Training in progress, step 10, checkpoint
Browse files
checkpoint-10/adapter_config.json
CHANGED
|
@@ -19,10 +19,10 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"o_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
"q_proj",
|
| 25 |
-
"
|
|
|
|
|
|
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
| 22 |
"q_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
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 sha256:1057833a6daf9aa561fb79c75b9ef644409e0871d0e6cfcf6bda16b175f26cb5
|
| 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 sha256:0577636b9e53fe801445e3cd67f4b7aae505b70f33095b73510ab40416325a56
|
| 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 sha256:6c177ae573c8aefd8c6d036efb4c1944760938edff11b9912aa45908ce978fea
|
| 3 |
size 14512
|
checkpoint-10/rng_state_1.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 sha256:97b67d70cbfded068187f0306192c376aaef826d7928c1676c82fe5a27d52072
|
| 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": 1.346017837524414,
|
| 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": 1.346017837524414,
|
| 14 |
+
"eval_runtime": 213.4062,
|
| 15 |
+
"eval_samples_per_second": 13.434,
|
| 16 |
+
"eval_steps_per_second": 3.36,
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 10,
|
| 25 |
+
"total_flos": 5285836115410944.0,
|
| 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 sha256:6eca42dff5d8b2b54aa900cf0ee9eb3066e00be2ddfee954656686f3abb123ad
|
| 3 |
size 5112
|