Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bed601b6a4b0e5b8478bf96683610cf809bc582506b6bcad340405f4117a03f
+oid sha256:0253ff711ef204baacaa2718fabc7c51423a24ffef027ddeb7ef5b3cedb7b783
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d989984c02868e4190a653e67fe531d4e5d20e70faf13a4e74cb0e20e648d6
+oid sha256:261d788ed9bfb8677e7ce0678565d41199f2afcad970f9ebfbb912bfbb027507
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0de3d8f3b1729f9e99699a9349a0004db7a133b95e4b3ff8dc08ea1c9aface8
+oid sha256:ac18a99e0aeed2cfa1a52dad241a4d9583a3fd1a40119e4a4fc39f21e1df86f5
 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": 0.20025673940949937,
+  "epoch": 0.25673940949935814,
   "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": 0.0286,
       "step": 35
+    },
+    {
+      "epoch": 0.20539152759948653,
+      "grad_norm": 0.6951243281364441,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.025,
+      "step": 40
+    },
+    {
+      "epoch": 0.20539152759948653,
+      "eval_loss": 0.027688663452863693,
+      "eval_runtime": 15.4394,
+      "eval_samples_per_second": 5.311,
+      "eval_steps_per_second": 2.656,
+      "step": 40
+    },
+    {
+      "epoch": 0.23106546854942234,
+      "grad_norm": 0.38530200719833374,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0153,
+      "step": 45
+    },
+    {
+      "epoch": 0.25673940949935814,
+      "grad_norm": 0.6311851739883423,
+      "learning_rate": 0.0,
+      "loss": 0.0215,
+      "step": 50
+    },
+    {
+      "epoch": 0.25673940949935814,
+      "eval_loss": 0.02496899664402008,
+      "eval_runtime": 15.4922,
+      "eval_samples_per_second": 5.293,
+      "eval_steps_per_second": 2.646,
+      "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": 1.4287883816927232e+16,
+  "total_flos": 1.8356925162848256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null