chauhoang commited on
Commit
867b7a8
·
verified ·
1 Parent(s): ad70043

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:bf26af092495dae48ab5e31a5b55b1d32b556dd45e143c0284b78580c0054289
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a76fcd13078f6ba7f5a191bc795fbae553b888fe44138c403ab57a91d44631
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0939f4e1c8fe3242851d4a84e919a03ac39c0b19675e4d16086cb18025906c0a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6532950d0076dc6e55064969d6d1446a6e2b29bb32f08d57bc4be05a18bad92
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66d743f7d7f1e483fc21966690f23e79e8c531a6f00323f193d4a604fb0e9d14
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87e4caf284f84836b86fbb9d15f85d95c4be4769dd1ae693ef400a82f62b7ca
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": 0.0018479690109812004,
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": 3.3916,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4644660295237632.0,
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": 0.002771953516471801,
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": 3.3916,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.002132271935747539,
72
+ "grad_norm": 32.019588470458984,
73
+ "learning_rate": 5e-05,
74
+ "loss": 3.6857,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.002132271935747539,
79
+ "eval_loss": 0.9380649328231812,
80
+ "eval_runtime": 396.5294,
81
+ "eval_samples_per_second": 14.94,
82
+ "eval_steps_per_second": 7.47,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002487650591705462,
87
+ "grad_norm": 14.430593490600586,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.3664,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7010807992811520.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null