Training in progress, step 2550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31463c340dbc666aac7e225725fb9ad3360f9e62eea45ec33c678a92ce7f17eb
+oid sha256:dd6be1a1e8dba63fda5837c7f72a318a4ccc16a21490df3b362f7fbc12cf3ce1
 size 394815560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d1c8f4c06aaf25f2e2c9c7f82cb3bf81269efc82425c06532c3d05719146f7
+oid sha256:9286d7bb63631c27497c1665788ea8e50b3032d5786d5d2cdc68be60a59615e0
 size 711495290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff3f41874ddf41d16b0af5bb1930c6f1c9d073c3e2c471b0a984d6a624cf5509
+oid sha256:40d9b2439b514e816a44784dde57cac1f97b6409754b7cfedefda3e959232c33
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92004acc1e8872397c2b3d090ade00b417621b7e605504bae6bb3ef764136468
+oid sha256:33d3220dbd31e88d495721958a661ce79eb3e88c61eb9620c091aa5a27bed962
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.5657522678375244,
   "best_model_checkpoint": "./output/checkpoint-1650",
-  "epoch": 1.288244766505636,
+  "epoch": 1.3687600644122382,
   "eval_steps": 150,
-  "global_step": 2400,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1815,6 +1815,119 @@
       "eval_samples_per_second": 13.943,
       "eval_steps_per_second": 13.943,
       "step": 2400
+    },
+    {
+      "epoch": 1.2936124530327429,
+      "grad_norm": 8.595821380615234,
+      "learning_rate": 4.358557235613734e-05,
+      "loss": 2.1494,
+      "step": 2410
+    },
+    {
+      "epoch": 1.2989801395598497,
+      "grad_norm": 8.649581909179688,
+      "learning_rate": 4.333007628713158e-05,
+      "loss": 2.138,
+      "step": 2420
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 8.213851928710938,
+      "learning_rate": 4.3074443331732674e-05,
+      "loss": 2.1286,
+      "step": 2430
+    },
+    {
+      "epoch": 1.3097155126140634,
+      "grad_norm": 8.641511917114258,
+      "learning_rate": 4.281868399801016e-05,
+      "loss": 2.0917,
+      "step": 2440
+    },
+    {
+      "epoch": 1.3150831991411702,
+      "grad_norm": 8.759982109069824,
+      "learning_rate": 4.256280879922852e-05,
+      "loss": 2.0891,
+      "step": 2450
+    },
+    {
+      "epoch": 1.320450885668277,
+      "grad_norm": 9.908300399780273,
+      "learning_rate": 4.230682825341498e-05,
+      "loss": 2.0988,
+      "step": 2460
+    },
+    {
+      "epoch": 1.325818572195384,
+      "grad_norm": 9.921548843383789,
+      "learning_rate": 4.205075288292717e-05,
+      "loss": 2.1693,
+      "step": 2470
+    },
+    {
+      "epoch": 1.3311862587224907,
+      "grad_norm": 8.90367603302002,
+      "learning_rate": 4.17945932140206e-05,
+      "loss": 2.0252,
+      "step": 2480
+    },
+    {
+      "epoch": 1.3365539452495974,
+      "grad_norm": 8.375697135925293,
+      "learning_rate": 4.1538359776415936e-05,
+      "loss": 2.1367,
+      "step": 2490
+    },
+    {
+      "epoch": 1.3419216317767042,
+      "grad_norm": 8.196423530578613,
+      "learning_rate": 4.128206310286622e-05,
+      "loss": 2.1237,
+      "step": 2500
+    },
+    {
+      "epoch": 1.347289318303811,
+      "grad_norm": 9.057501792907715,
+      "learning_rate": 4.102571372872382e-05,
+      "loss": 2.1228,
+      "step": 2510
+    },
+    {
+      "epoch": 1.3526570048309179,
+      "grad_norm": 9.608572006225586,
+      "learning_rate": 4.0769322191507485e-05,
+      "loss": 2.1579,
+      "step": 2520
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 8.915650367736816,
+      "learning_rate": 4.051289903046909e-05,
+      "loss": 2.1421,
+      "step": 2530
+    },
+    {
+      "epoch": 1.3633923778851316,
+      "grad_norm": 8.882908821105957,
+      "learning_rate": 4.025645478616045e-05,
+      "loss": 2.111,
+      "step": 2540
+    },
+    {
+      "epoch": 1.3687600644122382,
+      "grad_norm": 8.42502498626709,
+      "learning_rate": 4e-05,
+      "loss": 2.1635,
+      "step": 2550
+    },
+    {
+      "epoch": 1.3687600644122382,
+      "eval_loss": 2.5890932083129883,
+      "eval_runtime": 36.6753,
+      "eval_samples_per_second": 13.66,
+      "eval_steps_per_second": 13.66,
+      "step": 2550
     }
   ],
   "logging_steps": 10,
@@ -1834,7 +1947,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5427337167931392.0,
+  "total_flos": 5767973348014080.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null