Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997f59dac049ace08d3c2aa9b2616dc078885922ef74c835f895dadceaa9adbd
+oid sha256:225569657199feda7d7475300d8f83d66df59c17bfdea8ee3c0517e3b6b73490
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e20290954ade71a5ee82bc3736c650c7bea48ac9697a1d6b4485f58c5ab7cf
+oid sha256:1e955c01de5877ee883c324f977eabcda489a7a061944e72e1a48ba15e703954
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb741ceb2611e708b8beae9bffd57a8e55c445dd3ca6820048f715cbcf26250
+oid sha256:dad5ca413a28a04500ccdf7fb740f3879efead86332719f7e40c744246e58702
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010291771728503062,
+  "epoch": 0.0020583543457006123,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 11.195,
       "eval_steps_per_second": 5.598,
       "step": 15
+    },
+    {
+      "epoch": 0.0012350126074203674,
+      "grad_norm": 0.7983511686325073,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.7473,
+      "step": 18
+    },
+    {
+      "epoch": 0.0013722362304670749,
+      "eval_loss": 2.6068038940429688,
+      "eval_runtime": 548.4556,
+      "eval_samples_per_second": 11.19,
+      "eval_steps_per_second": 5.596,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014408480419904287,
+      "grad_norm": 0.8311195373535156,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.606,
+      "step": 21
+    },
+    {
+      "epoch": 0.00164668347656049,
+      "grad_norm": 0.7099039554595947,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.6212,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017152952880838436,
+      "eval_loss": 2.561319351196289,
+      "eval_runtime": 548.4564,
+      "eval_samples_per_second": 11.19,
+      "eval_steps_per_second": 5.596,
+      "step": 25
+    },
+    {
+      "epoch": 0.001852518911130551,
+      "grad_norm": 0.6791161298751831,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.6852,
+      "step": 27
+    },
+    {
+      "epoch": 0.0020583543457006123,
+      "grad_norm": 0.9040237069129944,
+      "learning_rate": 0.0,
+      "loss": 2.6256,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020583543457006123,
+      "eval_loss": 2.549128770828247,
+      "eval_runtime": 548.3967,
+      "eval_samples_per_second": 11.191,
+      "eval_steps_per_second": 5.596,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6378728076607488.0,
+  "total_flos": 1.2407936806551552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null