Training in progress, step 500

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "trl-lib/pythia-1b-deduped-tldr-sft",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "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:c4fb7dd74f76ecec18706231eb8b3b34db9779e1412c809e17aa19cddca73256
+size 4047149576

runs/Sep12_15-04-12_ip-26-0-163-147/events.out.tfevents.1726153505.ip-26-0-163-147.1615410.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bb015bd792af318aceccc4ed38463399bbc3fb250a4ed0e55c769c3c48a12c
-size 57196
+oid sha256:d9872efc0e630450a7c126e987eff50f70e770bf5ef65ef0c6997e52d3b40e6b
+size 62301

runs/Sep12_15-05-41_ip-26-0-171-249/events.out.tfevents.1726153587.ip-26-0-171-249.165790.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0e83bf9073b1e23c33b9b84e9ec98f3315adfd077531448be68885fc2a1204
-size 52091
+oid sha256:6f72329327c34de3e4c64ca4044222075a1ddd96ee538f523036e5ca3f3f3a1d
+size 57196

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d44c9780ea0d7ae8ef36d0aba48aa291d400685d85fd896a81b2c4c1c3f7861
+oid sha256:7226337352746496a66bde9b34b64748a2e86d32c156bfd67306408d26739145
 size 5496