Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351cfb04c2b0f9add37e720892e6a52f18214235926505d5529df3bb42033726
+oid sha256:a3f97f2ab628ed293d0a432a3593d711e966f0ae92bd49f5be0ee552a68c469a
 size 28548400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4cea7616bbec6b7b5125e4f42f472033e3f89400dea906e2004541fd059c485
+oid sha256:6092d35a12ec05f084457a6372be6553f54f5c27a27df2038c735775f6a0cee5
 size 57261498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba2b37c4fb71a9ccfcc8845dbdd436d485b99a717e10365577c8c5f36e225fe
+oid sha256:a6950194ebb19bcb53b00c81fc7ad3ced6cd8fcb55c47b77f84c6bbe4c8dda34
 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": 0.0004995878400319736,
+  "epoch": 0.0007493817600479605,
   "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": 7.9661,
       "step": 18
+    },
+    {
+      "epoch": 0.0005245672320335723,
+      "grad_norm": 2.8843653202056885,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.7912,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005995054080383684,
+      "grad_norm": 2.694774627685547,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.3834,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005995054080383684,
+      "eval_loss": 1.754106879234314,
+      "eval_runtime": 415.5851,
+      "eval_samples_per_second": 40.562,
+      "eval_steps_per_second": 20.282,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006744435840431644,
+      "grad_norm": 2.984825611114502,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.4132,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007493817600479605,
+      "grad_norm": 2.498382329940796,
+      "learning_rate": 0.0,
+      "loss": 7.2103,
+      "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": 400600156078080.0,
+  "total_flos": 583731655999488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null