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:b66ad94752d62c7598ba4ec118ee026b855a5f494603e8fe6ab1f569316e32ca
+oid sha256:682c860bd236fb45100dd0a2248a8f937f13880f0ad2dde15e950250399b6ecf
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a927d8456f159ca3ef5617bf5b4c9ea624fe5a97a3204d854474ed3d41938e3
+oid sha256:ae7bbfc939adce7678b55470e194bcf4f45c9bc0d75555189bf266eefbbf8a18
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930d555ae32a6a3ef15da629b0dbf3a06900868465fc5e03b6b9434e4eae54f6
+oid sha256:2aca601cc331a87eee7a832e141a13869177225edb786e1de300173561df264a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010526315789473684,
+  "epoch": 0.017543859649122806,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 126.158,
       "eval_steps_per_second": 63.079,
       "step": 6
+    },
+    {
+      "epoch": 0.012280701754385965,
+      "grad_norm": 631.5029907226562,
+      "learning_rate": 0.00014,
+      "loss": 9.8423,
+      "step": 7
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 993.0007934570312,
+      "learning_rate": 0.00016,
+      "loss": 7.2848,
+      "step": 8
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 1311.847412109375,
+      "learning_rate": 0.00018,
+      "loss": 14.4826,
+      "step": 9
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "eval_loss": 2.4422192573547363,
+      "eval_runtime": 1.8963,
+      "eval_samples_per_second": 126.561,
+      "eval_steps_per_second": 63.281,
+      "step": 9
+    },
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 1083.43798828125,
+      "learning_rate": 0.0002,
+      "loss": 9.7772,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 28386247311360.0,
+  "total_flos": 48333340016640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null