Training in progress, step 25, checkpoint
Browse files
checkpoint-25/adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
checkpoint-25/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 26235864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebe4050447deec581bd3ff93dfbe198cc18566d7b2d38d43238acf2738c2abdd
|
3 |
size 26235864
|
checkpoint-25/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 52523386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4cb47b2b9565fe2265c4b343bef6711b4cb97a25458bf2ab7f0af03098f83fb
|
3 |
size 52523386
|
checkpoint-25/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:abd83e428a64cc7191cf368e64a77290525a3cadd3b210219a78a857e2fdb8ae
|
3 |
size 14244
|
checkpoint-25/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 sha256:30b5ec54b43ed8952919b704047aa882c4dd3048daa7c693f2bdcae16f7aa402
|
3 |
size 1064
|
checkpoint-25/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
"best_model_checkpoint": "./Qwen1-5-4B-Chat-hindi-sft/checkpoint-25",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
@@ -10,26 +10,26 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 6.
|
16 |
"step": 25
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.0,
|
20 |
-
"eval_loss":
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 1.
|
23 |
-
"eval_steps_per_second": 1.
|
24 |
"step": 25
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 25,
|
28 |
-
"max_steps":
|
29 |
"num_input_tokens_seen": 0,
|
30 |
-
"num_train_epochs":
|
31 |
"save_steps": 25,
|
32 |
-
"total_flos":
|
33 |
"train_batch_size": 1,
|
34 |
"trial_name": null,
|
35 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 5.88370418548584,
|
3 |
"best_model_checkpoint": "./Qwen1-5-4B-Chat-hindi-sft/checkpoint-25",
|
4 |
+
"epoch": 0.003574747980267391,
|
5 |
"eval_steps": 25,
|
6 |
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"grad_norm": 5.597507476806641,
|
14 |
+
"learning_rate": 7.936507936507936e-06,
|
15 |
+
"loss": 6.5107,
|
16 |
"step": 25
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.0,
|
20 |
+
"eval_loss": 5.88370418548584,
|
21 |
+
"eval_runtime": 27.753,
|
22 |
+
"eval_samples_per_second": 1.045,
|
23 |
+
"eval_steps_per_second": 1.045,
|
24 |
"step": 25
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 25,
|
28 |
+
"max_steps": 20979,
|
29 |
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 3,
|
31 |
"save_steps": 25,
|
32 |
+
"total_flos": 500129031075840.0,
|
33 |
"train_batch_size": 1,
|
34 |
"trial_name": null,
|
35 |
"trial_params": null
|
checkpoint-25/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9388d54f20b310f46b4eefba4bae25cec3658ca4bd837cd5c0be8d9c2b1f2f7
|
3 |
size 5048
|