Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22abb3cb394e294386074b56d365fa86d3c86e65de4c4587d0d5850a3bf2747
+oid sha256:ca165a549e4279662208d1e1d060fbe8eca07866d965abeb6aa7a95535f3bdd0
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683c7103746e725d0f94cd18be9daf9481363c039a21118b78746ecf71e6f0c3
+oid sha256:8027c099d2c15aab7a5d30c8267d3411d22c5a3f353136a581c40c99f3ab8fcf
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de9c4b0a8f08ccbe4679f3211b5f5cb32a58695da285a9bc35e01eb7ef4c46f6
+oid sha256:93159e748760564f8ab001b1ac34d31130729a4daae6ec52572e87ec6f8cc715
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024531850519257502,
+  "epoch": 0.0036797775778886254,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.0001963525491562421,
       "loss": 2.3264,
       "step": 18
+    },
+    {
+      "epoch": 0.0025758443045220377,
+      "grad_norm": 1.6911269426345825,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 2.2865,
+      "step": 21
+    },
+    {
+      "epoch": 0.0029438220623109004,
+      "grad_norm": 0.7457146048545837,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 2.0923,
+      "step": 24
+    },
+    {
+      "epoch": 0.0029438220623109004,
+      "eval_loss": 2.2382869720458984,
+      "eval_runtime": 334.9773,
+      "eval_samples_per_second": 7.687,
+      "eval_steps_per_second": 3.845,
+      "step": 24
+    },
+    {
+      "epoch": 0.0033117998200997627,
+      "grad_norm": 0.9372111558914185,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 2.0104,
+      "step": 27
+    },
+    {
+      "epoch": 0.0036797775778886254,
+      "grad_norm": 0.9846737384796143,
+      "learning_rate": 0.0,
+      "loss": 1.9179,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9521684545536000.0,
+  "total_flos": 1.4282526818304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null