Training in progress, step 6000

.gitignore

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

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "PerceiverForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "audio_samples_per_frame": 1920,
+  "cross_attention_shape_for_attention": "kv",
+  "cross_attention_widening_factor": 1,
+  "d_latents": 1280,
+  "d_model": 768,
+  "hidden_act": "gelu",
+  "image_size": 56,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "perceiver",
+  "num_blocks": 1,
+  "num_cross_attention_heads": 8,
+  "num_frames": 16,
+  "num_hidden_layers": 6,
+  "num_latents": 256,
+  "num_self_attends_per_block": 26,
+  "num_self_attention_heads": 8,
+  "output_shape": [
+    1,
+    16,
+    224,
+    224
+  ],
+  "qk_channels": null,
+  "samples_per_patch": 16,
+  "self_attention_widening_factor": 1,
+  "torch_dtype": "float32",
+  "train_size": [
+    368,
+    496
+  ],
+  "transformers_version": "4.19.4",
+  "use_query_residual": true,
+  "v_channels": null,
+  "vocab_size": 262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5f2f66a63e0e2314c6f2080678027eac8ab0d406afa74ce9a644ac12f8b59d
+size 1077435567

runs/Jun12_18-31-53_b3e5817f7f49/1655058749.6576886/events.out.tfevents.1655058749.b3e5817f7f49.229.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c3b34c05500b53fb889f584d348de6069d6b0bdbdeb34371f6ff3c2943b4a4
+size 5167

runs/Jun12_18-31-53_b3e5817f7f49/events.out.tfevents.1655058749.b3e5817f7f49.229.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6f207f82389354e0646883659e37985d747796e9922ed31622de615fa91ae3
+size 4156

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1e5c7584b3706dc13d4f6f0d7974bdfeed18a4bda7c2d941a1c159d64593c1
+size 3247