Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798291a48541d51ec27dccfb04969ed84a240c4b5aad0fb27cc0e2669bfd528d
+oid sha256:bfee01d8103d09d582705d572b496d7643cb63480e69b153f1382b5081aa8af8
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc8f86ad37f0cf51611f9aeecc8a395f82787608cb2ce6f7ccf27330ce2e6ee
+oid sha256:0ec7a651830d44bcee6bff272d2302cedf7b43d75bfde70141fda080f96fb44f
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ea9ad2466bee9501938172cccd6c85022832f061db4916ca506511c63fd6ce
+oid sha256:7d83117332e05dc7fd0876bf6486e3944c984131f2f9ab4cca3b30ddf4c26a56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f9c194f14d5c67265ac71b8d34cb6f960441ca9a99e80d33d78e02859e649b
+oid sha256:afb9c3c0c925ea8cf32a1dcba2e2f6242aaac5236534a8df451537dd590ac10a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36411378555798685,
+  "epoch": 0.5461706783369803,
   "eval_steps": 50,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -197,6 +197,97 @@
       "learning_rate": 0.0001492129799588288,
       "loss": 2.2783,
       "step": 26
+    },
+    {
+      "epoch": 0.37811816192560177,
+      "grad_norm": 14.870774269104004,
+      "learning_rate": 0.0001489294560698738,
+      "loss": 3.1369,
+      "step": 27
+    },
+    {
+      "epoch": 0.39212253829321664,
+      "grad_norm": 14.277947425842285,
+      "learning_rate": 0.000148602759460456,
+      "loss": 2.5122,
+      "step": 28
+    },
+    {
+      "epoch": 0.4061269146608315,
+      "grad_norm": 17.441390991210938,
+      "learning_rate": 0.0001482330809121954,
+      "loss": 2.9346,
+      "step": 29
+    },
+    {
+      "epoch": 0.4201312910284464,
+      "grad_norm": 10.07897663116455,
+      "learning_rate": 0.00014782063630695388,
+      "loss": 2.3027,
+      "step": 30
+    },
+    {
+      "epoch": 0.43413566739606124,
+      "grad_norm": 9.020223617553711,
+      "learning_rate": 0.00014736566650076636,
+      "loss": 1.944,
+      "step": 31
+    },
+    {
+      "epoch": 0.44814004376367617,
+      "grad_norm": 12.858219146728516,
+      "learning_rate": 0.00014686843718318744,
+      "loss": 1.5195,
+      "step": 32
+    },
+    {
+      "epoch": 0.46214442013129103,
+      "grad_norm": 10.95540714263916,
+      "learning_rate": 0.00014632923872213652,
+      "loss": 2.419,
+      "step": 33
+    },
+    {
+      "epoch": 0.4761487964989059,
+      "grad_norm": 10.858210563659668,
+      "learning_rate": 0.0001457483859943307,
+      "loss": 2.6077,
+      "step": 34
+    },
+    {
+      "epoch": 0.49015317286652077,
+      "grad_norm": 7.009860515594482,
+      "learning_rate": 0.00014512621820140611,
+      "loss": 2.3664,
+      "step": 35
+    },
+    {
+      "epoch": 0.5041575492341357,
+      "grad_norm": 6.658543109893799,
+      "learning_rate": 0.0001444630986718332,
+      "loss": 1.1082,
+      "step": 36
+    },
+    {
+      "epoch": 0.5181619256017506,
+      "grad_norm": 5.971487998962402,
+      "learning_rate": 0.00014375941464874368,
+      "loss": 1.558,
+      "step": 37
+    },
+    {
+      "epoch": 0.5321663019693654,
+      "grad_norm": 7.628395080566406,
+      "learning_rate": 0.0001430155770637909,
+      "loss": 1.949,
+      "step": 38
+    },
+    {
+      "epoch": 0.5461706783369803,
+      "grad_norm": 14.131255149841309,
+      "learning_rate": 0.00014223202029717776,
+      "loss": 2.6442,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -216,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6534945488896e+17,
+  "total_flos": 3.9802418233344e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null