Training in progress, step 240, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbfedb128c3a8a90f3c52d5cb8498cfc4a1cc5679a309d2ba9e24f4e116613c
+oid sha256:f317c2f9c0e1904127f0b0ce934aa07af2b7229ad58b9705ab9439b52063d79b
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aaa39867ef9a795fc2fde473bb2d03cac009f05ada558ae7564b3b55853713c
+oid sha256:ef4793eaa5e68cb9e4770c48af11f8b45736f6d545fc0af49f5658489d799143
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7333eda3fb157e4797c9458ec4e20fb25f3cea65d779dd1876520831c6fa7301
+oid sha256:dc199d50ee7acd60b0e618740a19710d9cb29c2225fb47541ee35fdc79228cad
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddfe446a5a284cd678d00b6a2a398b1ec19fbab21ddba1394b97157f0314350
+oid sha256:64f87fdf6af8f44bb6d6b07cf2d135d04fedbac4a4a784047f9932793daf148b
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134925db3ae71cb88cb92756cc2cdea3066935b4ecbf838e78bbfa60c95c3818
+oid sha256:108ec0968af236f6199c1f716a40487225162213cb414b717c6f1aeb82bcbc29
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.333333333333332,
+  "epoch": 20.0,
   "eval_steps": 40,
-  "global_step": 220,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -209,6 +209,28 @@
       "learning_rate": 0.00015000000000000001,
       "loss": 3.1968,
       "step": 220
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 3.1189,
+      "step": 230
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 3.75,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 3.0702,
+      "step": 240
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 3.0596697330474854,
+      "eval_runtime": 10.3849,
+      "eval_samples_per_second": 144.537,
+      "eval_steps_per_second": 2.311,
+      "step": 240
     }
   ],
   "logging_steps": 10,
@@ -228,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.425922867593216e+16,
+  "total_flos": 1.5547920996630528e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null