Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05da4c24ac4b7c4f2368e5abedb8673d7286fbd69139e2721f8a2205536410f1
+oid sha256:1bc701ffcdb1c9dc953b68604618c84f9d6126c42315341fe7bc2f9c9ec19dab
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec9c951cac743aa59ec473bf1926392d0ca681d13667bff8d1b405eabc1fdaa
+oid sha256:7f6ac507907ccc1c538614b2147dfdc2c30c1027507fdbdc78585a60cc82d5e0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bf4117ac4a9cc57e4e3f5625f417b55d8e841adc65edec97e866e352493250
+oid sha256:f41a60c160b469210da790763cb3d9680471c6efcd791d69930d3b519117e236
 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": 0.06008411776487082,
+  "epoch": 0.08011215701982775,
   "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": 40.282,
       "eval_steps_per_second": 20.141,
       "step": 150
+    },
+    {
+      "epoch": 0.06408972561586221,
+      "grad_norm": 1.4128129482269287,
+      "learning_rate": 0.0002,
+      "loss": 2.0029,
+      "step": 160
+    },
+    {
+      "epoch": 0.06809533346685359,
+      "grad_norm": 1.0108970403671265,
+      "learning_rate": 0.0002,
+      "loss": 2.0651,
+      "step": 170
+    },
+    {
+      "epoch": 0.07210094131784499,
+      "grad_norm": 1.4025979042053223,
+      "learning_rate": 0.0002,
+      "loss": 2.067,
+      "step": 180
+    },
+    {
+      "epoch": 0.07610654916883637,
+      "grad_norm": 1.2762507200241089,
+      "learning_rate": 0.0002,
+      "loss": 1.8669,
+      "step": 190
+    },
+    {
+      "epoch": 0.08011215701982775,
+      "grad_norm": 1.2802047729492188,
+      "learning_rate": 0.0002,
+      "loss": 1.9135,
+      "step": 200
+    },
+    {
+      "epoch": 0.08011215701982775,
+      "eval_loss": 1.9592642784118652,
+      "eval_runtime": 26.2011,
+      "eval_samples_per_second": 40.151,
+      "eval_steps_per_second": 20.076,
+      "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": 7613981860036608.0,
+  "total_flos": 1.0164478246649856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null