Hugging Face's logo

abaddon182
/
4211dd7b-7323-4f98-88a0-2c950d914fad

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
abaddon182 commited on
Commit
83779ff
·
verified ·
1 Parent(s): 70bc33b

Training in progress, step 4, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:150be46ad6090c4b152a8deafe131adfa39d5aeda1c90a1baca7aaa0aaef3596
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e522fd18ca52c6c805d083bb1803160e5fe1ce85471868170d354193552679d
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:179fe3e2b893cbf6ebcba63f46a3de19bef5cb6b3428cf8c8160022aa4df8e12
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3559ad91682008c40098b870ad0efb12cce6a3cb9e4f757bdbcdb3a65f90bdc3
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1f47b5f2e025366f2430f034970f13abbfd8f90c05993c7e1938d926e51ad7b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65293843f2d14305bbb58a7fbb23f21732235c44beeafac5102adf9a01c13594
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac01bbf201ba89720441ca90ef11c9612960dc721566d0729d34a65968b31a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f953ff4bb836c89ef1b065bbf1be04f9af91f178ed8426b92cb557c106d331
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": 0.0001234110823151919,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 5.563,
38
  "eval_steps_per_second": 5.563,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 32814277853184.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002468221646303838,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 5.563,
38
  "eval_steps_per_second": 5.563,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00018511662347278786,
43
+ "grad_norm": 36.02967071533203,
44
+ "learning_rate": 0.00012,
45
+ "loss": 6.8351,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0002468221646303838,
50
+ "grad_norm": 44.15762710571289,
51
+ "learning_rate": 0.00016,
52
+ "loss": 5.8279,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0002468221646303838,
57
+ "eval_loss": 3.248542547225952,
58
+ "eval_runtime": 304.8755,
59
+ "eval_samples_per_second": 5.596,
60
+ "eval_steps_per_second": 5.596,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 65628555706368.0,
82
  "train_batch_size": 1,
83
  "trial_name": null,
84
  "trial_params": null