Training in progress, step 120

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293349c713afcdea02bc6a8a279412e13531ae4babc655ca92aff7c0575f31d9
+size 1621370224

runs/Feb11_17-51-04_392802f82d37/events.out.tfevents.1707674144.392802f82d37.302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50431b3471f7fa8bc7979b9be0532e7d99e21f3a703097ca8b0c85a49d2eac7b
+size 23072

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdd642d3f831637d3c8356e5a6872a0c378cf472ab106232aabce2c6c7674be
+size 4600