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:e1861456a4db563cfdee9788bb2f5b902516de3232d2f91ab60f34df13c2e1c0
+oid sha256:1ca5a8c920b7205782e3d5c80206b37900fbb04f744acd9ca6761799cee8dbf3
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8310a1171314cfabac6bef0417b0fda4d5ea8e59a62f58b8279dd2dbca11fdd
+oid sha256:1d7719ff0b563957b1f4159268811559be4e3a9dd4c9220399710265b3ccd371
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3331cc302a61aa064f985147e8e79318930d0caafedff2e0a96c6c36feb0abd
+oid sha256:b9d60eda0dcffa1a523ae1a7c1d969dd4b68ff9a4d4e1a3cd25269528662fc8d
 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": 0.07136485280999108,
+  "epoch": 0.10704727921498662,
   "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": 10.627,
       "eval_steps_per_second": 5.313,
       "step": 100
+    },
+    {
+      "epoch": 0.07850133809099019,
+      "grad_norm": 0.26714345812797546,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.3431,
+      "step": 110
+    },
+    {
+      "epoch": 0.08563782337198929,
+      "grad_norm": 0.21566510200500488,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.2721,
+      "step": 120
+    },
+    {
+      "epoch": 0.0927743086529884,
+      "grad_norm": 0.25159725546836853,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.3095,
+      "step": 130
+    },
+    {
+      "epoch": 0.09991079393398751,
+      "grad_norm": 0.2559829652309418,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.3015,
+      "step": 140
+    },
+    {
+      "epoch": 0.10704727921498662,
+      "grad_norm": 0.22735165059566498,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.2623,
+      "step": 150
+    },
+    {
+      "epoch": 0.10704727921498662,
+      "eval_loss": 0.2916809618473053,
+      "eval_runtime": 55.5435,
+      "eval_samples_per_second": 10.622,
+      "eval_steps_per_second": 5.311,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.079132314435584e+16,
+  "total_flos": 6.116132979631718e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null