chauhoang commited on
Commit
d931cc5
·
verified ·
1 Parent(s): 93a1725

Training in progress, step 39, 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:f73bbc7bddee874a3b0c8d6a530b608534681c1b6ac8b86b32e378c03f96bbb1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea13678076f3681def9a2376e8e6f636c663f7781272739f3908c6d516aa493
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac01e0d5038b0a32bcbb40cb195cf2a9051337e0c5126729eb1dfa2d218dbfa1
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6bb542e23c27a45c2bc16d3bf27a79aaf3a82210d70dc3661145015f689103c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.006370987503062975,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 4.2422,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9113893355913216.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009556481254594462,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 4.2422,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0073511394266111245,
72
+ "grad_norm": 6.922292232513428,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.8974,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0073511394266111245,
79
+ "eval_loss": 0.9152467250823975,
80
+ "eval_runtime": 204.0154,
81
+ "eval_samples_per_second": 8.426,
82
+ "eval_steps_per_second": 4.215,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008576329331046312,
87
+ "grad_norm": 5.732418060302734,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 4.1309,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3670840033869824e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null