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:b3352ee5153ab0e338f7c753a04e9e2588546fec26aacad34384d1c12d97b0dc
+oid sha256:361c8ee273b7a573d1be4a0267f438a79f136857a66acea855acfc829899aa38
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbada1898ba08f19ffc8ebc697b3ccb0126c65de2f2f384c1095ac3bbeeae79
+oid sha256:4f7a4cbb63ada018df87730f23105cc3b2275df187b6168b06bb9dd8aeb22251
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce11c3f224a15fd2f1c113011a6004c8483a4a221a4b185f689fd129b0ce9f9
+oid sha256:90a37d9b772c0e335f07efb1184717a15d25cc68d9f9eba27489fa3663eb5e4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007517760709676611,
+  "epoch": 0.0015035521419353222,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 4.912,
       "eval_steps_per_second": 2.456,
       "step": 15
+    },
+    {
+      "epoch": 0.0009021312851611933,
+      "grad_norm": 0.6857808232307434,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5791,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010023680946235482,
+      "eval_loss": 1.332275629043579,
+      "eval_runtime": 1712.161,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 2.454,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010524864993547256,
+      "grad_norm": 0.6557658314704895,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3637,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012028417135482577,
+      "grad_norm": 0.5096169114112854,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.5006,
+      "step": 24
+    },
+    {
+      "epoch": 0.001252960118279435,
+      "eval_loss": 1.3074328899383545,
+      "eval_runtime": 1248.175,
+      "eval_samples_per_second": 6.731,
+      "eval_steps_per_second": 3.366,
+      "step": 25
+    },
+    {
+      "epoch": 0.00135319692774179,
+      "grad_norm": 0.603471040725708,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2413,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015035521419353222,
+      "grad_norm": 0.6203583478927612,
+      "learning_rate": 0.0,
+      "loss": 1.2903,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015035521419353222,
+      "eval_loss": 1.299818515777588,
+      "eval_runtime": 802.6314,
+      "eval_samples_per_second": 10.468,
+      "eval_steps_per_second": 5.234,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6398777820708864.0,
+  "total_flos": 1.2704819730972672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null