Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125b149f67aaf987afdd2b913cedcc6a65d156a61e20f3c2eff5f407f4fea489
+oid sha256:dc05d25d5176b36120e4c36a074179848ff23a6172d7588ce388a8234dcf7782
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d0faa64298ab4c11103651f0cf310c99be508e96835c2cda6045f84ae5bd28
+oid sha256:53296cea240aa304242819905ba5087bf05193b9168e102846b8b17893cf9645
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874723cc0f15f7a6222b2ce8d237c217bdd9417b4f7ac5e951e49b54fd60b9e9
+oid sha256:6068d70357544e4f8bd1773d37bacfbd2333a446690d81affc20b7866b8a9f67
 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": 0.019895421502359394,
+  "epoch": 0.025506950644050504,
   "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": 10.793,
       "step": 35
+    },
+    {
+      "epoch": 0.020405560515240402,
+      "grad_norm": 229.1206512451172,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.203,
+      "step": 40
+    },
+    {
+      "epoch": 0.020405560515240402,
+      "eval_loss": 2.649484395980835,
+      "eval_runtime": 11.1489,
+      "eval_samples_per_second": 74.088,
+      "eval_steps_per_second": 37.044,
+      "step": 40
+    },
+    {
+      "epoch": 0.022956255579645455,
+      "grad_norm": 247.60263061523438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.5119,
+      "step": 45
+    },
+    {
+      "epoch": 0.025506950644050504,
+      "grad_norm": 233.02708435058594,
+      "learning_rate": 0.0,
+      "loss": 10.8377,
+      "step": 50
+    },
+    {
+      "epoch": 0.025506950644050504,
+      "eval_loss": 2.6493141651153564,
+      "eval_runtime": 11.0618,
+      "eval_samples_per_second": 74.671,
+      "eval_steps_per_second": 37.336,
+      "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": 220185215631360.0,
+  "total_flos": 283095277240320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null