duyphu commited on
Commit
d1f05d6
·
verified ·
1 Parent(s): b55dfea

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 sha256:51b9e7a30a90459e9bfb3435247d9b214aa785232b6101ec5ed200a21074259e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5526156b7cd90ac05bc7e2670119db18f33835cb255dc78f9dbb9d2e0847738
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b7e2e5bab8705ff3a81c20e02a717d2814826b251d1c23fedb1ba3e3ad98a5a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a132b35e8bb67737c8530f91a86e2374d587ef1b4c92fb1b78305fbf5916f7a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab39d8fbd2c874407a81c5039399b6ff46c2237e5cccded63b3457667cba4d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25afd9068ad49cc1f37cdaa4254cebdce9d6a41cc38a3d73d13119002c050c9
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": 0.0304093567251462,
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": 4.8952,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5038931422740480.0,
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": 0.0456140350877193,
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": 4.8952,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03508771929824561,
72
+ "grad_norm": 9.96809196472168,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.8127,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03508771929824561,
79
+ "eval_loss": 1.3962314128875732,
80
+ "eval_runtime": 26.2943,
81
+ "eval_samples_per_second": 13.729,
82
+ "eval_steps_per_second": 6.884,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.04093567251461988,
87
+ "grad_norm": 17.325239181518555,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.5318,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7492671941640192.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null