Saving weights and log at step 400000

ckpt-400000/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "/home/yeb/data/gpt2-large-dutch-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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
+    }
+  },
+  "transformers_version": "4.13.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

ckpt-400000/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a559af74cf46f616b3804854c1d500cfc5193b199f0195892aa3ef4b4dbb0105
+size 3096134690

ckpt-400000/opt_state.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc98a35b272df8ebfa96388d92aba838d97edea00178a6eefe5a1442d1a0bc8f
+size 5611008

ckpt-400000/training_state.json

@@ -0,0 +1 @@
+{"step": 400001}

runs/events.out.tfevents.1641055391.t1v-n-f9cfcc28-w-0.112189.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a583ef507312253e62d4ea82ed51917a55ccf61c10a4e41ac592dd47cf94fcc5
-size 53752823
+oid sha256:117900743772bb4b91532ebca51190b534c4bcc1e8255614fb29f99b0274371a
+size 60168291