chauhoang commited on
Commit
c15822c
·
verified ·
1 Parent(s): d9b20f0

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 sha256:882965f17d26484f21b7422b127431b39e9bc167de2756137b2bffa6c145ce15
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f63aa33a43723d6a15d9c22056078913adc4f8abfc8baa7a90d1ae614141e6
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cde728115d951d44b9c7f3858fc718d126db8d944084c0825c7cb8111395365
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e5f32f5b9b8f7a03fd548f0abccb03ea48af8e63fea28903daa9192145e379
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b7297c953f542071b9668195e42c49c3ecf8c10d91797c114451fa250854b4c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98afc215468fe49340fcc1e8d06e1a0e4426237e618a149fa37ce1204c3ce0e
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": 0.07262569832402235,
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": 6.7389,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7417293931806720.0,
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": 0.10893854748603352,
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": 6.7389,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.08379888268156424,
72
+ "grad_norm": 4.825051307678223,
73
+ "learning_rate": 5e-05,
74
+ "loss": 6.4153,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.08379888268156424,
79
+ "eval_loss": 1.5849660634994507,
80
+ "eval_runtime": 12.6209,
81
+ "eval_samples_per_second": 11.964,
82
+ "eval_steps_per_second": 6.022,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.09776536312849161,
87
+ "grad_norm": 4.308661937713623,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 6.0258,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.112594089771008e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null