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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56491872a208ff227c56d67f1f1a29494d38977d18be9961d8f4c32526a2e6e4
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6ba671e3027fba1c79fbf358ab0330c13044f9e72662f64a471aba358854afa
|
3 |
size 640009682
|
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 sha256:5fc9dbb623e3f171e33d9832b06d94b67f7dfbbcfe98e23137b132240f34a4be
|
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 sha256:7cec5e5f4f3cb8de86741361ea071d377a7169e2898cbb10708e17cdfc15a7dc
|
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": 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": 9.396,
|
147 |
"eval_steps_per_second": 4.698,
|
148 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
149 |
}
|
150 |
],
|
151 |
"logging_steps": 3,
|
@@ -165,7 +194,7 @@
|
|
165 |
"attributes": {}
|
166 |
}
|
167 |
},
|
168 |
-
"total_flos": 2.
|
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": 0.029955534753100865,
|
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": 9.396,
|
147 |
"eval_steps_per_second": 4.698,
|
148 |
"step": 40
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.026211092908963257,
|
152 |
+
"grad_norm": 0.6331055164337158,
|
153 |
+
"learning_rate": 0.00015508969814521025,
|
154 |
+
"loss": 0.8609,
|
155 |
+
"step": 42
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.02808331383103206,
|
159 |
+
"grad_norm": 0.3308071494102478,
|
160 |
+
"learning_rate": 0.00014338837391175582,
|
161 |
+
"loss": 0.7784,
|
162 |
+
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.029955534753100865,
|
166 |
+
"grad_norm": 0.3475176692008972,
|
167 |
+
"learning_rate": 0.00013090169943749476,
|
168 |
+
"loss": 0.7766,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.029955534753100865,
|
173 |
+
"eval_loss": 0.7678617835044861,
|
174 |
+
"eval_runtime": 574.3416,
|
175 |
+
"eval_samples_per_second": 9.399,
|
176 |
+
"eval_steps_per_second": 4.699,
|
177 |
+
"step": 48
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 3,
|
|
|
194 |
"attributes": {}
|
195 |
}
|
196 |
},
|
197 |
+
"total_flos": 2.5536922059276288e+17,
|
198 |
"train_batch_size": 2,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|