duyphu commited on
Commit
dfd724f
·
verified ·
1 Parent(s): 3ea8034

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 sha256:7c6841fea302ef83141677c77ca36713813e94051c34cb7e5987089ea171fe27
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12d03b93d192a01bcdba4b2d963b48f1c70b95a506d38ca040c5e431624c835
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e31944392f87d4bd80a55b6015c0b5acb8a73c397e67c2be9c0162778710b1e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3493ad00c0f744392164e94b22b641d74c5e51eb7290167cc1f965ec5e6fc0ac
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6132c086c411e9bdb0c32c2a53364b7f55dda21e5dfc4747b9c3b8e7b9d6df
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": 0.0395286963131889,
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": 1.8536,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9617734090358784.0,
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": 0.059293044469783354,
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": 1.8536,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04561003420752566,
72
+ "grad_norm": 2.080104351043701,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7014,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04561003420752566,
79
+ "eval_loss": 1.656833291053772,
80
+ "eval_runtime": 35.495,
81
+ "eval_samples_per_second": 7.804,
82
+ "eval_steps_per_second": 3.916,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0532117065754466,
87
+ "grad_norm": 1.8273946046829224,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.56,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.4380362029334528e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null