Training in progress, step 25

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "bn22/Mistral-7B-v0.1-sharded",
+  "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
-    "down_proj",
-    "v_proj",
-    "gate_proj",
     "k_proj",
-    "up_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ce65206cf6ca0cf316938d51c6c033e151e1e6ac908945246c9b956f4a10d9
-size 83945296
+oid sha256:87e72f051c9990ed66920d67ffad6a5dc9574b7d6c2caf2ebb83db07d22983eb
+size 42002136

runs/Dec01_12-06-48_18e317ed094a/events.out.tfevents.1701432678.18e317ed094a.7554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4df8976cd60ce330cd84860032860d838cb68d93361cb549e50b983227d2f70
+size 9696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ea6bf03014c5571a57a6c0be1bd7d4982e07b90a7aa5f37b84f0659c1586a3
-size 4600
+oid sha256:0aca71db67798b119d2c3693b55cd6a103898a7e935aaf7759e9079b3f6bc999
+size 6264

training_config.json

@@ -9,7 +9,7 @@
   "force_fp16": false,
   "from_gptq": false,
   "huggingface_hub_token": null,
-  "deepspeed_stage": 0,
+  "deepspeed_stage": 2,
   "deepspeed_config_path": null,
   "fsdp_strategy": "",
   "fsdp_offload": true,
@@ -38,7 +38,7 @@
   "tokenizer_padding_side": null,
   "collator_key": "lm",
   "max_length": 2048,
-  "model_name_or_path": "bn22/Mistral-7B-v0.1-sharded",
+  "model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
   "push_to_hub_bos_add_bos_token": false,
   "use_flash_attention_2": false,
   "trust_remote_code": false,