Training in progress, step 114, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4627a384ccfb90bc59a01e8a25eb50a60e5c9d9a7cbc4781a18e1ed2574854e
+oid sha256:91556df02a9492e4ed535604154a309f209fa3a7e2fcf4bd56b539e4e83f286a
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2150c51d63f89d1bc1d324172bc8d004bf72d5ec3681b8fa7f23855405bf6f
+oid sha256:6bf915dd720836012c07e2ba039e6167731cfebbcc2ab85674c1bd895783e189
 size 148053627

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ac64e05ebf46af43b314fca9573cea163c2749e9f4c0fcee8ac426f60f5872
+oid sha256:9840a2e654651667352c6dcbb85523a16aa0b41cfd2a4a5b46fb280d4019f8a8
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254aa974d264413ca1b60d5980136d8531f6cb9e9b28340b9a2daa2496d48c4c
+oid sha256:ea9f4d1e39b6645a7b25d344c5b4f804a6f6c61e0865871d9bb1dbfa28a7cc9d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f784d5566457719ec24fd9e3c13871706202c23a784efd0979d8609621573572
+oid sha256:3d9b13455c65c7b9f204af76375fe10bffaade07e56cd2645998a3d0cb0ca5ff
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1066666666666665,
+  "epoch": 3.0,
   "eval_steps": 100,
-  "global_step": 80,
+  "global_step": 114,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,56 @@
       "learning_rate": 0.0001317266107909975,
       "loss": 0.6193,
       "step": 80
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.19134873151779175,
+      "learning_rate": 9.934134090518593e-05,
+      "loss": 0.5563,
+      "step": 85
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 0.19149252772331238,
+      "learning_rate": 7.052201923388955e-05,
+      "loss": 0.5774,
+      "step": 90
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 0.2055027186870575,
+      "learning_rate": 4.59507719109446e-05,
+      "loss": 0.5472,
+      "step": 95
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.20931023359298706,
+      "learning_rate": 2.6209177161234443e-05,
+      "loss": 0.5133,
+      "step": 100
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.8378572463989258,
+      "eval_runtime": 6.3722,
+      "eval_samples_per_second": 2.668,
+      "eval_steps_per_second": 2.668,
+      "step": 100
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 0.19245073199272156,
+      "learning_rate": 1.1764499893210877e-05,
+      "loss": 0.5179,
+      "step": 105
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 0.20502211153507233,
+      "learning_rate": 2.9586319796851556e-06,
+      "loss": 0.525,
+      "step": 110
     }
   ],
   "logging_steps": 5,
@@ -134,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5159761905451008.0,
+  "total_flos": 7347762207129600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null