dixedus commited on
Commit
1bb8919
·
verified ·
1 Parent(s): f6ff290

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:a837c13d578e456627561a53f18821ea077f3c23952dbdc52a5446f206b8a64d
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6053bf147bc20ef8b243585537a70e77a866778db9b912a3984f5246acdad46
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a972369b92c3c2629dcb3abba53e875d8264fe8840ee1cbdb3b59d663a1278a
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c35e6b7b33d019ee2bb02ff2e1c45df37d344660949d021c2de9bb86676851
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5224358fefc4a6c20673e2c295e1dbc37dff7b6514472d01bd9b5aa0159f5f9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3295d9b8e6727a0572a17fcd9e9c0c197ca020ea3fd15f4c9bf4d70bd654e602
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": 0.0038894741106879505,
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": 6.937,
132
  "eval_steps_per_second": 0.867,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 9.492926984670413e+16,
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": 0.004861842638359939,
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": 6.937,
132
  "eval_steps_per_second": 0.867,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.00421359695324528,
137
+ "grad_norm": 0.7065563201904297,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 1.7901,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.0045377197958026095,
144
+ "grad_norm": 0.7974684834480286,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 1.8999,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.004861842638359939,
151
+ "grad_norm": 0.7784953713417053,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 1.829,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.004861842638359939,
158
+ "eval_loss": 1.8407630920410156,
159
+ "eval_runtime": 2249.9599,
160
+ "eval_samples_per_second": 6.929,
161
+ "eval_steps_per_second": 0.866,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.1866158730838016e+17,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null