Hugging Face's logo

besimray
/
test

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
 Community
besimray commited on
Commit
361ea83
·
verified ·
1 Parent(s): 9d05236

Training in progress, step 10, 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 +54 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9e40d3e7c56cb46cd5a983275df9d038d806fdd848e034c4a041da2524b91e6
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f9f2ba371ac6239986a187862d63b0c1f7449185826263eb86caf58f5e95ff
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64cd5a60aa5e8bf4a4a45861316793a730820db2579d5d8c328fce981f9761b7
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fd9205f7754a8180253d59128b1434f95073a69191aad2881984b31890661e
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2580185eb0877da29c17fcb94b565a0adbb4fd61496abf5f574b0e4cc05bd14
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71b0de01fd8deb2ce3d1a6777f8505ab846afca04e147faad39279892d064e8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.47619047619047616,
5
  "eval_steps": 3,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -58,6 +58,57 @@
58
  "learning_rate": 0.0001,
59
  "loss": 1.2785,
60
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  }
62
  ],
63
  "logging_steps": 1,
@@ -77,7 +128,7 @@
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 956760087330816.0,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9523809523809523,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
58
  "learning_rate": 0.0001,
59
  "loss": 1.2785,
60
  "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.5714285714285714,
64
+ "grad_norm": 0.26828739047050476,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2706,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.5714285714285714,
71
+ "eval_loss": 1.2105836868286133,
72
+ "eval_runtime": 6.3215,
73
+ "eval_samples_per_second": 15.819,
74
+ "eval_steps_per_second": 7.91,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.6666666666666666,
79
+ "grad_norm": 0.3657456636428833,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2182,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.7619047619047619,
86
+ "grad_norm": 0.49670976400375366,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.2607,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.8571428571428571,
93
+ "grad_norm": 0.42949965596199036,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2699,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.8571428571428571,
100
+ "eval_loss": 1.1932201385498047,
101
+ "eval_runtime": 6.3734,
102
+ "eval_samples_per_second": 15.69,
103
+ "eval_steps_per_second": 7.845,
104
+ "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.9523809523809523,
108
+ "grad_norm": 0.281423419713974,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.2143,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1913520174661632.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null