Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6dcbd5085cbf63ac5085958a9d245f623f90de7b262515ecb6483d5a345d64
+oid sha256:96f108561954d411231186b19665481fd2f6df3b3efb920d539791a1741ba1eb
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba54a248bc76bac335ee13460016b219d8382ba3654620cfa36781575fe05a8
+oid sha256:c868badaae7a9c159e414415a8db956178586ef11a34074f4ae1cb75a6cde069
 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": 2.1983,
       "step": 18
+    },
+    {
+      "epoch": 0.0034153283187639766,
+      "grad_norm": 0.8231281042098999,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.3862,
+      "step": 21
+    },
+    {
+      "epoch": 0.0039032323643016873,
+      "grad_norm": 0.6137740015983582,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.558,
+      "step": 24
+    },
+    {
+      "epoch": 0.0039032323643016873,
+      "eval_loss": 0.6066776514053345,
+      "eval_runtime": 337.8357,
+      "eval_samples_per_second": 7.663,
+      "eval_steps_per_second": 3.833,
+      "step": 24
+    },
+    {
+      "epoch": 0.004391136409839398,
+      "grad_norm": 0.8133916854858398,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.3135,
+      "step": 27
+    },
+    {
+      "epoch": 0.00487904045537711,
+      "grad_norm": 0.6444946527481079,
+      "learning_rate": 0.0,
+      "loss": 2.3194,
+      "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