Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91fd7fef7c913bb40166ed36edd2f41fccb334c604d8ad710dd729958231a38c
+oid sha256:28c13b7b19ef580ad42a2f99f24213ccaa4472c6b4b059a794da90412c9ac0b4
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44bc94aa5951947f3a443e56090b2942fbbc3833f1851ba62e08e0d0b08ab9b
+oid sha256:a758a18680bfdfc600ed0491e712113dd602c7edc2f701d2cf8f3ef60a372168
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5a8207eb085bcd0143e42fa68c8c3ba984241f8e091d2d1b847c4f98e5ec17
+oid sha256:e2709c70a3faf4f234941f28397ed1c327ceb35087b102618458597e5d291411
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.344450980424881,
   "best_model_checkpoint": "./opt_trained2/checkpoint-803",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1606,
+  "global_step": 2409,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,21 @@
       "eval_samples_per_second": 10.466,
       "eval_steps_per_second": 2.616,
       "step": 1606
+    },
+    {
+      "epoch": 2.4906600249066004,
+      "grad_norm": 1.186563491821289,
+      "learning_rate": 0.000350186799501868,
+      "loss": 2.2782,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.366046667098999,
+      "eval_runtime": 272.9944,
+      "eval_samples_per_second": 10.462,
+      "eval_steps_per_second": 2.615,
+      "step": 2409
     }
   ],
   "logging_steps": 500,
@@ -63,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.257442833136e+16,
+  "total_flos": 9.386164249704e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null