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:
|
3 |
size 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c88853c0c7fbb83191805d7dddba7b419b637c6f703fcc914f694695f0e683c
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f5085db9d4b21bee1f086feab633a6e6fcd5c6b5cc1ea1753ba5747e083b9cd
|
3 |
size 37965300
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb48600f5c0be872f5604a4284b7a785b06f1698395c195456b60d50b40442d1
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
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.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
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": 30.118,
|
132 |
"eval_steps_per_second": 3.765,
|
133 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos": 1.
|
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": 0.0015178217571316542,
|
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": 30.118,
|
132 |
"eval_steps_per_second": 3.765,
|
133 |
"step": 36
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.0013154455228474337,
|
137 |
+
"grad_norm": 0.2760739028453827,
|
138 |
+
"learning_rate": 3.824798160583012e-05,
|
139 |
+
"loss": 0.7797,
|
140 |
+
"step": 39
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.0014166336399895438,
|
144 |
+
"grad_norm": 0.2843494117259979,
|
145 |
+
"learning_rate": 3.5959278669726935e-05,
|
146 |
+
"loss": 0.7533,
|
147 |
+
"step": 42
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.0015178217571316542,
|
151 |
+
"grad_norm": 0.23762422800064087,
|
152 |
+
"learning_rate": 3.355050358314172e-05,
|
153 |
+
"loss": 0.7663,
|
154 |
+
"step": 45
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.0015178217571316542,
|
158 |
+
"eval_loss": 0.8193370699882507,
|
159 |
+
"eval_runtime": 1657.7176,
|
160 |
+
"eval_samples_per_second": 30.122,
|
161 |
+
"eval_steps_per_second": 3.765,
|
162 |
+
"step": 45
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 1.3846449670324224e+16,
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|