Hugging Face's logo

tuanna08go
/
87e605dc-7855-4690-84e6-8164f5e9f81e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
723db23
·
verified ·
1 Parent(s): 50115f3

Training in progress, step 50, 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 +34 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6813fdbe8bdc8489de4b64f15ce24261dd873e6b848088555a29a119ace00a54
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7008ff38ae46be7c3a5e62fe27ae4709fb6866384ed10bbf219f94cd12cad737
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5905f32d61f5500b36cdf11068219588a57abff5c8fb51ea2dbb46eaacce0605
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ce80a2152eb639310dffd7b92e4a75c37124ef352c410a6114d1004a63f222
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92a42c33445a7e2c9138790db707c29bb8500bafdae7c74040b6354c5f251439
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed120440b6875f99cd3aa80cc375b968f1df799f3d3c11c1bef77e318695614
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.1080706615864219,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 41.085,
61
  "eval_steps_per_second": 5.138,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 3.0209032631353344e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.13855213023900242,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 41.085,
61
  "eval_steps_per_second": 5.138,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.11084170419120194,
66
+ "grad_norm": 0.7959256768226624,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 2.3263,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.11084170419120194,
73
+ "eval_loss": 2.277695655822754,
74
+ "eval_runtime": 59.3343,
75
+ "eval_samples_per_second": 40.971,
76
+ "eval_steps_per_second": 5.124,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.13855213023900242,
81
+ "grad_norm": 0.8115575909614563,
82
+ "learning_rate": 0.0,
83
+ "loss": 2.2721,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.13855213023900242,
88
+ "eval_loss": 2.2608070373535156,
89
+ "eval_runtime": 58.9517,
90
+ "eval_samples_per_second": 41.237,
91
+ "eval_steps_per_second": 5.157,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 3.880364310056141e+16,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null