Training in progress, step 1042, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb5c823ef74dfadc52b27febc38a2ac3a875bb51704bb51249b3924e6ee6f2b
+oid sha256:e4dee753b9fd5e325d98ea73fa4a364829616b41c3c5b0874fed1e35477e96f8
 size 268858112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bbf0d8ee6289b2e585cda8bdd7541a68981e8fbe801a50960d7cef7275b8b9
+oid sha256:9ac8d611eadf762b6417b8fc45f0f3bd33ee0cd4b6a0553f1069d9d3b34fe36c
 size 137668197

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfad65ecdebf4d2a4ef23aa53c40f8dd23f710c224d047e20d32dc51c4015de2
+oid sha256:53371309ce8a2079e2c22bdc9bc5a9a1a2387150aad0de6421e37a4c6f73ba93
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9596928982725528,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1042,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,6 +1408,62 @@
       "learning_rate": 0.0001,
       "loss": 0.2554,
       "step": 1000
+    },
+    {
+      "epoch": 0.9644913627639156,
+      "grad_norm": 0.1351858526468277,
+      "learning_rate": 0.0001,
+      "loss": 0.2633,
+      "step": 1005
+    },
+    {
+      "epoch": 0.9692898272552783,
+      "grad_norm": 0.1442970633506775,
+      "learning_rate": 0.0001,
+      "loss": 0.2579,
+      "step": 1010
+    },
+    {
+      "epoch": 0.974088291746641,
+      "grad_norm": 0.1590578258037567,
+      "learning_rate": 0.0001,
+      "loss": 0.2843,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9788867562380038,
+      "grad_norm": 0.15692369639873505,
+      "learning_rate": 0.0001,
+      "loss": 0.2669,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9836852207293666,
+      "grad_norm": 0.13090096414089203,
+      "learning_rate": 0.0001,
+      "loss": 0.2589,
+      "step": 1025
+    },
+    {
+      "epoch": 0.9884836852207294,
+      "grad_norm": 0.1544967144727707,
+      "learning_rate": 0.0001,
+      "loss": 0.2686,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9932821497120922,
+      "grad_norm": 0.14533308148384094,
+      "learning_rate": 0.0001,
+      "loss": 0.2666,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9980806142034548,
+      "grad_norm": 0.13683825731277466,
+      "learning_rate": 0.0001,
+      "loss": 0.2695,
+      "step": 1040
     }
   ],
   "logging_steps": 5,
@@ -1422,12 +1478,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.323888912649138e+17,
+  "total_flos": 3.461829523913416e+17,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null