Hugging Face's logo

chauhoang
/
7a350c97-86f1-2489-eb69-5c501cb910b8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
5ffad49
·
verified ·
1 Parent(s): 6e829b9

Training in progress, step 50, 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 +41 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:127873b7305818cd7e60569481d41668f6dc8150974caae12256230d5ad0deee
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34332030ed3aa721714e3a4244b095931a697549cc6558f65c363b0740a5ba9
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba1a95a688802cb10228a22c5a6bfd432ed4962bd83d51a814e3295f2e390eb6
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f95bac47e27284eea06c8b10736c80cf399f3f0b1c415fa5130f39dace5910
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:da26dee88a42596264962a92b56f68e88d23390849451a2002407b381d6b271a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a0a1af2e8a5fb71ec2ab727cb154638fb24e9fe4c9f17e8067e5894b0fdd8b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.0005912562299835131,
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,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.8441,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 1010378314088448.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0007580208076711706,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.8441,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.0006064166461369364,
94
+ "grad_norm": 3.01552677154541,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.6886,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.0006064166461369364,
101
+ "eval_loss": 1.7529908418655396,
102
+ "eval_runtime": 866.3009,
103
+ "eval_samples_per_second": 32.06,
104
+ "eval_steps_per_second": 16.03,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0006822187269040535,
109
+ "grad_norm": 3.4633240699768066,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.8264,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0007580208076711706,
116
+ "grad_norm": 2.898524284362793,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.5719,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0007580208076711706,
123
+ "eval_loss": 1.7475738525390625,
124
+ "eval_runtime": 879.3545,
125
+ "eval_samples_per_second": 31.585,
126
+ "eval_steps_per_second": 15.792,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 1291749490163712.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null