End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9964912280701754,
+    "eval_loss": 2.0167758464813232,
+    "eval_runtime": 0.6818,
+    "eval_samples": 25,
+    "eval_samples_per_second": 35.201,
+    "eval_steps_per_second": 1.467,
     "total_flos": 6.954534912540017e+17,
     "train_loss": 1.4842075613183034,
     "train_runtime": 638.3404,

config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 32768,
+  "eos_token_id": 32769,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 32769,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32770
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9964912280701754,
+    "eval_loss": 2.0167758464813232,
+    "eval_runtime": 0.6818,
+    "eval_samples": 25,
+    "eval_samples_per_second": 35.201,
+    "eval_steps_per_second": 1.467
+}

runs/Nov19_01-49-35_35e0caefddda/events.out.tfevents.1732001037.35e0caefddda.1229.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e93460938a83d80c16a9125462de3013d68ce9f57599545865f222fa5a4595
+size 359