Hugging Face's logo

abaddon182
/
4211dd7b-7323-4f98-88a0-2c950d914fad

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
abaddon182 commited on
Commit
0e24749
·
verified ·
1 Parent(s): a21e208

Training in progress, step 5, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. 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 sha256:6e522fd18ca52c6c805d083bb1803160e5fe1ce85471868170d354193552679d
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385a5fb32b93dfa0066750595a4e1768fa4f565efc59fe182985d20827b81b28
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3559ad91682008c40098b870ad0efb12cce6a3cb9e4f757bdbcdb3a65f90bdc3
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aeca986a05ab99fcff2a07c545a04c002781e5db17bbb5cdb4ab0a72bbd7738
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65293843f2d14305bbb58a7fbb23f21732235c44beeafac5102adf9a01c13594
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f207c0393f6e88e1bd3fd4a26645c2734162ee3e99b07f0d271c29cb37330a89
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f953ff4bb836c89ef1b065bbf1be04f9af91f178ed8426b92cb557c106d331
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b73b70b4d55707d0e07cefd5db81f7d92e9aa0ccc0fcacc15d9b1610bf62f6
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": 0.0002468221646303838,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 5.596,
60
  "eval_steps_per_second": 5.596,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 65628555706368.0,
82
  "train_batch_size": 1,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00030852770578797977,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 5.596,
60
  "eval_steps_per_second": 5.596,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.00030852770578797977,
65
+ "grad_norm": 31.3842716217041,
66
+ "learning_rate": 0.0002,
67
+ "loss": 6.0541,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 82035694632960.0,
89
  "train_batch_size": 1,
90
  "trial_name": null,
91
  "trial_params": null