duyphu commited on
Commit
232c8b0
·
verified ·
1 Parent(s): 95dd663

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 sha256:40da3d206a0dfec1d9028db5d9959fdfdade70a179e1ba648cb170845bad6143
3
  size 144805440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3627bb0249f1432f24d597e26dc9f3aa5635f899383447f4d5953a476dc48756
3
  size 144805440
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53661628ec792ae15e2a747f4930c5fd51c4620aa4980e417b5c27e0a82653c0
3
  size 74291604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeaf5dfc9f4c1252e10c73f9f208e162778cfed7c108cc1413c493cf547bf0ab
3
  size 74291604
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53096b7b975e8fce7922c5448a91ed2f4ff5fa0388f5ac5c6e7d67e4278aeafd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cce00927943e545f38db920e14c68afdcbd9c32a13585978045f5eaff63d9c2
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": 0.06855636123928807,
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": 0.4806,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8420750184677376.0,
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": 0.10283454185893211,
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": 0.4806,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.07910349373764008,
72
+ "grad_norm": 19.870271682739258,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.3225,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.07910349373764008,
79
+ "eval_loss": 0.1717974841594696,
80
+ "eval_runtime": 20.0121,
81
+ "eval_samples_per_second": 7.995,
82
+ "eval_steps_per_second": 3.998,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0922874093605801,
87
+ "grad_norm": 4.610195636749268,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.1221,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2631125277016064e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null