tuanna08go commited on
Commit
ce54c04
·
verified ·
1 Parent(s): b7946f8

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:b8219bf80ba13decae5e08235ea4784bb4bc37080b7680e90c515ffacf7e092a
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db3b4a7f0b3c2f3d1cdb00db09f1ba2e6e2568e09a0149a38b4a2ed19a94839
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a65f7751332d556bcb67779dbffc71f81bca7402b299c492db83999ac8e1561f
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885068ce09292161cb869ffdc8bcb771bbf4f978e0b05e894b7fe480c87488e3
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
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": 0.05239294710327456,
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": 11.9293,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5848989696.0,
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": 0.07858942065491184,
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": 11.9293,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.060453400503778336,
72
+ "grad_norm": 0.008746370673179626,
73
+ "learning_rate": 5e-05,
74
+ "loss": 11.929,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.060453400503778336,
79
+ "eval_loss": 11.928698539733887,
80
+ "eval_runtime": 2.928,
81
+ "eval_samples_per_second": 71.381,
82
+ "eval_steps_per_second": 35.861,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07052896725440806,
87
+ "grad_norm": 0.004675919655710459,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 11.9269,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8743944192.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null