Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897a2d76b46c37666339a32f0e70836619e29545db41fd7abc14ad6a6fd8ea24
+oid sha256:1a72aea82d33a0df376039af26e4fb5cea26ea4417d8c78ed85fc757bb6a39ca
 size 4682414560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf8f34d230bfa09c07aa594b3482bd9e2f1f6cd0b2ab88dc019359c8235308f
+oid sha256:0ea46decce79789e325e0aa6d402cfa5b28b69b0c3e037f2a401da9623e1a137
 size 2498736801

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50132d3e2de48497717bc53ff4eacaef759623dee33ac6c4bcd02871b0690b2f
+oid sha256:227e3caad3f787fbe810fbac3c378957e1394c039f30869d94e84d08288a0af5
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e24dc0c109295a9322692845301bb3e884fbf9ab2ee06ac92f5d40034eb5191
+oid sha256:ad0bfa5100128a3b17f1f0f23b4edee8f727028cbe6ad3d5850d5d9861a5a8b4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005758854485037549,
+  "epoch": 0.006061952089513209,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1338,6 +1338,76 @@
       "learning_rate": 9.942435716043681e-05,
       "loss": 3.2088824462890626,
       "step": 9500
+    },
+    {
+      "epoch": 0.005789164245485115,
+      "grad_norm": 1.6147823333740234,
+      "learning_rate": 9.942132618508106e-05,
+      "loss": 3.2871713256835937,
+      "step": 9550
+    },
+    {
+      "epoch": 0.005819474005932681,
+      "grad_norm": 1.877769947052002,
+      "learning_rate": 9.94182952097253e-05,
+      "loss": 3.21473876953125,
+      "step": 9600
+    },
+    {
+      "epoch": 0.005849783766380247,
+      "grad_norm": 2.283907413482666,
+      "learning_rate": 9.941526423436957e-05,
+      "loss": 3.3842514038085936,
+      "step": 9650
+    },
+    {
+      "epoch": 0.0058800935268278134,
+      "grad_norm": 1.681667685508728,
+      "learning_rate": 9.941223325901382e-05,
+      "loss": 3.2447711181640626,
+      "step": 9700
+    },
+    {
+      "epoch": 0.005910403287275379,
+      "grad_norm": 1.9879530668258667,
+      "learning_rate": 9.940920228365808e-05,
+      "loss": 3.2267584228515624,
+      "step": 9750
+    },
+    {
+      "epoch": 0.005940713047722945,
+      "grad_norm": 2.1548056602478027,
+      "learning_rate": 9.940617130830233e-05,
+      "loss": 3.269433898925781,
+      "step": 9800
+    },
+    {
+      "epoch": 0.005971022808170511,
+      "grad_norm": 1.723276138305664,
+      "learning_rate": 9.940314033294658e-05,
+      "loss": 3.36541748046875,
+      "step": 9850
+    },
+    {
+      "epoch": 0.006001332568618077,
+      "grad_norm": 2.4308693408966064,
+      "learning_rate": 9.940010935759084e-05,
+      "loss": 3.1993017578125,
+      "step": 9900
+    },
+    {
+      "epoch": 0.006031642329065643,
+      "grad_norm": 2.3158278465270996,
+      "learning_rate": 9.93970783822351e-05,
+      "loss": 3.168118896484375,
+      "step": 9950
+    },
+    {
+      "epoch": 0.006061952089513209,
+      "grad_norm": 1.8310009241104126,
+      "learning_rate": 9.939410802638646e-05,
+      "loss": 3.175491943359375,
+      "step": 10000
     }
   ],
   "logging_steps": 50,
@@ -1357,7 +1427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.56581258564608e+16,
+  "total_flos": 3.755622008506368e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null