duyphu commited on
Commit
1b2a10c
·
verified ·
1 Parent(s): 7617dda

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:f858914822aed8ad7a6e6cbac56e0f2135171987b473ab07759f0f86ae930d8b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be22d011adcbef0cea503d6f1ccfaac1cf9de9fc405b50375ac1cfc4d6717fca
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f694b43e613a1edb1eb9626d4dbd11a83fa86fe1be69c8adeec2debd4cb4047
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a995303ede4d4e9f2d5474533649928ee32e0f833589bb86a2909aaac82c6bd
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bcd094c31c6302ab0f6b8a0d552c64675298946a65fbc2f7cfe61f1f9a1ad9d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b2b655181cbd20071e25a8c2ca5953708370f3dc36111fe4dce52cd2f9b572
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": 0.004246457882487445,
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": 1.9025,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5040062576197632.0,
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": 0.006369686823731167,
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": 1.9025,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0048997590951778205,
72
+ "grad_norm": 1.7180277109146118,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.785,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0048997590951778205,
79
+ "eval_loss": 1.8614076375961304,
80
+ "eval_runtime": 184.3567,
81
+ "eval_samples_per_second": 13.984,
82
+ "eval_steps_per_second": 6.992,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005716385611040791,
87
+ "grad_norm": 2.3482632637023926,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7852,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7583213417398272.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null