BobaZooba commited on
Commit
064eb15
1 Parent(s): b0dab01

Training in progress, step 25

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "bn22/Mistral-7B-v0.1-sharded",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -16,13 +16,13 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "o_proj",
20
  "q_proj",
21
- "down_proj",
22
- "v_proj",
23
- "gate_proj",
24
  "k_proj",
25
- "up_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "v_proj",
20
+ "up_proj",
21
  "o_proj",
22
  "q_proj",
 
 
 
23
  "k_proj",
24
+ "down_proj",
25
+ "gate_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53ce65206cf6ca0cf316938d51c6c033e151e1e6ac908945246c9b956f4a10d9
3
- size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e72f051c9990ed66920d67ffad6a5dc9574b7d6c2caf2ebb83db07d22983eb
3
+ size 42002136
runs/Dec01_12-06-48_18e317ed094a/events.out.tfevents.1701432678.18e317ed094a.7554.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4df8976cd60ce330cd84860032860d838cb68d93361cb549e50b983227d2f70
3
+ size 9696
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59ea6bf03014c5571a57a6c0be1bd7d4982e07b90a7aa5f37b84f0659c1586a3
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aca71db67798b119d2c3693b55cd6a103898a7e935aaf7759e9079b3f6bc999
3
+ size 6264
training_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "force_fp16": false,
10
  "from_gptq": false,
11
  "huggingface_hub_token": null,
12
- "deepspeed_stage": 0,
13
  "deepspeed_config_path": null,
14
  "fsdp_strategy": "",
15
  "fsdp_offload": true,
@@ -38,7 +38,7 @@
38
  "tokenizer_padding_side": null,
39
  "collator_key": "lm",
40
  "max_length": 2048,
41
- "model_name_or_path": "bn22/Mistral-7B-v0.1-sharded",
42
  "push_to_hub_bos_add_bos_token": false,
43
  "use_flash_attention_2": false,
44
  "trust_remote_code": false,
 
9
  "force_fp16": false,
10
  "from_gptq": false,
11
  "huggingface_hub_token": null,
12
+ "deepspeed_stage": 2,
13
  "deepspeed_config_path": null,
14
  "fsdp_strategy": "",
15
  "fsdp_offload": true,
 
38
  "tokenizer_padding_side": null,
39
  "collator_key": "lm",
40
  "max_length": 2048,
41
+ "model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
42
  "push_to_hub_bos_add_bos_token": false,
43
  "use_flash_attention_2": false,
44
  "trust_remote_code": false,