744495,
93
+ "grad_norm": 1.2344245910644531,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.656,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002151720180744495,
100
+ "eval_loss": 3.1701889038085938,
101
+ "eval_runtime": 988.1134,
102
+ "eval_samples_per_second": 17.824,
103
+ "eval_steps_per_second": 8.912,
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