Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cdcca758e4f51b86ca61d6dd0e1f205a4136be14bada11320e201462d69597d
+oid sha256:1666525d583366d295538c84ef9529168875a20d3ebe9824162516c748f871c5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ce688998528313f8a65f43827d8582ea44a8e07d8a071787455a2ff2b245bd
+oid sha256:68fc8db1ad4a1c07896120d18abd12339645e01333003defab3e257dfea73c72
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f388398ea994e40704f6497243bd60adc9aa3f265cb5542e356410fda11e77
+oid sha256:4362fcd5a37a292cbf977b943f0b3f947ac977ee861d18729b9f450b9c75768d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021052631578947368,
+  "epoch": 0.042105263157894736,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 0.4201,
       "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 1.294385552406311,
+      "learning_rate": 0.00012,
+      "loss": 0.3502,
+      "step": 6
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 0.14960011839866638,
+      "eval_runtime": 29.4235,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 1.699,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 0.3078320622444153,
+      "learning_rate": 0.00014,
+      "loss": 0.0808,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.6034978032112122,
+      "learning_rate": 0.00016,
+      "loss": 0.0923,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 0.5751827955245972,
+      "learning_rate": 0.00018,
+      "loss": 0.0495,
+      "step": 9
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "eval_loss": 0.04392697289586067,
+      "eval_runtime": 29.5398,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 1.693,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.9490816593170166,
+      "learning_rate": 0.0002,
+      "loss": 0.0434,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2794842929233920.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null