Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3c2a4b3043758db87aea66ab315fa2cbc313165bb80462915bc105c60af228
+oid sha256:3d8f8a0cfa513e2a6305a160856085e017d9a164e89689999a9c89b2f142d83c
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d72e3443f6773246671b21cfde17e1159a1de68d5073dbfe8c386d124d2a2c
+oid sha256:30a428c202e00784e51e5bd519c42c8e9068fd66210ac7977b89d70c17cd50c6
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03508771929824561,
+  "epoch": 0.0449842555105713,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 11.9284,
       "step": 35
+    },
+    {
+      "epoch": 0.03598740440845704,
+      "grad_norm": 0.34404051303863525,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9186,
+      "step": 40
+    },
+    {
+      "epoch": 0.03598740440845704,
+      "eval_loss": 11.928149223327637,
+      "eval_runtime": 11.5262,
+      "eval_samples_per_second": 40.603,
+      "eval_steps_per_second": 20.302,
+      "step": 40
+    },
+    {
+      "epoch": 0.04048582995951417,
+      "grad_norm": 0.47935619950294495,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9246,
+      "step": 45
+    },
+    {
+      "epoch": 0.0449842555105713,
+      "grad_norm": 0.46782049536705017,
+      "learning_rate": 0.0,
+      "loss": 11.9246,
+      "step": 50
+    },
+    {
+      "epoch": 0.0449842555105713,
+      "eval_loss": 11.927846908569336,
+      "eval_runtime": 11.3217,
+      "eval_samples_per_second": 41.337,
+      "eval_steps_per_second": 20.668,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4881081434112.0,
+  "total_flos": 6257796710400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null