chauhoang commited on
Commit
60380b4
·
verified ·
1 Parent(s): 8375b95

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a9e99d43c71e573d67c410ef836ede6e0367c7540d8009ec904d47bc7e1cc9d
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0f704e6dcf2a4b4953137ca8a2cf0673c7d5d9c33234148e10837a14a59784
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c242245516d16c47287ea296d338e46ebb26c84486a3ffeda15397429416af1
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61374d2475c716213718b19b31ccf57556f56383ff11b168ad117101a4ceb2aa
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66858b40af83947edf569c3acabc2f826bba88e0c12f7d5c52a38d9c298d66a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d8d8d8dd02127c696bffc33ab79e1129defd31e86a0d3b3a8a9782d336a86a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.0016555237185609678,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 20.523,
38
  "eval_steps_per_second": 10.265,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1147943025377280.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0033110474371219356,
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,
 
37
  "eval_samples_per_second": 20.523,
38
  "eval_steps_per_second": 10.265,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0019102196752626551,
43
+ "grad_norm": 0.5668697953224182,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 1.806,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0025469595670168737,
50
+ "grad_norm": 0.5659977197647095,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.6358,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0025469595670168737,
57
+ "eval_loss": 2.3336341381073,
58
+ "eval_runtime": 162.3412,
59
+ "eval_samples_per_second": 20.371,
60
+ "eval_steps_per_second": 10.188,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.003183699458771092,
65
+ "grad_norm": 0.5387349128723145,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.4841,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 2243706822328320.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null