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:b2571169a9842531ceea70ef73b26eff5def8a8e9d0c11528402700c141e00d8
+oid sha256:4f8cf4ba5b930094a19ef5160a461a696020a81d708bd6406725a7b830b8f8bc
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33b222ebc1b4389474297cdb5def5494cc054f98b6ae39c5665acf4cea9c020
+oid sha256:a026e0ce7e740017134e7212717a0bbd1e39eef61cca3d6e0788a7d054b9c928
 size 1324026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
+oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
 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": 0.002761795166858458,
+  "epoch": 0.004142692750287687,
   "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": 14.708,
       "eval_steps_per_second": 7.362,
       "step": 6
+    },
+    {
+      "epoch": 0.003222094361334868,
+      "grad_norm": 0.5202929377555847,
+      "learning_rate": 0.00014,
+      "loss": 11.9359,
+      "step": 7
+    },
+    {
+      "epoch": 0.003682393555811277,
+      "grad_norm": 0.5931057929992676,
+      "learning_rate": 0.00016,
+      "loss": 11.9279,
+      "step": 8
+    },
+    {
+      "epoch": 0.004142692750287687,
+      "grad_norm": 0.615904688835144,
+      "learning_rate": 0.00018,
+      "loss": 11.9165,
+      "step": 9
+    },
+    {
+      "epoch": 0.004142692750287687,
+      "eval_loss": 11.914743423461914,
+      "eval_runtime": 62.3061,
+      "eval_samples_per_second": 14.686,
+      "eval_steps_per_second": 7.351,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6093665206272.0,
+  "total_flos": 9140497809408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null