Training in progress, epoch 0

adapter_config.json

@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ae74624600ac4f8e404a42663f036a9ccaa373089dcd54579c5686cd86259c
+oid sha256:7689ddfff93bbceb4a0c2dff091f8df469b5e47451340e2e92098ecc18be0370
 size 18893616

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.41.2"
+}

runs/Jun11_02-58-40_37800b88aefd/events.out.tfevents.1718074720.37800b88aefd.16310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77082d69aa9025781cd9690a83e530604c4e42161ff0c0810c96336d084ed394
+size 7870

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e582c0aba1eef1b2c5034c44bb0a27561d3bf4d98716f1f179575976cfc8131
+oid sha256:d0de1eedf61cf6fc50ad143d7e40d134c280356143c306af1dd76584132ca32a
 size 5112