Training in progress, step 14, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332cf6808556d7a494ce2f0aa34b22d4c16c9bc4e8c4834a3f8870bf2f34c47b
+oid sha256:f9bafac06c2c177b6873285cba9faa63a0aad0c7fde76726cc9c9ef561423470
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecefe9cb2134c36ac32f344736764510c8f969de1bcd9fdaedb31d523c78438
+oid sha256:297e7ddbc295a07cecddf760a69f80e7807fb90e55e9ae40a8c01ff1aacc7519
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373892a68dd4fdd748ed14777df992f68b324bb9261684875ca84ff9c7bd0fb1
+oid sha256:b3fa8e33d36e4355c9c88316639a14b52060c5a44fe868e2fd61ab111f6ed180
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e096882cd5f2725064920833a5d82c69883609bddf4126e13e653e290fdb396a
+oid sha256:8f1660560e734c40e5470cca2d00d4f738c021882bc0c1304da944a20144bee2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25925925925925924,
+  "epoch": 0.5185185185185185,
   "eval_steps": 7,
-  "global_step": 7,
+  "global_step": 14,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -72,6 +72,63 @@
       "eval_samples_per_second": 10.063,
       "eval_steps_per_second": 2.543,
       "step": 7
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": NaN,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": NaN,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": NaN,
+      "learning_rate": 7.128896457825364e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": NaN,
+      "learning_rate": 5.9369065729286245e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": NaN,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "eval_loss": NaN,
+      "eval_runtime": 18.089,
+      "eval_samples_per_second": 10.061,
+      "eval_steps_per_second": 2.543,
+      "step": 14
     }
   ],
   "logging_steps": 1,
@@ -91,7 +148,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5658466354711757e+17,
+  "total_flos": 3.1316932709423514e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null