Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63cfacd2d61ad699f2ba5bfd93efc6cae76e074f156838a2a28013931b4d0f0b
+oid sha256:3f1a98205660750b55034d5295a2f2db92642d072b0a867e4a6f059b7ab4f6e6
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11815f4319fe649a93bb4062e36961316515762337b10cf345507e172f6b2fb7
+oid sha256:8ddd0e2815260257ba6fcd9bbc6317f4e9a9efea8ab9fa5a819a7fa904a07e1a
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd2dcf10dab10ab8ee0931b3c2ef546aa966f1aae45a22c8b6f6a0effcde90e
+oid sha256:d90cf65f6bbcc4fad1cb2c49809b69f70bf2a56d8f25e35bd8090866bbc4f07a
 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": 0.0032526936369180726,
+  "epoch": 0.00487904045537711,
   "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": 2.1966,
       "step": 18
+    },
+    {
+      "epoch": 0.0034153283187639766,
+      "grad_norm": 0.8114487528800964,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.3838,
+      "step": 21
+    },
+    {
+      "epoch": 0.0039032323643016873,
+      "grad_norm": 0.5942605137825012,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.5547,
+      "step": 24
+    },
+    {
+      "epoch": 0.0039032323643016873,
+      "eval_loss": 0.6068182587623596,
+      "eval_runtime": 324.2749,
+      "eval_samples_per_second": 7.984,
+      "eval_steps_per_second": 3.994,
+      "step": 24
+    },
+    {
+      "epoch": 0.004391136409839398,
+      "grad_norm": 0.7476170063018799,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.3127,
+      "step": 27
+    },
+    {
+      "epoch": 0.00487904045537711,
+      "grad_norm": 0.6413885354995728,
+      "learning_rate": 0.0,
+      "loss": 2.3178,
+      "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": 1.856740263985152e+16,
+  "total_flos": 2.85652348305408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null