dimasik1987 commited on
Commit
9ed411b
1 Parent(s): 537cb51

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:b11aefe9a1538f385ae21a0e6b19afb4577944491677ad225b8993d75a68501a
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebce020e97bb7a4a1f7921ece1e76e7b39843dbfff849f01e2f1673feb633451
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdfc44d11d6d5a64d35f84be1a796859fef8cb45ce4df4f9011aaf91dc79b406
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8a595b1c6ba334f1c3e577bdbea70f8fa2fbcd56244ec5eb272104c48a7410
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:f207c0393f6e88e1bd3fd4a26645c2734162ee3e99b07f0d271c29cb37330a89
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0bee0f47e046288a8ab410015fc2b2510b7d505ae807cb056407e3f2c1143e
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": 0.00017190130000358127,
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": 102.443,
74
  "eval_steps_per_second": 51.225,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 41151180570624.0,
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": 0.0002578519500053719,
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": 102.443,
74
  "eval_steps_per_second": 51.225,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00020055151667084482,
79
+ "grad_norm": 1.3280445337295532,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.7227,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00022920173333810837,
86
+ "grad_norm": 0.8306891918182373,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.9452,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002578519500053719,
93
+ "grad_norm": 0.9781473278999329,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.8849,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002578519500053719,
100
+ "eval_loss": 0.8975035548210144,
101
+ "eval_runtime": 143.4712,
102
+ "eval_samples_per_second": 102.439,
103
+ "eval_steps_per_second": 51.223,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 61726770855936.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null