Hugging Face's logo

phungkhaccuong
/
b9ff78f8-f9d4-0eee-0d8e-f560c5e8e55f

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
adb1d69
·
verified ·
1 Parent(s): 2a17bea

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 sha256:8d20492bbc38b629bf23775e83780db6b1a6e1d3427bf72b3e74d4af4fc86221
3
  size 10624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3e1c7a637035553499403e83ffe53afc6711f4184a9fc5119c43f467d69b3a
3
  size 10624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25c3307719858634dd917f839d906502f2dbcad9f40bba8fca43487351f70c1c
3
  size 26562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f2a834784d11af679385eeb35490a92680abfb4d01dd54656cd5a5390a478f
3
  size 26562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0142a686d2f42ce8f779f95a994c62a8be5e12e27afd368335d9d4d2472185ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
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": 0.002882217090069284,
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": 12.4126,
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": 3879862272.0,
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": 0.003695150115473441,
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": 12.4126,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.002956120092378753,
94
+ "grad_norm": 0.0450810082256794,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 12.4069,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.002956120092378753,
101
+ "eval_loss": 12.408092498779297,
102
+ "eval_runtime": 64.2755,
103
+ "eval_samples_per_second": 88.65,
104
+ "eval_steps_per_second": 44.325,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.003325635103926097,
109
+ "grad_norm": 0.05601131543517113,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 12.4158,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.003695150115473441,
116
+ "grad_norm": 0.04103691503405571,
117
+ "learning_rate": 0.0,
118
+ "loss": 12.4073,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.003695150115473441,
123
+ "eval_loss": 12.408075332641602,
124
+ "eval_runtime": 64.2388,
125
+ "eval_samples_per_second": 88.7,
126
+ "eval_steps_per_second": 44.35,
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": 4974182400.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null