cwaud commited on
Commit
1d0150c
·
verified ·
1 Parent(s): 751187e

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:a7473f77b946c7c513173cd4405ef728ce59f0a9491b4fb794afe42da11cf532
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500bc48447ad7124a6b18e9030ffd8f63255517fec8a37f6ba68e248c8fa0ce7
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50daabdacea79216e77d59760abbbcd4b415de99a52efea819a3911a2ceef4b8
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264605a4677d66fb350fa1e72033d20feca480b19a89048b0a02fa4e414de755
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a20f33989dffe3003804dd757d62c88a7f05f8903e3d773efe493f14f5224860
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dfd6fb4a20b8dcf94292962018e29e81f262d6cf300d71b9548100e09281b3
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": 0.031496062992125984,
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": 20.612,
103
  "eval_steps_per_second": 10.391,
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": 617045972484096.0,
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": 0.03499562554680665,
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": 20.612,
103
  "eval_steps_per_second": 10.391,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.03499562554680665,
108
+ "grad_norm": 1.2513223886489868,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.9052,
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": 685606636093440.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null