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:f4d2c93dc5e6fe1c8061e8407ae5586210c4af0b0962e99d588182e9b11af41d
+oid sha256:43da2a1eb2790fe62f293e01d8ada013a0d966df4f2ada2660b9a71af9f5002a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5234a04f78dd0b72e6ab48c05b348bc8f273c06f7b5ab51e050911896206e570
+oid sha256:39701fa216f95fd1e0171751e98aa83608c72ac9eb0c890e4ab69484314eeeed
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a85c74230107fa7712e9fba79705e62f241775a7bdb5cde899d6d3cfa910a86
+oid sha256:13893f254074b0dec5e8003565583ed9154abab49baf146f6045b5d48206e343
 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": 0.10526315789473684,
+  "epoch": 0.21052631578947367,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 1.2373,
       "step": 5
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 0.5380682349205017,
+      "learning_rate": 0.00012,
+      "loss": 1.3893,
+      "step": 6
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "eval_loss": 1.2157351970672607,
+      "eval_runtime": 15.0706,
+      "eval_samples_per_second": 6.635,
+      "eval_steps_per_second": 0.664,
+      "step": 6
+    },
+    {
+      "epoch": 0.14736842105263157,
+      "grad_norm": 0.6841205358505249,
+      "learning_rate": 0.00014,
+      "loss": 1.3356,
+      "step": 7
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.4957394599914551,
+      "learning_rate": 0.00016,
+      "loss": 1.2216,
+      "step": 8
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_loss": 1.2087069749832153,
+      "eval_runtime": 15.1596,
+      "eval_samples_per_second": 6.596,
+      "eval_steps_per_second": 0.66,
+      "step": 8
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 0.5728506445884705,
+      "learning_rate": 0.00018,
+      "loss": 1.2016,
+      "step": 9
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.4859888255596161,
+      "learning_rate": 0.0002,
+      "loss": 1.3764,
+      "step": 10
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.1915773153305054,
+      "eval_runtime": 15.0938,
+      "eval_samples_per_second": 6.625,
+      "eval_steps_per_second": 0.663,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -80,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4838612847820800.0,
+  "total_flos": 9677225695641600.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null