Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5353d5197c576ad551e487d6a6f388c772e1e01055d3e384b3b2c86d4c0570
+oid sha256:25c20297a0e836abc32b088e36fa15132b683c36b1a2bb85ca726976ac95ae46
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675c31ccb56d5cfc9c70108f2c9c558baa14555088d3e56b2700dff24a226f9d
+oid sha256:5294a37b41cd7210d7e48bfc9e4294487904234addb69e82ff1ff77eb108f910
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44a760472ceed5f9e772e6e36ed36f260083e4ed06786de702401390793c2ac
+oid sha256:07703071124c9464561e249e710033a0d880b7f0ff84200df9cc28035d6cc976
 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": 0.0010473397570171764,
+  "epoch": 0.0015710096355257646,
   "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": 0.9721,
       "step": 18
+    },
+    {
+      "epoch": 0.0010997067448680353,
+      "grad_norm": 0.26690998673439026,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7824,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012568077084206116,
+      "grad_norm": 0.3476714789867401,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9719,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012568077084206116,
+      "eval_loss": 0.8725840449333191,
+      "eval_runtime": 1341.7597,
+      "eval_samples_per_second": 5.993,
+      "eval_steps_per_second": 2.997,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014139086719731882,
+      "grad_norm": 0.2700293958187103,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9492,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015710096355257646,
+      "grad_norm": 0.3039461672306061,
+      "learning_rate": 0.0,
+      "loss": 0.8429,
+      "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": 1.437406611898368e+16,
+  "total_flos": 2.160746713369805e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null