Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76a39a55093a69020896e508f8aa0b8f940673017d91952fe1bc0085bfa486a
+oid sha256:b208becf3d84dba51a7f0d56de7549aef5a2ada9d69bff877be1b523ad05c003
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d08b223ece5136cf70130d577dae3d580d7805e5ace2b96ec5d1febc6e260b
+oid sha256:e96a66cfed09831bba9d6ce190d88538a5f6f24b8cf34f7b3ca3a79aebbaca7f
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4bed0903c780937f11285fedbcf413818acafcbc967640aa38cd8370d5c0035
+oid sha256:6b34fbb0e20cc40736bf18c443f9c4f8468a7375c8a0da36bd0188e80d03249c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20725388601036268,
+  "epoch": 0.31088082901554404,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 9.503,
       "eval_steps_per_second": 4.751,
       "step": 100
+    },
+    {
+      "epoch": 0.22797927461139897,
+      "grad_norm": 0.8191409707069397,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 2.3543,
+      "step": 110
+    },
+    {
+      "epoch": 0.24870466321243523,
+      "grad_norm": 0.9439878463745117,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 2.5457,
+      "step": 120
+    },
+    {
+      "epoch": 0.2694300518134715,
+      "grad_norm": 0.7924945950508118,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 2.6822,
+      "step": 130
+    },
+    {
+      "epoch": 0.29015544041450775,
+      "grad_norm": 0.7882089614868164,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 2.5139,
+      "step": 140
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.8719218373298645,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 2.3399,
+      "step": 150
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "eval_loss": 0.6230465173721313,
+      "eval_runtime": 21.4544,
+      "eval_samples_per_second": 9.509,
+      "eval_steps_per_second": 4.754,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.51445192359936e+16,
+  "total_flos": 9.77592459460608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null