Training in progress, step 1100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703662f67d3e9c690769d54fb804e87a29ff8bf79e3e8252b54853998eb7c3eb
+oid sha256:f6adc9954515c2a6c8270a1f55a43bdcd35c3c879a458287434024777b2c6983
 size 265493026

tokenizer.json

@@ -3,13 +3,11 @@
   "truncation": {
     "direction": "Right",
     "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
+    "strategy": "OnlySecond",
+    "stride": 128
   },
   "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

trainer_state.json

@@ -153,16 +153,16 @@
       "step": 1020,
       "total_flos": 5.148633647651021e+16,
       "train_loss": 0.028946983113008386,
-      "train_runtime": 26.811,
-      "train_samples_per_second": 19470.051,
-      "train_steps_per_second": 38.044
+      "train_runtime": 26.7355,
+      "train_samples_per_second": 19525.044,
+      "train_steps_per_second": 38.152
     },
     {
       "epoch": 4.0,
       "eval_loss": 1.3930128812789917,
-      "eval_runtime": 8.3512,
-      "eval_samples_per_second": 1433.204,
-      "eval_steps_per_second": 11.256,
+      "eval_runtime": 8.3016,
+      "eval_samples_per_second": 1441.77,
+      "eval_steps_per_second": 11.323,
       "step": 1020
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d8a461b292d1c7d936212be6c7619b9698a1a89d0479a510f55cfd2a15f38a
+oid sha256:3345a9daf4130375c7a09b812dbb5af19f7b2a07a23d3827bb495e8766983668
 size 4664