cvoffer commited on
Commit
30f00c5
·
verified ·
1 Parent(s): e300657

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:047bfec94dd4307534f5cf6253b202f9654ceb0a3e6d3069153b140a0e42aba7
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b6236381d43814e1b2b0d51fbaea878bc10d2779b08b98d13c6a8d52093454
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7404766f16a9e55096785c420aaab2bef8f7538cc8c191b5df02d68d6a87fbaf
3
  size 436251442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1130b581c9bd7a46ca081d9707140011852890ab8dfaf37f7bff8ac59c3c2b
3
  size 436251442
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:392b9c52b7fb22f3a767332e485a1dd77fd7a23feefdd656a7eb90b952e75649
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e80fe8013099179804cba7e785ae81acdfe6acb57dc3e039e4261594bc2e7a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5368123054504395,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.0022456770716370988,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,50 @@
89
  "eval_samples_per_second": 4.074,
90
  "eval_steps_per_second": 2.037,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -112,12 +156,12 @@
112
  "should_evaluate": false,
113
  "should_log": false,
114
  "should_save": true,
115
- "should_training_stop": false
116
  },
117
  "attributes": {}
118
  }
119
  },
120
- "total_flos": 9323049136422912.0,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5274834036827087,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-30",
4
+ "epoch": 0.0033685156074556477,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 4.074,
90
  "eval_steps_per_second": 2.037,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.0023579609252189536,
95
+ "grad_norm": 0.34568342566490173,
96
+ "learning_rate": 5.7422070843492734e-05,
97
+ "loss": 0.5287,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.002694812485964518,
102
+ "grad_norm": 0.32576116919517517,
103
+ "learning_rate": 2.7103137257858868e-05,
104
+ "loss": 0.5571,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.002807096339546373,
109
+ "eval_loss": 0.5289449095726013,
110
+ "eval_runtime": 922.3702,
111
+ "eval_samples_per_second": 4.066,
112
+ "eval_steps_per_second": 2.033,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.003031664046710083,
117
+ "grad_norm": 0.7168234586715698,
118
+ "learning_rate": 7.022351411174866e-06,
119
+ "loss": 0.5479,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0033685156074556477,
124
+ "grad_norm": 0.3806007504463196,
125
+ "learning_rate": 0.0,
126
+ "loss": 0.5298,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0033685156074556477,
131
+ "eval_loss": 0.5274834036827087,
132
+ "eval_runtime": 921.6759,
133
+ "eval_samples_per_second": 4.069,
134
+ "eval_steps_per_second": 2.034,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
156
  "should_evaluate": false,
157
  "should_log": false,
158
  "should_save": true,
159
+ "should_training_stop": true
160
  },
161
  "attributes": {}
162
  }
163
  },
164
+ "total_flos": 1.3560798743887872e+16,
165
  "train_batch_size": 2,
166
  "trial_name": null,
167
  "trial_params": null