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:b2716bd992cccc420c37ed8ca8708fb160f98fc81e7a6650a4f48016ac7a0a16
+oid sha256:d07dcbb831121bebe475922522a591ef66e87ee4c839e531144e22632f0c73c9
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb4a806fb9fd4bc54beb4a20ec1625548792cc84f312749c74501d2fadd2c49
+oid sha256:0f3660743e8366bcd2d8a5ca040bbbe5915a9af262bd692ddd6da3de1151f6e0
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
 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": 0.0031960009014361515,
+  "epoch": 0.004097437053123271,
   "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": 44.2834,
       "step": 35
+    },
+    {
+      "epoch": 0.0032779496424986173,
+      "grad_norm": 2.347105026245117,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.3563,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032779496424986173,
+      "eval_loss": 11.085442543029785,
+      "eval_runtime": 23.6199,
+      "eval_samples_per_second": 217.528,
+      "eval_steps_per_second": 108.764,
+      "step": 40
+    },
+    {
+      "epoch": 0.0036876933478109442,
+      "grad_norm": 2.081935167312622,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.3719,
+      "step": 45
+    },
+    {
+      "epoch": 0.004097437053123271,
+      "grad_norm": 2.254896640777588,
+      "learning_rate": 0.0,
+      "loss": 44.3704,
+      "step": 50
+    },
+    {
+      "epoch": 0.004097437053123271,
+      "eval_loss": 11.084413528442383,
+      "eval_runtime": 23.3204,
+      "eval_samples_per_second": 220.322,
+      "eval_steps_per_second": 110.161,
+      "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": 376147279872.0,
+  "total_flos": 482240102400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null