Training in progress, step 200

config.json

@@ -0,0 +1,33 @@
+{
+  "abili": false,
+  "architectures": [
+    "MptForCausalLM"
+  ],
+  "attn_config": {
+    "model_type": ""
+  },
+  "d_model": 1024,
+  "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": 16,
+  "n_layers": 24,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "pad_token_id": 128009,
+  "resid_pdrop": 0.0,
+  "rope": true,
+  "rope_theta": 100000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 128256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abef13efbcea36bc3e7796c6d26fcb13e81cc78cbefcc493587307627fc32ce3
+size 1733513312

runs/Sep24_01-37-36_kao-dgxa-e10-u17/events.out.tfevents.1727141863.kao-dgxa-e10-u17.1357.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8222668fea6694558c0e393561daa4125650fd8adb109bf67f5804d5bd559e4
+size 46742

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bffc827746c3249776b8f9f8bc2f4fc50b064c52bd1fb80707e76c682a15e489
+size 5176