Aivesa commited on
Commit
1c53cc9
·
verified ·
1 Parent(s): db379d2

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 sha256:1c23d5ff48b7154fd37cd789d23a5e4cd540d2dcbcd9aa45dacf35b0c357318b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de25f8c2395816f95a61bce9caaeb22e6f074eea3e5fc10d298013248aec53a7
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7a7ef63d8aff9c4ad47aee11109db0fda985304aeab4ae63ea4cb168d11737c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d791260306bf85a3a169612fe93b5181c920b101d07281bfe6ba016788ce166e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
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": 0.011869436201780416,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 14.721,
66
  "eval_steps_per_second": 7.395,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 1109738548887552.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.017804154302670624,
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,
 
65
  "eval_samples_per_second": 14.721,
66
  "eval_steps_per_second": 7.395,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.013847675568743818,
71
+ "grad_norm": 1.8498936891555786,
72
+ "learning_rate": 0.00014,
73
+ "loss": 3.0711,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.01582591493570722,
78
+ "grad_norm": 1.8731578588485718,
79
+ "learning_rate": 0.00016,
80
+ "loss": 2.6369,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.017804154302670624,
85
+ "grad_norm": 2.1558492183685303,
86
+ "learning_rate": 0.00018,
87
+ "loss": 2.8718,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.017804154302670624,
92
+ "eval_loss": 2.8179714679718018,
93
+ "eval_runtime": 12.1815,
94
+ "eval_samples_per_second": 17.486,
95
+ "eval_steps_per_second": 8.784,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1664607823331328.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null