duyphu commited on
Commit
eba929d
·
verified ·
1 Parent(s): bd2ca7e

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 sha256:8ea78328f2f597c0c70d7fc67da2b91100da55e1369ca999c08e507a5a5b0ba3
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740856405ad051a96012c949b4ffb8e0a42c0718414d33832561240336c55fa8
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4588d300e134727b50b1e595cc5e44d8feaa1ec73bc7fe2120b27b78286c960b
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96bfc2f423a1a07f6d255e42ec6993c3a261d676ba57ecc01dd12b421556c8ae
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b695a29e22170d1ae27e56b21cf712df1aa34038fab82f3b2d96a03cb6f4e98b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1886754a6b20d3842ee62d8a95f1549c9cf7c692e0339998abe883efc3c28e13
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": 0.004396533502430776,
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": 0.4213,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 267114491412480.0,
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": 0.006594800253646164,
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": 0.4213,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0050729232720355105,
72
+ "grad_norm": 2.361287832260132,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.1518,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0050729232720355105,
79
+ "eval_loss": 0.17949983477592468,
80
+ "eval_runtime": 86.3702,
81
+ "eval_samples_per_second": 28.829,
82
+ "eval_steps_per_second": 14.415,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005918410484041429,
87
+ "grad_norm": 4.176590442657471,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2436,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 414027461689344.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null