Hugging Face's logo

robiulawaldev
/
9c58422c-4b66-4fca-8308-373ce5071dd7

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
robiulawaldev commited on
Commit
e55b63b
·
verified ·
1 Parent(s): f22d9f8

Training in progress, step 150, 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 +46 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a54350408200bc1357989790163a6aa405ed9e129a0552a7996f9a60ea021bf8
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed1ceb692bae22db1ad91729d2901d0af7fcb11d116b374a26fcfc1cd403311
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b699235bded1c63a6b7a91d16a8331390716ace0728ad516b4b32e7bccf11bfe
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473a5f39f15a92a45ddc816c89d96b42dca50305fe77169dc8d19c1e7f8222c
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca3f694a84171edc9dc9e6d56083f03e3ff035daf7f49aee80739ba0381f7d71
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4148d3742d324ab4c5163342706d0ad83b1af275c7c1216ee94b4ed6afbd051
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
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": 0.02545500827287769,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -101,6 +101,49 @@
101
  "eval_samples_per_second": 32.789,
102
  "eval_steps_per_second": 16.395,
103
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
  }
105
  ],
106
  "logging_steps": 10,
@@ -120,7 +163,7 @@
120
  "attributes": {}
121
  }
122
  },
123
- "total_flos": 3493411559571456.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.038182512409316534,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
101
  "eval_samples_per_second": 32.789,
102
  "eval_steps_per_second": 16.395,
103
  "step": 100
104
+ },
105
+ {
106
+ "epoch": 0.02800050910016546,
107
+ "grad_norm": 3.6178667545318604,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.4882,
110
+ "step": 110
111
+ },
112
+ {
113
+ "epoch": 0.030546009927453228,
114
+ "grad_norm": 3.847907781600952,
115
+ "learning_rate": 0.0002,
116
+ "loss": 1.2551,
117
+ "step": 120
118
+ },
119
+ {
120
+ "epoch": 0.033091510754740996,
121
+ "grad_norm": 2.4163215160369873,
122
+ "learning_rate": 0.0002,
123
+ "loss": 1.2833,
124
+ "step": 130
125
+ },
126
+ {
127
+ "epoch": 0.03563701158202876,
128
+ "grad_norm": 5.160815715789795,
129
+ "learning_rate": 0.0002,
130
+ "loss": 1.5816,
131
+ "step": 140
132
+ },
133
+ {
134
+ "epoch": 0.038182512409316534,
135
+ "grad_norm": 3.6169214248657227,
136
+ "learning_rate": 0.0002,
137
+ "loss": 1.2131,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.038182512409316534,
142
+ "eval_loss": 1.3646901845932007,
143
+ "eval_runtime": 25.3107,
144
+ "eval_samples_per_second": 32.713,
145
+ "eval_steps_per_second": 16.357,
146
+ "step": 150
147
  }
148
  ],
149
  "logging_steps": 10,
 
163
  "attributes": {}
164
  }
165
  },
166
+ "total_flos": 5202418653462528.0,
167
  "train_batch_size": 2,
168
  "trial_name": null,
169
  "trial_params": null