philip-hightech commited on
Commit
56115cc
·
verified ·
1 Parent(s): f8f64a9

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 sha256:13d6f33d8dad33a2b2ea9fbbba8b00773b3ac3cd5c5ac33c4df9f7c50ced727e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370ffb785c35b85be3b69622c9efa0b453ac38bcf82f4208c7d11a523365656e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:852b6360fe401857aa8e534958e865674111b4c3233d8b5eaab167dcf4a456bd
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989f6f5328df04d9ba312d6fa16319e837a56a627eae1ed812fab29c7756545c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dfaa23317e25a3dfb1920162c79f11c9369ae8f82d55d4f95f12072fcc6e327
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2737be7f238db2b0a7251046c7812f99f19c9213229454fd164ad3fb8682d8
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": 0.01284796573875803,
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": 24.112,
74
  "eval_steps_per_second": 12.117,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1358319864250368.0,
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": 0.019271948608137045,
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": 24.112,
74
  "eval_steps_per_second": 12.117,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.014989293361884369,
79
+ "grad_norm": 8.569844245910645,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.2315,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.017130620985010708,
86
+ "grad_norm": 5.71522855758667,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.9675,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.019271948608137045,
93
+ "grad_norm": 6.9149298667907715,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.0579,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.019271948608137045,
100
+ "eval_loss": 1.174412488937378,
101
+ "eval_runtime": 8.1316,
102
+ "eval_samples_per_second": 24.227,
103
+ "eval_steps_per_second": 12.175,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2147021720911872.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null