Training in progress, step 10, checkpoint
Browse files
checkpoint-10/adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"q_proj",
|
| 23 |
-
"o_proj",
|
| 24 |
"k_proj",
|
|
|
|
| 25 |
"v_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"q_proj",
|
|
|
|
| 23 |
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
"v_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
checkpoint-10/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27297032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad7edadd0173530939f388f4b5aeca9bb6ff6d497bbf0605833181cd4db3832d
|
| 3 |
size 27297032
|
checkpoint-10/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 54678010
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78174670b788b2cafec59ee3c5966333c6b8f8c2a4aad0a13fcbd4829fed7796
|
| 3 |
size 54678010
|
checkpoint-10/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42d83b94c8ac5fc9478b91d2426ff1842349919562d432c6c2618e3dc7fdc544
|
| 3 |
size 14512
|
checkpoint-10/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.006199628022318661,
|
| 5 |
"eval_steps": 10,
|
|
@@ -10,10 +10,10 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
-
"eval_loss": 1.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second": 13.
|
| 16 |
-
"eval_steps_per_second": 3.
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 10,
|
| 25 |
-
"total_flos":
|
| 26 |
"train_batch_size": 8,
|
| 27 |
"trial_name": null,
|
| 28 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.353695273399353,
|
| 3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.006199628022318661,
|
| 5 |
"eval_steps": 10,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
+
"eval_loss": 1.353695273399353,
|
| 14 |
+
"eval_runtime": 211.2183,
|
| 15 |
+
"eval_samples_per_second": 13.574,
|
| 16 |
+
"eval_steps_per_second": 3.395,
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 10,
|
| 25 |
+
"total_flos": 4887826864799744.0,
|
| 26 |
"train_batch_size": 8,
|
| 27 |
"trial_name": null,
|
| 28 |
"trial_params": null
|
checkpoint-10/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8e1a7d78795fa69fe8e3bb1a18304b885d78d38897e6462ed8a482e70228ab3
|
| 3 |
size 5112
|