Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4a7691e7cd2fe5785a78bf212d26aadf3c814be08b43ca6e24094b93d1b632
+oid sha256:f2788df99e965d8ae8e0f1de7c97c40bfb428cb17932d5cecc21060b7ec3c567
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69815d0b02d4093787212496ad1c2421e8902a92e6bb004f8d5dfeda4e261b07
+oid sha256:3cd02f4f58c2fab83f6a63f5484ec28dc69257c4bdac454028bba822aabd61bb
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0d6a68d922e782698a018376b53b85027f73e542c47378e687b580096f86bd
+oid sha256:515ed9c683dff41b64c1d3a2ae8782a348f041debee6ea93d6dd2fcee4c2fcd4
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c230e4a3d3176d8f4a84949e99fccf4bc6db16aab7ec60a204be03a7a4d58c
+oid sha256:9c2ce6466218d3478f547123414311551be483ec15bd6249d9e7ad7c1f4b6834
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5485714285714286,
+  "epoch": 0.7032967032967034,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 11.598,
       "eval_steps_per_second": 2.906,
       "step": 39
+    },
+    {
+      "epoch": 0.5626373626373626,
+      "grad_norm": 0.09625887870788574,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7666,
+      "step": 40
+    },
+    {
+      "epoch": 0.5767032967032967,
+      "grad_norm": 0.09051655977964401,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7939,
+      "step": 41
+    },
+    {
+      "epoch": 0.5907692307692308,
+      "grad_norm": 0.09801479429006577,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.762,
+      "step": 42
+    },
+    {
+      "epoch": 0.6048351648351649,
+      "grad_norm": 0.0950697809457779,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8127,
+      "step": 43
+    },
+    {
+      "epoch": 0.6189010989010989,
+      "grad_norm": 0.08845943212509155,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7691,
+      "step": 44
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.09417203068733215,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7847,
+      "step": 45
+    },
+    {
+      "epoch": 0.6470329670329671,
+      "grad_norm": 0.09285993129014969,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7798,
+      "step": 46
+    },
+    {
+      "epoch": 0.6610989010989011,
+      "grad_norm": 0.09379366785287857,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7899,
+      "step": 47
+    },
+    {
+      "epoch": 0.6751648351648352,
+      "grad_norm": 0.08996466547250748,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8066,
+      "step": 48
+    },
+    {
+      "epoch": 0.6892307692307692,
+      "grad_norm": 0.09068991243839264,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7763,
+      "step": 49
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.089011549949646,
+      "learning_rate": 0.0,
+      "loss": 0.7753,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.227198361602621e+17,
+  "total_flos": 1.0547690207182848e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null