Training in progress, step 500

config.json

@@ -26,7 +26,7 @@
   "position_biased_input": false,
   "relative_attention": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.19.0.dev0",
+  "transformers_version": "4.18.0",
   "type_vocab_size": 0,
   "vocab_size": 50265
 }

ipu_config.json

@@ -4,6 +4,7 @@
   "enable_half_first_order_momentum": true,
   "enable_half_partials": true,
   "executable_cache_dir": "./exe_cache",
+  "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 32,
   "inference_device_iterations": 4,
   "inference_replication_factor": 4,
@@ -21,13 +22,14 @@
     0.1
   ],
   "optimizer_state_offchip": true,
-  "optimum_version": "1.0.0",
+  "optimum_version": "1.1.1",
   "output_mode": "final",
   "profile_dir": "",
   "recompute_checkpoint_every_layer": true,
   "replicated_tensor_sharding": true,
   "replication_factor": 4,
   "seed": 1984,
-  "transformers_version": "4.19.0.dev0",
+  "sharded_execution_for_inference": false,
+  "transformers_version": "4.18.0",
   "use_popdist": false
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c53de7a6f355194542f010b25d2591fb9ca83acda557a8734b3b17ed060f8d9
+oid sha256:0e1f09f6119a29f383a3d1ea74bf0c26235173cda966dd57182282e10454a2b6
 size 277274547

runs/May23_13-05-50_gbnwp-pod015-2.ipu.graphcore.ai/1653308353.434315/events.out.tfevents.1653308353.gbnwp-pod015-2.ipu.graphcore.ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95929573ae79478ad324196f12e15d087032bd0cc2365bcca195d1249961d885
+size 3919

runs/May23_13-05-50_gbnwp-pod015-2.ipu.graphcore.ai/events.out.tfevents.1653308353.gbnwp-pod015-2.ipu.graphcore.ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dae6908f3231386220522caf514e158d17f209d360490f753490571ecb536f
+size 10664

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 384,
+    "strategy": "OnlySecond",
+    "stride": 128
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 384
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -53,7 +67,8 @@
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": false,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -133,7 +148,8 @@
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "model": {
     "type": "BPE",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182fd1bfb055d8a087a848be1e08eb491fd553ac431da5330a9b5e2216525bbf
-size 2671
+oid sha256:4ecb4a491a038022196f4b2927d2d70e5ef54d75e818e8c1e37227d522c2a430
+size 2735