Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bb2099c48dd39eac1ddaaf3dc6af81394460d7e7a738336a3913f0183b45c1
+oid sha256:da81394b95ebd109865a4a2370b2b893fa42e9e60c7643b0183c694359ff5037
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208414e1d5606b2236ecb58c0055c62608cbb96ea40273f76f733691882a45b2
+oid sha256:79ca987a6f1d0f9c3b287ac2c2eb46fa4044d55ed2ef0a92cdcbbb93c06a2df1
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3faa6995019b380f926c9f7b20bf89b74419b1ffde988ba23f2a689051e46b9
+oid sha256:6ca92aaab0bb5a63fbc1aa638ed19e137102bd4f97cf3cecdc81a9ace9716d17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002823662289990117,
+  "epoch": 0.005647324579980234,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 2.7004,
       "step": 5
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "grad_norm": 1.2651362419128418,
+      "learning_rate": 0.00012,
+      "loss": 2.2558,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033883947479881405,
+      "eval_loss": 2.0722131729125977,
+      "eval_runtime": 216.6706,
+      "eval_samples_per_second": 3.443,
+      "eval_steps_per_second": 1.722,
+      "step": 6
+    },
+    {
+      "epoch": 0.003953127205986164,
+      "grad_norm": 1.5344648361206055,
+      "learning_rate": 0.00014,
+      "loss": 2.0793,
+      "step": 7
+    },
+    {
+      "epoch": 0.004517859663984188,
+      "grad_norm": 3.190638303756714,
+      "learning_rate": 0.00016,
+      "loss": 1.9202,
+      "step": 8
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "grad_norm": 2.3235151767730713,
+      "learning_rate": 0.00018,
+      "loss": 2.085,
+      "step": 9
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "eval_loss": 1.96136474609375,
+      "eval_runtime": 216.473,
+      "eval_samples_per_second": 3.446,
+      "eval_steps_per_second": 1.723,
+      "step": 9
+    },
+    {
+      "epoch": 0.005647324579980234,
+      "grad_norm": 1.474921464920044,
+      "learning_rate": 0.0002,
+      "loss": 1.4197,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1306268836823040.0,
+  "total_flos": 2612537673646080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null