auxyus commited on
Commit
d26e59f
·
verified ·
1 Parent(s): cc29136

Training in progress, step 90, 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:adca24c088ae3064673c96e464b0b5eb9253b21ef141b878b97e9ed5b2923d64
3
  size 17425352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7a1dee865be65b2abfc28de0631a7389055b139440dafdb365df1265404d77
3
  size 17425352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de8f03d74e8beff9335eededd2325c1935f7078a5eedb5b1ea5a64dd7efa36d6
3
  size 10251668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1979f0be7d31ded2faef7d3bd3a448b45b42de387efa30dccff2493642941744
3
  size 10251668
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac564aab16c172e33ed70be43603bd16c90e9919ba57413e6141b17ae5103921
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49efe4d02f8ecea18dd22b5963355d96fe082e5f38212558a53764a758a95dd5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
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": 0.1883720930232558,
5
  "eval_steps": 9,
6
- "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 69.751,
277
  "eval_steps_per_second": 8.767,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 5079787194286080.0,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.20930232558139536,
5
  "eval_steps": 9,
6
+ "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
276
  "eval_samples_per_second": 69.751,
277
  "eval_steps_per_second": 8.767,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.19534883720930232,
282
+ "grad_norm": 0.8051215410232544,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 3.3875,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.20232558139534884,
289
+ "grad_norm": 1.0949082374572754,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 3.6471,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.20930232558139536,
296
+ "grad_norm": 0.9996029138565063,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 3.5462,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.20930232558139536,
303
+ "eval_loss": 3.5418734550476074,
304
+ "eval_runtime": 10.3865,
305
+ "eval_samples_per_second": 69.706,
306
+ "eval_steps_per_second": 8.761,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 5644207993651200.0,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null