Hugging Face's logo

Paladiso
/
56e46106-55ee-42fc-b514-64b2448c7b69

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
1
Paladiso commited on
Commit
7dc1235
·
verified ·
1 Parent(s): 8cefc74

Training in progress, step 6, 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 sha256:5a5ee48bc4774e595084532880248bfb7475fcc0bb0247db5055aab90db95e06
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa0ac5421769d5719178d5a3107fde5b044b10fb6c80c58eec6a9c6decd05f1
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa2a53340e738356ad853ed10039e887f156051ffdc694aa6652a50f867ccff0
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b645069f9a659914796b2d7b0efd0b6a4ddca4744902a0add688904ed228e27
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f683ddb734a49a81357cf94290689cd53aeaac91c3f07e9e55fa6eb78450c109
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6872307f4470a047155c6b916b2c9040d688e2f96562192a9d5c5fb6108984b7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 9.400999639628348e-05,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -36,6 +36,35 @@
36
  "eval_samples_per_second": 14.806,
37
  "eval_steps_per_second": 7.404,
38
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 1,
@@ -55,7 +84,7 @@
55
  "attributes": {}
56
  }
57
  },
58
- "total_flos": 205681990828032.0,
59
  "train_batch_size": 2,
60
  "trial_name": null,
61
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00018801999279256695,
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,
 
36
  "eval_samples_per_second": 14.806,
37
  "eval_steps_per_second": 7.404,
38
  "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0001253466618617113,
42
+ "grad_norm": 5.215977668762207,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.4588,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.00015668332732713913,
49
+ "grad_norm": 4.574519157409668,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.3348,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.00018801999279256695,
56
+ "grad_norm": 3.121293544769287,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.2783,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.00018801999279256695,
63
+ "eval_loss": 1.8826760053634644,
64
+ "eval_runtime": 919.8555,
65
+ "eval_samples_per_second": 14.608,
66
+ "eval_steps_per_second": 7.304,
67
+ "step": 6
68
  }
69
  ],
70
  "logging_steps": 1,
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 411363981656064.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null