Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b2ab048ce855984cf97ee78a2766832af57903ff2dca8459aed193b59cc2bb
+oid sha256:741e4b7c0871582130206a815bfcc42176e273e770414a6c1c9c4f0cfd7d0259
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f32937d43b31399634479436e8300bef357fda17aa308d50382ee919126e2f86
+oid sha256:1c3342aa241c4b975cb8cb4679e720403ba29e78c0142b13fd9a2c7073428fad
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87186703aed64a28f7aa092aa66ac4cff9ccd6f164d6515ce692fb3a15c4760e
+oid sha256:f7a008e4416221a92675c1aa1d6ef4a2ecef81cd840382268d055b69f64f070b
 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": 0.0008005523811429886,
+  "epoch": 0.001200828571714483,
   "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": 8.465,
       "eval_steps_per_second": 4.233,
       "step": 20
+    },
+    {
+      "epoch": 0.0008405800002001381,
+      "grad_norm": 0.46694231033325195,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.0624,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009606628573715864,
+      "grad_norm": 0.5135141015052795,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9919,
+      "step": 24
+    },
+    {
+      "epoch": 0.001000690476428736,
+      "eval_loss": 2.003922939300537,
+      "eval_runtime": 1243.2088,
+      "eval_samples_per_second": 8.461,
+      "eval_steps_per_second": 4.231,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010807457145430347,
+      "grad_norm": 0.5257859826087952,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0548,
+      "step": 27
+    },
+    {
+      "epoch": 0.001200828571714483,
+      "grad_norm": 0.4982208013534546,
+      "learning_rate": 0.0,
+      "loss": 1.98,
+      "step": 30
+    },
+    {
+      "epoch": 0.001200828571714483,
+      "eval_loss": 1.9978368282318115,
+      "eval_runtime": 1243.215,
+      "eval_samples_per_second": 8.461,
+      "eval_steps_per_second": 4.231,
+      "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": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null