tuanna08go commited on
Commit
aca8e8d
·
verified ·
1 Parent(s): 2ee2511

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c2dd9ef27509c35d481ad14420910649053c4e80bdefd9f04be3de516d724f1
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bac3e8316cf3415aff07cf2de9f2178932d236471a9809d3aa85cc05fcc59c6
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58805ddb5f577ab760cb80c91ded55f3043d6f20740c4a7ae258ad980711a4fd
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0917b7387490b1f1af3c51292c4ee53e956fe707dfd9346fb5de55817d3e9a44
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31b4df29f171e0a5db139772bc58f4e323c668cf8081aa0d05e252b0103816a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f2e9cfc489ab39b06d1f7093738f22710b5eb729d191272ce46a91be4a256c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.004239188032446093,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.096,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1016304802725888.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006358782048669139,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.096,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004891370806668569,
72
+ "grad_norm": 0.6601759195327759,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0926,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004891370806668569,
79
+ "eval_loss": 1.1310490369796753,
80
+ "eval_runtime": 98.6894,
81
+ "eval_samples_per_second": 26.173,
82
+ "eval_steps_per_second": 13.092,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005706599274446664,
87
+ "grad_norm": 0.8596938848495483,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0772,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1509423109373952.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null