Training in progress, step 3320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf840ad1b562e045bc92ac31e01aee8f4cd67d1a73eca73333298edfbae1ad20
+oid sha256:9cea960f50a7271a5b2bba71996a92c7510add6435cf258a5c6606f9afdf5a9f
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b115b07f9fe38375bcc96df9244e270a0061e3396e94a2fc540b35e81b2080b
+oid sha256:c2d9cb9f3e787a8028fa8d1eca6622c7c4dfbba28974558a4fd13d01082cfc82
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709dbfd8db569dd59d549977ea4d372bd8a3fee22ca873f7f07f76ee57da1c03
+oid sha256:715afa7fa80b309ab5f3a3ffeab1c984abb1f23fc1fdeeb9a5d9e680a111f9d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10d973e668b5505b78d845d8bcd5008b3bbe632800fe01e15ed61bbadd63be9
+oid sha256:ba3845b027cbf32ba8978367629ed9d5fe41b951f8e9b22618a87d5fbc8d6666
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.2656,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1057,6 +1057,118 @@
       "learning_rate": 2.8881318444640564e-05,
       "loss": 3.5043,
       "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 26.047521591186523,
+      "learning_rate": 2.8862836261972873e-05,
+      "loss": 3.6236,
+      "step": 3020
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 39.91059494018555,
+      "learning_rate": 2.8844208664712577e-05,
+      "loss": 3.4851,
+      "step": 3040
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 57.92033004760742,
+      "learning_rate": 2.882543584825435e-05,
+      "loss": 3.5578,
+      "step": 3060
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 99.40699005126953,
+      "learning_rate": 2.880651800951616e-05,
+      "loss": 3.577,
+      "step": 3080
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 30.7738094329834,
+      "learning_rate": 2.8787455346937182e-05,
+      "loss": 3.5683,
+      "step": 3100
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 55.61745834350586,
+      "learning_rate": 2.876824806047573e-05,
+      "loss": 3.4959,
+      "step": 3120
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 23.431480407714844,
+      "learning_rate": 2.8748896351607145e-05,
+      "loss": 3.5882,
+      "step": 3140
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 20.944149017333984,
+      "learning_rate": 2.8729400423321693e-05,
+      "loss": 3.6096,
+      "step": 3160
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 46.77301788330078,
+      "learning_rate": 2.8709760480122443e-05,
+      "loss": 3.5665,
+      "step": 3180
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 36.645328521728516,
+      "learning_rate": 2.8689976728023103e-05,
+      "loss": 3.5087,
+      "step": 3200
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 32.61063003540039,
+      "learning_rate": 2.8670049374545873e-05,
+      "loss": 3.5054,
+      "step": 3220
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 47.47910690307617,
+      "learning_rate": 2.8649978628719256e-05,
+      "loss": 3.5674,
+      "step": 3240
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 40.817115783691406,
+      "learning_rate": 2.8629764701075885e-05,
+      "loss": 3.4504,
+      "step": 3260
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 32.290626525878906,
+      "learning_rate": 2.8609407803650295e-05,
+      "loss": 3.4699,
+      "step": 3280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 26.942697525024414,
+      "learning_rate": 2.8588908149976702e-05,
+      "loss": 3.5642,
+      "step": 3300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 30.925710678100586,
+      "learning_rate": 2.856826595508678e-05,
+      "loss": 3.6097,
+      "step": 3320
     }
   ],
   "logging_steps": 20,
@@ -1064,7 +1176,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 7092703910756352.0,
+  "total_flos": 7875682626207744.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null