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:a043732993f7c31cdf66025809eb944de5cad7cf74801b421b832fabf636bafa
+oid sha256:a3d1c1d483693fc0ba437659057239167ffff98088af49fe4b06f061b46e56ca
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066a500f14185f1c89daade1a45efdecf932058931c37bebcdbe6044807a69b0
+oid sha256:6eb44fe6db464c8c085ab429037a3bad53a962e45b7ce8ec5579f647361142bb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
+oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
 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": 0.0004099270671426375,
+  "epoch": 0.0006148906007139563,
   "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": 19.675,
       "eval_steps_per_second": 9.839,
       "step": 6
+    },
+    {
+      "epoch": 0.0004782482449997438,
+      "grad_norm": 2.577486276626587,
+      "learning_rate": 0.00014,
+      "loss": 3.7822,
+      "step": 7
+    },
+    {
+      "epoch": 0.00054656942285685,
+      "grad_norm": 3.868285894393921,
+      "learning_rate": 0.00016,
+      "loss": 4.489,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006148906007139563,
+      "grad_norm": 3.044187545776367,
+      "learning_rate": 0.00018,
+      "loss": 3.7794,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006148906007139563,
+      "eval_loss": 3.3595550060272217,
+      "eval_runtime": 317.28,
+      "eval_samples_per_second": 19.424,
+      "eval_steps_per_second": 9.714,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 985899139596288.0,
+  "total_flos": 1478848709394432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null