Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c31e3a76e9336897d319f0f3ecb0bc7a07191077bcded795047309c1e7116c2
+oid sha256:cd087e2a4836d64ac7ad08b78b043ebb03881f68b83c32323065eaa841d6f2f2
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890d72b34727cf1bab38fc84572ba02d0bb3a24db4da322168bfab9960ae705a
+oid sha256:76da1e3aa21a5d9e0238e49278ff7e1e183d6a485701905b1d3fe8480e2a058f
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f953fdf6c988b7d77f08e75aab575eda62336edabf15a3a415e1c0b311234f69
+oid sha256:ef0ef582e555b2318afd484104e122f2ed17bee7953ab960b85fd42965e00786
 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": 0.0009799518190355642,
+  "epoch": 0.0014699277285533461,
   "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": 80.847,
       "eval_steps_per_second": 40.424,
       "step": 6
+    },
+    {
+      "epoch": 0.0011432771222081581,
+      "grad_norm": 2.7405037879943848,
+      "learning_rate": 0.00014,
+      "loss": 5.6114,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013066024253807521,
+      "grad_norm": 2.1372079849243164,
+      "learning_rate": 0.00016,
+      "loss": 5.2708,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014699277285533461,
+      "grad_norm": 1.879054069519043,
+      "learning_rate": 0.00018,
+      "loss": 5.0464,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014699277285533461,
+      "eval_loss": 1.2333914041519165,
+      "eval_runtime": 31.673,
+      "eval_samples_per_second": 81.394,
+      "eval_steps_per_second": 40.697,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 79200472006656.0,
+  "total_flos": 118800708009984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null