philip-hightech commited on
Commit
1b5f367
·
verified ·
1 Parent(s): dc3bc75

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:c34d0ab3f769eb6f131d2298b19c9f685f4d19880278c28b99fb6a994e43ffad
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28c22dacb22458c2e23e2b0abe7d61b1cd156de9b928772f0139a322c89c412
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e323229fe93089232fc9e8715f4398c40070624f90d498f431d53ad45f923fa3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e572d1b3cf04d87914b0565f3e216cca951dad87b4be3825f3afcb675e35ab00
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
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": 0.0009324009324009324,
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": 23.073,
74
  "eval_steps_per_second": 11.537,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1664607823331328.0,
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": 0.0013986013986013986,
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": 23.073,
74
  "eval_steps_per_second": 11.537,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0010878010878010878,
79
+ "grad_norm": 2.6836624145507812,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.7178,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0012432012432012432,
86
+ "grad_norm": 3.25949764251709,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.602,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013986013986013986,
93
+ "grad_norm": 3.4510438442230225,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.7354,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013986013986013986,
100
+ "eval_loss": 5.102389335632324,
101
+ "eval_runtime": 117.4294,
102
+ "eval_samples_per_second": 23.078,
103
+ "eval_steps_per_second": 11.539,
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