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:b00ec88d67b0ab5defdc0d685242dfc674836f82e7fe19bcb6972e2dac7ab832
+oid sha256:fa1bb324bc96e47a8a558654e5438628de8527d43b6125e8d87f5a42f782caf9
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a054d8f62d28b3250fcf98d6b9aedef837495f8ff7c68b1f7c02d52e6393083
+oid sha256:1f375e4cee72aa1ec623e56e441fce658214be15d8becce442ccef3fd629b574
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3886ce23ead9c8f84d5743fd13c973d242104a71174bb2259238c10511cad5
+oid sha256:759196af96a334932875327409b6daf225daf60d9921bf7b561c94ddb6081144
 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": 0.0009289471545187474,
+  "epoch": 0.001393420731778121,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.072,
       "eval_steps_per_second": 7.536,
       "step": 20
+    },
+    {
+      "epoch": 0.0009753945122446847,
+      "grad_norm": 0.33748558163642883,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8459,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011147365854224968,
+      "grad_norm": 0.2766661047935486,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.8379,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011611839431484342,
+      "eval_loss": 1.811337947845459,
+      "eval_runtime": 560.6304,
+      "eval_samples_per_second": 16.171,
+      "eval_steps_per_second": 8.086,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012540786586003089,
+      "grad_norm": 0.24097251892089844,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.812,
+      "step": 27
+    },
+    {
+      "epoch": 0.001393420731778121,
+      "grad_norm": 0.2926323711872101,
+      "learning_rate": 0.0,
+      "loss": 1.8368,
+      "step": 30
+    },
+    {
+      "epoch": 0.001393420731778121,
+      "eval_loss": 1.806317687034607,
+      "eval_runtime": 561.7222,
+      "eval_samples_per_second": 16.14,
+      "eval_steps_per_second": 8.07,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1892327324909568.0,
+  "total_flos": 2903743653740544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null