Hugging Face's logo

dimasik87
/
72c2c260-2713-4915-922b-1925fe806e3d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
dimasik87 commited on
Commit
3d2e23c
·
verified ·
1 Parent(s): 8372a60

Training in progress, step 20, 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 +42 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fd7c3d4dc756e1da82f3d92e749f239ddc7b1e78c1d416c4e35f399b3cb8da3
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74016ba80c25894450882f5a0a23d523f3443696ce07255e925de217368e15e
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:952051dfd504f1532b31ba3b18bdf1b7a7a28d779ce89233f6bd69daa92e5ff1
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20477e35f2b74f1e37b41a7da8b10ea5d4c11abe4f0497d580e9910e6663805a
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9aa6123e9019a8d581677b82c7cd72aa7a50c75d4a4169521ebac3db896d60b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f601e5723b7977940291127d4234689f9b9aaaff2705528d580c2f361e9ecdd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3972467184066772,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.006146281499692686,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 15.441,
53
  "eval_steps_per_second": 7.732,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 4265851880472576.0,
84
  "train_batch_size": 2,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.247101902961731,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.012292562999385371,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 15.441,
53
  "eval_steps_per_second": 7.732,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.007375537799631223,
58
+ "grad_norm": 0.5950524210929871,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 1.1126,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.00921942224953903,
65
+ "grad_norm": 0.7039989829063416,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 1.0127,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.00921942224953903,
72
+ "eval_loss": 1.302493929862976,
73
+ "eval_runtime": 44.531,
74
+ "eval_samples_per_second": 15.383,
75
+ "eval_steps_per_second": 7.702,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.011063306699446834,
80
+ "grad_norm": 0.684798002243042,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 0.9299,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.012292562999385371,
87
+ "eval_loss": 1.247101902961731,
88
+ "eval_runtime": 44.4753,
89
+ "eval_samples_per_second": 15.402,
90
+ "eval_steps_per_second": 7.712,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 8531703760945152.0,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null