Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843cba4b3e81054050c1c8b16fe3d72610de13da96a25cfd3a66da50db03ba19
+oid sha256:c2865ac223aaf2258b943599d521d3936de1c0602a9d87c3866ab455828fa437
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e65a2ebeb383e088f82c4048574d61facefce2da766775b042bce0e395aa527
+oid sha256:1056e5a11f3361ae565dc7ba196187d5de7b5879650096ffa751d58013159ec2
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a713c54e84cd48df8f7467fb50d1ee9fbe2656c83e7b41aac5e97a0c0dbebd
+oid sha256:5dbb430077813eebb78e89f25ad57a8b8a506e2650404fdf80d07e549f36aeda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee1e582342ae1078e771a171c799cb711145cb11265428051f9e7562adbe8b0
+oid sha256:e80e230602e7a193cb259f6d595adaedbdfa6e184c93cf7d550ef28b903e0783
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5374372005462646,
   "best_model_checkpoint": "./opt_trained3/checkpoint-60",
-  "epoch": 4.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,30 @@
       "eval_samples_per_second": 50.03,
       "eval_steps_per_second": 12.507,
       "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5423746705055237,
+      "eval_runtime": 5.9878,
+      "eval_samples_per_second": 50.102,
+      "eval_steps_per_second": 12.525,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.5467855930328369,
+      "eval_runtime": 5.9773,
+      "eval_samples_per_second": 50.19,
+      "eval_steps_per_second": 12.547,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.5484521389007568,
+      "eval_runtime": 5.9799,
+      "eval_samples_per_second": 50.168,
+      "eval_steps_per_second": 12.542,
+      "step": 105
     }
   ],
   "logging_steps": 500,
@@ -58,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2226422453760000.0,
+  "total_flos": 3896239294080000.0,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null