Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b9cdd843fedf73beb8713fb0b17322ff23177375f420ca7ee52778a4d73d00
+oid sha256:3149020860cc1b956d74a1f56580dcef4ca4453a4f0efead5e6c89170603f785
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ca68ae35918b5b24b311bf249dd1546cb15ce4d937dc2dd608ebeabf245133
+oid sha256:6b8b7de5e71b8d433ad334059114a13872f3bf9374c9e65c00a85c37784e0716
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a4a3475bbbd37ecdd810d8257811f1364a7006e49ca0ea2393e9b025bf14bc
+oid sha256:2f16ab8460fa2cb912d5d34530659e6add7c303582d2a9356451d5d525613b77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04299889746416759,
+  "epoch": 0.05512679162072767,
   "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": 17.034,
       "eval_steps_per_second": 8.517,
       "step": 39
+    },
+    {
+      "epoch": 0.044101433296582136,
+      "grad_norm": 4.886397361755371,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.2276,
+      "step": 40
+    },
+    {
+      "epoch": 0.04520396912899669,
+      "grad_norm": 4.3510332107543945,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 3.1627,
+      "step": 41
+    },
+    {
+      "epoch": 0.04630650496141125,
+      "grad_norm": 4.668325901031494,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.767,
+      "step": 42
+    },
+    {
+      "epoch": 0.047409040793825796,
+      "grad_norm": 4.192807197570801,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 2.6006,
+      "step": 43
+    },
+    {
+      "epoch": 0.04851157662624035,
+      "grad_norm": 3.6173996925354004,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4846,
+      "step": 44
+    },
+    {
+      "epoch": 0.04961411245865491,
+      "grad_norm": 4.095741271972656,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.8095,
+      "step": 45
+    },
+    {
+      "epoch": 0.050716648291069456,
+      "grad_norm": 4.493954181671143,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 4.394,
+      "step": 46
+    },
+    {
+      "epoch": 0.05181918412348401,
+      "grad_norm": 4.2892584800720215,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 3.0646,
+      "step": 47
+    },
+    {
+      "epoch": 0.05292171995589857,
+      "grad_norm": 5.72744083404541,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 2.4661,
+      "step": 48
+    },
+    {
+      "epoch": 0.05402425578831312,
+      "grad_norm": 3.8518455028533936,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 3.37,
+      "step": 49
+    },
+    {
+      "epoch": 0.05512679162072767,
+      "grad_norm": 3.915316104888916,
+      "learning_rate": 0.0,
+      "loss": 2.9115,
+      "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": 1.3670832182132736e+16,
+  "total_flos": 1.75267079258112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null