Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79621d85d469fbd0ccaadc92fe2506f0de3ab61822336d0fb940202c4aa66f46
+oid sha256:476713da9e936d5c58f76e0b38d5858dc3f725ab677f7e7bd7c590b9759da147
 size 268290900

run-0/checkpoint-500/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "vocab_size": 30522
 }

run-0/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec4efd86bcf6b06a64cea1361877859cf36ed7829ff9d816e1d409874c6dc3b
+oid sha256:476713da9e936d5c58f76e0b38d5858dc3f725ab677f7e7bd7c590b9759da147
 size 268290900

run-0/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b89469e1d668fd616103420fde7b486b059819d80b61e30304428825dfdf4a3
+oid sha256:5c682f8eb21695d7a7c995c96cdaab5aa7063607f2f92a9b9506b3db56a0aed8
 size 536643898

run-0/checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e084ad07c2d27cc577805a9c8f6017f86ea9b329ece8cacf3ca09b34ec4080
+oid sha256:b9fb2a0dfb1b0ccef3590fe01e9bd16b6db86f247cc9c7e77290c217a53bac20
 size 14244

run-0/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eac12b4c195da6cab1b505aba932a27ce723fdd77152ce67948ab5c49e2d3e1
+oid sha256:bb78b1e790f49c38375a9a03add3c9373ef72cf0138709ffb96775535ef084c6
 size 1064

run-0/checkpoint-500/tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

run-0/checkpoint-500/trainer_state.json

@@ -10,29 +10,31 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5754838709677419,
-      "eval_loss": 0.20387691259384155,
-      "eval_runtime": 1.5385,
-      "eval_samples_per_second": 2014.929,
-      "eval_steps_per_second": 42.249,
+      "eval_accuracy": 0.5735483870967742,
+      "eval_loss": 0.19929757714271545,
+      "eval_runtime": 1.4262,
+      "eval_samples_per_second": 2173.603,
+      "eval_steps_per_second": 45.576,
       "step": 318
     },
     {
       "epoch": 1.57,
-      "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3199,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3159,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3180,
-  "num_train_epochs": 10,
+  "max_steps": 1908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "total_flos": 130072209152340.0,
+  "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.07045036665217985,
-    "num_train_epochs": 10,
-    "temperature": 12
+    "alpha": 0.3767704932875351,
+    "num_train_epochs": 6,
+    "temperature": 15
   }
 }

run-0/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb85b846081dd97ad6e4da5112d241c8d9ca5b0ec1461a002fe8e508f5a0fab2
-size 4600
+oid sha256:7c7da1b515f43ac78928813d20ab8c56ddf199b3995c4b246a4307e26d4e7619
+size 4728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f1ea6435ca364fe64c4458d121e39307100c1520814f8e693138813dc74f1c
+oid sha256:7c7da1b515f43ac78928813d20ab8c56ddf199b3995c4b246a4307e26d4e7619
 size 4728