trenden commited on
Commit
156b662
1 Parent(s): c8de0e5

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:bbaeca37841fa37100361a22e41438b8f3308b84af52ea0bd9bb943674f390a1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefc4831d1edbd3fe47ad11871898f76f81cddfe9516eabd96c994dd0e62d737
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38519b0fd6f14fcacabbf9848d4ba1e646ff47a40b579df8616f8379d4b3fa01
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7361ebcfcd8b169d2c119791f10f7ffda1dad7d03eb16bc0d20852d480d3b6c4
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:ccefe07c55c3a71d889b8afe9c246ca4fe002fb51cf63fcb0e5c6615aebb4f78
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": 0.0002392702258112756,
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": 23.861,
74
  "eval_steps_per_second": 11.932,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1525890504720384.0,
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": 0.0003589053387169134,
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": 23.861,
74
  "eval_steps_per_second": 11.932,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00027914859677982153,
79
+ "grad_norm": 28.602575302124023,
80
+ "learning_rate": 0.00014,
81
+ "loss": 9.9776,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003190269677483675,
86
+ "grad_norm": 13.103843688964844,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.213,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003589053387169134,
93
+ "grad_norm": 16.657100677490234,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.471,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003589053387169134,
100
+ "eval_loss": 3.651150941848755,
101
+ "eval_runtime": 442.6764,
102
+ "eval_samples_per_second": 23.853,
103
+ "eval_steps_per_second": 11.927,
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