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:ca816da92bd90cd0954e224090d9333aad65e6be928ea121da2cfae23a53b9ef
+oid sha256:17ebc2bbe593a3700786b8b8753bca09f11f7d0273e525f06569f0129ddf53ea
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b476ef20ddcb1980d54664c8af07eadb8595c45b2b8235b534ca4762ee859f
+oid sha256:00aed5b101ef60fe18fb2e863c6049f3be27a5fb18fb28d88cd8815322025dce
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba58db7a4cd44d949f7914b684133d8cfddbc29710a68668016a0017331fb50
+oid sha256:d66f33b1e5b2c0ef27fc599d33982d25847a4ce9cf07845c46b50ef9632d1f27
 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": 0.003076923076923077,
+  "epoch": 0.004615384615384616,
   "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": 67.38,
       "eval_steps_per_second": 33.69,
       "step": 6
+    },
+    {
+      "epoch": 0.0035897435897435897,
+      "grad_norm": 28.07773780822754,
+      "learning_rate": 0.00014,
+      "loss": 20.8542,
+      "step": 7
+    },
+    {
+      "epoch": 0.0041025641025641026,
+      "grad_norm": 24.7640323638916,
+      "learning_rate": 0.00016,
+      "loss": 17.5828,
+      "step": 8
+    },
+    {
+      "epoch": 0.004615384615384616,
+      "grad_norm": 29.232324600219727,
+      "learning_rate": 0.00018,
+      "loss": 18.9759,
+      "step": 9
+    },
+    {
+      "epoch": 0.004615384615384616,
+      "eval_loss": 3.9376187324523926,
+      "eval_runtime": 12.1491,
+      "eval_samples_per_second": 67.659,
+      "eval_steps_per_second": 33.83,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 179259385577472.0,
+  "total_flos": 268889078366208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null