brixeus commited on
Commit
0ade2d8
·
verified ·
1 Parent(s): 4bbe887

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e5c9a04786a612b0b663a80159895bed0bda8693f2a1c7e4ac68199af51e874
3
  size 25192688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9040483db66f32334ac2e0917a6b3ce462502d9c8a1789f439a0f7c052c487d
3
  size 25192688
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7c241aa414c67b4eb9cfccfc58df6fbdffe17627783fe6188bf0dbfbdba1055
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fafa642648ebd0e25fd263dfea0499352ca03fffda6204f137399538b90c63
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03f8abc0ac033d78acba855f87d5f656143d83115aecf8ca8831672edbc5e5ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200addda4e16c30aee5c9188591f49e1173e02e3f38d848b2fd7e27ccec3556b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.01196112633939696,
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,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 22.903,
132
  "eval_steps_per_second": 2.865,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 2927530038263808.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0149514079242462,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 22.903,
132
  "eval_steps_per_second": 2.865,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.01295788686768004,
137
+ "grad_norm": 4.891085147857666,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 6.0951,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.01395464739596312,
144
+ "grad_norm": 4.013057231903076,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 6.5056,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.0149514079242462,
151
+ "grad_norm": 3.513582468032837,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 6.14,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.0149514079242462,
158
+ "eval_loss": 1.614381194114685,
159
+ "eval_runtime": 221.2948,
160
+ "eval_samples_per_second": 22.906,
161
+ "eval_steps_per_second": 2.865,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 3776968805842944.0,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null