fats-fme commited on
Commit
845c543
·
verified ·
1 Parent(s): 1503988

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:ef3e3e0ba01181159ea2329979e45a86e7b141b54c907813c904dc63abb39ed4
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835a05bea8b920044351cf9bbf13ed89428fc60ac0fb1f3c54bcbc15f0ca35aa
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aedb846cd4e431a2a0457a149428f18fd10108420094d75a5b3e9e8732c5c49d
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f62f08123e1d4cdd74bc9822cf423608015326db7ddec1e5cf7668dd5f5804
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:170719929f951e3d30eece53e118823123a22b2e8555a551a599b149ca453b69
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6d51f12e3f9c5a361768047223feb6775db64aa121716b67d57cbb0fda80a5
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": 0.004916018025399427,
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": 3.352,
45
  "eval_steps_per_second": 1.682,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 580633541738496.0,
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": 0.009832036050798854,
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": 3.352,
45
  "eval_steps_per_second": 1.682,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.006554690700532569,
50
+ "grad_norm": 1.6242179870605469,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.0485,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00819336337566571,
57
+ "grad_norm": 1.4690097570419312,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.8352,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.009832036050798854,
64
+ "grad_norm": 1.6833231449127197,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.8784,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.009832036050798854,
71
+ "eval_loss": 1.8704971075057983,
72
+ "eval_runtime": 79.2873,
73
+ "eval_samples_per_second": 3.241,
74
+ "eval_steps_per_second": 1.627,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1161267083476992.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null