Training in progress, step 1300

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": 512,
+  "max_position_embeddings": 1024,
+  "model_type": "mistral",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "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:eeb256257e095023202df2821297a8d339ad1834d968399938dd0c2e0d61ddb0
+size 66690264

runs/Jun12_13-45-34_SandersLaptop2.home/events.out.tfevents.1749728735.SandersLaptop2.home

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1673281af540f5e86b089865ad560c73783f91b65bc27c3956b69e4b084e525
+size 5406

runs/Jun12_13-49-00_SandersLaptop2.home/events.out.tfevents.1749728941.SandersLaptop2.home

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5652c54dd4fe62b6f1f7023407cafe75c2597df7bc4e13a07ff3b4fabb95a6
+size 21724

runs/Jun12_14-55-19_SandersLaptop2.home/events.out.tfevents.1749732921.SandersLaptop2.home

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7fd0040f6d06d91d2783bffcbd557dc4cf18d907ae0e61e1f4d3bd2f4f06c0
+size 5857

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e652f371cbe27456b95b1d9e9643f9465e54ffa6734a66c5db4740dea53b2296
+size 5368