End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9951219512195122,
+    "eval_loss": 1.5499577522277832,
+    "eval_runtime": 1.7323,
+    "eval_samples": 518,
+    "eval_samples_per_second": 112.567,
+    "eval_steps_per_second": 1.732,
     "total_flos": 4.281868708751606e+17,
     "train_loss": 1.6186961426454431,
     "train_runtime": 363.7432,

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": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32770
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9951219512195122,
+    "eval_loss": 1.5499577522277832,
+    "eval_runtime": 1.7323,
+    "eval_samples": 518,
+    "eval_samples_per_second": 112.567,
+    "eval_steps_per_second": 1.732
+}

runs/Nov18_17-51-21_bold-food-flourishes-fin-02/events.out.tfevents.1731953746.bold-food-flourishes-fin-02.106436.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772873b98aac50d110265537c99c08fa7b3db772755b8a02f708d362aeae3ece
+size 354