Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c871ba6e5308533a6c2e71da5591e4f8295239332304f774a2692b128e942a1b
+oid sha256:b8cfc0aef9900eec40ad433ac5ee417c2275cd16011927e2df0bce589206c0bd
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d502ab2c817ccbf0bf3e62309a7910cdae244d50ffebfebfb8e68dac962dc11
+oid sha256:f26de96710ea85c8be9b28b08e3e8d7e983fbb0b673c1c0ae28262ab34da16a8
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5288644c922e2117f3e11b4b967b0f30510aac94060552820b4109c2ef15b429
+oid sha256:bfc458b664b09b64efe583bff2ca130afda3e8a2e35b780ba084fa8f89afaf1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e0a5fc5e4e82feb4ca34ac150b36b36710ce3de350e213fb71cf5993062420
+oid sha256:8531775f4e5c3819ae81b2ea1cfeb7e992dc0ca011334fb9ed6fb83e3392e473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017738359201773836,
+  "epoch": 0.022172949002217297,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,49 @@
       "eval_samples_per_second": 6.569,
       "eval_steps_per_second": 1.646,
       "step": 20
+    },
+    {
+      "epoch": 0.01862527716186253,
+      "grad_norm": 1.4212274551391602,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 1.7193,
+      "step": 21
+    },
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 1.1630442142486572,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 1.6274,
+      "step": 22
+    },
+    {
+      "epoch": 0.020399113082039913,
+      "grad_norm": 1.1326076984405518,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 1.3282,
+      "step": 23
+    },
+    {
+      "epoch": 0.021286031042128603,
+      "grad_norm": 1.1382163763046265,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 1.7554,
+      "step": 24
+    },
+    {
+      "epoch": 0.021286031042128603,
+      "eval_loss": 1.4955854415893555,
+      "eval_runtime": 72.2954,
+      "eval_samples_per_second": 6.57,
+      "eval_steps_per_second": 1.646,
+      "step": 24
+    },
+    {
+      "epoch": 0.022172949002217297,
+      "grad_norm": 1.1630949974060059,
+      "learning_rate": 0.0,
+      "loss": 1.4209,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -209,12 +252,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3704278509158400.0,
+  "total_flos": 4692086111600640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null