Hugging Face's logo

Paladiso
/
e60510e7-49f8-4df0-b938-c6cafe3f3d52

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
d8c1851
·
verified ·
1 Parent(s): d4c9cf2

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0450469acee40f1a0c1733a675092fc1201ae8919905653452ec51f7d4fed613
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30ab9e321a61a916fca5be1ca673e677573192d67953dce64f98de28a6197fe
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243d41b2bf58defe55c37f2acd95e2ef71e14758e5adc2179681d532eb78a65d
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8333c79e0ef8da6021d8a754fd6e13296ea852ea23e1cb4771ff0e5f2311975f
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0014924444997201666,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 17.287,
66
  "eval_steps_per_second": 8.649,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 977394500370432.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00223866674958025,
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,
 
65
  "eval_samples_per_second": 17.287,
66
  "eval_steps_per_second": 8.649,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0017411852496735279,
71
+ "grad_norm": 0.4195449948310852,
72
+ "learning_rate": 0.00014,
73
+ "loss": 1.7803,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0019899259996268887,
78
+ "grad_norm": 0.5913130044937134,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.8943,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.00223866674958025,
85
+ "grad_norm": 0.3698888123035431,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.5226,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.00223866674958025,
92
+ "eval_loss": 1.7042946815490723,
93
+ "eval_runtime": 94.8426,
94
+ "eval_samples_per_second": 17.851,
95
+ "eval_steps_per_second": 8.931,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1466091750555648.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null