Hugging Face's logo

Paladiso
/
0c6c9df4-71bb-4138-9f19-cb71e610e37a

PEFT
Safetensors
olmo
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
d35aeec
·
verified ·
1 Parent(s): 63890ba

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:eb375bff6222943faeb64bcf5cd2a7bbf83342511b1875324307a326320ee5a8
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a636040998b2f471f96acc7a825421b929aa8a55c25c4be55f629fa260e9e0ef
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fd37241d023d6c4863375ca16152e19f2934d94d7d66a485240415b28e80ad8
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f661138f91e6270eb04799e38917af607c84183ed092c771f55a92453abeaa
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 0.0019390805526379575,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 346.438,
74
  "eval_steps_per_second": 173.352,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 615221821440.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0029086208289569363,
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,
 
73
  "eval_samples_per_second": 346.438,
74
  "eval_steps_per_second": 173.352,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002262260644744284,
79
+ "grad_norm": 0.18067824840545654,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.8133,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00258544073685061,
86
+ "grad_norm": 0.15925225615501404,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.8202,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0029086208289569363,
93
+ "grad_norm": 0.16329418122768402,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.8138,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0029086208289569363,
100
+ "eval_loss": 10.82058334350586,
101
+ "eval_runtime": 3.7228,
102
+ "eval_samples_per_second": 350.004,
103
+ "eval_steps_per_second": 175.136,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 881817944064.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null