Training in progress, step 200

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

runs/May06_17-48-20_kao-dgxa-e10-u17/events.out.tfevents.1715014120.kao-dgxa-e10-u17.1476366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908e592c2411f15f298ea46912d482d14231a3d89db709913d789f25875e89cd
+size 46706

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102b26f48bf89fba34045df86b77f1e0c9f2efdd9e684aff8cd5dd8ec2ec94e7
+size 5112