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
2e1d59a
·
verified ·
1 Parent(s): afa1c23

Training in progress, step 26, 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 sha256:8a6908413ac9794fa0b18a92490c5e7e07bcaaef386b4f00ffa4306dd51b97d4
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e6cec64888336ff31b695a24173b5ede3f2baf4904a568fecedc1bfc340525
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dccc52eacd15bc832d65a57e6f62232c10b549ace10e25f363a13bc8a6bcbe57
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6935599e9519997281a203d811c6734dc5e62a086d4f19441643330029099c55
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
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": 0.0028613877730699388,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,21 @@
30
  "eval_samples_per_second": 414.618,
31
  "eval_steps_per_second": 207.417,
32
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 1148414066688.0,
53
  "train_batch_size": 2,
54
  "trial_name": null,
55
  "trial_params": null
 
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,
 
30
  "eval_samples_per_second": 414.618,
31
  "eval_steps_per_second": 207.417,
32
  "step": 13
33
+ },
34
+ {
35
+ "epoch": 0.004402135035492214,
36
+ "grad_norm": 0.30338501930236816,
37
+ "learning_rate": 0.00015000000000000001,
38
+ "loss": 10.8123,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.0057227755461398775,
43
+ "eval_loss": 10.785100936889648,
44
+ "eval_runtime": 4.74,
45
+ "eval_samples_per_second": 403.585,
46
+ "eval_steps_per_second": 201.898,
47
+ "step": 26
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 2296828133376.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null