Hugging Face's logo

dimasik87
/
7d8264c0-1221-4895-93fd-59d0aeba6a21

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
dimasik87 commited on
Commit
3fedd51
·
verified ·
1 Parent(s): 3fcc744

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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cff874c6b121c11b3454d0ad8f12faa58a9679acd0ed10e969d0061e120355a
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6dcbd5085cbf63ac5085958a9d245f623f90de7b262515ecb6483d5a345d64
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b715ac9bde8be5564439cb87e3bdee6f1e9d25fbc0cd3de84d2437252d1fe5
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba54a248bc76bac335ee13460016b219d8382ba3654620cfa36781575fe05a8
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42d8829c82d04d9ec6bacfc38deb032d975006f94a9426c44cbbf68416e46129
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd2dcf10dab10ab8ee0931b3c2ef546aa966f1aae45a22c8b6f6a0effcde90e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.0016263468184590363,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 0.00018,
45
  "loss": 2.532,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 9363049194455040.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0032526936369180726,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 0.00018,
45
  "loss": 2.532,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0019516161821508437,
50
+ "grad_norm": 1.2829382419586182,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 2.7196,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.002439520227688555,
57
+ "grad_norm": 0.62413090467453,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 2.7893,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.0026021549095344584,
64
+ "eval_loss": 0.6180543899536133,
65
+ "eval_runtime": 338.4899,
66
+ "eval_samples_per_second": 7.649,
67
+ "eval_steps_per_second": 3.826,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.0029274242732262655,
72
+ "grad_norm": 0.5762659311294556,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 2.1983,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1.856740263985152e+16,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null