leixa commited on
Commit
0a36d81
·
verified ·
1 Parent(s): c1176e3

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f59bc570d543b6b0554de9391d058c0bee714e969a651048b759effae1f67b6
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0e4201b909dc6c9653f558d9207c4fba1d90c65547bc291f6763f4ab2c5ad4
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:450694e91ccd7f4bb54a7d50a6022ab59f4a3f77ea7faf6d8d0dc4055793d836
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f2303b9ae95ba5bb82964e9841472e31f3eac3da71e4ef73a8601291096e45
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3387820e8b3261399f0705d97f791410f18832b41df41d206dca89c9c3aadac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55534edeb16a30ba2060c2d5b41f5d3a9adf813094ee82e943b4e8cd4729116
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.45425867507886436,
5
  "eval_steps": 9,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 59.8,
132
  "eval_steps_per_second": 7.587,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 2847769488261120.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5678233438485805,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 59.8,
132
  "eval_steps_per_second": 7.587,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.4921135646687697,
137
+ "grad_norm": 0.704291045665741,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 1.5021,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.5299684542586751,
144
+ "grad_norm": 0.725155234336853,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 1.712,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.5678233438485805,
151
+ "grad_norm": 0.6382411122322083,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 1.587,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.5678233438485805,
158
+ "eval_loss": 1.6629996299743652,
159
+ "eval_runtime": 2.2344,
160
+ "eval_samples_per_second": 59.971,
161
+ "eval_steps_per_second": 7.608,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 3568723789086720.0,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null