Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590c596111d09f05d064a98572d3be2382f4b464f1379fa1d3bfa3ad681f83cb
+oid sha256:abd0355940898ebbd1a0325c2b54948920c8b71414deb399f34b3085f4552906
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351a8c4ab85c457f285ed90379d0797d91dcfd4ab3d7e80c79e888a1a641352b
+oid sha256:61d32db7cb61732763b4c9000b7edef4709312a7d001e48e35bbca290a50c3e5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b21fb67f5f4512660437b010e40e50275600c45b564c27a08b826c53f80548
+oid sha256:7aea207963bba17accdf021f1b35d9a5835bf7061400ff116aa71013feec46be
 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": 0.00014019428591456327,
+  "epoch": 0.0002102914288718449,
   "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": 19.095,
       "eval_steps_per_second": 9.548,
       "step": 6
+    },
+    {
+      "epoch": 0.00016356000023365715,
+      "grad_norm": 1.1779074668884277,
+      "learning_rate": 0.00014,
+      "loss": 3.1902,
+      "step": 7
+    },
+    {
+      "epoch": 0.000186925714552751,
+      "grad_norm": 1.1536974906921387,
+      "learning_rate": 0.00016,
+      "loss": 3.2861,
+      "step": 8
+    },
+    {
+      "epoch": 0.0002102914288718449,
+      "grad_norm": 1.2713385820388794,
+      "learning_rate": 0.00018,
+      "loss": 3.4101,
+      "step": 9
+    },
+    {
+      "epoch": 0.0002102914288718449,
+      "eval_loss": 0.7832401990890503,
+      "eval_runtime": 1120.8965,
+      "eval_samples_per_second": 16.077,
+      "eval_steps_per_second": 8.039,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628733135912960.0,
+  "total_flos": 2443099703869440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null