Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c7cbcbac8657cc58b55ec396fa0f079614a09cb21946a7edfc29124baa4960
+oid sha256:ae2474df63592a715df30159fc00d913bcc4af0e9b5f2c7c01c6122b1785df98
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344e7e90842f04fa5062258f996144d39a859f985da74af1108f2dadb8b68a0c
+oid sha256:1b085395b81126568100729c6eab2ff44b74c4b41dff67c1f4998e6a26f7235b
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b025d32d9f0bf93a3dd3d37717c04c2ea80ab3a81ad3f37756c0738a6d7d43
+oid sha256:c9a7f00d84cccccec73d165447765975c70507721d402a7542181fd064c2457f
 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": 0.007399186089530152,
+  "epoch": 0.011098779134295227,
   "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": 13.628,
       "eval_steps_per_second": 6.82,
       "step": 20
+    },
+    {
+      "epoch": 0.00776914539400666,
+      "grad_norm": 1.3720582723617554,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.4971,
+      "step": 21
+    },
+    {
+      "epoch": 0.008879023307436182,
+      "grad_norm": 1.0679662227630615,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3067,
+      "step": 24
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "eval_loss": 2.4402551651000977,
+      "eval_runtime": 83.5954,
+      "eval_samples_per_second": 13.625,
+      "eval_steps_per_second": 6.819,
+      "step": 25
+    },
+    {
+      "epoch": 0.009988901220865706,
+      "grad_norm": 1.1763719320297241,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4056,
+      "step": 27
+    },
+    {
+      "epoch": 0.011098779134295227,
+      "grad_norm": 1.2664074897766113,
+      "learning_rate": 0.0,
+      "loss": 2.4649,
+      "step": 30
+    },
+    {
+      "epoch": 0.011098779134295227,
+      "eval_loss": 2.433227777481079,
+      "eval_runtime": 83.5169,
+      "eval_samples_per_second": 13.638,
+      "eval_steps_per_second": 6.825,
+      "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": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null