Hugging Face's logo

laquythang
/
c63ae018-2509-4e3c-a76c-a24c918c49ef

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
laquythang commited on
Commit
e999ddd
·
verified ·
1 Parent(s): b2243b1

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6399990e1e2d238a0da7b9e9570287d67cd3d3ccbc7c9f89660b815dede143ed
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6451334e4fd4a70915c2322f912661ac2047ae730f3de17847c8fb87a7b7df7a
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a26e57d7424105c38fd2203e8267cf23595612b321c069d2b00842a4f484fa2
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b3cae86a3589d6e22506f1594a5e3b858b2bad29db97c017c55cbc37583c95
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0014110176965136105,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 68.609,
74
  "eval_steps_per_second": 34.324,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1240694784.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0021165265447704155,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 68.609,
74
  "eval_steps_per_second": 34.324,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0016461873125992123,
79
+ "grad_norm": 0.0062783206813037395,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.9318,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.001881356928684814,
86
+ "grad_norm": 0.005060715135186911,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.9324,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0021165265447704155,
93
+ "grad_norm": 0.00466363737359643,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.9289,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0021165265447704155,
100
+ "eval_loss": 11.93252944946289,
101
+ "eval_runtime": 26.0435,
102
+ "eval_samples_per_second": 68.77,
103
+ "eval_steps_per_second": 34.404,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1890582528.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null