chauhoang commited on
Commit
0de76b2
·
verified ·
1 Parent(s): 6d29fbc

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 sha256:9d0f704e6dcf2a4b4953137ca8a2cf0673c7d5d9c33234148e10837a14a59784
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08e2bc3b719745a9e91095aae53d13c3ae11d96ba9deeeb409ba615eaeebc54
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61374d2475c716213718b19b31ccf57556f56383ff11b168ad117101a4ceb2aa
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d9afa8a3bb4a7620179fc7db72f98d57f6b729de28a708fc26b5d95c8f48f4
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d8d8d8dd02127c696bffc33ab79e1129defd31e86a0d3b3a8a9782d336a86a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b690cc0be3f085e7988aab186ba333a6d5ce3dea047c99159f04ae1d28d68308
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": 0.0033110474371219356,
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": 1.4841,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2243706822328320.0,
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": 0.0049665711556829036,
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": 1.4841,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0038204393505253103,
72
+ "grad_norm": 0.6737701892852783,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.8006,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0038204393505253103,
79
+ "eval_loss": 2.275390625,
80
+ "eval_runtime": 161.8295,
81
+ "eval_samples_per_second": 20.435,
82
+ "eval_steps_per_second": 10.221,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.004457179242279528,
87
+ "grad_norm": 0.6395950317382812,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7372,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3322077543137280.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null