Training in progress, step 21, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bafac06c2c177b6873285cba9faa63a0aad0c7fde76726cc9c9ef561423470
+oid sha256:8d66c403cdd318e9ea464acc3be84788a49b39f3efcac2737e1c82743e5fb752
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297e7ddbc295a07cecddf760a69f80e7807fb90e55e9ae40a8c01ff1aacc7519
+oid sha256:20a29dde21dfe173516419b977db3c1775d1cd4ba8f6bd6e1a59919a4f0685ef
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3fa8e33d36e4355c9c88316639a14b52060c5a44fe868e2fd61ab111f6ed180
+oid sha256:3cd3306f67ab1d184a941a93922d03608c525054b65e45368eab572e7e3d4940
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1660560e734c40e5470cca2d00d4f738c021882bc0c1304da944a20144bee2
+oid sha256:d0eef01f601d0942e2858e183d109e520edd8d27fcbc4627e3dd5104e8484712
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5185185185185185,
+  "epoch": 0.7777777777777778,
   "eval_steps": 7,
-  "global_step": 14,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -129,6 +129,63 @@
       "eval_samples_per_second": 10.061,
       "eval_steps_per_second": 2.543,
       "step": 14
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": NaN,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": NaN,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": NaN,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "eval_loss": NaN,
+      "eval_runtime": 18.0827,
+      "eval_samples_per_second": 10.065,
+      "eval_steps_per_second": 2.544,
+      "step": 21
     }
   ],
   "logging_steps": 1,
@@ -148,7 +205,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1316932709423514e+17,
+  "total_flos": 4.697539906413527e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null