oldiday commited on
Commit
42482ab
·
verified ·
1 Parent(s): 209cf1e

Training in progress, step 27, 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:e3af37ff3bbce768880dbff966acd2aababdc9924dc6f3a4771a44782d69e62d
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95153b98fb168b4884240ffc2ef45079aa37a623b9bc59dde30695a9aa9b586
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a13b773c59c1bfb5f57ee3688ff002d571c74b9e5dc4c35f58197c5d2bf2ab44
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f1e6f1eca8d4a2792a172490c37f10cc37bec5301fd0ff7ab82fb95e4d075a
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e12db8b1297bf4ff7ebc4572e7aa50020604ce22ce865ff919ce44bc4b2927
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb18e53aadef196cfd29560c4fbd21def93e501db51849971530281d527a19db
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.0006071287028526617,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 30.115,
74
  "eval_steps_per_second": 3.765,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 5682269440180224.0,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009106930542789925,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 30.115,
74
  "eval_steps_per_second": 3.765,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.0007083168199947719,
79
+ "grad_norm": 0.2874149978160858,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 0.8283,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.0008095049371368823,
86
+ "grad_norm": 0.2777639329433441,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 0.7365,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.0009106930542789925,
93
+ "grad_norm": 0.2506990432739258,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 0.8006,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.0009106930542789925,
100
+ "eval_loss": 0.830035924911499,
101
+ "eval_runtime": 1657.6879,
102
+ "eval_samples_per_second": 30.122,
103
+ "eval_steps_per_second": 3.765,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 8490747439349760.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null