Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2aa39907dc5ef3b94d502a5b8fd7e2741bc930c5b38483d70042aba0e7a8576
+oid sha256:5fe60a83fc8ab9ce94540e824abfda25a6d58d18f3fa8f4df0aac01a82f86f2f
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6a862bbbd5abb505758d4ad7e6770678d34ccefa06b7a1a6932483ba5dde72
+oid sha256:d71497f2ba6463d2f439f341b074070db8ec5cc10227a3101e4ce9f1a9ccc588
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b91b616bd452b894e1aea50022754f9be4afc2c867b79623be361a63b980b2
+oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024888003982080638,
+  "epoch": 0.03733200597312095,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 410.396,
       "eval_steps_per_second": 205.198,
       "step": 100
+    },
+    {
+      "epoch": 0.0273768043802887,
+      "grad_norm": 1.7987827062606812,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 43.3514,
+      "step": 110
+    },
+    {
+      "epoch": 0.029865604778496764,
+      "grad_norm": 2.542839288711548,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 43.314,
+      "step": 120
+    },
+    {
+      "epoch": 0.03235440517670483,
+      "grad_norm": 2.2360215187072754,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 43.3931,
+      "step": 130
+    },
+    {
+      "epoch": 0.03484320557491289,
+      "grad_norm": 1.8195124864578247,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 43.2444,
+      "step": 140
+    },
+    {
+      "epoch": 0.03733200597312095,
+      "grad_norm": 1.9710547924041748,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 43.2804,
+      "step": 150
+    },
+    {
+      "epoch": 0.03733200597312095,
+      "eval_loss": 10.805563926696777,
+      "eval_runtime": 4.1589,
+      "eval_samples_per_second": 406.842,
+      "eval_steps_per_second": 203.421,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 964480204800.0,
+  "total_flos": 1446720307200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null