Training in progress, step 118

config.json

@@ -1,31 +1,30 @@
 {
   "_name_or_path": "microsoft/phi-2",
+  "activation_function": "gelu_new",
   "architectures": [
     "PhiForCausalLM"
   ],
-  "attention_dropout": 0.0,
+  "attn_pdrop": 0.0,
   "auto_map": {
     "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
     "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
   },
-  "bos_token_id": null,
   "embd_pdrop": 0.0,
-  "eos_token_id": null,
-  "hidden_act": "gelu_new",
-  "hidden_size": 2560,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
+  "img_processor": null,
   "initializer_range": 0.02,
-  "intermediate_size": 10240,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "phi",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "partial_rotary_factor": 0.4,
-  "qk_layernorm": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
   "resid_pdrop": 0.1,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rotary_dim": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.37.0.dev0",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6945732dc97ffe13097af00878127f2e1892b6625039d9d6d97d420a6263fc97
+oid sha256:c67201b896b290970d7f4b444c7f49a41ad5190ca72e99ef204736c0d49d9279
 size 5240