Training in progress, epoch 1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/CodeQwen1.5-7B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 13440,
+  "max_position_embeddings": 65536,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000,
+  "rotary_emb_base": 1000000,
+  "seq_length": 65536,
+  "sliding_window": 65536,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 92302
+}

runs/Aug15_17-48-42_fzai-gpu-a1-3xlarge/events.out.tfevents.1723744127.fzai-gpu-a1-3xlarge.2303016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a395a877e768d50e6dce995f9fc2d75e7908d01ca179ed653741304a52066d28
+size 4872

runs/Aug15_19-46-43_fzai-gpu-a1-3xlarge/events.out.tfevents.1723751220.fzai-gpu-a1-3xlarge.2326905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb688345e6fd1e81645db2e98c1a0871f7bfc78b7b0aef821f9305a164864e52
+size 4484

runs/Aug15_19-48-22_fzai-gpu-a1-3xlarge/events.out.tfevents.1723751303.fzai-gpu-a1-3xlarge.2327303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3b2199d00def9337f92f821e4640c5d544aeb9931a3b0a9be4b73a7989e3fe
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06cb8dbdb68c2ddcd723200adcfb871b4e39aed0955b7d8c492852328161ef4b
+oid sha256:63522410262d20511b2043e968e3c79da07be35f0edaad6d80b57ac60b0a60b7
 size 4728