Training in progress, step 71, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0df244eb2f8332e926e805c277a6ffe69bc0f657965b1271cb385887c8171c
+oid sha256:01671e0696bc791f2cb203a9f8665b8ce23c4c5488c8f4671cf0103f445b1193
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf801bc99321e2d3c82853ff38a6cfef9b3ac10b1187af5e4cb577c3639a2f5d
+oid sha256:b41cdd80373983cf0a05312a373db8fbd2037aebc5350b758f7adb9c17b081aa
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a909c715180823565ad9db0e6325239110ff40066207a387cb9aadecb8ec8a
+oid sha256:93e1d2ed1657f3ff1bb614efce27feacbb4cdefa75aaf9d42964795ef4214f28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd52f72ba6b98f035e019b9f67412a4096a5905d83c8b9be59eb63847361da2b
+oid sha256:3e683effdbf1801ca21c52b8334cbe1684c23fef6e33fad16cce510e4700ea65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03400735294117647,
+  "epoch": 0.06525735294117647,
   "eval_steps": 55,
-  "global_step": 37,
+  "global_step": 71,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -99,6 +99,91 @@
       "learning_rate": 9.729729729729731e-05,
       "loss": 11.3811,
       "step": 36
+    },
+    {
+      "epoch": 0.035845588235294115,
+      "grad_norm": 1.9527369737625122,
+      "learning_rate": 9.91486549841951e-05,
+      "loss": 11.2562,
+      "step": 39
+    },
+    {
+      "epoch": 0.03860294117647059,
+      "grad_norm": 1.9870686531066895,
+      "learning_rate": 9.475816456775313e-05,
+      "loss": 10.7468,
+      "step": 42
+    },
+    {
+      "epoch": 0.04136029411764706,
+      "grad_norm": 2.22705340385437,
+      "learning_rate": 8.695044586103296e-05,
+      "loss": 11.1675,
+      "step": 45
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 1.8868488073349,
+      "learning_rate": 7.63216081438678e-05,
+      "loss": 10.5914,
+      "step": 48
+    },
+    {
+      "epoch": 0.046875,
+      "grad_norm": 1.6964952945709229,
+      "learning_rate": 6.368314950360415e-05,
+      "loss": 10.8578,
+      "step": 51
+    },
+    {
+      "epoch": 0.04963235294117647,
+      "grad_norm": 1.9597607851028442,
+      "learning_rate": 5e-05,
+      "loss": 10.8131,
+      "step": 54
+    },
+    {
+      "epoch": 0.050551470588235295,
+      "eval_loss": 2.1706061363220215,
+      "eval_runtime": 43.8837,
+      "eval_samples_per_second": 13.057,
+      "eval_steps_per_second": 6.54,
+      "step": 55
+    },
+    {
+      "epoch": 0.05238970588235294,
+      "grad_norm": 1.783805251121521,
+      "learning_rate": 3.631685049639586e-05,
+      "loss": 10.7253,
+      "step": 57
+    },
+    {
+      "epoch": 0.05514705882352941,
+      "grad_norm": 1.9075720310211182,
+      "learning_rate": 2.3678391856132204e-05,
+      "loss": 10.9743,
+      "step": 60
+    },
+    {
+      "epoch": 0.057904411764705885,
+      "grad_norm": 1.7084569931030273,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 10.8425,
+      "step": 63
+    },
+    {
+      "epoch": 0.06066176470588235,
+      "grad_norm": 1.9370617866516113,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 11.0226,
+      "step": 66
+    },
+    {
+      "epoch": 0.06341911764705882,
+      "grad_norm": 1.7810252904891968,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 11.1265,
+      "step": 69
     }
   ],
   "logging_steps": 3,
@@ -113,12 +198,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.520224872431616e+16,
+  "total_flos": 2.917188268720128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null