Hugging Face's logo

kooff11
/
c097e8b9-c870-4487-abcb-4ecfbb127315

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
kooff11 commited on
Commit
eb72304
•
1 Parent(s): 416beb7

Training in progress, step 10, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f83afac017a56c5dff80e4ce3601f3b2096c940cbbb447cb1dd764452c57b8aa
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1a466fd57a777ef30c7f71ebe4713fd283c43df295251b7e9111fdb44593f2
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e91d070186b59530ca750f9db7d630fb313ef9136c1c9f5468e11a0b0be4547d
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81948f2ce5a1f977e53f87416d738fcb50d2e11a25874d1b8a6e6f948e5e8e25
3
  size 111142
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02b01d0e486dff2cb85accbdc44d4df7dcae2859f47fe7b514d80ec6d14b00a8
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b46fee296677e35f2ad177eaabae0909c73f72ed0e5ce86ac9f5a96191fde29
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da9184a96ec4d1e06ae289f0051378762191f4ba60f23b6d59e9aba10761c2ed
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc3fb143ef8d489fabeeeeeae6a634eeb010a9de2a20ac3dfbdda64924dfa54
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:491c54d7af28cf6eaa7a5ccd9b218155b2b3b0de07fd7b2323686cf341c901fa
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7459a954ccc4816e325f14a333fe8c0713705997af520491056cecb78e7a8a50
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbe024f27ffc6e5316283ccc9cfc939e46edfe07ea42e65b4dc94b8ae9077ad3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c368dbe31dc6b9b04073e894c77abdadf5dc5612333a7aff1ba3f8b4504119
3
  size 15024
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": 0.03290676416819013,
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": 460.563,
103
  "eval_steps_per_second": 57.945,
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": 3765776154624.0,
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": 0.03656307129798903,
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": 460.563,
103
  "eval_steps_per_second": 57.945,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.03656307129798903,
108
+ "grad_norm": 0.07217925786972046,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.3636,
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": 4184195727360.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null