infogeo commited on
Commit
b461410
·
verified ·
1 Parent(s): 9cacb08

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 sha256:7923d423270ba9e9e9207f2eb870a3eae93072a8285c7a34e94b58d0a7c328aa
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0808f97bb35bf652a5639d2cfbd7b2e8bc5a77318836430c1914c3577de0decc
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38e2c390bc005a2ba87f7640582bdc80426b068bd272b2900d9ce80a3ccb1950
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeed0cbd4c4f1a22f7e5152d0233a74a8726a423b66ef884aa57f35f4add2d5c
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:566129576c794ccbe4ac1a736a7a294fcd3a010107c9e0c82300770dcb5b6ba9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09fcb86a8d93a49138d2392b44fd22e24b82209f76b99e4eb19290d2ae9e9dbb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5642491579055786,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.08629989212513485,
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": 4.385,
90
  "eval_steps_per_second": 1.102,
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": 2.5391158788096e+16,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4860066175460815,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-30",
4
+ "epoch": 0.12944983818770225,
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": 4.385,
90
  "eval_steps_per_second": 1.102,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.09061488673139159,
95
+ "grad_norm": 0.7784251570701599,
96
+ "learning_rate": 2.8711035421746367e-05,
97
+ "loss": 1.5033,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.10355987055016182,
102
+ "grad_norm": 0.9875249862670898,
103
+ "learning_rate": 1.3551568628929434e-05,
104
+ "loss": 1.468,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.10787486515641856,
109
+ "eval_loss": 1.4989583492279053,
110
+ "eval_runtime": 44.5228,
111
+ "eval_samples_per_second": 4.38,
112
+ "eval_steps_per_second": 1.101,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.11650485436893204,
117
+ "grad_norm": 0.7232942581176758,
118
+ "learning_rate": 3.511175705587433e-06,
119
+ "loss": 1.5199,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.12944983818770225,
124
+ "grad_norm": 0.8101120591163635,
125
+ "learning_rate": 0.0,
126
+ "loss": 1.5326,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.12944983818770225,
131
+ "eval_loss": 1.4860066175460815,
132
+ "eval_runtime": 44.5057,
133
+ "eval_samples_per_second": 4.381,
134
+ "eval_steps_per_second": 1.101,
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": 3.8086738182144e+16,
165
  "train_batch_size": 4,
166
  "trial_name": null,
167
  "trial_params": null