Hugging Face's logo

sn56
/
f0df7cd5-f615-4d17-939b-43c83b9b09d7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
RoyJoy commited on
Commit
023faf1
·
verified ·
1 Parent(s): 4c0cd6a

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 sha256:40c7cd42ed97dc9675d5b4f219a63ef9589657602c51d586750bbd4b33d0355a
3
  size 2185308216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64581fdb145e4b707be0feee5c7730b7fa710eaccc6734d95710525151e1d5b1
3
  size 2185308216
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:797d563b1d990520c1d4e928826a675b5c08ea9beff07ff27ad9d89de03c0280
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3659c9b8a5837c167f9f7ec90525d21eafeb6e12bae9f6174ffcbdbcf9d78f95
3
  size 43122580
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36c1d677a7607ca32315adc7f7772af06af5397c445695f113d08019db775e01
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e749ea5abc9b36412ea78978a7c234fe484f5c402b73fb23f59ea915998840cc
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0e1a13078c908bc2f98627872b482fdc1df86c5723e3c94011a1c6fa67d609d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5661aa70ed2b3c9d6db9805561bca7e5354325748358cad3002acc19459c4b
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:d49d0a5a1be8d097e2f2422239656e8d0f9ab68e169fb94db3b15958b67c5cb5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76fcd815824f4fbaf15a9c49b696fa47dd62ae670bf0f21f596d25fe7ab94c5
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 sha256:117498f142890dae2994492453bf6b6e9a451a0e3fd4382bc37ecfff4455b98c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57f281309e1d548cf86f3dc2f6a088f8c37ffe1d212b254cec960eac7e54ea8
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": 0.0821917808219178,
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": 52.375,
103
  "eval_steps_per_second": 6.795,
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": 1.3316869834407936e+16,
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": 0.091324200913242,
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": 52.375,
103
  "eval_steps_per_second": 6.795,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.091324200913242,
108
+ "grad_norm": 2.410445213317871,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.1257,
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": 1.479652203823104e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null