Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4099398d4992c9561ffb00ab28756dd070c9988bddb3271f1abffd3caa053a
+oid sha256:c94dc39f5fcef7d44fe78fa0dbc001789067720bd96a42c3f854888a764c5b36
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc614a800e882af331e4ba1cd076bb2eb2e21ee3b045e6dd443afdbf681e00e
+oid sha256:409d332100530f6a4d333ac3bdd2f5ddd59a61fc4d890a268c73b29a00e0644a
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be36be1bae19d21e97c18d3feb6fdf2fae0c8a83054e9fbc351ec88b60632ffc
+oid sha256:9872f9b561fa3e28de55ecdf158937157966562f9fe1d4847e91af118049f7d5
 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": 0.003711952487008166,
+  "epoch": 0.005567928730512249,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 5.0935,
       "step": 18
+    },
+    {
+      "epoch": 0.0038975501113585748,
+      "grad_norm": 4.368784427642822,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.6337,
+      "step": 21
+    },
+    {
+      "epoch": 0.004454342984409799,
+      "grad_norm": 3.697722911834717,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.247,
+      "step": 24
+    },
+    {
+      "epoch": 0.004454342984409799,
+      "eval_loss": 1.2021467685699463,
+      "eval_runtime": 235.9349,
+      "eval_samples_per_second": 9.617,
+      "eval_steps_per_second": 4.811,
+      "step": 24
+    },
+    {
+      "epoch": 0.005011135857461025,
+      "grad_norm": 1.3606876134872437,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.4003,
+      "step": 27
+    },
+    {
+      "epoch": 0.005567928730512249,
+      "grad_norm": 1.3388198614120483,
+      "learning_rate": 0.0,
+      "loss": 3.6189,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9883555303784448.0,
+  "total_flos": 1.4621127267581952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null