Training in progress, step 100

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a577466e410fd96608bbc26e6213b4817374239b4e2273fd1009a3397476ad6
+size 86625328

runs/Jun13_19-29-27_SandersLaptop2.home/events.out.tfevents.1749835768.SandersLaptop2.home

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099041b6dfdfb30c8a211edb829280e07088abefc6ec24c98cab6ccf818c0845
+size 5838

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19541da69462e28477ec37349103478c4f8dc3b1f73eaa4f8fd09a8158386701
+size 5368