ClarenceDan commited on
Commit
2c178eb
·
verified ·
1 Parent(s): 21f56bb

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 sha256:46dea8d43ab8496760c45c48b299820309f3f14a791d1d18362376c55275e152
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132307270330bfd3131afc2cd539b02488e30d0ed79d5247eb4ca35e56250650
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad4abc9a4a7567c86dbe258419f512f7e93137f7a8fa51cb14ca8e4763773bdf
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90a9f7def3410d1a6cba225d8389bc8758c8e9704295d8b6978c5e00f1652cd
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8181bbb6dbbe773b6043f4d0c1ba0a1b3a6b72812530d5f0820e8cb22570383
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9908c81d4f08fa0707f543eeeb598037560bf300bf9c35b62655c74c41b96908
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": 0.0013852014313748124,
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": 51.318,
45
  "eval_steps_per_second": 25.659,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 97289477554176.0,
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": 0.0027704028627496247,
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": 51.318,
45
  "eval_steps_per_second": 25.659,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0018469352418330831,
50
+ "grad_norm": 3.2831156253814697,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.8543,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.002308669052291354,
57
+ "grad_norm": 2.9065184593200684,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.4665,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0027704028627496247,
64
+ "grad_norm": 3.7608373165130615,
65
+ "learning_rate": 0.00012,
66
+ "loss": 4.4131,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0027704028627496247,
71
+ "eval_loss": 3.7788474559783936,
72
+ "eval_runtime": 17.9858,
73
+ "eval_samples_per_second": 50.707,
74
+ "eval_steps_per_second": 25.353,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 194578955108352.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null