havinash-ai commited on
Commit
27f2bb1
·
verified ·
1 Parent(s): b9940f3

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 sha256:5b5a18a8fda81303b62d149d9367e70882e882375f28f3f802ddc432944c69db
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b284ad11d773e0e68a0b8daadd2d089b974cbc050c3067fcce65f59d8a26f000
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0bf6fbc2a767bb92121e6366574b5bfd937f868350550ea828a4c3feaf579ef
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3476fcf166f9ba53ebc02b833268ac2b142a1fa8fb8f4730f13c9d441c04fb
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76713a142f1f54e59696c036a43b5e5cd041e21d5bbbb12d7a1ad0ac9254ae59
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ec8e820de8f414b03f2e240cd9c97035e62ddaed041c2d0bff8aaaa002b5dd
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": 0.015789473684210527,
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": 19.701,
103
  "eval_steps_per_second": 9.851,
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": 2579973411962880.0,
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": 0.017543859649122806,
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": 19.701,
103
  "eval_steps_per_second": 9.851,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.017543859649122806,
108
+ "grad_norm": 3.516273260116577,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.8574,
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": 2866637124403200.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null