dimasik87 commited on
Commit
b504a46
1 Parent(s): 4606feb

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176547987b3d2520de9b89220868668052d8fce8938cf7e1bc8b7e1db77aa9bd
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5a7f03be06dc349ac4d435d35083a6b338d1f289a270f3e8513b26b86673ed
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43ee20f66afd9d615f175a105a1b8670d0f20bced7f7de4560e8bfb69cfc90b4
3
  size 320082106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71147b1455f8cf84a401825958bf6be1bde83a5648434fbb00a148dc43e9df6a
3
  size 320082106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c634ec1feddbb2fb10e8538cd879c5f6ee136aebc9b8c375b6e4d57f003cbcfd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763215bea5d1a4c574744e6c699e3f1500c51935002767db23d636da54b8f9a6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.00011487430836093508,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 5.451,
45
  "eval_steps_per_second": 2.726,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1960374605709312.0,
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": 0.00022974861672187016,
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,
 
44
  "eval_samples_per_second": 5.451,
45
  "eval_steps_per_second": 2.726,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00015316574448124678,
50
+ "grad_norm": 3.5897583961486816,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.2432,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00019145718060155847,
57
+ "grad_norm": 1.8159574270248413,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.0641,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00022974861672187016,
64
+ "grad_norm": 0.7535229325294495,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.82,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00022974861672187016,
71
+ "eval_loss": 2.150543451309204,
72
+ "eval_runtime": 1008.4579,
73
+ "eval_samples_per_second": 5.452,
74
+ "eval_steps_per_second": 2.726,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3920749211418624.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null