Hugging Face's logo

ajtaltarabukin2022
/
704b9953-dc7e-4dac-8809-b2fbb1339964

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
 Community
ajtaltarabukin2022 commited on
Commit
f2cdd02
·
verified ·
1 Parent(s): a9f470e

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 +40 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09917567ed6a38773dc8af1e913c88fb75150b338b11791c1bc2250d1a3f8f4
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a5e61507b150febec91fb65a139aac52c422f21588bbee7447873070abe68e
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce0043d0cee8dc26738b1332844ffca8fc943ecdf31433fee5f4cd21521866f
3
  size 436251442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d043b0a210d45339a3fea4cd83be346b5722565a18c85f7b05acb35a7e9abc
3
  size 436251442
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1de06a3ec8f2999c325313798cdaabe41b0bd52e48723224e7203f53719d206b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b800b6d302bd5c5bc6607adcd64c98c8846be4c2323ad836fe3e601910de836
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 sha256:3e2686563472cd649084082a2c329fd627ce86023a87d1ac3f5dd126e100dfda
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": 0.01077295987072448,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 9.185,
53
  "eval_steps_per_second": 4.604,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +108,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 4661524568211456.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02154591974144896,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 9.185,
53
  "eval_steps_per_second": 4.604,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.012927551844869378,
58
+ "grad_norm": 0.8018312454223633,
59
+ "learning_rate": 0.00019781476007338058,
60
+ "loss": 0.7179,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.016159439806086723,
65
+ "grad_norm": 0.7042528390884399,
66
+ "learning_rate": 0.00018660254037844388,
67
+ "loss": 0.7305,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.016159439806086723,
72
+ "eval_loss": 0.7286339998245239,
73
+ "eval_runtime": 42.5738,
74
+ "eval_samples_per_second": 9.184,
75
+ "eval_steps_per_second": 4.604,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.019391327767304067,
80
+ "grad_norm": 0.8068830966949463,
81
+ "learning_rate": 0.00016691306063588583,
82
+ "loss": 0.6155,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.02154591974144896,
87
+ "eval_loss": 0.6511708498001099,
88
+ "eval_runtime": 42.5513,
89
+ "eval_samples_per_second": 9.189,
90
+ "eval_steps_per_second": 4.606,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 9217105396236288.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null