jssky commited on
Commit
79b026f
·
verified ·
1 Parent(s): bfc657f

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 sha256:62a52e0a3ee95ef8a4cc2fa1c61bb51f9c51f78af0df5dcb38c1a3cbe4d0ecf2
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb712faf6e70975bde60820c8f06e2f87597fa4a332dd2d3314a9ccdb1e55e4e
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8664f27bf3189214229ace05c258dfc6b2e1af745b06cc63e3d29bae99b2a67c
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3127a99f2056582e89628fe1627c6449f7414e88942b204beef69227a73673c
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0017525923762231634,
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": 2.371,
74
  "eval_steps_per_second": 2.371,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4218776992088064.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002628888564334745,
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": 2.371,
74
  "eval_steps_per_second": 2.371,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002044691105593691,
79
+ "grad_norm": 72.1349105834961,
80
+ "learning_rate": 8e-05,
81
+ "loss": 7.8116,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0023367898349642177,
86
+ "grad_norm": 44.42057800292969,
87
+ "learning_rate": 0.0001,
88
+ "loss": 7.5031,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002628888564334745,
93
+ "grad_norm": 57.80799102783203,
94
+ "learning_rate": 0.00012,
95
+ "loss": 9.857,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002628888564334745,
100
+ "eval_loss": 1.883453607559204,
101
+ "eval_runtime": 303.9552,
102
+ "eval_samples_per_second": 2.372,
103
+ "eval_steps_per_second": 2.372,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6328165488132096.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null