Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd87f0847e09344045a25e17d3ade5b44bc8c2026cac0add69bcde206f8beaa6
+oid sha256:f2e1414169b0e33599c1f2306c2251aab3d3be4df46c976f6471f1cf36133248
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346b276a380a8aee9559e75c91a0b09fba4ed9fcdb5805569da99d5a629970bd
+oid sha256:1aa14df040f9a603025de02d94e9def5b76c063fb82b664d31e4b71d85e47ea6
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a1465b568049063c0707d9322eb5b7d29583306348c6dcd79a87cdb3bd71f9
+oid sha256:8b138580fd1455e247dfc8e822f1b487e5eb2e008976b6c875eb6f11c4c9bc8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.047244094488188976,
+  "epoch": 0.07086614173228346,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.836,
       "eval_steps_per_second": 4.918,
       "step": 6
+    },
+    {
+      "epoch": 0.05511811023622047,
+      "grad_norm": 5.364976406097412,
+      "learning_rate": 0.00014,
+      "loss": 7.5692,
+      "step": 7
+    },
+    {
+      "epoch": 0.06299212598425197,
+      "grad_norm": 6.0303497314453125,
+      "learning_rate": 0.00016,
+      "loss": 7.0766,
+      "step": 8
+    },
+    {
+      "epoch": 0.07086614173228346,
+      "grad_norm": 6.065710067749023,
+      "learning_rate": 0.00018,
+      "loss": 5.7276,
+      "step": 9
+    },
+    {
+      "epoch": 0.07086614173228346,
+      "eval_loss": 5.128417015075684,
+      "eval_runtime": 5.5492,
+      "eval_samples_per_second": 9.731,
+      "eval_steps_per_second": 4.866,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1045581627654144.0,
+  "total_flos": 1568372441481216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null