Training in progress, step 1

tmp-checkpoint-64/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-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": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

tmp-checkpoint-64/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

tmp-checkpoint-64/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4a481e63661707c2a7c3c2f87e58269688719eb3d3419cce0f04da9fd2cc4f
+size 4943162336

tokenizer.json

@@ -1,7 +1,7 @@
 {
   "version": "1.0",
   "truncation": {
-    "direction": "Right",
+    "direction": "Left",
     "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9337c3cd56d39bfaf8a50d3f58ddb73daf29b8e5e9b11dcee3dd7a7511f74576
+oid sha256:c85b0e83429c10989d7e00bf1a6c141ab1cab54db8c95a698ae383a946ddf73e
 size 4984