Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed9ca6aca3e3d22f05c9dc40c0f7871eb19c4546f3942172a4ff51b92b7913e
+oid sha256:0a04f0c7f13be3b3a3511c50e0031cbf9f107a739ab4a94424045d762e0170a9
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9210e16dd760401fdcac0e3cfe8e27cf45a9d8d0fb84eebf3d8ab11af0b9b3a
+oid sha256:4b90d721341c7cc34f827b72df5cd552566df9509a10d37297e77a1a799b2b3b
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de67efb49eeb0cd60dd9f379af798cd40c1503e02cb34d3293f97d54c2e636a7
+oid sha256:c08cb012f68d5fb209b1b3dd6f8f55841816cbeb8f6f20b824d9cf9376e11d91
 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": 0.0005574394945881915,
+  "epoch": 0.0008361592418822874,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 37.578,
       "eval_steps_per_second": 18.789,
       "step": 6
+    },
+    {
+      "epoch": 0.0006503460770195569,
+      "grad_norm": 49.813106536865234,
+      "learning_rate": 0.00014,
+      "loss": 13.3381,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007432526594509221,
+      "grad_norm": 56.85946273803711,
+      "learning_rate": 0.00016,
+      "loss": 13.0585,
+      "step": 8
+    },
+    {
+      "epoch": 0.0008361592418822874,
+      "grad_norm": 59.996639251708984,
+      "learning_rate": 0.00018,
+      "loss": 13.6718,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008361592418822874,
+      "eval_loss": 3.4120981693267822,
+      "eval_runtime": 121.112,
+      "eval_samples_per_second": 37.42,
+      "eval_steps_per_second": 18.71,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 54830353612800.0,
+  "total_flos": 83342137491456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null