Training in progress, step 1000

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "wanderer2k1/base_LLM_183MB_chunk_and_concat_w_domain",
+  "abili": false,
+  "architectures": [
+    "MptForCausalLM"
+  ],
+  "attn_config": {
+    "model_type": ""
+  },
+  "d_model": 768,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "init_device": "cpu",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 8192,
+  "model_type": "mpt",
+  "n_heads": 12,
+  "n_layers": 12,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "pad_token_id": 128001,
+  "resid_pdrop": 0.0,
+  "rope": true,
+  "rope_theta": 100000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 128256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3addbae8c447aae8a326e7c9718ed031891c072fccf0ab57312890887a888d60
+size 733826032

runs/Oct21_02-54-02_kao-dgxa-e10-u17/events.out.tfevents.1729475670.kao-dgxa-e10-u17.1024105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50873577ca3420cd1c1282d86dfd155b022421a912952411028eed42f311fb8
+size 16496

runs/Oct21_03-20-10_kao-dgxa-e10-u17/events.out.tfevents.1729477225.kao-dgxa-e10-u17.1240955.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3e7ce5720f201d4c8241124b42a35d31451cceea288927838f7412cbddbf70
+size 7001

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd834fb0e2b388a074d4968da29950aaeea2bbb0df3e3955ccc4bcc7cfbb7597
+size 5112