Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902c658ff614e8a6f79159a8b2a853b46097f89740c2f500993a6543a309027d
+oid sha256:070e9047813199e58d5bbac097593f9d1efbc798c1aaf02fd3ec644574ffdc06
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05ebf3b04fa14148c71d8991b7eaad221d8896e8e24dca8612ea8bdad63c993
+oid sha256:aeb0fdd2af9056795ae9699aeaa9a03650af351bd5fa9fa101d1978f44db5902
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38df829ab74f8ff37df815bbd9bba3b8110af7cddffe5b95e2567b635d18af11
+oid sha256:8b453903d08153f576c10e1892a0535fb09ece105a29e0721c2e414bf14170ba
 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": 0.0004736717454803821,
+  "epoch": 0.0009473434909607642,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 27.911,
       "eval_steps_per_second": 13.961,
       "step": 3
+    },
+    {
+      "epoch": 0.0006315623273071762,
+      "grad_norm": 0.21612311899662018,
+      "learning_rate": 8e-05,
+      "loss": 1.0022,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007894529091339702,
+      "grad_norm": 0.3548424541950226,
+      "learning_rate": 0.0001,
+      "loss": 1.4068,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009473434909607642,
+      "grad_norm": 0.2541038393974304,
+      "learning_rate": 0.00012,
+      "loss": 1.0515,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009473434909607642,
+      "eval_loss": 1.0915995836257935,
+      "eval_runtime": 99.2772,
+      "eval_samples_per_second": 26.864,
+      "eval_steps_per_second": 13.437,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 121501189668864.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null