Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297065c2c96d50dbd1ea718b80f0d9fcdbb43875faab8daf01b83053b3840841
+oid sha256:e4097e59a1c53e9fcf435202e29fd4955549ef3dc568cef1212e843d1b3ec3b3
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9cb890737bafaccd8534e5d51bf13ca6fcec83b94f1636d9f7df0255b5c351e
+oid sha256:5bee8ed018f7dd567c434f88a3c083b64446dfbb571b028dfdea3ace989f6575
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6dab5ce8be281b2163660616a9f104911daee6f1d7649a7ed99e7b629a87678
+oid sha256:b0c78ffb2ece3ee48440663e83d05a5a837f51057fc8cd456cd95a980b500f8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014045930191726947,
+  "epoch": 0.018727906922302594,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 59.577,
       "eval_steps_per_second": 29.795,
       "step": 150
+    },
+    {
+      "epoch": 0.014982325537842078,
+      "grad_norm": 5.981997966766357,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 7.3475,
+      "step": 160
+    },
+    {
+      "epoch": 0.015918720883957207,
+      "grad_norm": 6.102133750915527,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 7.6612,
+      "step": 170
+    },
+    {
+      "epoch": 0.016855116230072336,
+      "grad_norm": 4.5994415283203125,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 7.8129,
+      "step": 180
+    },
+    {
+      "epoch": 0.017791511576187465,
+      "grad_norm": 6.005730628967285,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 7.5827,
+      "step": 190
+    },
+    {
+      "epoch": 0.018727906922302594,
+      "grad_norm": 5.3117547035217285,
+      "learning_rate": 0.0,
+      "loss": 8.1106,
+      "step": 200
+    },
+    {
+      "epoch": 0.018727906922302594,
+      "eval_loss": 1.9164881706237793,
+      "eval_runtime": 75.4722,
+      "eval_samples_per_second": 59.585,
+      "eval_steps_per_second": 29.799,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9826887322828800.0,
+  "total_flos": 1.30916339417088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null