Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773d5be16d0b1f77ed94bc618da582a6b353963d7936b548eeafff4831feab4a
+oid sha256:68df85013375934e91caefaf6cc6f6fd84b5fe4ed9277117d59db102676792cc
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed098cf6f8f031b92dcdc55f0a7bd0550e9e02b192f45c6dde20deed66df1e6f
+oid sha256:3afefce42a5f385cba975fd58eaef69b4f38eb804fd247a0e82850a485f3e495
 size 14714004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.12249705535924617,
+  "epoch": 0.1570475068708284,
   "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": 105.294,
       "eval_steps_per_second": 52.745,
       "step": 39
+    },
+    {
+      "epoch": 0.12563800549666274,
+      "grad_norm": 0.8021316528320312,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4157,
+      "step": 40
+    },
+    {
+      "epoch": 0.12877895563407932,
+      "grad_norm": 0.7694814205169678,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.5601,
+      "step": 41
+    },
+    {
+      "epoch": 0.13191990577149587,
+      "grad_norm": 0.7779421210289001,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.5739,
+      "step": 42
+    },
+    {
+      "epoch": 0.13506085590891245,
+      "grad_norm": 0.7546217441558838,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.4719,
+      "step": 43
+    },
+    {
+      "epoch": 0.138201806046329,
+      "grad_norm": 0.7798016667366028,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4474,
+      "step": 44
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 0.840283215045929,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7683,
+      "step": 45
+    },
+    {
+      "epoch": 0.14448370632116214,
+      "grad_norm": 0.7780207991600037,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4508,
+      "step": 46
+    },
+    {
+      "epoch": 0.14762465645857872,
+      "grad_norm": 0.8037830591201782,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.6177,
+      "step": 47
+    },
+    {
+      "epoch": 0.15076560659599528,
+      "grad_norm": 0.7928768396377563,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.7592,
+      "step": 48
+    },
+    {
+      "epoch": 0.15390655673341186,
+      "grad_norm": 0.7950629591941833,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.6647,
+      "step": 49
+    },
+    {
+      "epoch": 0.1570475068708284,
+      "grad_norm": 0.737506091594696,
+      "learning_rate": 0.0,
+      "loss": 1.5088,
+      "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": 5849542759022592.0,
+  "total_flos": 7504614496665600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null