leixa commited on
Commit
5d30a04
·
verified ·
1 Parent(s): 8ba25eb

Training in progress, step 81, 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:a319a6c673e8da45f7bc1d8d8e147f97d3467c0b704bbb6998954a91d9925eaa
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1e407c7336bbb5eba0e677032d85c0c182f790fd761bcfb2cab4e1154da476
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5967d5c28b739972aad74d00c8a96ba6872c3449c001d43b46ab8513d8dbb9fc
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7228d6a0afffc8f0c5fd0e24752eb68bd801b14582f1aa812b926249001c156f
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:045b4c272e1eb6e89091f4c9d82e18f4b0934375c807b878adae2bc236109356
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b43e51c818353fdc58a80e47797b9309f858b46f69d4373d744fb2a934a15b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 0.30670926517571884,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 36.214,
248
  "eval_steps_per_second": 4.584,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.8810271250251776e+16,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3450479233226837,
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,
 
247
  "eval_samples_per_second": 36.214,
248
  "eval_steps_per_second": 4.584,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.3194888178913738,
253
+ "grad_norm": 0.7148558497428894,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 0.6001,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.33226837060702874,
260
+ "grad_norm": 0.5377858877182007,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 0.5808,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.3450479233226837,
267
+ "grad_norm": 0.4729587733745575,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 0.517,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.3450479233226837,
274
+ "eval_loss": 0.5606918931007385,
275
+ "eval_runtime": 10.9225,
276
+ "eval_samples_per_second": 36.164,
277
+ "eval_steps_per_second": 4.578,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 2.116155515653325e+16,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null