Training in progress, step 48, 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 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e279de9d08e2f68196982fcbcd99ce1c3e3248c392a1ed26db5572a0a0e6a86
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2eb34834f0c6aae0786503ea1068a9fc22566e275287fe2a1b90b386752b24b
|
3 |
size 212298
|
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 sha256:3ff8d5b65027d6fc74b0bb24f566be3eda3ca422b85222f3bb621c3651f0b68d
|
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 sha256:92b68be7d1926bbc86e8d15b055b4e03eade05923839fcf4d090c3ed2945b763
|
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": 1.
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -146,6 +146,35 @@
|
|
146 |
"eval_samples_per_second": 134.788,
|
147 |
"eval_steps_per_second": 68.089,
|
148 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
149 |
}
|
150 |
],
|
151 |
"logging_steps": 3,
|
@@ -165,7 +194,7 @@
|
|
165 |
"attributes": {}
|
166 |
}
|
167 |
},
|
168 |
-
"total_flos":
|
169 |
"train_batch_size": 2,
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6969365426695844,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 48,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
146 |
"eval_samples_per_second": 134.788,
|
147 |
"eval_steps_per_second": 68.089,
|
148 |
"step": 40
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.486870897155361,
|
152 |
+
"grad_norm": 0.1934972107410431,
|
153 |
+
"learning_rate": 0.00015000000000000001,
|
154 |
+
"loss": 10.3704,
|
155 |
+
"step": 42
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.5919037199124726,
|
159 |
+
"grad_norm": 0.19271045923233032,
|
160 |
+
"learning_rate": 0.00013716624556603274,
|
161 |
+
"loss": 10.3807,
|
162 |
+
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.6969365426695844,
|
166 |
+
"grad_norm": 0.14647410809993744,
|
167 |
+
"learning_rate": 0.00012357589355094275,
|
168 |
+
"loss": 10.2948,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.6969365426695844,
|
173 |
+
"eval_loss": 10.299408912658691,
|
174 |
+
"eval_runtime": 0.7215,
|
175 |
+
"eval_samples_per_second": 134.448,
|
176 |
+
"eval_steps_per_second": 67.917,
|
177 |
+
"step": 48
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 3,
|
|
|
194 |
"attributes": {}
|
195 |
}
|
196 |
},
|
197 |
+
"total_flos": 20595493699584.0,
|
198 |
"train_batch_size": 2,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|