tuantmdev commited on
Commit
c693e80
·
verified ·
1 Parent(s): 9943460

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d0d23e704cdea01490c820e42fdd840657f2957a1e9b292df4c1a538e62af1a
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd7f13142692ac37e8a92313bbe047d856d80ebdea2115e909fd31dae38df8
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab216b0452c26a3e24efd82ee8e3ea1f46521a2a264e56103ede5421f7f1dee
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10db2503a90b1e05c2086b21d9c57bb498bc4d98eb4128472b3110afb71ac0e7
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0d5a7d54c93ecd3f4e8fa6889b459b14554a16ac8e5c6ae5718291742bf3789
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41d7486b6f0e1d5cbadc21d2d25210696331bd49b226e0316086e1dc208c3ed
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb148ad6cd6502048dc3eee274a6708e5b4f6b72c0d56ebc272935446c220acd
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": 0.024858471786605555,
5
  "eval_steps": 40,
6
- "global_step": 160,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 42.361,
76
  "eval_steps_per_second": 21.183,
77
  "step": 160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 40,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 9311165979820032.0,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.031073089733256946,
5
  "eval_steps": 40,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
75
  "eval_samples_per_second": 42.361,
76
  "eval_steps_per_second": 21.183,
77
  "step": 160
78
+ },
79
+ {
80
+ "epoch": 0.031073089733256946,
81
+ "grad_norm": 0.2943527400493622,
82
+ "learning_rate": 0.0,
83
+ "loss": 0.0411,
84
+ "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.031073089733256946,
88
+ "eval_loss": 0.04576389119029045,
89
+ "eval_runtime": 255.7957,
90
+ "eval_samples_per_second": 42.381,
91
+ "eval_steps_per_second": 21.193,
92
+ "step": 200
93
  }
94
  ],
95
  "logging_steps": 40,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.1599446789586944e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null