havinash-ai commited on
Commit
69b4e7e
·
verified ·
1 Parent(s): e238d41

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:ad6864d01107f96d45467b63695d964696bdd5fe11c021bb3cc08ed9fed9ceeb
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6ce35e23b27fd6e8d1d435b62502338591f11531a5f8a43f0234c840188472
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90979888aa30531135ef0c5ed3b7ddc1365a98397a8c0ae8c733324aefaee7d1
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1803d7ed40b584bcc9f71c2bb29e9cf16ac34d3d187a78c084a9dbd530b5650
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c031411eb4bfcead7feb84c4a628477e310fe2fc58a2fbd615313c54c2e802e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c3c915a3bb8b4192b1fe9ab2e40a6b8012bb6b2e4c94a894df47ee8a987a0e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.012711864406779662,
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": 7.951,
45
  "eval_steps_per_second": 3.976,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 700324742430720.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.025423728813559324,
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": 7.951,
45
  "eval_steps_per_second": 3.976,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.01694915254237288,
50
+ "grad_norm": 0.4075331687927246,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.7026,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0211864406779661,
57
+ "grad_norm": 0.29102247953414917,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.8396,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.025423728813559324,
64
+ "grad_norm": 0.7371453046798706,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.7147,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.025423728813559324,
71
+ "eval_loss": 1.7477717399597168,
72
+ "eval_runtime": 12.5608,
73
+ "eval_samples_per_second": 7.961,
74
+ "eval_steps_per_second": 3.981,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1359453911777280.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null