Hugging Face's logo

tuanna08go
/
79dc50ff-498a-43bf-a1ed-73e41506c69d

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
tuanna08go commited on
Commit
5bf6bf2
·
verified ·
1 Parent(s): 5a7169e

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 sha256:545cace0debf6c62badf2cfc7c039a5bd7cccc1927b7e5e27770749139a95fa2
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06265794ca652133088eccc26e0ef32e7dd8939325b4376e38c1601f3be8b6b
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:566212a8fcc479fe94635551f5c70ad1df82001f898857b5b7cb79f4ef58afa5
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c34b9441e1facefe06c4b66dea59942a39617fd33a1cadf637f3fa3f7c09378
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd19e18c4ac18e3c1719cc1acfa191482fdb0394cd8eba0fe84d1e0799ffc4cb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f403cb5e05ae1077a947e2a55947ef4aa0ffcee6d22e5bec100d80304d34344d
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": 0.4105263157894737,
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": 0.1224,
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": 3580018173149184.0,
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": 0.5263157894736842,
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": 0.1224,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.42105263157894735,
94
+ "grad_norm": 0.2548942565917969,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.0171,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.42105263157894735,
101
+ "eval_loss": 0.009264972992241383,
102
+ "eval_runtime": 2.0997,
103
+ "eval_samples_per_second": 19.05,
104
+ "eval_steps_per_second": 9.525,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.47368421052631576,
109
+ "grad_norm": 0.15702055394649506,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.044,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.5263157894736842,
116
+ "grad_norm": 2.154541254043579,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.0187,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.5263157894736842,
123
+ "eval_loss": 0.009186025708913803,
124
+ "eval_runtime": 2.1278,
125
+ "eval_samples_per_second": 18.799,
126
+ "eval_steps_per_second": 9.399,
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": 4589766888652800.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null