Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65dd7fdabcd8f041decff9145f6d5f320a45b99620e926c5e31bfd0933eb299
+oid sha256:3c7a6f6edeabec336202683807d27cf59811fd4d8c12ecb3f7288b8537eedc2f
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3dfa0b678f286f3b76414826e8329ded0fa28522a81a28a27b71d6d6865017
+oid sha256:dbc4db7136f606b8f086296a04b412b6f9983cbb3c17eb08de679769e23865fb
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd2e5f3e4558a8f89907cd145f31b241282f581b4fc141f9c7b4bff7123d98a
+oid sha256:1d26119094700b045e9c480a0c7cf82f1620d9eb1119abdd7291f7017ea443b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000947193937958797,
+  "epoch": 0.001894387875917594,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 22.542,
       "eval_steps_per_second": 11.271,
       "step": 3
+    },
+    {
+      "epoch": 0.0012629252506117293,
+      "grad_norm": 1.4192756414413452,
+      "learning_rate": 8e-05,
+      "loss": 2.7306,
+      "step": 4
+    },
+    {
+      "epoch": 0.0015786565632646618,
+      "grad_norm": 1.209413766860962,
+      "learning_rate": 0.0001,
+      "loss": 2.43,
+      "step": 5
+    },
+    {
+      "epoch": 0.001894387875917594,
+      "grad_norm": 1.26327645778656,
+      "learning_rate": 0.00012,
+      "loss": 2.498,
+      "step": 6
+    },
+    {
+      "epoch": 0.001894387875917594,
+      "eval_loss": 2.5173232555389404,
+      "eval_runtime": 59.6766,
+      "eval_samples_per_second": 22.354,
+      "eval_steps_per_second": 11.177,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 159080282849280.0,
+  "total_flos": 305923620864000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null