Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e43d6d5883c6e405ab763c54b77b09403de689500e3c5a4449a17c605cb8fb1
+oid sha256:6e6951f5b6175d14b7d614bbce6929619d9cf30d6d20d54326aa56b20ddbeb4b
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1864703aea5625377248a418a56cf5af58afba9add15606aef291917de466f34
+oid sha256:6c306a3827a197b1ca828f33365b5de56fe798f71b75b5a49bb3a17dbdeda00b
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c89db017fa9ddc5e9dc27f58a34fa74d457c810061d28b6ffc48e288f1a4f35
+oid sha256:eeb8c4dc6cb76a5543d18a9fb3156b407bc6d7f8294b806ca5fe4cfa45f8f56a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05413208228076507,
+  "epoch": 0.07217610970768676,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 14.979,
       "eval_steps_per_second": 7.496,
       "step": 150
+    },
+    {
+      "epoch": 0.05593648502345724,
+      "grad_norm": 0.39626944065093994,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.1199,
+      "step": 155
+    },
+    {
+      "epoch": 0.057740887766149405,
+      "grad_norm": 0.5094817280769348,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.1201,
+      "step": 160
+    },
+    {
+      "epoch": 0.059545290508841574,
+      "grad_norm": 0.5557631254196167,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.1154,
+      "step": 165
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 0.6784803867340088,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.1254,
+      "step": 170
+    },
+    {
+      "epoch": 0.06315409599422592,
+      "grad_norm": 0.3143410086631775,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.115,
+      "step": 175
+    },
+    {
+      "epoch": 0.06495849873691809,
+      "grad_norm": 0.5348233580589294,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.1222,
+      "step": 180
+    },
+    {
+      "epoch": 0.06676290147961025,
+      "grad_norm": 0.29956620931625366,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.1101,
+      "step": 185
+    },
+    {
+      "epoch": 0.06856730422230242,
+      "grad_norm": 0.3928939998149872,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.1205,
+      "step": 190
+    },
+    {
+      "epoch": 0.07037170696499459,
+      "grad_norm": 0.42990320920944214,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.1136,
+      "step": 195
+    },
+    {
+      "epoch": 0.07217610970768676,
+      "grad_norm": 0.6331201791763306,
+      "learning_rate": 0.0,
+      "loss": 0.124,
+      "step": 200
+    },
+    {
+      "epoch": 0.07217610970768676,
+      "eval_loss": 0.11012110859155655,
+      "eval_runtime": 77.7727,
+      "eval_samples_per_second": 15.005,
+      "eval_steps_per_second": 7.509,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -263,12 +341,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.773278842997965e+16,
+  "total_flos": 3.698847801724109e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null