dimasik2987 commited on
Commit
57c2a2b
·
verified ·
1 Parent(s): 4de2393

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2cbcff71a8dc8512c8115de623cd1e8a41bc1b560eea80a2369031bc642f47
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a63d70ff2aedd429eee8ffa82e10c579494a24291c0f33a9de2fafd30cc56b3
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85d54ae7ae8059379cf7396f83731943e3a39c84e2b23c8693670f089551f57b
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9386f11300018f520d4701b620154d3060b35b5fdf3b8e73a5ed88dac67195ad
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea700645d5d847c0004a54d122e57717513cffc5f5cad95acb6fbff114711511
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef73aa36afabdfbf7be74c4769cba6429bbaaf8e4ecdfa5b7e9a2a21434f561
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.007454342154304882,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 0.00018,
45
  "loss": 3.0066,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 69418793041920.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.014908684308609765,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 0.00018,
45
  "loss": 3.0066,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.008945210585165859,
50
+ "grad_norm": 1.5807294845581055,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 2.4554,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.011181513231457324,
57
+ "grad_norm": 2.061957836151123,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 2.0364,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.011926947446887812,
64
+ "eval_loss": 1.6609691381454468,
65
+ "eval_runtime": 7.9127,
66
+ "eval_samples_per_second": 71.404,
67
+ "eval_steps_per_second": 35.765,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.013417815877748788,
72
+ "grad_norm": 2.554117202758789,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 1.6773,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 138837586083840.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null