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:b5af3a07781f05de7535bdcf0582e305d5484ef5a3dd809c0985be305a58663d
+oid sha256:1bbe93bd745ef8684230b92ea4ea195c80c3857ad216f1918a529441149eaa2c
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5fe98bc3b6549d7fbd42ad73dcba05fcce41ebfa79595ae6e0215c34472adc
+oid sha256:7f7332ed51393a44959315d9d2e6595e4745f28c4cae7eae4b0c8408c21ed09f
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a730a343a863d4216549392bfe668d1a20b027b7071c0dc0f4c8937109e105f0
+oid sha256:0c5d32480fe2b55ccec5bc9dc6ed03aaa85fcf9703fb06e7c8e52b632b5ff929
 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": 0.004920452681646712,
+  "epoch": 0.006560603575528949,
   "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": 43.719,
       "eval_steps_per_second": 21.86,
       "step": 150
+    },
+    {
+      "epoch": 0.0052484828604231586,
+      "grad_norm": 26.385774612426758,
+      "learning_rate": 0.0002,
+      "loss": 1.588,
+      "step": 160
+    },
+    {
+      "epoch": 0.005576513039199606,
+      "grad_norm": 48.93403244018555,
+      "learning_rate": 0.0002,
+      "loss": 1.5966,
+      "step": 170
+    },
+    {
+      "epoch": 0.005904543217976054,
+      "grad_norm": 46.73294448852539,
+      "learning_rate": 0.0002,
+      "loss": 1.872,
+      "step": 180
+    },
+    {
+      "epoch": 0.0062325733967525014,
+      "grad_norm": 62.82195281982422,
+      "learning_rate": 0.0002,
+      "loss": 1.8653,
+      "step": 190
+    },
+    {
+      "epoch": 0.006560603575528949,
+      "grad_norm": 235.28477478027344,
+      "learning_rate": 0.0002,
+      "loss": 2.8933,
+      "step": 200
+    },
+    {
+      "epoch": 0.006560603575528949,
+      "eval_loss": 4.4589738845825195,
+      "eval_runtime": 293.3215,
+      "eval_samples_per_second": 43.761,
+      "eval_steps_per_second": 21.88,
+      "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": 1.041211453341696e+16,
+  "total_flos": 1.38119886667776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null