Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092f436d4f62136a8d834e9904cd3881f3abc8263ed2598732b1dec29c8a553b
+oid sha256:7286a2b298d14b748bb239d6149094c7bee2312d74d025d96e4d3b1f971075d3
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7298b173a690f25ca036382c6168428b4f071babb3896bd09e7673963d5ca3a
+oid sha256:95d3896af151b026c8f33e9a1dd7ba11b6e7c0043c98cd63cfda9182ee380cfa
 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": 0.003235198964736331,
+  "epoch": 0.006470397929472662,
   "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": 2.1188,
       "step": 5
+    },
+    {
+      "epoch": 0.0038822387576835974,
+      "grad_norm": 2.7621817588806152,
+      "learning_rate": 0.00012,
+      "loss": 2.1992,
+      "step": 6
+    },
+    {
+      "epoch": 0.0038822387576835974,
+      "eval_loss": 1.9894273281097412,
+      "eval_runtime": 197.5555,
+      "eval_samples_per_second": 3.295,
+      "eval_steps_per_second": 1.65,
+      "step": 6
+    },
+    {
+      "epoch": 0.004529278550630864,
+      "grad_norm": 2.016754150390625,
+      "learning_rate": 0.00014,
+      "loss": 1.9136,
+      "step": 7
+    },
+    {
+      "epoch": 0.00517631834357813,
+      "grad_norm": 2.454011917114258,
+      "learning_rate": 0.00016,
+      "loss": 2.1053,
+      "step": 8
+    },
+    {
+      "epoch": 0.005823358136525397,
+      "grad_norm": 2.2127492427825928,
+      "learning_rate": 0.00018,
+      "loss": 1.7395,
+      "step": 9
+    },
+    {
+      "epoch": 0.005823358136525397,
+      "eval_loss": 1.4898217916488647,
+      "eval_runtime": 197.4151,
+      "eval_samples_per_second": 3.298,
+      "eval_steps_per_second": 1.651,
+      "step": 9
+    },
+    {
+      "epoch": 0.006470397929472662,
+      "grad_norm": 2.3387913703918457,
+      "learning_rate": 0.0002,
+      "loss": 1.5252,
+      "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