Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614720e79b355f15bcaf8d5ddee8de35ad8e25a04f86d48a78e9f0d868469067
+oid sha256:ddb850d5efce0bc612e4825dc5fc5d45066b831aee41273177681c9d0b0691c3
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b182fa4d93eea2118d709461648b46cfd60b0671ba2ab6cbe73ed01970187874
+oid sha256:33ce53c52ce06cba65799d10a260899879bed9e45dafd41d7144b33face532d8
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2972d332e3d5fa4abdd6b0429885a3ecc36eabdf15f91d3aebed7cea929537a
+oid sha256:9651cf822486034420437c791f4ec2317d0a774d1a54b1d0661a1c1cac338931
 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": 0.020942408376963352,
+  "epoch": 0.031413612565445025,
   "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": 7.955,
       "eval_steps_per_second": 1.994,
       "step": 20
+    },
+    {
+      "epoch": 0.02198952879581152,
+      "grad_norm": 0.5128723382949829,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 3.1497,
+      "step": 21
+    },
+    {
+      "epoch": 0.023036649214659685,
+      "grad_norm": 0.6108046174049377,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 3.3197,
+      "step": 22
+    },
+    {
+      "epoch": 0.024083769633507852,
+      "grad_norm": 0.45397162437438965,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 3.2883,
+      "step": 23
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "grad_norm": 0.5446158647537231,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 3.4563,
+      "step": 24
+    },
+    {
+      "epoch": 0.025130890052356022,
+      "eval_loss": 1.7306746244430542,
+      "eval_runtime": 50.6678,
+      "eval_samples_per_second": 7.954,
+      "eval_steps_per_second": 1.993,
+      "step": 24
+    },
+    {
+      "epoch": 0.02617801047120419,
+      "grad_norm": 0.4350343346595764,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 3.4126,
+      "step": 25
+    },
+    {
+      "epoch": 0.027225130890052355,
+      "grad_norm": 0.49152126908302307,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 3.5553,
+      "step": 26
+    },
+    {
+      "epoch": 0.028272251308900525,
+      "grad_norm": 0.38575446605682373,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 3.2485,
+      "step": 27
+    },
+    {
+      "epoch": 0.02931937172774869,
+      "grad_norm": 0.5538058280944824,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 3.663,
+      "step": 28
+    },
+    {
+      "epoch": 0.02931937172774869,
+      "eval_loss": 1.7304288148880005,
+      "eval_runtime": 50.7219,
+      "eval_samples_per_second": 7.945,
+      "eval_steps_per_second": 1.991,
+      "step": 28
+    },
+    {
+      "epoch": 0.030366492146596858,
+      "grad_norm": 0.5756243467330933,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 3.3005,
+      "step": 29
+    },
+    {
+      "epoch": 0.031413612565445025,
+      "grad_norm": 0.4113498628139496,
+      "learning_rate": 0.0,
+      "loss": 3.3099,
+      "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": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null