ccore commited on
Commit
20ef9ab
·
verified ·
1 Parent(s): 436a9df

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2e096f0f51e0c0eb883ddad1c7b1ff62a258cdabda750fcb19250f8a3ab5d11
3
  size 1447317080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad270e4ae06b3fac619d8b1fb85856fe5e8cc29589c7f3276108f5777cedcfa
3
  size 1447317080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64a6b0997847f2b0ada221298830b2deb0ed4b07bb97ee70cf344ddceb01e46a
3
  size 2894813242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47952d6077e1285f4d8dfe00e2f33b1cb254d344181d9a5be504758bd4b26dc7
3
  size 2894813242
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7882a938f81b5d65dc6792ab79e376aa68f8b34a702d85d3e51323da0429a7e5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed22877ea2616e14580013613cbdf42da1e4be0a7ad911cf5f55acc3370b1f6
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.5563850402832031,
3
  "best_model_checkpoint": "./opt_trained2/checkpoint-43",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 43,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -15,6 +15,14 @@
15
  "eval_samples_per_second": 17.758,
16
  "eval_steps_per_second": 4.44,
17
  "step": 43
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 500,
@@ -34,7 +42,7 @@
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 1968190425273600.0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
  "best_metric": 0.5563850402832031,
3
  "best_model_checkpoint": "./opt_trained2/checkpoint-43",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 86,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
15
  "eval_samples_per_second": 17.758,
16
  "eval_steps_per_second": 4.44,
17
  "step": 43
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_loss": 0.5786572694778442,
22
+ "eval_runtime": 16.9078,
23
+ "eval_samples_per_second": 17.743,
24
+ "eval_steps_per_second": 4.436,
25
+ "step": 86
26
  }
27
  ],
28
  "logging_steps": 500,
 
42
  "attributes": {}
43
  }
44
  },
45
+ "total_flos": 3936380850547200.0,
46
  "train_batch_size": 8,
47
  "trial_name": null,
48
  "trial_params": null