Training in progress, epoch 1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629c0cf2146b73079aefeef2b867a033aef5a0777825eec24073af4a9b0a47bd
+size 1855983640

runs/Feb19_03-47-35_020d1a1e0686/events.out.tfevents.1708314456.020d1a1e0686.980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0df800fe54bb11883a1a0058d6464403ba7b668946c97d672be4084e6ae17d
+size 5847

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156ef38c462ff12e8551beb130fa94f60ec351a654b354c44c750fc1b4965b67
+size 4920