philip-hightech commited on
Commit
09c4c54
·
verified ·
1 Parent(s): 4cb2855

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:f71596ad0ea43ffb20a06233167b403875ac6dcddeff50e07aeff2f3afbd1571
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34c50aafd3d3efc71a839fe2c538aed96b6e852297d5f1c2b8b1ca090164934
3
  size 5752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58c44e53809e6d1231504047c5ce62130ecdea1f8e6dfbadecb14ec81328b0a
3
  size 15814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54869875cfb5d089c406f3e2b75998cede94c845e97b3ffe1d2da103a3640f35
3
  size 15814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
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": 0.003810733566211496,
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": 184.163,
74
  "eval_steps_per_second": 92.22,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 129498710016.0,
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": 0.0057161003493172435,
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": 184.163,
74
  "eval_steps_per_second": 92.22,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004445855827246745,
79
+ "grad_norm": 1.4344588635140099e-05,
80
+ "learning_rate": 0.00014,
81
+ "loss": 46.0,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0050809780882819944,
86
+ "grad_norm": 1.4874678527121432e-05,
87
+ "learning_rate": 0.00016,
88
+ "loss": 46.0,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0057161003493172435,
93
+ "grad_norm": 2.7079668143414892e-05,
94
+ "learning_rate": 0.00018,
95
+ "loss": 46.0,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0057161003493172435,
100
+ "eval_loss": 11.5,
101
+ "eval_runtime": 3.6694,
102
+ "eval_samples_per_second": 180.685,
103
+ "eval_steps_per_second": 90.479,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 189267345408.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null