fay-ong commited on
Commit
9113eda
1 Parent(s): ce7f69c

Training in progress, step 62

Browse files
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "q_proj",
25
  "gate_proj",
26
- "k_proj",
27
- "down_proj",
28
  "o_proj",
29
- "v_proj"
 
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "gate_proj",
 
 
24
  "o_proj",
25
+ "down_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d1197ee041c6595499a01997abfe3bda9bb3619938fddb9647e9ccb55179f87
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0697573b4ab9eff5d6e8336a5c45bef2da6ab5b8ba8f003d4850abe6f27522c
3
  size 83945296
runs/Aug02_19-40-25_jupyter-sze-2eong-2e23-40ucl-2eac-2euk/events.out.tfevents.1722624070.jupyter-sze-2eong-2e23-40ucl-2eac-2euk.2011.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a47c1c648da29ca2a0f2baa3db2f0ce0f52bb1b28ebb15a6089899818a3615
3
+ size 7218
trainer_log.jsonl CHANGED
@@ -1,7 +1,7 @@
1
- {"current_steps": 10, "total_steps": 62, "loss": 0.2622, "learning_rate": 1.9853538358476933e-05, "epoch": 0.16, "percentage": 16.13, "elapsed_time": "0:02:35", "remaining_time": "0:13:31", "throughput": "0.00", "total_tokens": 0}
2
- {"current_steps": 20, "total_steps": 62, "loss": 0.2174, "learning_rate": 1.736741137876405e-05, "epoch": 0.32, "percentage": 32.26, "elapsed_time": "0:05:09", "remaining_time": "0:10:50", "throughput": "0.00", "total_tokens": 0}
3
- {"current_steps": 30, "total_steps": 62, "loss": 0.1544, "learning_rate": 1.2542183341934873e-05, "epoch": 0.48, "percentage": 48.39, "elapsed_time": "0:07:45", "remaining_time": "0:08:16", "throughput": "0.00", "total_tokens": 0}
4
- {"current_steps": 40, "total_steps": 62, "loss": 0.0843, "learning_rate": 6.909830056250527e-06, "epoch": 0.64, "percentage": 64.52, "elapsed_time": "0:10:19", "remaining_time": "0:05:40", "throughput": "0.00", "total_tokens": 0}
5
- {"current_steps": 50, "total_steps": 62, "loss": 0.1001, "learning_rate": 2.2585838936091753e-06, "epoch": 0.8, "percentage": 80.65, "elapsed_time": "0:12:51", "remaining_time": "0:03:05", "throughput": "0.00", "total_tokens": 0}
6
- {"current_steps": 60, "total_steps": 62, "loss": 0.126, "learning_rate": 6.51826465144978e-08, "epoch": 0.96, "percentage": 96.77, "elapsed_time": "0:15:25", "remaining_time": "0:00:30", "throughput": "0.00", "total_tokens": 0}
7
- {"current_steps": 62, "total_steps": 62, "epoch": 0.992, "percentage": 100.0, "elapsed_time": "0:15:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
 
1
+ {"current_steps": 10, "total_steps": 62, "loss": 0.2839, "learning_rate": 1.9853538358476933e-05, "epoch": 0.16, "percentage": 16.13, "elapsed_time": "0:02:51", "remaining_time": "0:14:50", "throughput": "0.00", "total_tokens": 0}
2
+ {"current_steps": 20, "total_steps": 62, "loss": 0.2157, "learning_rate": 1.736741137876405e-05, "epoch": 0.32, "percentage": 32.26, "elapsed_time": "0:05:41", "remaining_time": "0:11:56", "throughput": "0.00", "total_tokens": 0}
3
+ {"current_steps": 30, "total_steps": 62, "loss": 0.1568, "learning_rate": 1.2542183341934873e-05, "epoch": 0.48, "percentage": 48.39, "elapsed_time": "0:08:31", "remaining_time": "0:09:06", "throughput": "0.00", "total_tokens": 0}
4
+ {"current_steps": 40, "total_steps": 62, "loss": 0.0839, "learning_rate": 6.909830056250527e-06, "epoch": 0.64, "percentage": 64.52, "elapsed_time": "0:11:21", "remaining_time": "0:06:14", "throughput": "0.00", "total_tokens": 0}
5
+ {"current_steps": 50, "total_steps": 62, "loss": 0.1057, "learning_rate": 2.2585838936091753e-06, "epoch": 0.8, "percentage": 80.65, "elapsed_time": "0:14:09", "remaining_time": "0:03:23", "throughput": "0.00", "total_tokens": 0}
6
+ {"current_steps": 60, "total_steps": 62, "loss": 0.1226, "learning_rate": 6.51826465144978e-08, "epoch": 0.96, "percentage": 96.77, "elapsed_time": "0:16:59", "remaining_time": "0:00:33", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 62, "total_steps": 62, "epoch": 0.992, "percentage": 100.0, "elapsed_time": "0:17:35", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65546b1b5d58312c3d0a58192010fcf425c29d27a15ffd2d45e2d9d5e105b0c0
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262df9e9ddeb3572ff35bb2826dee22b133aac3e488a66b9ce8533bf185f924b
3
  size 5368