Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a686cce172d17a8c1539406b3cd60e2e463eda551f2d97d7bf8baff61fb1fed
+oid sha256:db25e0a9ba5f133eef9e5a6815c1af1b3c21b0e72f6402a92fa9de3802e239a2
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33573aa695d9d3eb958949d8b47d79e854db28f500ceea94500dbeb8118ed995
+oid sha256:36f012f2e470c209cfc7696d76d9bbd4ff812fdbc60c4f05b49a05405b767f4b
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b663b5eda4d0da2dcb843509e2c21a870da154750c8ea7d398f43a7e0cf8632
+oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
 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": 0.000487685930260912,
+  "epoch": 0.000975371860521824,
   "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": 37.463,
       "eval_steps_per_second": 18.739,
       "step": 3
+    },
+    {
+      "epoch": 0.0006502479070145493,
+      "grad_norm": 1.5361990928649902,
+      "learning_rate": 8e-05,
+      "loss": 8.7738,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008128098837681866,
+      "grad_norm": 1.0650941133499146,
+      "learning_rate": 0.0001,
+      "loss": 7.3005,
+      "step": 5
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "grad_norm": 1.2282767295837402,
+      "learning_rate": 0.00012,
+      "loss": 7.6635,
+      "step": 6
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "eval_loss": 2.0658681392669678,
+      "eval_runtime": 69.579,
+      "eval_samples_per_second": 37.238,
+      "eval_steps_per_second": 18.626,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 489743409217536.0,
+  "total_flos": 979486818435072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null