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:beba6214af6dcb3fe8505521ac0e7deac72ae5c47a48cfd8ff5dfb0dd3243def
+oid sha256:e4bb808df24dbec8c8de306ab0efee4e34596aa0a6828f2d3d0439ff945eee61
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ce4df190f1227d6737ad46a820ec48e24289ca3639a15847cccff79476e375
+oid sha256:d043245fbed614e487db1f99539a562d104b6550cec8b118e9ab352aeb472a4f
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb41e8375905d48dcd8901f6af72766406ea5e7650177eb1b957638273694f4
+oid sha256:b5833316299b94cb804acc4a3a7c611a4749a2ea2a1b97cff1db930ec5a6105a
 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": 0.0343112026076514,
+  "epoch": 0.0457482701435352,
   "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": 17.503,
       "eval_steps_per_second": 8.756,
       "step": 150
+    },
+    {
+      "epoch": 0.03659861611482816,
+      "grad_norm": 0.8852552771568298,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.2929,
+      "step": 160
+    },
+    {
+      "epoch": 0.038886029622004915,
+      "grad_norm": 0.8863615989685059,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.2717,
+      "step": 170
+    },
+    {
+      "epoch": 0.041173443129181676,
+      "grad_norm": 0.7533473372459412,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.2377,
+      "step": 180
+    },
+    {
+      "epoch": 0.04346085663635844,
+      "grad_norm": 0.8003175854682922,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.2844,
+      "step": 190
+    },
+    {
+      "epoch": 0.0457482701435352,
+      "grad_norm": 0.7734489440917969,
+      "learning_rate": 0.0,
+      "loss": 0.2607,
+      "step": 200
+    },
+    {
+      "epoch": 0.0457482701435352,
+      "eval_loss": 0.06249726563692093,
+      "eval_runtime": 105.2622,
+      "eval_samples_per_second": 17.49,
+      "eval_steps_per_second": 8.75,
+      "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": 5.096051048448e+16,
+  "total_flos": 6.794734731264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null