Training in progress, step 2940, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9eae585410e6c4e007ed705b17ea180f557ccdb77b71dae164ab1cfc21d7306
+oid sha256:8e06eb6076d702c790a643108cff6e70d61f27c4a8c0054750ad24aee92e626a
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9a4f20bb62043714271be0923e8f2528623da5a2b230e1be9d2c2df0841db1
+oid sha256:7e62a38f86d28296ff1681105797c41a05458f9c85c4b56c154bc85e7488e2e2
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e591371ba4dbea3966383ac9936deb4708f1de98d91436af921256e07f908a07
+oid sha256:9cf226528602f349c7c927b31d9819774aa5266cf6c2feebd36b0cbe6a6007a5
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261b865a2e8538257e1ae75e688a880c8008ed5ea5dcbb21a4e46fdc6eaf51d9
+oid sha256:4c94daa81f21e6e941509b67ca17cfdc205162f25da470dddc0aedfdfaedfe74
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1695505272857583,
+  "epoch": 1.2039520835466366,
   "eval_steps": 500,
-  "global_step": 2856,
+  "global_step": 2940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2003,6 +2003,69 @@
       "learning_rate": 7.806207228653921e-05,
       "loss": 0.3635621309280396,
       "step": 2850
+    },
+    {
+      "epoch": 1.1711886966315144,
+      "grad_norm": 0.17187663912773132,
+      "learning_rate": 7.741551233134628e-05,
+      "loss": 0.4021602153778076,
+      "step": 2860
+    },
+    {
+      "epoch": 1.1752841199959045,
+      "grad_norm": 0.23882046341896057,
+      "learning_rate": 7.676994572462312e-05,
+      "loss": 0.3855579137802124,
+      "step": 2870
+    },
+    {
+      "epoch": 1.179379543360295,
+      "grad_norm": 0.16917739808559418,
+      "learning_rate": 7.612540086075313e-05,
+      "loss": 0.3872795104980469,
+      "step": 2880
+    },
+    {
+      "epoch": 1.183474966724685,
+      "grad_norm": 0.1488448679447174,
+      "learning_rate": 7.548190608917964e-05,
+      "loss": 0.3769106149673462,
+      "step": 2890
+    },
+    {
+      "epoch": 1.1875703900890755,
+      "grad_norm": 0.19162490963935852,
+      "learning_rate": 7.48394897131591e-05,
+      "loss": 0.3580836534500122,
+      "step": 2900
+    },
+    {
+      "epoch": 1.1916658134534657,
+      "grad_norm": 0.19842198491096497,
+      "learning_rate": 7.419817998851623e-05,
+      "loss": 0.3587891340255737,
+      "step": 2910
+    },
+    {
+      "epoch": 1.195761236817856,
+      "grad_norm": 0.1560589224100113,
+      "learning_rate": 7.355800512240115e-05,
+      "loss": 0.38894004821777345,
+      "step": 2920
+    },
+    {
+      "epoch": 1.1998566601822462,
+      "grad_norm": 0.1998666226863861,
+      "learning_rate": 7.29189932720487e-05,
+      "loss": 0.40459065437316893,
+      "step": 2930
+    },
+    {
+      "epoch": 1.2039520835466366,
+      "grad_norm": 0.20374324917793274,
+      "learning_rate": 7.228117254354005e-05,
+      "loss": 0.35155019760131834,
+      "step": 2940
     }
   ],
   "logging_steps": 10,
@@ -2022,7 +2085,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.9561366538376806e+17,
+  "total_flos": 5.1019023841848115e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null