Paladiso commited on
Commit
a30ffb9
·
verified ·
1 Parent(s): cade0c4

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:c3dfcd65846721527933efd65966afc003eb7cbd4c5955c085d396fae07eae26
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e0ba20d5714ae24a0b9eb17cbd060776fb120139115f6d1611b62088a53ac8
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deb48d5e8eed6149592b84babb8248d5f948aba6b333b9d5d96eaab0e74703ef
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3471068a8fee7756d85d2a80ff0e42011e4bd627d25ddcd6fb2e04ee9c250c
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd4b54f7345bbcce1595809d79d03f9645e1cdb1a732503f567a12164b7e76ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f962f3aeee84895d12d77fcc89b352232c7e33129610fc6571d50b4a4c4806
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": 0.0025646505663603335,
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": 11.082,
74
  "eval_steps_per_second": 5.547,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3799445007237120.0,
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": 0.0038469758495405003,
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": 11.082,
74
  "eval_steps_per_second": 5.547,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002992092327420389,
79
+ "grad_norm": 0.8319992423057556,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.8613,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0034195340884804444,
86
+ "grad_norm": 0.9422582387924194,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.7223,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0038469758495405003,
93
+ "grad_norm": 1.0702905654907227,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.6078,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0038469758495405003,
100
+ "eval_loss": 1.7832024097442627,
101
+ "eval_runtime": 88.9288,
102
+ "eval_samples_per_second": 11.076,
103
+ "eval_steps_per_second": 5.544,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5699167510855680.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null