daniel40 commited on
Commit
ee9c5a0
·
verified ·
1 Parent(s): 5ec8d34

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 sha256:48fbfebce89e4df4bd35ae1e7850921000eb824ee36ecfd3011a291e403ba5e2
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f7a131125cb99964e816becdd3ef44b0a1186667719f363a61d8e9429b601b
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:935f86892a96761c6454f48a85996df492e1a505d595fff9ffc27aa36915382e
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08503b6479a39b8be10297988fb400f2852a7a40b5c4937b0d53dbcc4bacec2
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3b2ed62d3c3041d929f4689e56812b00363ecda2ba4abac93da71f834cdd0c0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74e3c925ceec40baf5d508fc3d6ea8a468f31ee20a14f9330a7ee79c304b1d4
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": 0.00024156777485883382,
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": 61.514,
74
  "eval_steps_per_second": 30.76,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 293686676029440.0,
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": 0.00036235166228825073,
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": 61.514,
74
  "eval_steps_per_second": 30.76,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002818290706686395,
79
+ "grad_norm": 3.6897239685058594,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.5946,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003220903664784451,
86
+ "grad_norm": 4.003920555114746,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.5745,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00036235166228825073,
93
+ "grad_norm": 2.6077499389648438,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.2364,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00036235166228825073,
100
+ "eval_loss": 0.16095003485679626,
101
+ "eval_runtime": 171.0825,
102
+ "eval_samples_per_second": 61.134,
103
+ "eval_steps_per_second": 30.57,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 440530014044160.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null