Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c722c7e6ad69b33e8930f3d6306deb3ed03fbe3d3e954fcbeca754f361557ef
+oid sha256:d168701ff5fb8067fea9e13e7fa259f4c444e6af60c3058729ba89b011dec53a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d98ad2b30003fed948619cf52886aaac79622688402f5a78a8290e41440441
+oid sha256:12ef72062c1393e56405f826bffdd370d66766c8fe0f352e3a54cf14cdd03545
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185f5a451f9abc72729e973512be4f639b0b150a8950a48ddb47a15c2cc0c531
+oid sha256:317794345936cd47f7a3a54e3f8c8b54036a873d685eff898bd380a2a827db47
 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": 0.00523209015293802,
+  "epoch": 0.006707807888382077,
   "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": 6.4626,
       "step": 35
+    },
+    {
+      "epoch": 0.005366246310705662,
+      "grad_norm": 4.602436065673828,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.2598,
+      "step": 40
+    },
+    {
+      "epoch": 0.005366246310705662,
+      "eval_loss": 1.5123776197433472,
+      "eval_runtime": 207.4951,
+      "eval_samples_per_second": 15.128,
+      "eval_steps_per_second": 7.566,
+      "step": 40
+    },
+    {
+      "epoch": 0.006037027099543869,
+      "grad_norm": 7.203092575073242,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.7316,
+      "step": 45
+    },
+    {
+      "epoch": 0.006707807888382077,
+      "grad_norm": 11.299540519714355,
+      "learning_rate": 0.0,
+      "loss": 5.535,
+      "step": 50
+    },
+    {
+      "epoch": 0.006707807888382077,
+      "eval_loss": 1.5105700492858887,
+      "eval_runtime": 207.9992,
+      "eval_samples_per_second": 15.091,
+      "eval_steps_per_second": 7.548,
+      "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": 7145279736250368.0,
+  "total_flos": 9205575120322560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null