kostiantynk1205 commited on
Commit
5e85a23
·
verified ·
1 Parent(s): 3ba151a

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 sha256:59116b16a704ddd3f569f2bab269641b989a3282b06217d7524a99bc409d1f56
3
  size 66103768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6cf99cd37e59c16b37331fcb15133a4053695ddf6085ababe7436d36e9fb7f1
3
  size 66103768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87f86091bbf26328ec561878e8c67897c08d741bbcb9c0d4e5341fa517bd80a5
3
  size 33939412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f735dd95cbf7fae2206de36161f83ce1ce84625824b0f15a00a60b88d1c38b
3
  size 33939412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1b713c9def3d23a6b3ba921494e605c08b34003105171b1b74a2fe3bc599bd1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c24c62e4cd7b0332ff8817426a459e70a6e7e90cb15d9bcaac496100d630999
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": 0.0008335648791330926,
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": 18.397,
74
  "eval_steps_per_second": 9.201,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1656448963203072.0,
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": 0.0012503473186996387,
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": 18.397,
74
  "eval_steps_per_second": 9.201,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.000972492358988608,
79
+ "grad_norm": 1.6884574890136719,
80
+ "learning_rate": 0.00014,
81
+ "loss": 7.8317,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0011114198388441233,
86
+ "grad_norm": 2.2202513217926025,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.912,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0012503473186996387,
93
+ "grad_norm": 1.8601514101028442,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.7306,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0012503473186996387,
100
+ "eval_loss": 2.223845958709717,
101
+ "eval_runtime": 164.824,
102
+ "eval_samples_per_second": 18.389,
103
+ "eval_steps_per_second": 9.198,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2376644164595712.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null