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:f7b28adda79ba303f372d26b7170053d794a329cf5f97c7ed98f9c4da8e3bce6
+oid sha256:a40d459a214b85af91f272f7ae3d8fa915bb91b2fd42cb4f263d7582df5cd94e
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9c36651c0f257aeb67ac887f552236648761d011304adec516cdbefdbe2ff4
+oid sha256:c2858d01d87a4f20f1990e278bd37585dadd1fa732abd83f8173e91d36520c39
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dab678f8341cb1f6a50c07bf4f3f2e6d7185a7a6a288def2d3180b15023b3f
+oid sha256:f8d9b17a2f1b7c6b27a130ebf79d0ed6c4ef331cc0a119753b7e2218a86e1003
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015601841017240034,
+  "epoch": 0.002340276152586005,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 21.45,
       "eval_steps_per_second": 10.725,
       "step": 20
+    },
+    {
+      "epoch": 0.0016381933068102036,
+      "grad_norm": 0.672764003276825,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.6331,
+      "step": 21
+    },
+    {
+      "epoch": 0.001872220922068804,
+      "grad_norm": 0.703521728515625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.664,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019502301271550043,
+      "eval_loss": 2.586000919342041,
+      "eval_runtime": 251.6681,
+      "eval_samples_per_second": 21.449,
+      "eval_steps_per_second": 10.724,
+      "step": 25
+    },
+    {
+      "epoch": 0.0021062485373274046,
+      "grad_norm": 0.6120580434799194,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4989,
+      "step": 27
+    },
+    {
+      "epoch": 0.002340276152586005,
+      "grad_norm": 0.6435114741325378,
+      "learning_rate": 0.0,
+      "loss": 2.6526,
+      "step": 30
+    },
+    {
+      "epoch": 0.002340276152586005,
+      "eval_loss": 2.581470489501953,
+      "eval_runtime": 251.6229,
+      "eval_samples_per_second": 21.453,
+      "eval_steps_per_second": 10.726,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1305053327523840.0,
+  "total_flos": 1957579991285760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null