Hugging Face's logo

tuanna08go
/
e4b4ed3f-4fcd-46b6-97e5-7cd116b4627a

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
1247e43
·
verified ·
1 Parent(s): 24fe301

Training in progress, step 36, 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 +19 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49bc37df8f213a83aaba76f879d279a9a15fbab837051d8f64d7053d0cd12aab
3
  size 31064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c943642ba0fc14678c773530e973a201e9ed85157cf5d1dedc9b35718810ea3
3
  size 31064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f326cc1301ebee78c13713fe2a9dc74b172060380ac68cd27eb91b55d56bed
3
  size 71718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02983b2533d13af16090e6c1bac6be9b7ccefa20bb67ebe9570229b1c216115e
3
  size 71718
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76547a1434a8099b980d31411ba3150dd19b91e75d493c8b6a07c68c121916a8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ef6f4b0dc1a0ee466ac9818efdab5291728661390e42389cd9c4df42291c75
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
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": 0.7619047619047619,
5
  "eval_steps": 8,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -53,6 +53,21 @@
53
  "eval_samples_per_second": 512.043,
54
  "eval_steps_per_second": 64.273,
55
  "step": 24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  }
57
  ],
58
  "logging_steps": 10,
@@ -67,12 +82,12 @@
67
  "should_evaluate": false,
68
  "should_log": false,
69
  "should_save": true,
70
- "should_training_stop": false
71
  },
72
  "attributes": {}
73
  }
74
  },
75
- "total_flos": 17349415010304.0,
76
  "train_batch_size": 8,
77
  "trial_name": null,
78
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0246913580246915,
5
  "eval_steps": 8,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
53
  "eval_samples_per_second": 512.043,
54
  "eval_steps_per_second": 64.273,
55
  "step": 24
56
+ },
57
+ {
58
+ "epoch": 0.8465608465608465,
59
+ "grad_norm": 1.3938124179840088,
60
+ "learning_rate": 7.489143213519301e-06,
61
+ "loss": 165.7968,
62
+ "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.9029982363315696,
66
+ "eval_loss": 10.360464096069336,
67
+ "eval_runtime": 0.5412,
68
+ "eval_samples_per_second": 441.629,
69
+ "eval_steps_per_second": 55.435,
70
+ "step": 32
71
  }
72
  ],
73
  "logging_steps": 10,
 
82
  "should_evaluate": false,
83
  "should_log": false,
84
  "should_save": true,
85
+ "should_training_stop": true
86
  },
87
  "attributes": {}
88
  }
89
  },
90
+ "total_flos": 23226657669120.0,
91
  "train_batch_size": 8,
92
  "trial_name": null,
93
  "trial_params": null