Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380296421291f46b2e1e40f94252962d2e1e90b5772d1db70a2b4222d62a64ef
+oid sha256:3b96030990e2cbe8ee14c6d4e5b3bbf753192f33a85beec9614dd6a355e0cc5f
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094f53bd1e68ec3e3045a11621d1737fd86889ad811caf2dcdfb357ab6c0ef1c
+oid sha256:acc73adee685875ac0dacc76e3e0fb2d64cbe93f9774ccd7069590ba3e3aa0b2
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d931b9882728cfe64a4338d5ac53748948e5ba484ca21dd9d799b36dda5c3486
+oid sha256:c3ea31b610d850f9fc26adff71ce73d55526e0abaa93d2759bac7c6d670464b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9101cee162d32be872e0d83d786f5068febc6fec1aad26d76cb604ee21b3f7f9
+oid sha256:aeda744352ad310cba13ed1fede3477df33c07b3ec9690a40158ff4c28b0f319
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2871530055999756,
   "best_model_checkpoint": "./opt_trained/checkpoint-1365",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 2275,
+  "global_step": 2730,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 26.903,
       "eval_steps_per_second": 6.727,
       "step": 2275
+    },
+    {
+      "epoch": 5.4945054945054945,
+      "grad_norm": 2.2816271781921387,
+      "learning_rate": 3.300208187337489e-05,
+      "loss": 0.282,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.28762978315353394,
+      "eval_runtime": 210.5772,
+      "eval_samples_per_second": 26.893,
+      "eval_steps_per_second": 6.724,
+      "step": 2730
     }
   ],
   "logging_steps": 500,
@@ -94,7 +109,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0064206630656e+17,
+  "total_flos": 1.20770479567872e+17,
   "train_batch_size": 14,
   "trial_name": null,
   "trial_params": null