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:a25e5f6163481fecd314362d18afee8ac81132e7f6d2250ed11ed7387a912e5b
+oid sha256:936f1342f589a3913b1d56501ed8585e6f12b9c516841356b31bebe7b413703f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9a20784d1be2913d7af8982f1c16533ed601038f0424b9e772de812042f903
+oid sha256:1a080b1fe32e7af5eefdc99187c27aff96f7867710598f6c981e157feaeab493
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6523fa69959a6ab7a7833fbb02ba74fbc0ec8a21e9ada67420a5eacc365c9496
+oid sha256:819dac1b113dc714f1cd64b09efe98eac3ee828b415dee301e1006aa4da35ead
 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": 0.00264209741887406,
+  "epoch": 0.0033873043831718717,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.833,
       "step": 35
+    },
+    {
+      "epoch": 0.0027098435065374973,
+      "grad_norm": 0.7888218760490417,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8649,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027098435065374973,
+      "eval_loss": 1.938575267791748,
+      "eval_runtime": 479.4053,
+      "eval_samples_per_second": 12.966,
+      "eval_steps_per_second": 6.483,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030485739448546847,
+      "grad_norm": 0.7486097812652588,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1037,
+      "step": 45
+    },
+    {
+      "epoch": 0.0033873043831718717,
+      "grad_norm": 0.8270931839942932,
+      "learning_rate": 0.0,
+      "loss": 1.9445,
+      "step": 50
+    },
+    {
+      "epoch": 0.0033873043831718717,
+      "eval_loss": 1.9363861083984375,
+      "eval_runtime": 475.5221,
+      "eval_samples_per_second": 13.072,
+      "eval_steps_per_second": 6.536,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8138082691842048.0,
+  "total_flos": 1.0496277108228096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null