jssky commited on
Commit
1bb98e0
1 Parent(s): 08f12c9

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8402968e0804189df98747b0347afc6dc0a11241b64f28822cc0259b5d54c9bc
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6469d3ae2607d58a6715e255ba83374b9c6ba8d69448fb0489428012688021
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5915eb930342caf329d04c56b1e658d0dd7f1f30bd0f1d5d09a85634d106d31
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ca6fefee5d6771ccaa9ce6b4b89eb47c4901c76b1e260f9d0e091aec6b7fd5
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
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": 0.00012151652624756967,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 4.819,
45
  "eval_steps_per_second": 4.819,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 2225661850681344.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00024303305249513934,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 4.819,
45
  "eval_steps_per_second": 4.819,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00016202203499675956,
50
+ "grad_norm": 3.986837148666382,
51
+ "learning_rate": 6e-05,
52
+ "loss": 2.5492,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00020252754374594945,
57
+ "grad_norm": 2.91995906829834,
58
+ "learning_rate": 8e-05,
59
+ "loss": 1.8304,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00024303305249513934,
64
+ "grad_norm": 3.264693260192871,
65
+ "learning_rate": 0.0001,
66
+ "loss": 2.1765,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00024303305249513934,
71
+ "eval_loss": 2.262515068054199,
72
+ "eval_runtime": 1079.0465,
73
+ "eval_samples_per_second": 4.817,
74
+ "eval_steps_per_second": 4.817,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 4451323701362688.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null