Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d56ff701af02fe605448b713a4f4a3e1e8e81f1fd16e297a520155e4f93801
+oid sha256:76fb4fc866b4e3835fde5620d852dd3acf6af67a2f03ddba887ae93a33393041
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cba132f52109527b9ee2728ac354f4960ec64c5865c2c73114020bd19897561
+oid sha256:1faa1431821eeb0aca3ae47c122491c89e7c0d34b6a910eeabb62cdffa9be6e9
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de4498a0de62c098b1cb8172b9b1220b1b62c62b8e96d152d6e567f4efc9a50
+oid sha256:fb10c9d6bc9fa712342ab2014e39173dc6d0c92e3482143e2f8eef0197ae6c40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e2d1622657dcc0dcd51ce58722af936ea03498ab99a1d3c8cd80669cb28819
+oid sha256:c441f68d34987b8578be1b29313268756039e66819fc49dbcf77e0d1c8721b2c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.431854248046875,
   "best_model_checkpoint": "./opt_trained1/checkpoint-268",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 804,
+  "global_step": 1072,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,21 @@
       "eval_samples_per_second": 13.784,
       "eval_steps_per_second": 1.723,
       "step": 804
+    },
+    {
+      "epoch": 3.7320261437908497,
+      "grad_norm": 664899.9375,
+      "learning_rate": 0.0003250936329588015,
+      "loss": 2.3939,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 7.311771869659424,
+      "eval_runtime": 207.1535,
+      "eval_samples_per_second": 13.787,
+      "eval_steps_per_second": 1.723,
+      "step": 1072
     }
   ],
   "logging_steps": 500,
@@ -57,7 +72,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.429845542887424e+16,
+  "total_flos": 7.239794057183232e+16,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null