nat-hunt commited on
Commit
4a3220b
·
verified ·
1 Parent(s): f57e43d

Training in progress, step 9, 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:db28e6ce7f8be684dfa0bebd75e6c96f6c3d7f8911a30037be8765d30f7d2e59
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029b770d21460e8b79ad07c210d415fc085502cfce559e060f65f1a8cb381ec6
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dae6c0022ef3f13f96231e6174fe938db704632eff020c4452da0ced132226c
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a998d2415ace32187f99b7df5ed6bd83232e9655137f59793d671e90abf814b5
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f016496538b79288a5280d17dce870438c89b1623a2f3fe58754fcdbd1a274f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee20c2c505fab0536a0ec11d207ab1b18ac24ed0491c671a58d742747220d84
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 7.662737385218579e-05,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 109.142,
74
  "eval_steps_per_second": 54.573,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 20575590285312.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0001149410607782787,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 109.142,
74
  "eval_steps_per_second": 54.573,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 8.93986028275501e-05,
79
+ "grad_norm": 1.0605616569519043,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.6806,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00010216983180291439,
86
+ "grad_norm": 1.1009156703948975,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.5007,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0001149410607782787,
93
+ "grad_norm": 1.0189341306686401,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.4677,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0001149410607782787,
100
+ "eval_loss": 3.3343887329101562,
101
+ "eval_runtime": 304.9849,
102
+ "eval_samples_per_second": 108.1,
103
+ "eval_steps_per_second": 54.052,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 30863385427968.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null