ClarenceDan commited on
Commit
9628558
·
verified ·
1 Parent(s): b980e6e

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 sha256:87d4a0dcb7ea8cfbc8b2fc6a3737b69f917fb481fb28f08df3bb7b8f5213b52b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0008497c916c297f1ebd6bd74439f518a68a665eb78eefeb0b102ca0eafb72e1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e64e9ae0f83ff70d28ab01f9c254e7c120676bab4152808f2487f06e44742231
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6497fd39d4d02b0308ed4d495d9a3c4d06c518aed89b1a27bc3553b9560bbb7
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
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": 0.00014133776191654006,
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": 28.808,
45
  "eval_steps_per_second": 14.404,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
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": 0.00028267552383308013,
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": 28.808,
45
  "eval_steps_per_second": 14.404,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0001884503492220534,
50
+ "grad_norm": 1.0297633409500122,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.5147,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00023556293652756677,
57
+ "grad_norm": 1.0218156576156616,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.8729,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00028267552383308013,
64
+ "grad_norm": 1.0576367378234863,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.1551,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00028267552383308013,
71
+ "eval_loss": 2.1760523319244385,
72
+ "eval_runtime": 310.4139,
73
+ "eval_samples_per_second": 28.794,
74
+ "eval_steps_per_second": 14.397,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1109738548887552.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null