kostiantynk1205 commited on
Commit
fcda461
·
verified ·
1 Parent(s): ac51618

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:fad18b383fc89326d224d91971e296f2e3f644570ae4647490f82eba6c583e70
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f73cc123e2ecea4b09b0318265f92946307b5ac1df6d629a133e53b03a20a5a
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6acffbb5b8b0c463a7e1d65f643ee1c3e0131016dd689fbfb5f3e5e009e45f7b
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c836a35bbdeb7fd39b6f2cb4f69aa56f10ed497da1cab9ea7b4aea5799c5854f
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": 0.00025593448077292216,
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": 26.473,
45
  "eval_steps_per_second": 13.236,
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": 0.0005118689615458443,
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": 26.473,
45
  "eval_steps_per_second": 13.236,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00034124597436389616,
50
+ "grad_norm": 0.8757002353668213,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.9894,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0004265574679548702,
57
+ "grad_norm": 0.9721984267234802,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.1353,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0005118689615458443,
64
+ "grad_norm": 0.9829956889152527,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.9926,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0005118689615458443,
71
+ "eval_loss": 3.0818350315093994,
72
+ "eval_runtime": 186.681,
73
+ "eval_samples_per_second": 26.441,
74
+ "eval_steps_per_second": 13.22,
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