Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973f5003702306b371cda780db67d7e038379c8b244d67c35ce938c8ab0bf96b
+oid sha256:6622ac26fe235a79bb8b295cc951d493bb49eff64de84ffd09c19e199f2e0b46
 size 262219392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b96ffd460a0e1c3ba4e20bc59a3c67d71b5803fdaf98befbfd7b2a4a266160
+oid sha256:fcdaff135da8696151ceb5a5ee918bf9e78a07f05bdf03cba9ba121111ce1fc8
 size 133778341

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fee0874fa9afae54661807fadac685c3d3f843473b6af99cc43d812ec6e1b36
+oid sha256:20ab57b9b26fc7cb4418a4e1198e25ebb1da623aea7693e1fc71ff284d45724b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fd6c02ecd99f61cbdc485d41ab67693d370b3b850c6938a1f7e3f349931355
+oid sha256:57f5bbb5b4ba44d34a455960920ef8eaf75574205648b376b9b795cb9f0b32ae
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016,
+  "epoch": 0.0024,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,76 @@
       "learning_rate": 8.800000000000001e-05,
       "loss": 0.7709,
       "step": 20
+    },
+    {
+      "epoch": 0.00168,
+      "grad_norm": 0.07268717885017395,
+      "learning_rate": 8e-05,
+      "loss": 0.7329,
+      "step": 21
+    },
+    {
+      "epoch": 0.00176,
+      "grad_norm": 0.07336169481277466,
+      "learning_rate": 7.2e-05,
+      "loss": 0.5357,
+      "step": 22
+    },
+    {
+      "epoch": 0.00184,
+      "grad_norm": 0.15232133865356445,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.9113,
+      "step": 23
+    },
+    {
+      "epoch": 0.00192,
+      "grad_norm": 0.18304885923862457,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.7212,
+      "step": 24
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 0.11778385192155838,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5004,
+      "step": 25
+    },
+    {
+      "epoch": 0.00208,
+      "grad_norm": 0.08693696558475494,
+      "learning_rate": 4e-05,
+      "loss": 0.5905,
+      "step": 26
+    },
+    {
+      "epoch": 0.00216,
+      "grad_norm": 0.10036703199148178,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.659,
+      "step": 27
+    },
+    {
+      "epoch": 0.00224,
+      "grad_norm": 0.16843527555465698,
+      "learning_rate": 2.4e-05,
+      "loss": 0.6575,
+      "step": 28
+    },
+    {
+      "epoch": 0.00232,
+      "grad_norm": 0.1020098477602005,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6988,
+      "step": 29
+    },
+    {
+      "epoch": 0.0024,
+      "grad_norm": 0.07744976878166199,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.7703,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -162,12 +232,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9759882376581120.0,
+  "total_flos": 1.4619103575552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null