Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfbb1e6b2392de54c4ac843fbed396422b7a0d0c9106affbcc79fa9386970a2
+oid sha256:b66ad94752d62c7598ba4ec118ee026b855a5f494603e8fe6ab1f569316e32ca
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b21e81dc398ecf1180387e8a424e49549354cecea78e9fbe2547b46b3ce42d9
+oid sha256:7a927d8456f159ca3ef5617bf5b4c9ea624fe5a97a3204d854474ed3d41938e3
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3058f8f1ee14618db74217e8eeff91e9030a2fe706f1c21688e02cd2191222
+oid sha256:930d555ae32a6a3ef15da629b0dbf3a06900868465fc5e03b6b9434e4eae54f6
 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": 0.005263157894736842,
+  "epoch": 0.010526315789473684,
   "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": 126.939,
       "eval_steps_per_second": 63.47,
       "step": 3
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 865.8417358398438,
+      "learning_rate": 8e-05,
+      "loss": 10.3514,
+      "step": 4
+    },
+    {
+      "epoch": 0.008771929824561403,
+      "grad_norm": 982.4260864257812,
+      "learning_rate": 0.0001,
+      "loss": 12.5797,
+      "step": 5
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 1129.5501708984375,
+      "learning_rate": 0.00012,
+      "loss": 9.1177,
+      "step": 6
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "eval_loss": 2.460749387741089,
+      "eval_runtime": 1.9024,
+      "eval_samples_per_second": 126.158,
+      "eval_steps_per_second": 63.079,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 13809525719040.0,
+  "total_flos": 28386247311360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null