Training in progress, step 195

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.1",
+  "use_cache": true,
+  "vocab_size": 54400
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4e18a30122e266b425379f40a526ff228932229f0017eaba3078f7cf1c9978
+size 510501504

runs/Jul01_10-48-56_e096bb2db2b6/events.out.tfevents.1719830938.e096bb2db2b6.5141.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68826acd871ded6399de6e7eea355ef6d8d6b8e5f8d463439ee7f600d827225
+size 40

runs/Jul01_10-51-27_e096bb2db2b6/events.out.tfevents.1719831088.e096bb2db2b6.5734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fdb3cd275f4bc1ac9f42b3991989ad061908de2c6049602a794fcaca7fb5e8
+size 5354

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31ade813a626763ead23c17dd859ae05bca7209363076852f72785338f4b5b0
+size 4655