duyphu commited on
Commit
b6e5437
·
verified ·
1 Parent(s): c179e74

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 sha256:049c5a0e131073433ecec54196d30423a849de9abd06196cd1fc90bd3c3b3c1f
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3bb7b7160471f16bdc46e5261703f5a9156e79468e087a14dda90fab43a46fd
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118dffdad66759abd66b70354253327371a98b3c0e5ea331b12729a441b0434e
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e403950a9db23d682c08c54c7bab2e9bf3937f42ccf06a31812cb0623315455
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561edd6c679660a5ebcc3011ba3e03d78198a1f1bca740cee2349ad76dbcb2a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcac41dbd9142df5390346c9aeb20da7424d647bb3d8dc6eede3f489ba85d01
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": 0.0039851323906962485,
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": 1.0171,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7125707469619200.0,
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": 0.005977698586044373,
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": 1.0171,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004598229681572595,
72
+ "grad_norm": 0.543067216873169,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.1553,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004598229681572595,
79
+ "eval_loss": 1.1278762817382812,
80
+ "eval_runtime": 248.7104,
81
+ "eval_samples_per_second": 11.045,
82
+ "eval_steps_per_second": 5.524,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005364601295168027,
87
+ "grad_norm": 0.8109201788902283,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.9047,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.038317374144512e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null