chauhoang commited on
Commit
4c8e4f3
·
verified ·
1 Parent(s): 37dab37

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:efa1fac9bcc2d8c22e35acf1c306b2da0060642de2d3cd0a5c305f3ee4724b54
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d405e2ee3ba92bafdd5b014aeb0c1d0504cb05fd561d7d6a42fa05e921acb8a3
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e6e0f137a0aca99ae37472f194236e4e9e3de41e3a94f325c82f2db3eb7ecad
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a89eb81c970c05fd0bec3161de9211c0c314ecda087f84cc7d8cec8cc0195e3
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:f56b63135c9dc05fe1d067bd4c398584d316f2e05feed5be4a0452f5d1a8538c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc940837d9afbc0223097d82695a1b91df9895bd268e592c8f4e38ce5ea878e3
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": 0.009425412361790828,
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": 2.8699,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 451868681306112.0,
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": 0.014138118542686243,
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": 2.8699,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.010875475802066341,
72
+ "grad_norm": 0.6746653318405151,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.9307,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.010875475802066341,
79
+ "eval_loss": 2.8378565311431885,
80
+ "eval_runtime": 44.849,
81
+ "eval_samples_per_second": 25.909,
82
+ "eval_steps_per_second": 12.955,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.012688055102410731,
87
+ "grad_norm": 0.6385213732719421,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.8624,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 678915999006720.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null