Training in progress, step 3528, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a94cba7ea87fbf021935c11f8615cd03a048a31a588040545f87a93c2e3a95
+oid sha256:be42ef4e353e27392037dc2cec3bf00cc7c048f91ef9f46f59ee2562a86dfbd7
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b5081540569441715547ff43f37b97bf715f723d6d2b5b311557c590442d39
+oid sha256:8eecc4137559eec520e9026318cc1cc0f63e5ba22bfa7d05c1c8763355c098e3
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd742063009ee981d5848fe9bf7a543d4a8cbaadadaaa45de6889369e1d15c73
+oid sha256:bcab6042103a2fd0e8743c8a9400dce12c7ba68761a2938ae1a0e95e40c788f4
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf281356dd7e1d35a833a56918425e18fa9ac5fc5fd3a71e84ab0822f7136df
+oid sha256:2f7e988a5ca9ada98ba8f911d0fbe12db8b7bb0761e36d461671decfc40ec371
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4103614211119075,
+  "epoch": 1.444762977372786,
   "eval_steps": 500,
-  "global_step": 3444,
+  "global_step": 3528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2416,6 +2416,62 @@
       "learning_rate": 4.251114126628882e-05,
       "loss": 0.47037758827209475,
       "step": 3440
+    },
+    {
+      "epoch": 1.4128186751305416,
+      "grad_norm": 0.1985323578119278,
+      "learning_rate": 4.196975580515724e-05,
+      "loss": 0.3839314699172974,
+      "step": 3450
+    },
+    {
+      "epoch": 1.416914098494932,
+      "grad_norm": 0.19452232122421265,
+      "learning_rate": 4.14309227266662e-05,
+      "loss": 0.4456809043884277,
+      "step": 3460
+    },
+    {
+      "epoch": 1.4210095218593222,
+      "grad_norm": 0.2070169597864151,
+      "learning_rate": 4.089466573066773e-05,
+      "loss": 0.4107877254486084,
+      "step": 3470
+    },
+    {
+      "epoch": 1.4251049452237126,
+      "grad_norm": 0.17994366586208344,
+      "learning_rate": 4.036100840370818e-05,
+      "loss": 0.3586388111114502,
+      "step": 3480
+    },
+    {
+      "epoch": 1.4292003685881027,
+      "grad_norm": 0.19829167425632477,
+      "learning_rate": 3.982997421799095e-05,
+      "loss": 0.3823136568069458,
+      "step": 3490
+    },
+    {
+      "epoch": 1.4332957919524931,
+      "grad_norm": 0.19170702993869781,
+      "learning_rate": 3.930158653034418e-05,
+      "loss": 0.40462865829467776,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4373912153168833,
+      "grad_norm": 0.19950971007347107,
+      "learning_rate": 3.8775868581193264e-05,
+      "loss": 0.40454530715942383,
+      "step": 3510
+    },
+    {
+      "epoch": 1.4414866386812737,
+      "grad_norm": 0.2022354155778885,
+      "learning_rate": 3.825284349353876e-05,
+      "loss": 0.4281474113464355,
+      "step": 3520
     }
   ],
   "logging_steps": 10,
@@ -2435,7 +2491,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.97610359630803e+17,
+  "total_flos": 6.12221522209837e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null