Hugging Face's logo

tuanna08go
/
23c5533a-eeca-43b7-bd9c-a7cd7ea249c2

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
c4904bc
·
verified ·
1 Parent(s): 235b9f2

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:f7dca26cb073ba94bafeabc6ece769937b4630cee899724850a8bc805a128e26
3
  size 4731640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a88e2101f1016e0ded5ab82849281de2173d4bed33266fe99cad51da9a31d92
3
  size 4731640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b67fdb3bd87b4c23897c5857bb9d88b7e15c474cf95b9d0f6c183288211a5e7
3
  size 2505722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636effec1e513a16d1c1e465d6dd6fc188075be80865dc36c09ad54091b2767d
3
  size 2505722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a934335fbfd861630d57056002912e330d2695d0958904f2f5f97f3de8739bdd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfd0a9e4b3a85a09a77e47f4608b68646202349ee065091eff355751565e927
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": 0.001325493661421337,
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": 8.7606,
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": 171084679741440.0,
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": 0.0016993508479760731,
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": 8.7606,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.0013594806783808586,
94
+ "grad_norm": 5071.74755859375,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 9.2961,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.0013594806783808586,
101
+ "eval_loss": 2.235138416290283,
102
+ "eval_runtime": 139.9565,
103
+ "eval_samples_per_second": 88.52,
104
+ "eval_steps_per_second": 44.264,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0015294157631784659,
109
+ "grad_norm": 1860.71435546875,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 8.823,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0016993508479760731,
116
+ "grad_norm": 1949.494384765625,
117
+ "learning_rate": 0.0,
118
+ "loss": 8.6617,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0016993508479760731,
123
+ "eval_loss": 2.2213568687438965,
124
+ "eval_runtime": 143.0994,
125
+ "eval_samples_per_second": 86.576,
126
+ "eval_steps_per_second": 43.292,
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": 217883628011520.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null