chauhoang commited on
Commit
4bf477d
·
verified ·
1 Parent(s): b7a255a

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:a6be0c06046eed3618e4f12e7f1ab82597473ac175ac31c5bfa7b4d30e072e36
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d74874407495f81d087c2bed377bc01e08bb8cbb138c23c36e6a09538fa735
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c46d3b978e998c5247479b0b6f04deb042e7228f3cc98d28be87473cc0267e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3ae826ac619b88e305d1a79bf6a29067848c23f3516e23c87fd6d00b97570b
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:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
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": 0.0010297743407958967,
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": 0.7406,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9113882886930432.0,
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": 0.0015446615111938452,
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": 0.7406,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001188201162456804,
72
+ "grad_norm": 1.2997853755950928,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.702,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001188201162456804,
79
+ "eval_loss": 0.21118231117725372,
80
+ "eval_runtime": 1263.6849,
81
+ "eval_samples_per_second": 8.413,
82
+ "eval_steps_per_second": 4.207,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001386234689532938,
87
+ "grad_norm": 2.2332987785339355,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.9282,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3670824330395648e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null