Hugging Face's logo

tripathiarpan20
/
tuning-84ba9757-9076-4822-ab9e-11135834d1dd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
 Community
tripathiarpan20 commited on
Commit
e6dae5d
·
verified ·
1 Parent(s): 07032dd

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 +55 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f086230559938c8308c1f4477200a323c7788a89275a4366b52019f744b2f233
3
  size 119597408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f0595cf02d4267d014eef9751afada1f33715bfcf6add0b6d31e8a1fae1b29
3
  size 119597408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f3bc78c1e1e69f314635d09a55eedc015fea62ccbac255b7145f249ac8ac3c5
3
  size 61226900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b88c478021a05c2bd0a9570fefa8f0d08fa334d806c5feb4917687f5bdcf5e
3
  size 61226900
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:759f7b0f4a53221a1bcad0f1e0a83a3da5a495446fdf9afab24a2e4eb245428d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0926e91fae4cf81358220558f5afb4124c07519ef35f16a158b72d8e5db824dd
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": 0.0008150291372916582,
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": 10.6433,
60
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  }
62
  ],
63
  "logging_steps": 1,
@@ -72,12 +123,12 @@
72
  "should_evaluate": false,
73
  "should_log": false,
74
  "should_save": true,
75
- "should_training_stop": false
76
  },
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 3688821581414400.0,
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": 0.0016300582745833164,
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": 10.6433,
60
  "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0009780349647499898,
64
+ "grad_norm": 1.913991874121564e+17,
65
+ "learning_rate": 0.00012,
66
+ "loss": 10.064,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0009780349647499898,
71
+ "eval_loss": 9.447994232177734,
72
+ "eval_runtime": 903.8354,
73
+ "eval_samples_per_second": 2.858,
74
+ "eval_steps_per_second": 1.429,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0011410407922083214,
79
+ "grad_norm": 1.7332163570355405e+17,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.4746,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0013040466196666532,
86
+ "grad_norm": Infinity,
87
+ "learning_rate": 0.00016,
88
+ "loss": 9.2175,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0014670524471249848,
93
+ "grad_norm": Infinity,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.5814,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0014670524471249848,
100
+ "eval_loss": 9.504780769348145,
101
+ "eval_runtime": 904.1481,
102
+ "eval_samples_per_second": 2.857,
103
+ "eval_steps_per_second": 1.429,
104
+ "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0016300582745833164,
108
+ "grad_norm": Infinity,
109
+ "learning_rate": 0.0002,
110
+ "loss": 9.763,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 7377643162828800.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null