leixa commited on
Commit
5ee71b5
·
verified ·
1 Parent(s): d847374

Training in progress, step 50, 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:ff894d6f30e074a59d9f3411ae92cfd378c78b1d16d74e16a409fb632a0e0fcb
3
  size 10624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210b106f2b448ba4a5f4fa53b65ad0cb66f296014f74fb750b9ec3c1643b16ef
3
  size 10624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c62b65df488683e569d61b346d4c0afb10b11f43de2e62f54dad8e191f428cf
3
  size 26562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98abfd867069f224c97bb36fd7ff05cbd603cd520ebf5ae33c06e0a3f68bf225
3
  size 26562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0142a686d2f42ce8f779f95a994c62a8be5e12e27afd368335d9d4d2472185ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c4203910a67ecfc4f0278cc9fadd261f3008669f9aace0335be357a28472bc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.017289149950127453,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,27 @@
88
  "eval_samples_per_second": 158.419,
89
  "eval_steps_per_second": 79.21,
90
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +123,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 5073666048.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02216557685913776,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "eval_samples_per_second": 158.419,
89
  "eval_steps_per_second": 79.21,
90
  "step": 39
91
+ },
92
+ {
93
+ "epoch": 0.017732461487310208,
94
+ "grad_norm": 0.0038438846822828054,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 12.4633,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.019949019173223982,
101
+ "grad_norm": 0.004642875399440527,
102
+ "learning_rate": 3.8060233744356633e-06,
103
+ "loss": 12.4594,
104
+ "step": 45
105
+ },
106
+ {
107
+ "epoch": 0.02216557685913776,
108
+ "grad_norm": 0.003050952684134245,
109
+ "learning_rate": 0.0,
110
+ "loss": 12.4573,
111
+ "step": 50
112
  }
113
  ],
114
  "logging_steps": 5,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 6541049856.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null