Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ec89cb2a2f41547e2734e4f492abfa6f55f18845b4615436895799684087d4
+oid sha256:f146300a2c170ed0adabed7ab9e480f7af74e6e62407cd4cff07cc0fbf0e61b2
 size 216151256

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf32f254257f5605bd1ca3b461d0dc8f856888bd448cf45b92dcfd2b1c455372
+oid sha256:5bf3e985ab8f557a6dbfe2e670953c5e6041d523e9b1c45e30c2980b3dfe7eab
 size 432670070

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00a0485fe416c8ab076ad8521dac1925403dc1a690a1f6b5d22cb10b668fa683
+oid sha256:c4647940329d23c91f45d112aa9330e9cb4ce0172050e5ed349817bd996dd2d9
 size 216291274

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef728c024d198b97b7d4ad1c6116785a23ba990aed4efd7ea18dd8e4fb0c1796
+oid sha256:dacd37af46b06bb33efef9395813ad9f3ce39a228579184a431eebdbbc8af863
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685811f59c6fb114ebd7b7c9160431286c8a447abd6055898171eeb1c9f64557
+oid sha256:55a2affa0e6237a8d17332efac3c970f3e72bb50fc9ecb568b597a7966a32fac
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337059d54254bc9389c938dc292312990ce226dd122bd2ed92af370c28fd9326
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031926686867193854,
+  "epoch": 0.03547409651910428,
   "eval_steps": 3,
-  "global_step": 27,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,35 @@
       "eval_samples_per_second": 7.366,
       "eval_steps_per_second": 1.843,
       "step": 27
+    },
+    {
+      "epoch": 0.03310915675116399,
+      "grad_norm": 0.18309150636196136,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.1164,
+      "step": 28
+    },
+    {
+      "epoch": 0.03429162663513414,
+      "grad_norm": 0.17738613486289978,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 0.0813,
+      "step": 29
+    },
+    {
+      "epoch": 0.03547409651910428,
+      "grad_norm": 0.13816732168197632,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 0.0544,
+      "step": 30
+    },
+    {
+      "epoch": 0.03547409651910428,
+      "eval_loss": 0.04009544476866722,
+      "eval_runtime": 386.0297,
+      "eval_samples_per_second": 7.38,
+      "eval_steps_per_second": 1.847,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -291,12 +320,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.709081251263283e+16,
+  "total_flos": 5.409420967359283e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null