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:a1cb37dea7b558c8cf6e7a0983ec9aa484f3d7e43b041c6eea6f0eceed42e818
+oid sha256:a30687bcd005fcec158c28f62ace716be9c57679a57a2c352e2daea61d3a64ac
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae31359390ebd44baeca72772348828cbb370f33737791b739de72f9d91a9c2
-size 2280
+oid sha256:f834ae35b50d9b9fba36f0f4f6690c775ad958ecacde69108fd591e9ccff256b
+size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
+oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010614772224679346,
+  "epoch": 0.002122954444935869,
   "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": 5.081,
       "eval_steps_per_second": 5.081,
       "step": 3
+    },
+    {
+      "epoch": 0.0014153029632905795,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 16.9349,
+      "step": 4
+    },
+    {
+      "epoch": 0.0017691287041132243,
+      "grad_norm": 95.18614196777344,
+      "learning_rate": 2e-05,
+      "loss": 15.3692,
+      "step": 5
+    },
+    {
+      "epoch": 0.002122954444935869,
+      "grad_norm": 110.96968841552734,
+      "learning_rate": 4e-05,
+      "loss": 15.6412,
+      "step": 6
+    },
+    {
+      "epoch": 0.002122954444935869,
+      "eval_loss": 3.736077308654785,
+      "eval_runtime": 116.5658,
+      "eval_samples_per_second": 5.104,
+      "eval_steps_per_second": 5.104,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2110316208979968.0,
+  "total_flos": 4220632417959936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null