Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf0291871ea93dbea209fb2985c58523f617169fdf9dc24123ca1eeda1dd967
+oid sha256:0174b0116cfb9af7294711107315070cb5df5a403799c39097e36318345b480a
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b435d6de54230c9e25eca3d9b1e869fc663ecc5e4f4a0adca804b8b9be130aa1
+oid sha256:8804cc6d7eb057620b329159d309aa3c2e9154e9801508307ebcc5c8472c5480
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ccf8b0d2e98bf2ffc1b552009db8d48cc34af5e23f1a080c0f3f25744ca66b
+oid sha256:a4c90e73b569a38f99c2197447433676c2eaa22ce221aeecf0a7d6e7d0501c17
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc5adc9ecc7f2ef4cc81bc3d2c8c79e27e6a710a89b67da3b49f2f8440c6fb5
+oid sha256:ddc00765bb2f7c05738fc9294fd5cefadbd3816d98397372497b3027b71c424b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56,
+  "epoch": 0.6,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -988,6 +988,76 @@
       "learning_rate": 2.2186495176848876e-05,
       "loss": 0.6307,
       "step": 1400
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 12.709571838378906,
+      "learning_rate": 2.1985530546623795e-05,
+      "loss": 0.427,
+      "step": 1410
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 10.895342826843262,
+      "learning_rate": 2.1784565916398714e-05,
+      "loss": 0.4546,
+      "step": 1420
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 13.848987579345703,
+      "learning_rate": 2.1583601286173636e-05,
+      "loss": 0.4159,
+      "step": 1430
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 16.61017608642578,
+      "learning_rate": 2.1382636655948555e-05,
+      "loss": 0.733,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 10.283616065979004,
+      "learning_rate": 2.1181672025723473e-05,
+      "loss": 0.4581,
+      "step": 1450
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 11.248019218444824,
+      "learning_rate": 2.0980707395498395e-05,
+      "loss": 0.462,
+      "step": 1460
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 10.817742347717285,
+      "learning_rate": 2.0779742765273314e-05,
+      "loss": 0.451,
+      "step": 1470
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 10.615836143493652,
+      "learning_rate": 2.0578778135048233e-05,
+      "loss": 0.5714,
+      "step": 1480
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 12.22169017791748,
+      "learning_rate": 2.037781350482315e-05,
+      "loss": 0.8718,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 13.216890335083008,
+      "learning_rate": 2.0176848874598074e-05,
+      "loss": 0.3766,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -1007,7 +1077,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.523584640465101e+16,
+  "total_flos": 2.704157205966029e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null