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:df01b4badd5bf49732de3d91bc9ce56912d5638dc1c1078870379f0c3f43d635
+oid sha256:be97b6edf632530b581b1785612d77c06d017d9614ef490ffc2a998dbe2b9d3b
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e834aa01f2d094c80faea2a9bdd473a0e4e4a7d27877f375db9bb7ce583ad63f
+oid sha256:7c30133e73997305d99638f7e81b9839dc9202e7af07a0daaadcc6a97ac7e37a
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb497c5af9b6223634e749c7d63309d8d92eeb3a62f62e4e43c4a9a53c5796c6
+oid sha256:68c53ce31d82a209ba4636a55a590b66756b12ed145c1738d3c2fcbe19cedf9a
 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": 0.14285714285714285,
+  "epoch": 0.2857142857142857,
   "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": 0.9874,
       "step": 5
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.47366198897361755,
+      "learning_rate": 0.00012,
+      "loss": 0.9999,
+      "step": 6
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "eval_loss": 0.9416729211807251,
+      "eval_runtime": 2.2027,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 3.632,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4642522633075714,
+      "learning_rate": 0.00014,
+      "loss": 0.8724,
+      "step": 7
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.4463908076286316,
+      "learning_rate": 0.00016,
+      "loss": 0.8857,
+      "step": 8
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.41220560669898987,
+      "learning_rate": 0.00018,
+      "loss": 0.7828,
+      "step": 9
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "eval_loss": 0.8490126132965088,
+      "eval_runtime": 2.1982,
+      "eval_samples_per_second": 6.824,
+      "eval_steps_per_second": 3.639,
+      "step": 9
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.5196864604949951,
+      "learning_rate": 0.0002,
+      "loss": 0.927,
+      "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": 967722569564160.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null