Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d523458ce0eab058741cdac056053a3716847feb1d83d28b61c3882ed76c3c0
+oid sha256:7a703f298159eadc32930af5cdd24a00ea5172cdfd7c996c2098fa197e5a84a8
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1326afdbd10eb4bdfcedcb0a3cb37553fe138683120f6c8aff579b358f166a63
+oid sha256:1d5350938001da44f7001b1c1590c45c156f1c542c698883061872bbbc0ca12b
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e6f443edc13d76aeb2e648f13950faed9e7d242fc407fad39549fe00a76cac
+oid sha256:c71b5303d0e8a31d4a767c5665c015aabf6fdb331ed154e2dd5eac2f2642928a
 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": 0.044444444444444446,
+  "epoch": 0.06666666666666667,
   "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": 10.4623,
       "step": 18
+    },
+    {
+      "epoch": 0.04666666666666667,
+      "grad_norm": 3.8492417335510254,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.1835,
+      "step": 21
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 3.4258408546447754,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.0263,
+      "step": 24
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "eval_loss": 9.956049919128418,
+      "eval_runtime": 5.8907,
+      "eval_samples_per_second": 32.254,
+      "eval_steps_per_second": 16.127,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.2378265857696533,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 9.9196,
+      "step": 27
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 3.3411707878112793,
+      "learning_rate": 0.0,
+      "loss": 9.8884,
+      "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": 5328093315072.0,
+  "total_flos": 7907297722368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null