Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8463a52fc319432bff67aa1baeca3f850561ca7dc04f7fb3417896f2a9aeb66d
+oid sha256:02673018e5d7b5abad9d584e3717b31c81f89dc682431450cf1ab30c89434172
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090ae4b2d2868b79814301a171dc89d09736459dc0e80fc3e52272e32eb53289
+oid sha256:84a4505ad3b1d96144581b024dd81adc5172e0c310f418790ae8871d7bd11236
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076cf7ea73e41f50981742cf2332d56b991f8a151f1cf84b5aea488c356fb0e9
+oid sha256:bb90fb543b3f66ab7a54839dbbe02ad0392c6b0211d46805d2e1fd19aa7de95e
 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": 0.008252658308205046,
+  "epoch": 0.010580331164365445,
   "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": 8.9482,
       "step": 35
+    },
+    {
+      "epoch": 0.008464264931492356,
+      "grad_norm": 4.832591533660889,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.9949,
+      "step": 40
+    },
+    {
+      "epoch": 0.008464264931492356,
+      "eval_loss": 2.2863879203796387,
+      "eval_runtime": 175.0829,
+      "eval_samples_per_second": 11.366,
+      "eval_steps_per_second": 5.683,
+      "step": 40
+    },
+    {
+      "epoch": 0.0095222980479289,
+      "grad_norm": 6.3857831954956055,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.4195,
+      "step": 45
+    },
+    {
+      "epoch": 0.010580331164365445,
+      "grad_norm": 4.938572406768799,
+      "learning_rate": 0.0,
+      "loss": 8.6652,
+      "step": 50
+    },
+    {
+      "epoch": 0.010580331164365445,
+      "eval_loss": 2.277858018875122,
+      "eval_runtime": 174.7334,
+      "eval_samples_per_second": 11.389,
+      "eval_steps_per_second": 5.694,
+      "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": 5941610411489280.0,
+  "total_flos": 7598059374692352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null