pharaouk commited on
Commit
8e132a4
1 Parent(s): fb91834

Training in progress, step 800, checkpoint

Browse files
checkpoint-800/adapter_config.json CHANGED
@@ -15,12 +15,12 @@
15
  "revision": null,
16
  "target_modules": [
17
  "q_proj",
18
- "down_proj",
19
- "o_proj",
20
  "gate_proj",
21
  "up_proj",
22
- "k_proj",
23
- "v_proj"
 
 
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
15
  "revision": null,
16
  "target_modules": [
17
  "q_proj",
 
 
18
  "gate_proj",
19
  "up_proj",
20
+ "o_proj",
21
+ "v_proj",
22
+ "down_proj",
23
+ "k_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
checkpoint-800/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc2f7858a8ff96f60977fad5bd92e91abeb8173812981b82e87258907a51a5b2
3
  size 335706314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef66002c7178c57282bf27fedc208e1f7b78d32c24b17e4f32da11176268b22
3
  size 335706314
checkpoint-800/adapter_model/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.4.0
checkpoint-800/adapter_model/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "SkunkworksAI/Mistralic-7B-1",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "gate_proj",
19
+ "up_proj",
20
+ "o_proj",
21
+ "v_proj",
22
+ "down_proj",
23
+ "k_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-800/adapter_model/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef66002c7178c57282bf27fedc208e1f7b78d32c24b17e4f32da11176268b22
3
+ size 335706314
checkpoint-800/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d2a5495abf12e8b132e738630312831e3d550bffe1e196b0645d1ad9e51eefc
3
  size 1342453434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b32df6d9beee61f7567dd0428ac2c38d1db82a3492994f98d7e8ad6333952645
3
  size 1342453434
checkpoint-800/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8c4dc5b89a6d98c7bfb5ef8400604f47a610c2951a8ec6fb2ea50a20c2358b
3
  size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f83888bf8976b329472505e3ccacf1d8945c7c2cc14e552e9b24cbe1d72500d
3
  size 14180
checkpoint-800/trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-800/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0e0baa1bb2aa5937233bd631ead3549b3c1482ab16d538a9907b26a462c171
3
  size 6392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce34d49aa4450c07dcbbe4c7d4a2ac8bce147467e509d74b93474ba8ad8c7a4
3
  size 6392