Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4b0b4a59e85d7e6af4b7a34158cec3d0e0c3e8fada19f60fb8d999dde0b04d
+oid sha256:3f80aa8ccea89cb639b343d2ad8580715f157b72d00aa20168dddf65d0e7719f
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5215a327ce7bfdf3f861f72783d0a6dc057750c800a758bac5edb9af32981fc9
+oid sha256:2aadfde956bfba1a41c94a0e2a8d5c29c93edc8739d0b00174c1f5b9881b86dd
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1f40e5ed3949f09823dd3019104a35d1148f043d89b682818a1cc328fe11e9
+oid sha256:0310085a91ffe31e52ed785525e1b1bbd8d02ab8f4fd9ae7f554a009347d00a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,48 +1,31 @@
 {
-  "best_metric": 0.5381163358688354,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-340",
-  "epoch": 4.0,
+  "best_metric": 0.4036673307418823,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-803",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 340,
+  "global_step": 803,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_loss": 0.550789475440979,
-      "eval_runtime": 28.7861,
-      "eval_samples_per_second": 10.422,
-      "eval_steps_per_second": 2.605,
-      "step": 85
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.5468895435333252,
-      "eval_runtime": 28.8025,
-      "eval_samples_per_second": 10.416,
-      "eval_steps_per_second": 2.604,
-      "step": 170
+      "epoch": 0.6226650062266501,
+      "grad_norm": 0.7334734201431274,
+      "learning_rate": 0.0003875716064757161,
+      "loss": 3.2343,
+      "step": 500
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 0.5483385324478149,
-      "eval_runtime": 28.8239,
-      "eval_samples_per_second": 10.408,
-      "eval_steps_per_second": 2.602,
-      "step": 255
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.5381163358688354,
-      "eval_runtime": 28.8298,
-      "eval_samples_per_second": 10.406,
-      "eval_steps_per_second": 2.601,
-      "step": 340
+      "epoch": 1.0,
+      "eval_loss": 0.4036673307418823,
+      "eval_runtime": 273.6748,
+      "eval_samples_per_second": 10.436,
+      "eval_steps_per_second": 2.609,
+      "step": 803
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1680,
+  "max_steps": 16060,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -58,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3121269501824e+16,
+  "total_flos": 3.128721416568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398e7e7a79c7e812a6a1020ffa15321ac036a12ab5f062eb1380c17bb0b3f7bc
+oid sha256:69d0a29f401b9a755904f81ae972cbb11a5cf5b18ec1bf43f3d071d452c37c88
 size 5368