brixeus commited on
Commit
42e607d
·
verified ·
1 Parent(s): 6ff0cba

Training in progress, step 36, 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:a7eb505748dbb7bf16de72e0124352b954e4c7a31ece36a1b7a20eb2cc290c8d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2990810779cbc06206cd62e3f42a923a4c6b5709cd9a1ec81e95930ab447bfdd
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe4d78d527927b40739df46012adad2bf9f679b3375fcb423d6526ebe5d74bc3
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ec8a9130a303611186036c2b1dcb82ef44cf8cad7530685170d9e288f41d9e
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
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": 0.00823045267489712,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 13.896,
103
  "eval_steps_per_second": 1.738,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 3.796903641533645e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010973936899862825,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 13.896,
103
  "eval_steps_per_second": 1.738,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.009144947416552356,
108
+ "grad_norm": 3.946521043777466,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 5.4655,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.010059442158207591,
115
+ "grad_norm": 3.9313600063323975,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 5.3857,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.010973936899862825,
122
+ "grad_norm": 3.9708104133605957,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 5.1117,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.010973936899862825,
129
+ "eval_loss": 1.3252490758895874,
130
+ "eval_runtime": 397.7349,
131
+ "eval_samples_per_second": 13.891,
132
+ "eval_steps_per_second": 1.737,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 5.062538188711526e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null