Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c13b7b19ef580ad42a2f99f24213ccaa4472c6b4b059a794da90412c9ac0b4
+oid sha256:76fb97c1964b635d7be1205ccef676d0caa1dd98ed0ac8b59e7c755533e32712
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a758a18680bfdfc600ed0491e712113dd602c7edc2f701d2cf8f3ef60a372168
+oid sha256:2323db34f8f05f4d09cb6d1278b45c569a36b0afe0f5fd1eacf32a59e4fbd607
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2709c70a3faf4f234941f28397ed1c327ceb35087b102618458597e5d291411
+oid sha256:238f89c7881608a89c144adfd8d2cd6859c09e7f2d8a8e8db71c7c86758fd97b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.344450980424881,
   "best_model_checkpoint": "./opt_trained2/checkpoint-803",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 2409,
+  "global_step": 3212,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 10.462,
       "eval_steps_per_second": 2.615,
       "step": 2409
+    },
+    {
+      "epoch": 3.1133250311332503,
+      "grad_norm": 1.2075772285461426,
+      "learning_rate": 0.000337733499377335,
+      "loss": 2.1429,
+      "step": 2500
+    },
+    {
+      "epoch": 3.7359900373599,
+      "grad_norm": 1.2370275259017944,
+      "learning_rate": 0.00032528019925280203,
+      "loss": 1.7732,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.41189202666282654,
+      "eval_runtime": 272.6721,
+      "eval_samples_per_second": 10.474,
+      "eval_steps_per_second": 2.619,
+      "step": 3212
     }
   ],
   "logging_steps": 500,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.386164249704e+16,
+  "total_flos": 1.2514885666272e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null