Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1337d8fc97d161e13c15b1c73fe03b63c7b0be393222755ab943e276a9818546
+oid sha256:74bd599c15eda0b4cfb484d493d4e216f4f37aeae2c1e0b6cd03ee8c9b6b71ad
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befe0669f5b7a69dcc5dd081b3b02fc77985908d6b98157cc69660731b5cf35a
+oid sha256:960cd9845c564bfc5e3103367fd2ab34c17fd8f491a601ce226f7d51fce43bb8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d93d600975602b7dc557ea6bf2be1af32b3a49c58755d50746f1058367b602f
+oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002531378546566818,
+  "epoch": 0.0005062757093133636,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 19.322,
       "eval_steps_per_second": 9.661,
       "step": 3
+    },
+    {
+      "epoch": 0.00033751713954224236,
+      "grad_norm": 0.11388365179300308,
+      "learning_rate": 8e-05,
+      "loss": 1.4392,
+      "step": 4
+    },
+    {
+      "epoch": 0.00042189642442780296,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 2.0835,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005062757093133636,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 1.9221,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005062757093133636,
+      "eval_loss": NaN,
+      "eval_runtime": 256.9107,
+      "eval_samples_per_second": 19.423,
+      "eval_steps_per_second": 9.712,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977239881547776.0,
+  "total_flos": 1954479763095552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null