Baselhany commited on
Commit
4f2a98c
·
verified ·
1 Parent(s): f85485f

Training in progress, step 27312, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab3400935acbe3cf5f906085ec93d6116aa5d1e99af0633a73d3e706f2cd16a6
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8697dd2e30554939f3fdca476e8f8c14ef00252787d6ed337c4f9c24c9f4e2e
3
  size 223144592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bdd076291545d47b6464e519aaf46f4e9dfe2f8be4e7566d7c31c135a1c9323
3
  size 281574266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f55a81dbcdab168b5b56232e68b26448a34e74f5b0c7df45184f5e18e31d7e3
3
  size 281574266
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59f831aeb48368d39337afe7a48ffe4212a4e417eb7aff215653e8d3fa1dcee0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32de07988befbf143be2b9e32a6f8bc0b1b31db8931faad85d1d92ab132d45e6
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc8355cb3493000d81a40060fd9086d3994b8013129a708704b751a5d7398bbe
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b4a296cdf5148ddd1594a16e140d1d657863c4c29f02fff39c8abb2ac48881
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eae2ff98708f58a5d722c91db9dc346e6b11df9cbdf8ea9de78b33a14ae6319e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce753046bc02fca905121dc376e6ab4266dc1a838826882290e3881ef7934be
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 25000,
3
  "best_metric": 0.18243442381373415,
4
  "best_model_checkpoint": "./distil-whisper/checkpoint-25000",
5
- "epoch": 15.817223198594025,
6
  "eval_steps": 1000,
7
- "global_step": 27000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2141,6 +2141,27 @@
2141
  "eval_steps_per_second": 0.43,
2142
  "eval_wer": 0.18287651046271736,
2143
  "step": 27000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2144
  }
2145
  ],
2146
  "logging_steps": 100,
@@ -2155,12 +2176,12 @@
2155
  "should_evaluate": false,
2156
  "should_log": false,
2157
  "should_save": true,
2158
- "should_training_stop": false
2159
  },
2160
  "attributes": {}
2161
  }
2162
  },
2163
- "total_flos": 3.51197399089152e+19,
2164
  "train_batch_size": 8,
2165
  "trial_name": null,
2166
  "trial_params": null
 
2
  "best_global_step": 25000,
3
  "best_metric": 0.18243442381373415,
4
  "best_model_checkpoint": "./distil-whisper/checkpoint-25000",
5
+ "epoch": 16.0,
6
  "eval_steps": 1000,
7
+ "global_step": 27312,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2141
  "eval_steps_per_second": 0.43,
2142
  "eval_wer": 0.18287651046271736,
2143
  "step": 27000
2144
+ },
2145
+ {
2146
+ "epoch": 15.875805506736965,
2147
+ "grad_norm": 8.746485710144043,
2148
+ "learning_rate": 8.429061614202597e-07,
2149
+ "loss": 0.7027,
2150
+ "step": 27100
2151
+ },
2152
+ {
2153
+ "epoch": 15.934387814879907,
2154
+ "grad_norm": 7.414266109466553,
2155
+ "learning_rate": 4.699388333581979e-07,
2156
+ "loss": 0.7047,
2157
+ "step": 27200
2158
+ },
2159
+ {
2160
+ "epoch": 15.992970123022847,
2161
+ "grad_norm": 7.6758832931518555,
2162
+ "learning_rate": 1.0070117857675669e-07,
2163
+ "loss": 0.7324,
2164
+ "step": 27300
2165
  }
2166
  ],
2167
  "logging_steps": 100,
 
2176
  "should_evaluate": false,
2177
  "should_log": false,
2178
  "should_save": true,
2179
+ "should_training_stop": true
2180
  },
2181
  "attributes": {}
2182
  }
2183
  },
2184
+ "total_flos": 3.55254335963136e+19,
2185
  "train_batch_size": 8,
2186
  "trial_name": null,
2187
  "trial_params": null