Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad08c53167b40be4fe9f2cd1e1d453f6913c4bdddef03c689e4ccf00ccd5100
+oid sha256:1bf00bd1729e93096ba65d420e90a901035c7cde995818109e307db01e41fa9c
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37bd36a68a0567f982bfb2b7aaa7cdf0c9960b629cc5cb668d8df233bceabeb4
+oid sha256:5799b844a7352f37c92e44621a1173ea3584fd158ec0e52694ab64fda2dcdbe8
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1e9e74eb9ce556fb3a56ba6bf5b59adaffe1aec162bf64b4914e0fc6e813ef
+oid sha256:90457f2aa05b0bf6c779e9c18eabfb4d5b3e6a7ed4d46f5f4d989d3f73ffe883
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003389859236095221,
+  "epoch": 0.0006779718472190442,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 6.9199,
       "step": 9
+    },
+    {
+      "epoch": 0.00040678310833142654,
+      "grad_norm": 86.80118560791016,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 5.86,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005084788854142832,
+      "grad_norm": 1.8858240842819214,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.5372,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005423774777752354,
+      "eval_loss": 1.3532363176345825,
+      "eval_runtime": 2923.6367,
+      "eval_samples_per_second": 4.248,
+      "eval_steps_per_second": 2.124,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006101746624971398,
+      "grad_norm": 2.218549966812134,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.5828,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6808424939520000.0,
+  "total_flos": 1.361684987904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null