Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfd4e99cfb28bf233c7ce5d9000160eef6976c2ff68ef51281c303b6395d12b
+oid sha256:28d8c501d79a3bcf59bfd624d4d84b5f9eae91c9b56c1301b29e3de06ac57400
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a6e032022b30a178a505c2daa5e564650c9fec855ce8529fb0c8863da64df1
+oid sha256:cfe32c99cc425753325a78e9163c7af8daa1e3bb9656b385338160a6b359eccf
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c432173c3e03ab35f379f99e76ec96a95398876df77ad2334860facd5d9a0fd
+oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
 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": 0.007104795737122558,
+  "epoch": 0.010657193605683837,
   "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": 51.451,
       "eval_steps_per_second": 25.725,
       "step": 6
+    },
+    {
+      "epoch": 0.008288928359976317,
+      "grad_norm": 0.8361874222755432,
+      "learning_rate": 0.00014,
+      "loss": 1.8913,
+      "step": 7
+    },
+    {
+      "epoch": 0.009473060982830076,
+      "grad_norm": 0.7909893989562988,
+      "learning_rate": 0.00016,
+      "loss": 1.813,
+      "step": 8
+    },
+    {
+      "epoch": 0.010657193605683837,
+      "grad_norm": 0.801120400428772,
+      "learning_rate": 0.00018,
+      "loss": 1.7999,
+      "step": 9
+    },
+    {
+      "epoch": 0.010657193605683837,
+      "eval_loss": 1.5673933029174805,
+      "eval_runtime": 6.7071,
+      "eval_samples_per_second": 53.078,
+      "eval_steps_per_second": 26.539,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 71230531043328.0,
+  "total_flos": 120201521135616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null