Hugging Face's logo

shibajustfor
/
58d597c9-091f-4c62-b174-30cc8ad298b3

PEFT
Safetensors
olmo
axolotl
Generated from Trainer
Model card Files
xet
 Community
shibajustfor commited on
Commit
b540322
·
verified ·
1 Parent(s): 6f43d16

Training in progress, step 39, 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 +18 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37e6cec64888336ff31b695a24173b5ede3f2baf4904a568fecedc1bfc340525
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4612e95e65155c8efb1524186c45780ecc36cf0884f831e8b5481291f316d869
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6935599e9519997281a203d811c6734dc5e62a086d4f19441643330029099c55
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c303bfd66e4e4eabaa79ee5b239a51dff39a38f57da7116baf40100eb382986
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.0057227755461398775,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 403.585,
46
  "eval_steps_per_second": 201.898,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 2296828133376.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008584163319209817,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 403.585,
46
  "eval_steps_per_second": 201.898,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0066032025532383205,
51
+ "grad_norm": 0.40669751167297363,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 10.7946,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.008584163319209817,
58
+ "eval_loss": 10.771018981933594,
59
+ "eval_runtime": 4.6938,
60
+ "eval_samples_per_second": 407.559,
61
+ "eval_steps_per_second": 203.886,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 3404227411968.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null