Training in progress, step 1900, 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 25191576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c87b5c832471c3238ea317872535c1ff33bd77a07cb2ada2f5973186fe84a0d
|
3 |
size 25191576
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50444805
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bcf079ab7dfd33196ed96a3da814d53564b805c0861f550898c4c88461933f8
|
3 |
size 50444805
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432b633e5dda27995d4289f9c9b4c7fc095ba96fbfd82e14d7f383c303196238
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -259,6 +259,20 @@
|
|
259 |
"eval_samples_per_second": 5.451,
|
260 |
"eval_steps_per_second": 0.684,
|
261 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 100,
|
@@ -266,7 +280,7 @@
|
|
266 |
"num_input_tokens_seen": 0,
|
267 |
"num_train_epochs": 3,
|
268 |
"save_steps": 100,
|
269 |
-
"total_flos": 5.
|
270 |
"trial_name": null,
|
271 |
"trial_params": null
|
272 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9726464748382568,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1900",
|
4 |
+
"epoch": 2.533333333333333,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
259 |
"eval_samples_per_second": 5.451,
|
260 |
"eval_steps_per_second": 0.684,
|
261 |
"step": 1800
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.53,
|
265 |
+
"learning_rate": 0.0002,
|
266 |
+
"loss": 0.8292,
|
267 |
+
"step": 1900
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.53,
|
271 |
+
"eval_loss": 0.9726464748382568,
|
272 |
+
"eval_runtime": 353.9329,
|
273 |
+
"eval_samples_per_second": 5.453,
|
274 |
+
"eval_steps_per_second": 0.684,
|
275 |
+
"step": 1900
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 100,
|
|
|
280 |
"num_input_tokens_seen": 0,
|
281 |
"num_train_epochs": 3,
|
282 |
"save_steps": 100,
|
283 |
+
"total_flos": 5.3702940947828736e+17,
|
284 |
"trial_name": null,
|
285 |
"trial_params": null
|
286 |
}
|