pminervini commited on
Commit
a565180
·
verified ·
1 Parent(s): a5a1f85

Training in progress, step 8

Browse files
adapter_config.json CHANGED
@@ -15,17 +15,17 @@
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
- "r": 8,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
 
23
  "o_proj",
 
24
  "k_proj",
25
  "v_proj",
26
- "up_proj",
27
- "gate_proj",
28
- "down_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
 
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
+ "r": 32,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "down_proj",
23
+ "gate_proj",
24
  "o_proj",
25
+ "up_proj",
26
  "k_proj",
27
  "v_proj",
28
+ "q_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8999f058226d361ada283f3e986c2872e9f9674cfea65279ee031054703ce940
3
- size 42002584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553c30c183cde40f9dc125ac65099f9949ee8c99143b6267860860b9080235cb
3
+ size 167832688
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.38,
3
- "train_loss": 0.5409165602177382,
4
- "train_runtime": 341.6545,
5
- "train_samples_per_second": 2.997,
6
- "train_steps_per_second": 0.375
7
  }
 
1
  {
2
+ "epoch": 24.04,
3
+ "train_loss": 0.24291648308280855,
4
+ "train_runtime": 18372.1559,
5
+ "train_samples_per_second": 3.567,
6
+ "train_steps_per_second": 0.223
7
  }
best_metrics.json CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 0.39877966046333313}
 
1
+ {"eval_loss": 0.3460787236690521}
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.38,
3
- "train_loss": 0.5409165602177382,
4
- "train_runtime": 341.6545,
5
- "train_samples_per_second": 2.997,
6
- "train_steps_per_second": 0.375
7
  }
 
1
  {
2
+ "epoch": 24.04,
3
+ "train_loss": 0.24291648308280855,
4
+ "train_runtime": 18372.1559,
5
+ "train_samples_per_second": 3.567,
6
+ "train_steps_per_second": 0.223
7
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c485d6200f718439cc6b80827291400c877c6d24b89a32f39136f8b555aac86c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ca0d6be3f70c59aac907f159da38482d01d742f7ac083384b35f094a87276e
3
  size 4920