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:aacc3e9459558a0715206f71408318788c1a138b86dbe25078d85b7744b159bd
+oid sha256:55b792505145e876ad8a4936e10d257b699bbb0e93f0888613b910e08754b08b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f60de47404974b8762b860dcaff847d20f15b263751923f8379db82721710a2
+oid sha256:b2458d479fc914e91e5bc04c2ea5b309f54fa4c1791211b07e0785347703eac8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d11172069d3809e4b1d435d13824f7b7bfef9c55e762daff1ad8efa9119dcca
+oid sha256:d1bf24cd4bf25e308928bff2034c8266e5fe111aaec9b6d5c14e665ac843e0bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16178af669793c21eac8710459f1cc10bcf09af1984c5f2d80e76b26b329c8ba
+oid sha256:67680b8b35ea230d53acee387012f8809825a2c511bd41340f42320f849e349d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024451372333272204,
+  "epoch": 0.004890274466654441,
   "eval_steps": 34,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,41 @@
       "learning_rate": 3.3333333333333335e-05,
       "loss": 3.6677,
       "step": 5
+    },
+    {
+      "epoch": 0.0029341646799926646,
+      "grad_norm": 1.7147626876831055,
+      "learning_rate": 4e-05,
+      "loss": 3.8075,
+      "step": 6
+    },
+    {
+      "epoch": 0.0034231921266581087,
+      "grad_norm": 1.672584891319275,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 3.3499,
+      "step": 7
+    },
+    {
+      "epoch": 0.0039122195733235525,
+      "grad_norm": 2.0120997428894043,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 4.2653,
+      "step": 8
+    },
+    {
+      "epoch": 0.004401247019988997,
+      "grad_norm": 2.0601062774658203,
+      "learning_rate": 6e-05,
+      "loss": 3.3055,
+      "step": 9
+    },
+    {
+      "epoch": 0.004890274466654441,
+      "grad_norm": 2.0153276920318604,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 3.1547,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -69,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.219477097775104e+16,
+  "total_flos": 4.438954195550208e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null