Uploaded checkpoint-10000

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": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72802e7af36b48616e1812774c93464f0ad5dabdc662906f263b5c261dba6539
+size 2836579040

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf3465e6206adeabd26a7a253a4a0b2159555f84892968b2feeb302b5e2a174
+size 5673376169

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26348f958ae84e477c62bcfba7e832719ebcc87762b0098c458a859299f0052
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5337b43c992f219c148594c73e62ebb4c3810a5f39a27c7e30b6db51c1fa25
+size 1064

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2117a16b6e89539754b8133134b501d16a2d37a505f4e6ac76d53b15dfd4123
+size 4856