Paladiso commited on
Commit
ec5ba0b
·
verified ·
1 Parent(s): 195dc33

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c879aeee168f890c976200b36beb9641282bd8cdefaa42eaa8c57208d861e01
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8776298929864538058ef38e9e5dffabc6bbe1c080818ff288a29de226cb4a
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:197c4e83fc05fec25b84268d6da3b98521728065e9edefe982a66a79b4e03631
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ff09f7cdcee415daa8136b4ee31d75c45783cccb2208742424d4b05af93f6b
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea790a6d7ded2d403b9f6bb0e490729d25eeb947822fcee7d950e6fe6a5a2385
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bca983b309063a996168bc9ba0246dee10aad731d5eafae85ac843af75455c4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.004233799835352228,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 24.776,
95
  "eval_steps_per_second": 12.402,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 216490963894272.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004704222039280254,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 24.776,
95
  "eval_steps_per_second": 12.402,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004704222039280254,
100
+ "grad_norm": 1.0150742530822754,
101
+ "learning_rate": 0.0002,
102
+ "loss": 2.0675,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 240545515438080.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null