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:fb344edabd63ddc12a811dd0dc7ebe951783ffbbc5909edf86659ba392691ee6
+oid sha256:0c4bff4913790b4b2c1ae767d8320a9d22e145a3d0dec4b4278a91c95a45b403
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00740efa23f1b6f2235d7ead66522ddd335f7ad6d8762407f0fb28cbc3c4a1fd
+oid sha256:b3e0e080ba619cdf70a554943d23937ea828cf67cf49f927ca2a29ac97890913
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea628ea87ba872adb1ae483ce29898ce3709771334d6844a2812c271e7106160
+oid sha256:d9037ef050576e5b15bb337e29bad99f6c8bae2a651ea8bb96cde0ace1146164
 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": 0.0008150291372916582,
+  "epoch": 0.0016300582745833164,
   "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": 1.3427,
       "step": 5
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "grad_norm": 0.9615749716758728,
+      "learning_rate": 0.00012,
+      "loss": 1.5318,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009780349647499898,
+      "eval_loss": 1.399588704109192,
+      "eval_runtime": 1318.9507,
+      "eval_samples_per_second": 1.958,
+      "eval_steps_per_second": 0.98,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011410407922083214,
+      "grad_norm": 0.9091509580612183,
+      "learning_rate": 0.00014,
+      "loss": 1.4637,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013040466196666532,
+      "grad_norm": 4.046209335327148,
+      "learning_rate": 0.00016,
+      "loss": 1.9125,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "grad_norm": 0.7425318956375122,
+      "learning_rate": 0.00018,
+      "loss": 1.3163,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014670524471249848,
+      "eval_loss": 1.2187490463256836,
+      "eval_runtime": 1319.7023,
+      "eval_samples_per_second": 1.957,
+      "eval_steps_per_second": 0.979,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016300582745833164,
+      "grad_norm": 0.7953963875770569,
+      "learning_rate": 0.0002,
+      "loss": 1.0503,
+      "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": 7418872835604480.0,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null