Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a861871eaead25daa6451c7c108c5c0601f3393611263116897f65cc01fbd547
+oid sha256:8c1f6fdb340a7842c3b9d36197925fb5bf38a2e7f9b94b787db9723351428b75
 size 61392180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c0119f5d3097630878f694374b2e8cc6d0f63c7f1cc99a8168e3569e854780a
+oid sha256:1267e27514ca082f15efcd9adc6d0200682d3f44164420487cb0111523d9e10d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ba385b2209b4628cef50b2e3aed65d210b6944a543c1ec9207672d273a9084
+oid sha256:c647c105ea30c8bac469833b3ddfe277a90f35d8ed9ca5a5875bd90949ac4ce9
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1826163301141352,
+  "epoch": 0.3652326602282704,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 15.536,
       "eval_steps_per_second": 3.884,
       "step": 13
+    },
+    {
+      "epoch": 0.19666374012291485,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.21071115013169447,
+      "grad_norm": NaN,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.2247585601404741,
+      "grad_norm": NaN,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": NaN,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.2528533801580334,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.266900790166813,
+      "grad_norm": NaN,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.28094820017559263,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.29499561018437226,
+      "grad_norm": NaN,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.3090430201931519,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.3230904302019315,
+      "grad_norm": NaN,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.33713784021071114,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.35118525021949076,
+      "grad_norm": NaN,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.3652326602282704,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.3652326602282704,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8724,
+      "eval_samples_per_second": 15.548,
+      "eval_steps_per_second": 3.887,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.146970028554322e+17,
+  "total_flos": 2.293940057108644e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null