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:d5436435e64ddc8141bda15b0c9b4c92647774f5a0836592f7daf34a19919b81
+oid sha256:6f939652dd04005c3d2451e32e4bf8d528f1528ebf2c2c019292b62ec9db06ef
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a5ca59d1298ee70e7e61bba90e016551c1c9bd96f8d9c55975cdbc92e266e9
+oid sha256:edfb3a7c5c1363646263166f196a8fd83391df4a8ec0b74ba2eb887ce5123952
 size 7086458

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08db8b6d7fdf61656583db4688ab0937640a7e89ae78c8cef9d21ec57b947872
+oid sha256:cb99f881fd507ed941d1b5415daafcff09a468076b52be03a90f2705750747b3
 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": 0.004259850905218318,
+  "epoch": 0.008519701810436636,
   "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": 15.611,
       "eval_steps_per_second": 7.832,
       "step": 3
+    },
+    {
+      "epoch": 0.0056798012069577564,
+      "grad_norm": 2.796581268310547,
+      "learning_rate": 8e-05,
+      "loss": 2.3501,
+      "step": 4
+    },
+    {
+      "epoch": 0.007099751508697196,
+      "grad_norm": 2.2836456298828125,
+      "learning_rate": 0.0001,
+      "loss": 3.2729,
+      "step": 5
+    },
+    {
+      "epoch": 0.008519701810436636,
+      "grad_norm": 2.491248369216919,
+      "learning_rate": 0.00012,
+      "loss": 2.1742,
+      "step": 6
+    },
+    {
+      "epoch": 0.008519701810436636,
+      "eval_loss": 4.0644426345825195,
+      "eval_runtime": 19.0229,
+      "eval_samples_per_second": 15.613,
+      "eval_steps_per_second": 7.833,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 83302551650304.0,
+  "total_flos": 166605103300608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null