Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f8208969c787c86b244b9e9a71626f98e35ffdfeaecbcc5ef207a5ddc9659d
+oid sha256:01fa6858421fdb015bb654a425c3f690795d9e1cf96f456f6b27a6326b7d244c
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965dc697c3ab28072f197959f194ef0efcc91bb79803752fd97f500aa7e8a5df
+oid sha256:a4223bec74f7da5212aa0de8c7257e806561a45c5fccd2838265f2d310699b11
 size 1540661735

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb8116194227284009af0f32eb6c9bf39b120912678b54e07fcb6539f29b5b2
+oid sha256:b815622b7dfb0359193f2c3e6cdc190a4c07e6c28cfbaf526d6da260173bd4a4
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3161ebc22e167d90d7ee5cc1bfde367c6af5f0b04db44c912617eb26a593223
+oid sha256:94b7b1a014f5dad743694fda5858015bfe3bd4c82eac608d649238b91858a560
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,86 @@
       "eval_samples_per_second": 37.096,
       "eval_steps_per_second": 37.096,
       "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 31.606178283691406,
+      "learning_rate": 0.00015154431949464275,
+      "loss": 11.733912353515626,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.05017808219178082,
+      "eval_loss": 12.344472885131836,
+      "eval_runtime": 27.8267,
+      "eval_samples_per_second": 35.937,
+      "eval_steps_per_second": 35.937,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 60.602169036865234,
+      "learning_rate": 9.11646573017482e-05,
+      "loss": 12.59990234375,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.07920547945205479,
+      "eval_loss": 11.4829683303833,
+      "eval_runtime": 26.8514,
+      "eval_samples_per_second": 37.242,
+      "eval_steps_per_second": 37.242,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 28.155149459838867,
+      "learning_rate": 4.2578993244549506e-05,
+      "loss": 10.478193359375,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.08408610567514677,
+      "eval_loss": 9.93655776977539,
+      "eval_runtime": 26.6366,
+      "eval_samples_per_second": 37.542,
+      "eval_steps_per_second": 37.542,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 26.28119468688965,
+      "learning_rate": 1.1052337907897503e-05,
+      "loss": 9.994468383789062,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.0641252446183953,
+      "eval_loss": 9.959942817687988,
+      "eval_runtime": 26.6315,
+      "eval_samples_per_second": 37.549,
+      "eval_steps_per_second": 37.549,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 41.307456970214844,
+      "learning_rate": 1.093583978573065e-09,
+      "loss": 9.751447143554687,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.06885127201565558,
+      "eval_loss": 9.537232398986816,
+      "eval_runtime": 26.8522,
+      "eval_samples_per_second": 37.241,
+      "eval_steps_per_second": 37.241,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -102,7 +182,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }