duyphu commited on
Commit
c5a8449
·
verified ·
1 Parent(s): 9cba0df

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 sha256:340c20e04abafb6315b11749a01bd3f58d7f1353f4dfdbe7bd5bfc6760bec134
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77a12570603948f1640a382e9d11c104960fae7b18085d6b3406f9753d290c4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d71acb756adc1183623404f1798b70e592fbe12a6a4d45dc35f86d59889e1587
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d44ac5d1976ed5698788376d5ce1a394f8bda3f6ae1c0b530845747510d51f
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:d99c1d1224da0412675feecfbb86d16ad950c12e50186da4fa4c819eb75a71b9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69760d704f2e1f2ae55fb0e41b4294d3fa392d7fec1a79bfd80e4b1c835abbe
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": 0.0007868713540996754,
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": 0.4534,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4808867045179392.0,
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": 0.001180307031149513,
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": 0.4534,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009079284854996254,
72
+ "grad_norm": 5.501338958740234,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6805,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009079284854996254,
79
+ "eval_loss": 0.759836733341217,
80
+ "eval_runtime": 939.4983,
81
+ "eval_samples_per_second": 14.809,
82
+ "eval_steps_per_second": 7.405,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001059249899749563,
87
+ "grad_norm": 3.4861016273498535,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6598,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7213300567769088.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null