Training in progress, step 2000, 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 sha256:57b71b56bba626570fa22bc8e40aaecf44fce6608c0985d8a429673a2ede92e4
|
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 sha256:2825c4794a5f3d65e1245e0405d5c92fa9f490fcab4bbca2c80b77d935b7be51
|
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 sha256:7fc35b2465ed628ff7d1c151c6992ba75067041a43ade6dd7aea2af9126e5679
|
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 sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
|
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,
|
@@ -273,6 +273,20 @@
|
|
273 |
"eval_samples_per_second": 5.453,
|
274 |
"eval_steps_per_second": 0.684,
|
275 |
"step": 1900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 100,
|
@@ -280,7 +294,7 @@
|
|
280 |
"num_input_tokens_seen": 0,
|
281 |
"num_train_epochs": 3,
|
282 |
"save_steps": 100,
|
283 |
-
"total_flos": 5.
|
284 |
"trial_name": null,
|
285 |
"trial_params": null
|
286 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9692724347114563,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2000",
|
4 |
+
"epoch": 2.6666666666666665,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
273 |
"eval_samples_per_second": 5.453,
|
274 |
"eval_steps_per_second": 0.684,
|
275 |
"step": 1900
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.67,
|
279 |
+
"learning_rate": 0.0002,
|
280 |
+
"loss": 0.8272,
|
281 |
+
"step": 2000
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 2.67,
|
285 |
+
"eval_loss": 0.9692724347114563,
|
286 |
+
"eval_runtime": 354.2357,
|
287 |
+
"eval_samples_per_second": 5.448,
|
288 |
+
"eval_steps_per_second": 0.683,
|
289 |
+
"step": 2000
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 100,
|
|
|
294 |
"num_input_tokens_seen": 0,
|
295 |
"num_train_epochs": 3,
|
296 |
"save_steps": 100,
|
297 |
+
"total_flos": 5.652603258859438e+17,
|
298 |
"trial_name": null,
|
299 |
"trial_params": null
|
300 |
}
|