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:ad5210c2161fee9d3e90bcc7c275869f2b5841fe66c1effdcebbde45d3cdce5f
+oid sha256:792c84c469925b567550f27b70bf06b24a1203274508daadfc0d3212b0dd5f81
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be7f0566298e34c392cf874aec05701e628f7842a2c4137b701ca36cef012acb
+oid sha256:bde6ade44a6e5afe5d4c3966ed743a14fb7d9e5918d448466de180cf10194b02
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
+oid sha256:8a09ad7e826d10efce700906e00267beeb0fde82aeff880f7721e7c0c6d184a9
 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": 0.00598623166716552,
+  "epoch": 0.008979347500748278,
   "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": 69.254,
       "eval_steps_per_second": 17.326,
       "step": 20
+    },
+    {
+      "epoch": 0.0062855432505237955,
+      "grad_norm": 0.05960177257657051,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 10.3644,
+      "step": 21
+    },
+    {
+      "epoch": 0.006584854833882071,
+      "grad_norm": 0.050702810287475586,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 10.3665,
+      "step": 22
+    },
+    {
+      "epoch": 0.006884166417240347,
+      "grad_norm": 0.05289774015545845,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 10.3656,
+      "step": 23
+    },
+    {
+      "epoch": 0.007183478000598623,
+      "grad_norm": 0.061270881444215775,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 10.365,
+      "step": 24
+    },
+    {
+      "epoch": 0.007183478000598623,
+      "eval_loss": 10.365599632263184,
+      "eval_runtime": 19.9383,
+      "eval_samples_per_second": 70.568,
+      "eval_steps_per_second": 17.654,
+      "step": 24
+    },
+    {
+      "epoch": 0.0074827895839568994,
+      "grad_norm": 0.053589362651109695,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 10.3649,
+      "step": 25
+    },
+    {
+      "epoch": 0.007782101167315175,
+      "grad_norm": 0.05652034282684326,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 10.3647,
+      "step": 26
+    },
+    {
+      "epoch": 0.008081412750673452,
+      "grad_norm": 0.05931362509727478,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 10.3637,
+      "step": 27
+    },
+    {
+      "epoch": 0.008380724334031727,
+      "grad_norm": 0.055247027426958084,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 10.3635,
+      "step": 28
+    },
+    {
+      "epoch": 0.008380724334031727,
+      "eval_loss": 10.365592956542969,
+      "eval_runtime": 20.3235,
+      "eval_samples_per_second": 69.23,
+      "eval_steps_per_second": 17.32,
+      "step": 28
+    },
+    {
+      "epoch": 0.008680035917390003,
+      "grad_norm": 0.05701150745153427,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 10.3639,
+      "step": 29
+    },
+    {
+      "epoch": 0.008979347500748278,
+      "grad_norm": 0.055218130350112915,
+      "learning_rate": 0.0,
+      "loss": 10.3632,
+      "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": 1046048931840.0,
+  "total_flos": 1569073397760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null