nathanialhunt commited on
Commit
4e9b50a
·
verified ·
1 Parent(s): b5cbd1e

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 sha256:79be735bd9c70b3d40914eb27f2a8eadf1120404f2d66be8c405f9f9e885107b
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e285faa668504ac427bfba57e2f891e71628212e4dcec59001256361c3e0a2ea
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b514bc938383cca105fd9c6e2cef9b0961cb30f7d2324eabfab53df2ae58c49d
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2adcc1c17a767831504d20ac84def297609e8cb9b04cf5d7f4eceae82b630c
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
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": 0.00525164113785558,
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": 20.821,
45
  "eval_steps_per_second": 10.454,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 949861251809280.0,
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": 0.01050328227571116,
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": 20.821,
45
  "eval_steps_per_second": 10.454,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00700218818380744,
50
+ "grad_norm": 1.7818282842636108,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.524,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0087527352297593,
57
+ "grad_norm": 2.215709924697876,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.8649,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.01050328227571116,
64
+ "grad_norm": 3.172147750854492,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.0731,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.01050328227571116,
71
+ "eval_loss": 1.5807032585144043,
72
+ "eval_runtime": 11.6124,
73
+ "eval_samples_per_second": 20.754,
74
+ "eval_steps_per_second": 10.42,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1899722503618560.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null