Training in progress, step 104, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91178314d33fe4afb30171470054c3838d439aeb15a938f2197669aa0f5393ad
+oid sha256:8df7bdccf9b9ea018cf08637989d48944be5e3ee8a0970bee5233527cdc8082c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac2b837938592cae880bcac77ee86985aa64ee15912e19a5994c92cef802b1f
+oid sha256:abf811487858e391fe9c39fee5a148ac7ba91980cf9e43cff52525b26848fb97
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a663f94f9a2a2ab6df61c276b200d0d2fd085e9bf8a9f2e6c62a991d9b2f00cf
+oid sha256:919715e521e6fafa91c21eb71f1ef59a2a480a7d0fc641c8aac7133bb8caf2b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37872b45362e9c63412b1b167580155e0789faf44bbc81b017091d0c0912d87
+oid sha256:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6545454545454545,
+  "epoch": 1.8909090909090909,
   "eval_steps": 13,
-  "global_step": 91,
+  "global_step": 104,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -281,6 +281,42 @@
       "eval_samples_per_second": 9.964,
       "eval_steps_per_second": 1.286,
       "step": 91
+    },
+    {
+      "epoch": 1.690909090909091,
+      "grad_norm": 0.5781804323196411,
+      "learning_rate": 3.562003362839914e-05,
+      "loss": 0.1118,
+      "step": 93
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 0.557227373123169,
+      "learning_rate": 3.243125879593286e-05,
+      "loss": 0.0887,
+      "step": 96
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6238749623298645,
+      "learning_rate": 2.932207475167398e-05,
+      "loss": 0.0828,
+      "step": 99
+    },
+    {
+      "epoch": 1.8545454545454545,
+      "grad_norm": 0.6486019492149353,
+      "learning_rate": 2.630656687635007e-05,
+      "loss": 0.1015,
+      "step": 102
+    },
+    {
+      "epoch": 1.8909090909090909,
+      "eval_loss": 0.15355004370212555,
+      "eval_runtime": 9.3338,
+      "eval_samples_per_second": 9.964,
+      "eval_steps_per_second": 1.286,
+      "step": 104
     }
   ],
   "logging_steps": 3,
@@ -300,7 +336,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.068077834361897e+17,
+  "total_flos": 2.362237982217339e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null