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:f8ce952ebf798655774ad1bf11ee5d08b7895c2e28e5e396fa83b1960f9eb178
+oid sha256:bbed9eb8da4c13207088f5c37cdccb7707d0370a23d37c77d1e1291ba99def30
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd62e1239e176cef1ae175948bc75322502d2b1a67fbe7b416c2aad0cc5a3f4
+oid sha256:9fa85ed2fb81c524f05d4547ea9efb5772eb26e67fd5b6d9dae7a98e2d154e25
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f005639ce0865eae9775065c9fed38932da15f22f9e96d8e1fc81a298bdf6ae
+oid sha256:ccefe07c55c3a71d889b8afe9c246ca4fe002fb51cf63fcb0e5c6615aebb4f78
 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": 0.0001196351129056378,
+  "epoch": 0.0002392702258112756,
   "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": 22.945,
       "eval_steps_per_second": 11.474,
       "step": 3
+    },
+    {
+      "epoch": 0.00015951348387418374,
+      "grad_norm": 35.35398483276367,
+      "learning_rate": 8e-05,
+      "loss": 10.4589,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019939185484272969,
+      "grad_norm": 37.92613220214844,
+      "learning_rate": 0.0001,
+      "loss": 7.7222,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002392702258112756,
+      "grad_norm": 36.25010299682617,
+      "learning_rate": 0.00012,
+      "loss": 4.6559,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002392702258112756,
+      "eval_loss": 3.3957276344299316,
+      "eval_runtime": 460.4612,
+      "eval_samples_per_second": 22.931,
+      "eval_steps_per_second": 11.467,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 786064805462016.0,
+  "total_flos": 1525890504720384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null