tuantmdev commited on
Commit
34a085c
·
verified ·
1 Parent(s): 09102de

Training in progress, step 50, 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:ba1d39e6a45ce9ca1b6f5d86750724a1060d903084f981ece045a95b1a2e2ea8
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7fcf7d01f66123b7fbfc7e30882d941cfd57e1b61302635e775014e97fea85
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25ce3f812a1821964e3c9ff02f3162d5a5ab2d9838b9da7bed8f94ed403fd57d
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd37a357343c2b5d408f9964b7867f8894e44a9264dd38e6a2e5dea0068933a
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e0b90ee7b667b22c2f940fcda75f532eb85336078df18089de67b77b3b833c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064297d010231bc9ba87d05c6184aa47455d8655363a0f6bbb29596d61eefbf6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b23fe3d7c8cff984a05b7865b1b491bac693fd2f496a4e0e24b70ad75a25bd
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": 0.038373905744094015,
5
  "eval_steps": 10,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -54,6 +54,14 @@
54
  "eval_samples_per_second": 5.655,
55
  "eval_steps_per_second": 2.828,
56
  "step": 40
 
 
 
 
 
 
 
 
57
  }
58
  ],
59
  "logging_steps": 40,
@@ -68,12 +76,12 @@
68
  "should_evaluate": false,
69
  "should_log": false,
70
  "should_save": true,
71
- "should_training_stop": false
72
  },
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 5.06595888857088e+16,
77
  "train_batch_size": 2,
78
  "trial_name": null,
79
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04796738218011752,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
54
  "eval_samples_per_second": 5.655,
55
  "eval_steps_per_second": 2.828,
56
  "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.04796738218011752,
60
+ "eval_loss": 1.7664101123809814,
61
+ "eval_runtime": 308.078,
62
+ "eval_samples_per_second": 5.7,
63
+ "eval_steps_per_second": 2.85,
64
+ "step": 50
65
  }
66
  ],
67
  "logging_steps": 40,
 
76
  "should_evaluate": false,
77
  "should_log": false,
78
  "should_save": true,
79
+ "should_training_stop": true
80
  },
81
  "attributes": {}
82
  }
83
  },
84
+ "total_flos": 6.3324486107136e+16,
85
  "train_batch_size": 2,
86
  "trial_name": null,
87
  "trial_params": null