Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b96030990e2cbe8ee14c6d4e5b3bbf753192f33a85beec9614dd6a355e0cc5f
+oid sha256:64375e1af38a07ed8e1cc29a938b1f34f3ab759f0d65a3d643ffac639259f588
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc73adee685875ac0dacc76e3e0fb2d64cbe93f9774ccd7069590ba3e3aa0b2
+oid sha256:5f9938d52361021bf28559d8bf2778b2843659d210d6f7c3d6182636a7778911
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ea31b610d850f9fc26adff71ce73d55526e0abaa93d2759bac7c6d670464b0
+oid sha256:74de629c7745350da0e00702cc2f326f721bcf0ac1ce682d29c1868a0f52d5a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda744352ad310cba13ed1fede3477df33c07b3ec9690a40158ff4c28b0f319
+oid sha256:0d5de2d1585efa60c767314cb12e7426bee35362f5be2195f46e6beb21815a52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2871530055999756,
   "best_model_checkpoint": "./opt_trained/checkpoint-1365",
-  "epoch": 6.0,
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 2730,
+  "global_step": 3185,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,21 @@
       "eval_samples_per_second": 26.893,
       "eval_steps_per_second": 6.724,
       "step": 2730
+    },
+    {
+      "epoch": 6.593406593406593,
+      "grad_norm": 2.745879650115967,
+      "learning_rate": 3.0198652087802722e-05,
+      "loss": 0.28,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.288526713848114,
+      "eval_runtime": 210.0108,
+      "eval_samples_per_second": 26.965,
+      "eval_steps_per_second": 6.743,
+      "step": 3185
     }
   ],
   "logging_steps": 500,
@@ -109,7 +124,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.20770479567872e+17,
+  "total_flos": 1.40898892829184e+17,
   "train_batch_size": 14,
   "trial_name": null,
   "trial_params": null