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:c7e27f98ce6dc9dbb29ecae0ec44a4c5f12b6065d9ced4449f4574ab71fa4209
+oid sha256:ba33cc2a69f6ad4b1e9774cd56d8fed84e528c2fe481020072d1801a45bdc708
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21e81e321de57d893fe9b743b5962a5d10abfe50d838e5b4eb5967e50981805
+oid sha256:74d7551799b83ce2b4ab3afd3c7d13a1624bdaba1b45fc11f78caeb1180b5889
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6741176ba9bac623634dac7e5dea2b0fd80a22b3694da9c30b1d723141dd6551
+oid sha256:0acf01d000880525c60a0a79697850b59f86942a263d1be11dbe378d8315f24d
 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": 0.0018759086432490737,
+  "epoch": 0.0028138629648736106,
   "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": 7.905,
       "eval_steps_per_second": 1.977,
       "step": 20
+    },
+    {
+      "epoch": 0.0019697040754115274,
+      "grad_norm": 2.2492661476135254,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 1.9397,
+      "step": 21
+    },
+    {
+      "epoch": 0.002063499507573981,
+      "grad_norm": 2.5874478816986084,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 2.4379,
+      "step": 22
+    },
+    {
+      "epoch": 0.0021572949397364346,
+      "grad_norm": 2.168783187866211,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 2.5954,
+      "step": 23
+    },
+    {
+      "epoch": 0.0022510903718988887,
+      "grad_norm": 1.9641475677490234,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 2.2953,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022510903718988887,
+      "eval_loss": 2.123440980911255,
+      "eval_runtime": 568.41,
+      "eval_samples_per_second": 7.899,
+      "eval_steps_per_second": 1.976,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023448858040613424,
+      "grad_norm": 2.4187934398651123,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 1.7173,
+      "step": 25
+    },
+    {
+      "epoch": 0.002438681236223796,
+      "grad_norm": 1.4847743511199951,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.83,
+      "step": 26
+    },
+    {
+      "epoch": 0.0025324766683862496,
+      "grad_norm": 3.2388100624084473,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 2.4771,
+      "step": 27
+    },
+    {
+      "epoch": 0.0026262721005487033,
+      "grad_norm": 2.044548273086548,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 1.4278,
+      "step": 28
+    },
+    {
+      "epoch": 0.0026262721005487033,
+      "eval_loss": 2.120626211166382,
+      "eval_runtime": 567.8072,
+      "eval_samples_per_second": 7.908,
+      "eval_steps_per_second": 1.978,
+      "step": 28
+    },
+    {
+      "epoch": 0.002720067532711157,
+      "grad_norm": 2.0032973289489746,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 2.2627,
+      "step": 29
+    },
+    {
+      "epoch": 0.0028138629648736106,
+      "grad_norm": 2.9637610912323,
+      "learning_rate": 0.0,
+      "loss": 2.4295,
+      "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": 8717175581835264.0,
+  "total_flos": 1.3539442924978176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null