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:c9152c08f9e34aab44cf3c55615d38f4b384a0cb4c42877459d86ce58c8fea6a
+oid sha256:8756084e55e6fe04b8bf2e9e6ba9752b617254028e0d1494d9e59362294d9065
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e942cade6abe21da1e371d6af953eddea582e97872c764af1375fdb155cefb
+oid sha256:087c73cd358ebbe5e36ff64f73c94beedd748e32751880fc82c50ccaae6847d3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271ea2a12453046086fac6921baec0abf2f1b8633dd0656d5f44d34a1c9945bd
+oid sha256:31d31eabc2745a2c0cb96acaec7a168ad77c4cb99cee13197df1ec8bafb332bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.050933786078098474,
+  "epoch": 0.06791171477079797,
   "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": 29.641,
       "eval_steps_per_second": 14.821,
       "step": 150
+    },
+    {
+      "epoch": 0.05432937181663837,
+      "grad_norm": 1.7373266220092773,
+      "learning_rate": 0.0002,
+      "loss": 3.1273,
+      "step": 160
+    },
+    {
+      "epoch": 0.057724957555178265,
+      "grad_norm": 1.8070378303527832,
+      "learning_rate": 0.0002,
+      "loss": 2.9833,
+      "step": 170
+    },
+    {
+      "epoch": 0.06112054329371817,
+      "grad_norm": 1.3839212656021118,
+      "learning_rate": 0.0002,
+      "loss": 2.9064,
+      "step": 180
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 1.4498240947723389,
+      "learning_rate": 0.0002,
+      "loss": 2.9683,
+      "step": 190
+    },
+    {
+      "epoch": 0.06791171477079797,
+      "grad_norm": 1.7179659605026245,
+      "learning_rate": 0.0002,
+      "loss": 3.0199,
+      "step": 200
+    },
+    {
+      "epoch": 0.06791171477079797,
+      "eval_loss": 3.0113234519958496,
+      "eval_runtime": 41.8344,
+      "eval_samples_per_second": 29.641,
+      "eval_steps_per_second": 14.82,
+      "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": 2.917687601450189e+16,
+  "total_flos": 3.907204474208256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null