cwaud commited on
Commit
6434aa3
·
verified ·
1 Parent(s): 31aae31

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 sha256:05aff0e58bd6c97ecc624eafdee3a6014f1aedbfc46e415ecb5e1fffb2221e3d
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae4c4773633c32269b494649dd32914fdbe674fa83fc96540acbacc9a43e309
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:828882a98447ffc7d94cd35890f6f2074f97dd8aaadb299ca254e6dc02bc8085
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ea0e72a7b973ef876a9c26e4a5301c6606ccd0fcc9eddc89175b59902d7f56
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29d7ac4fdda5436de66ec4d46ceb489dabc6a8dd59f16fbc8cab9217f8f2f8c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc80769f72317c5ebc744d4740fbfa7d1523c0cbd1b5e59da0239cfec6ba806b
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": 0.0015594541910331384,
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": 8.523,
74
  "eval_steps_per_second": 4.261,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1913780359397376.0,
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": 0.0023391812865497076,
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": 8.523,
74
  "eval_steps_per_second": 4.261,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0018193632228719948,
79
+ "grad_norm": 0.4423791766166687,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8774,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002079272254710851,
86
+ "grad_norm": 0.4514065682888031,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.5614,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0023391812865497076,
93
+ "grad_norm": 0.4665509760379791,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.5434,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0023391812865497076,
100
+ "eval_loss": 0.11804177612066269,
101
+ "eval_runtime": 190.04,
102
+ "eval_samples_per_second": 8.525,
103
+ "eval_steps_per_second": 4.262,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2850311173570560.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null