Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "replit/replit-code-v1-3b",
+  "architectures": [
+    "MPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "replit/replit-code-v1-3b--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "replit/replit-code-v1-3b--modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 2560,
+  "emb_pdrop": 0,
+  "embedding_fraction": 1.0,
+  "eos_token_id": 1,
+  "expansion_ratio": 4,
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0,
+    "init_nonlinearity": "relu",
+    "init_std": 0.02,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "model_type": "mpt",
+  "n_heads": 32,
+  "n_layers": 32,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0,
+  "tokenizer_name": "replit/replit-code-v1-3b",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "verbose": 0,
+  "vocab_size": 32768
+}

runs/Jul08_18-50-47_nfggvg78sf/events.out.tfevents.1688842256.nfggvg78sf.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764527e143f9690cc4ca6aaedae39cc40c3572c95e054674dba572c09d06d7d8
+size 8593

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f8051e4314f9688e044d336f8164ffb177f96552e4b8dba62752cf575d3b25
+size 3951