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:b310e41f6b8aea952d721246436b7ff679bf3abcb9b4cfdee0fa87f87ce4a7a5
+oid sha256:604cbb2f5ace586d306163e7d7f7eff831f2f32e5fd62470eadf585f49d25b91
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaaa5c47cc34fcea46b6b705f522ea432c930bb8e9a8bb51b99fdd630d9db691
+oid sha256:1c34c8afa719505f584fab7d850dec671aa1513eb597804f4e660ef50b1c44c7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457548b77ed5d7703d69eacdc9aca9fe710c41943f0b7a77991d95d5848083b0
+oid sha256:8e88192bf334b9c7faf9c721400914bbaf7bfe8e40a198b1bf1017b765e863a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007979413114165454,
+  "epoch": 0.0011969119671248179,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 7.918,
       "eval_steps_per_second": 1.98,
       "step": 20
+    },
+    {
+      "epoch": 0.0008378383769873726,
+      "grad_norm": 51.12168884277344,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 2.8433,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008777354425581999,
+      "grad_norm": 42.92367935180664,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 3.4061,
+      "step": 22
+    },
+    {
+      "epoch": 0.0009176325081290271,
+      "grad_norm": 48.67538833618164,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 2.5314,
+      "step": 23
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "grad_norm": 40.84886169433594,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 4.1212,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "eval_loss": 2.49723744392395,
+      "eval_runtime": 1332.7969,
+      "eval_samples_per_second": 7.919,
+      "eval_steps_per_second": 1.98,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009974266392706816,
+      "grad_norm": 47.290653228759766,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 2.9426,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010373237048415089,
+      "grad_norm": 43.36201095581055,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 1.5726,
+      "step": 26
+    },
+    {
+      "epoch": 0.0010772207704123362,
+      "grad_norm": 42.42373275756836,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 1.8358,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011171178359831635,
+      "grad_norm": 37.12969970703125,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 3.81,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011171178359831635,
+      "eval_loss": 2.1374239921569824,
+      "eval_runtime": 1332.1784,
+      "eval_samples_per_second": 7.922,
+      "eval_steps_per_second": 1.981,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011570149015539908,
+      "grad_norm": 44.4539680480957,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 1.3792,
+      "step": 29
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "grad_norm": 41.076271057128906,
+      "learning_rate": 0.0,
+      "loss": 1.1189,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null