laquythang commited on
Commit
c4e296e
1 Parent(s): 028643c

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 sha256:436da44b7b0139eb3b3b9ab596b26fb36c1db09490cc4073d106437e64cb7065
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84fa7b80f6e1205130fca2729e0d401aecbd711486f79ba9bf23ce3bdc01a23
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a06eb9229500c9a9f00879e09f25053d3a67fc1912b642c19c576fa56af49fa0
3
  size 1003002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3216be0ad935ff48e228762faa5a60b56958e8a5dda23f4e3fa9dc25af2101
3
  size 1003002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494b33d421b03d1cd28f79b8a14e3ee58ac7b56ac617857ec95c88d4246e6c4f
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": 0.0013644633110976349,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 11.892,
103
  "eval_steps_per_second": 5.946,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 4886913613824.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0015160703456640388,
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,
 
102
  "eval_samples_per_second": 11.892,
103
  "eval_steps_per_second": 5.946,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0015160703456640388,
108
+ "grad_norm": 15.634693145751953,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.586,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
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": 5429904015360.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null