Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aba803942f648e1fc3d69dffd047244f4b5a1e4ff077327caa7163c5bb84720
+oid sha256:7f31b072a4f644c21137960d54fb6bba7f6c00e9c465a33a957d6ce71954fd57
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18df1a6af29e2dabc5f671683eaebfd3c40870430c6c948b490d20a868638662
+oid sha256:323cb8fa31ae08ee5bda4c9603d69f97fef557d314fc5f8651e8a9632256e148
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba73987568c30836825a978fecab9b15faa6043e7d4e8e74c5967b5c21e82d7
+oid sha256:e53cdd93f9bee1b725a165f35f02bfcd4b3549bed4a04b753dfda070552516fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16919739696312364,
+  "epoch": 0.21691973969631237,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 13.134,
       "eval_steps_per_second": 6.584,
       "step": 39
+    },
+    {
+      "epoch": 0.1735357917570499,
+      "grad_norm": 0.8120056390762329,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.101,
+      "step": 40
+    },
+    {
+      "epoch": 0.17787418655097614,
+      "grad_norm": 1.084051251411438,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 3.5951,
+      "step": 41
+    },
+    {
+      "epoch": 0.1822125813449024,
+      "grad_norm": 0.8113239407539368,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.2588,
+      "step": 42
+    },
+    {
+      "epoch": 0.18655097613882862,
+      "grad_norm": 0.8805438280105591,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 3.4257,
+      "step": 43
+    },
+    {
+      "epoch": 0.19088937093275488,
+      "grad_norm": 0.9256657958030701,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.4759,
+      "step": 44
+    },
+    {
+      "epoch": 0.19522776572668113,
+      "grad_norm": 0.9354608058929443,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5507,
+      "step": 45
+    },
+    {
+      "epoch": 0.19956616052060738,
+      "grad_norm": 0.8996797204017639,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.2725,
+      "step": 46
+    },
+    {
+      "epoch": 0.2039045553145336,
+      "grad_norm": 0.9552720189094543,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 3.4802,
+      "step": 47
+    },
+    {
+      "epoch": 0.20824295010845986,
+      "grad_norm": 0.9154345393180847,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 3.6361,
+      "step": 48
+    },
+    {
+      "epoch": 0.21258134490238612,
+      "grad_norm": 0.7522619962692261,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 3.4707,
+      "step": 49
+    },
+    {
+      "epoch": 0.21691973969631237,
+      "grad_norm": 0.7439150214195251,
+      "learning_rate": 0.0,
+      "loss": 3.2768,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.71990993920983e+16,
+  "total_flos": 1.117937171693568e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null