avsolatorio commited on
Commit
c4533b3
1 Parent(s): e41e0ee

Training in progress, step 6000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bfd067bc61e6bfcc59e3c54cec1c0021060e09321f234f56691f2aa3478b074
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9524abf571f381ab467394332b60f92d8a68f46c1e26127034ed52a5bf5b7c6f
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb831687d2acfe6bf1e666a18d84fc971aa14a65e6c52db2330c0ec58eb8e40
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f564e11824fd13f47c0e8b598087bcb5bd2c2abcb35bd00154ba446a413a23
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.045854322612285614,
3
- "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-5000",
4
- "epoch": 2.465483234714004,
5
  "eval_steps": 1000,
6
- "global_step": 5000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -137,6 +137,32 @@
137
  "eval_samples_per_second": 558.095,
138
  "eval_steps_per_second": 2.201,
139
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  }
141
  ],
142
  "logging_steps": 500,
@@ -165,7 +191,7 @@
165
  "attributes": {}
166
  }
167
  },
168
- "total_flos": 113147714600100.0,
169
  "train_batch_size": 4,
170
  "trial_name": null,
171
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.04293818399310112,
3
+ "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-6000",
4
+ "epoch": 2.9585798816568047,
5
  "eval_steps": 1000,
6
+ "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
137
  "eval_samples_per_second": 558.095,
138
  "eval_steps_per_second": 2.201,
139
  "step": 5000
140
+ },
141
+ {
142
+ "epoch": 2.712031558185404,
143
+ "grad_norm": 0.3125520646572113,
144
+ "learning_rate": 1.9457593688362923e-05,
145
+ "loss": 0.0453,
146
+ "step": 5500
147
+ },
148
+ {
149
+ "epoch": 2.9585798816568047,
150
+ "grad_norm": 0.4686921536922455,
151
+ "learning_rate": 1.940828402366864e-05,
152
+ "loss": 0.0436,
153
+ "step": 6000
154
+ },
155
+ {
156
+ "epoch": 2.9585798816568047,
157
+ "eval_accuracy": 0.9862800018701361,
158
+ "eval_f1": 0.5134646302250804,
159
+ "eval_loss": 0.04293818399310112,
160
+ "eval_precision": 0.7466393921683226,
161
+ "eval_recall": 0.39127105666156203,
162
+ "eval_runtime": 14.3533,
163
+ "eval_samples_per_second": 565.238,
164
+ "eval_steps_per_second": 2.229,
165
+ "step": 6000
166
  }
167
  ],
168
  "logging_steps": 500,
 
191
  "attributes": {}
192
  }
193
  },
194
+ "total_flos": 135828564625332.0,
195
  "train_batch_size": 4,
196
  "trial_name": null,
197
  "trial_params": null