Hugging Face's logo

kokovova
/
2a42f8b7-2545-4438-a6f2-98abdf5b3b05

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
kokovova commited on
Commit
907e545
·
verified ·
1 Parent(s): 8a1bef1

Training in progress, step 10, 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 +34 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c30241720e7dfc4bc893bc3cfa0fbf36a58214d8ebc40f944c425a9cd2ab620c
3
  size 2185308216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debb094c905ee358595c1205f2564519f1ab2c1690412096176df5e46537ea7d
3
  size 2185308216
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9693d7e08bf353091ba5371f8bd2a1835a8453beef385ae214b316ffc87853f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30d46f844a3304c9b1d85bba1b57b346e30dc4c282ab7455f32c6ec0339b53e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc074af99a8361dd81e5129a0d6955ddfbf082c51d665614b11b916a216bb1d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f0aeba592c738bf692b88ca55fe20a84c9c774c1673fd61017d5506f20c9aa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a422b6b544997208de6867a1c81052e30f98d8110bf29ff31596022ef4dcd51f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92895d149359090ddf3ae4a97578a9224915364b8880d14de783a868db38bfc8
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": 0.0006761039509824635,
5
  "eval_steps": 1,
6
- "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -127,6 +127,36 @@
127
  "eval_samples_per_second": 14.724,
128
  "eval_steps_per_second": 7.363,
129
  "step": 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 1,
@@ -141,12 +171,12 @@
141
  "should_evaluate": false,
142
  "should_log": false,
143
  "should_save": true,
144
- "should_training_stop": false
145
  },
146
  "attributes": {}
147
  }
148
  },
149
- "total_flos": 2959304407646208.0,
150
  "train_batch_size": 2,
151
  "trial_name": null,
152
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0008451299387280794,
5
  "eval_steps": 1,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
127
  "eval_samples_per_second": 14.724,
128
  "eval_steps_per_second": 7.363,
129
  "step": 8
130
+ },
131
+ {
132
+ "epoch": 0.0007606169448552715,
133
+ "grad_norm": 41.63628005981445,
134
+ "learning_rate": 4.8943483704846475e-06,
135
+ "loss": 3.1075,
136
+ "step": 9
137
+ },
138
+ {
139
+ "epoch": 0.0007606169448552715,
140
+ "eval_loss": 1.955424427986145,
141
+ "eval_runtime": 337.8945,
142
+ "eval_samples_per_second": 14.747,
143
+ "eval_steps_per_second": 7.375,
144
+ "step": 9
145
+ },
146
+ {
147
+ "epoch": 0.0008451299387280794,
148
+ "grad_norm": 20.781795501708984,
149
+ "learning_rate": 0.0,
150
+ "loss": 2.4637,
151
+ "step": 10
152
+ },
153
+ {
154
+ "epoch": 0.0008451299387280794,
155
+ "eval_loss": 1.9354504346847534,
156
+ "eval_runtime": 337.7267,
157
+ "eval_samples_per_second": 14.755,
158
+ "eval_steps_per_second": 7.379,
159
+ "step": 10
160
  }
161
  ],
162
  "logging_steps": 1,
 
171
  "should_evaluate": false,
172
  "should_log": false,
173
  "should_save": true,
174
+ "should_training_stop": true
175
  },
176
  "attributes": {}
177
  }
178
  },
179
+ "total_flos": 3699130509557760.0,
180
  "train_batch_size": 2,
181
  "trial_name": null,
182
  "trial_params": null