duyphu commited on
Commit
57ad929
·
verified ·
1 Parent(s): febfdb1

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 sha256:835c80cbaf94a39db43c728896c665527a0368269cd59778d9de0b0e528675ed
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfc4e9c3313c32f426528a528bf20b4a5f3737784c2dd4e4c6549fa97811660
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a61137babe9389b0360cf384beafd855758f1ef9d55f4a66249bd43e21fb91d8
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0c91c6ce2a791e80385d799ea8eeb4c9ec389258fb0847be4e767b49e186ed
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01fc1ce580e28a619d9332a6abc08d276d77522f73350afe3c772a2760eb6750
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e84a92a389e8f8225a67e1edf059475566aba99fba047ec4f43babf6cf1df1
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": 0.0013018225515722011,
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": 1.3294,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 776288159662080.0,
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": 0.0019527338273583016,
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": 1.3294,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0015021029441217705,
72
+ "grad_norm": 10.626105308532715,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.5351,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0015021029441217705,
79
+ "eval_loss": 0.272754430770874,
80
+ "eval_runtime": 191.9567,
81
+ "eval_samples_per_second": 43.812,
82
+ "eval_steps_per_second": 21.906,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0017524534348087322,
87
+ "grad_norm": 9.206679344177246,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0722,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1164432239493120.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null