JacksonBrune commited on
Commit
2189e88
·
verified ·
1 Parent(s): bb4e590

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 sha256:6b17c951d6e6dc040bff8e2d9e453e353e3008be5fa6a23c1131b4b496beec0f
3
  size 51431872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa9c02ef7fb7f23f3dedb775d918d3f63767389ae1f3cafcca734f6949e076e
3
  size 51431872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d7ab7fec6b4c36488244f9d0ab2bb817ab578c141942fefd9a806b6cf4f98c0
3
  size 26550260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fc41d9a1e9d22b661f617dc4e95f842e688fd619768a654e1e656e5ac415cb
3
  size 26550260
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d3ac8cf56c37661f02b6960eef4b4eb6788a7a9ae526e6ecc598498c98e4c67
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6539bd42c0dce152efffa7664d58b831bb7ebc921fb94bd7cee48d50104952
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": 0.0012201942142457674,
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": 39.486,
74
  "eval_steps_per_second": 19.752,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 456499239321600.0,
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": 0.0018302913213686513,
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": 39.486,
74
  "eval_steps_per_second": 19.752,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001423559916620062,
79
+ "grad_norm": 1.5832951068878174,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.5218,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0016269256189943566,
86
+ "grad_norm": 1.4458744525909424,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.4054,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0018302913213686513,
93
+ "grad_norm": 1.9726817607879639,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.1215,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0018302913213686513,
100
+ "eval_loss": 1.4680432081222534,
101
+ "eval_runtime": 52.0572,
102
+ "eval_samples_per_second": 39.783,
103
+ "eval_steps_per_second": 19.901,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 684748858982400.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null