Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e54d2e8e7166fb89cd0c0195df7c2cd4e64abc4d59c5b1be70162f5a83ae53
+oid sha256:0d84ed5631d7bfc7e788345594dc90daaba1f354866f06adc5e73afcb30a455b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0aa1781fb7a2c2be0e242a7185aa1c87d923820a533ef77b99e4ca3b282f3a
+oid sha256:7203da03e41aee312dc316dacab1bb451a85b3f446f7e1adf18a8a7a3d9efc60
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afb383c7427b2624c032eb9cec3a33da0380c9292fc9c147c59c840fa8dd709
+oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003879352148191252,
+  "epoch": 0.007758704296382504,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 22.44,
       "eval_steps_per_second": 11.225,
       "step": 5
+    },
+    {
+      "epoch": 0.004655222577829503,
+      "grad_norm": 24.650022506713867,
+      "learning_rate": 6e-05,
+      "loss": 21.8922,
+      "step": 6
+    },
+    {
+      "epoch": 0.005431093007467753,
+      "grad_norm": 30.706462860107422,
+      "learning_rate": 7e-05,
+      "loss": 21.2497,
+      "step": 7
+    },
+    {
+      "epoch": 0.0062069634371060035,
+      "grad_norm": 26.0838565826416,
+      "learning_rate": 8e-05,
+      "loss": 19.2692,
+      "step": 8
+    },
+    {
+      "epoch": 0.0069828338667442535,
+      "grad_norm": 21.70370101928711,
+      "learning_rate": 9e-05,
+      "loss": 20.4647,
+      "step": 9
+    },
+    {
+      "epoch": 0.007758704296382504,
+      "grad_norm": 20.149873733520508,
+      "learning_rate": 0.0001,
+      "loss": 19.2082,
+      "step": 10
+    },
+    {
+      "epoch": 0.007758704296382504,
+      "eval_loss": NaN,
+      "eval_runtime": 55.6653,
+      "eval_samples_per_second": 39.001,
+      "eval_steps_per_second": 19.509,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3505339571896320.0,
+  "total_flos": 7010679143792640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null