chauhoang commited on
Commit
0e8ede5
·
verified ·
1 Parent(s): 43e92cb

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 sha256:49abefb69a6c7eb051bb712bb5aa2da34f5144bebb7ee56579f6fa4979d2ab59
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609fecfc02b71ccf0a033c4586fb0976ef48b273f562f4483cc687699ce00b57
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6479dd8945ccc10c5af5786e09446e9bc958a4285b896a45528f7a546ff7d59e
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3df16404d7eb8e780fa3e23198126898e7bc22fb5289cad0ad299ccd46fc80
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de77f7287ed01a202ddb7611953f4ab18428065bfab18b190a6c36e48d8d0054
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b074dd7788a357c83e204bf182c8046b1383eb0a9ff02da64031fe764375a72b
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": 0.0041284585764757254,
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": 2.4165,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8121578202857472.0,
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": 0.006192687864713589,
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": 2.4165,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004763606049779683,
72
+ "grad_norm": 46.6011848449707,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.5225,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004763606049779683,
79
+ "eval_loss": 0.33293241262435913,
80
+ "eval_runtime": 278.8215,
81
+ "eval_samples_per_second": 9.511,
82
+ "eval_steps_per_second": 4.756,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00555754039140963,
87
+ "grad_norm": 19.61571502685547,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.1785,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2161961328902144e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null