Hugging Face's logo

phungkhaccuong
/
18d6d3aa-3fae-4913-8e78-59701e8aa297

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
5db4ad2
·
verified ·
1 Parent(s): 4323ad4

Training in progress, step 39, 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 sha256:21b676609e98e932eca37c09ec8cc3ffe000935c3be8daeedd99ac2ecbaaa70b
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b63bcceffbfd1c2bdbfa91b0d572fbf65d28ef12d6d28d41b2a539cea59090a
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06c3915aece43c2f9bb8dcd39aed9ca307e6be7952a60087b70290dd0476582d
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151dac7ca58cc16239451ca75db69c467aa68023c1d71d72f688bfb4debae72f
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.07262569832402235,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 4.1238,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 665059143450624.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10893854748603352,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 4.1238,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.08379888268156424,
72
+ "grad_norm": 3.5850486755371094,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.7438,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.08379888268156424,
79
+ "eval_loss": 3.5863335132598877,
80
+ "eval_runtime": 4.88,
81
+ "eval_samples_per_second": 30.942,
82
+ "eval_steps_per_second": 15.574,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.09776536312849161,
87
+ "grad_norm": 3.6995723247528076,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.3512,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 997588715175936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null