Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a9ee090ad760e99b3700928e3c68e317052b0f6909ba8679a5d153896f54d1
+oid sha256:cfa4dbcb618f9ee6c50825eadf051314911b104e1986cfb9e998364430f0178c
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51d552ac66bf3dcfe3c5d89168b878810e29e21bc85031d478f0fb1277ccba3
+oid sha256:9fef9433341957a499f12b38e1e401ef4cd3661d2ae8b2fa098f19d8eacf3618
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
+oid sha256:01ae0673394c6d0448d87a05b8dce85b58d04fafa4d6c418a5ee6c92aeaab53d
 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": 0.005274725274725275,
+  "epoch": 0.007912087912087912,
   "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": 4.671,
       "eval_steps_per_second": 2.341,
       "step": 6
+    },
+    {
+      "epoch": 0.006153846153846154,
+      "grad_norm": 0.7527095079421997,
+      "learning_rate": 0.00014,
+      "loss": 1.0641,
+      "step": 7
+    },
+    {
+      "epoch": 0.007032967032967033,
+      "grad_norm": 0.7447927594184875,
+      "learning_rate": 0.00016,
+      "loss": 0.9921,
+      "step": 8
+    },
+    {
+      "epoch": 0.007912087912087912,
+      "grad_norm": 0.8400495648384094,
+      "learning_rate": 0.00018,
+      "loss": 1.0762,
+      "step": 9
+    },
+    {
+      "epoch": 0.007912087912087912,
+      "eval_loss": 1.0189640522003174,
+      "eval_runtime": 99.2662,
+      "eval_samples_per_second": 4.825,
+      "eval_steps_per_second": 2.418,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 432572580495360.0,
+  "total_flos": 648858870743040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null