kokovova commited on
Commit
c837cb9
·
verified ·
1 Parent(s): 7a92abc

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 sha256:5a31f88865b9268018427c7cea413f9496745f91c9c90684d113e75cadea782f
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f67e954968353fa80c1969dc74382b4ebc7cbd2e20c03f63febaa3b2754dca3
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea9d020c079fb5422cfd7eeb0ebcb8b20c79efed2024c3b3cd625d14b6fd418
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5028ffd2f143aa768ca76abed34f698ef664656210aecaccae607986b9a3b4f3
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 0.0007801833430856252,
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": 331.351,
74
  "eval_steps_per_second": 165.727,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 161636352000.0,
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": 0.0011702750146284377,
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": 331.351,
74
  "eval_steps_per_second": 165.727,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0009102139002665627,
79
+ "grad_norm": 0.03581219166517258,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.3755,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0010402444574475,
86
+ "grad_norm": 0.04298155754804611,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.3806,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0011702750146284377,
93
+ "grad_norm": 0.03351699560880661,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.3799,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0011702750146284377,
100
+ "eval_loss": 10.381875038146973,
101
+ "eval_runtime": 9.6341,
102
+ "eval_samples_per_second": 336.2,
103
+ "eval_steps_per_second": 168.152,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 239221800960.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null