Training in progress, step 3401
Browse files- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- trainer_log.jsonl +2 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
-
"target_modules": "^(?!.*patch_embed).*(?:
|
23 |
"task_type": "CAUSAL_LM",
|
24 |
"use_dora": false,
|
25 |
"use_rslora": false
|
|
|
19 |
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
+
"target_modules": "^(?!.*patch_embed).*(?:proj|v_proj|fc1|gate_proj|down_proj|o_proj|fc2|k_proj|q_proj|up_proj|qkv).*",
|
23 |
"task_type": "CAUSAL_LM",
|
24 |
"use_dora": false,
|
25 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29034840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302b9ce048dad99dc59725f9bc543136929b03fd0548bef61608ff98a26b885e
|
3 |
size 29034840
|
trainer_log.jsonl
CHANGED
@@ -753,3 +753,5 @@
|
|
753 |
{"current_steps": 3395, "total_steps": 6770, "loss": 0.1766, "lr": 5.389190766672056e-05, "epoch": 1.0029542097488922, "percentage": 50.15, "elapsed_time": "8:41:34", "remaining_time": "8:38:30", "throughput": 1126.54, "total_tokens": 35254992}
|
754 |
{"current_steps": 3400, "total_steps": 6770, "loss": 0.2173, "lr": 5.3770139799461824e-05, "epoch": 1.0044313146233383, "percentage": 50.22, "elapsed_time": "8:43:01", "remaining_time": "8:38:24", "throughput": 1125.07, "total_tokens": 35305984}
|
755 |
{"current_steps": 3400, "total_steps": 6770, "eval_loss": 0.40779221057891846, "epoch": 1.0044313146233383, "percentage": 50.22, "elapsed_time": "8:43:20", "remaining_time": "8:38:43", "throughput": 1124.38, "total_tokens": 35305984}
|
|
|
|
|
|
753 |
{"current_steps": 3395, "total_steps": 6770, "loss": 0.1766, "lr": 5.389190766672056e-05, "epoch": 1.0029542097488922, "percentage": 50.15, "elapsed_time": "8:41:34", "remaining_time": "8:38:30", "throughput": 1126.54, "total_tokens": 35254992}
|
754 |
{"current_steps": 3400, "total_steps": 6770, "loss": 0.2173, "lr": 5.3770139799461824e-05, "epoch": 1.0044313146233383, "percentage": 50.22, "elapsed_time": "8:43:01", "remaining_time": "8:38:24", "throughput": 1125.07, "total_tokens": 35305984}
|
755 |
{"current_steps": 3400, "total_steps": 6770, "eval_loss": 0.40779221057891846, "epoch": 1.0044313146233383, "percentage": 50.22, "elapsed_time": "8:43:20", "remaining_time": "8:38:43", "throughput": 1124.38, "total_tokens": 35305984}
|
756 |
+
{"current_steps": 3405, "total_steps": 6770, "loss": 0.2062, "lr": 5.364834943958688e-05, "epoch": 1.0059084194977843, "percentage": 50.3, "elapsed_time": "8:44:51", "remaining_time": "8:38:41", "throughput": 1122.78, "total_tokens": 35357880}
|
757 |
+
{"current_steps": 3401, "total_steps": 3400, "epoch": 1.0047267355982274, "percentage": 100.03, "elapsed_time": "0:01:43", "remaining_time": "0:00:00", "throughput": 341090.05, "total_tokens": 35316128}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85339a802dfd06cbba7d2568099cd0116c5715fbc57a8d66871ebfbd39c462c6
|
3 |
size 7480
|