Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f464bb34c079c49fc4894f86d25745fe89898016c82a86a608f7319e127060fb
+oid sha256:d32ac3feded5c3479ac17b89c6c7d6fc8a6a5c9e382b0cd178658d12631f6320
 size 3826461296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a0275491ae162fc646c048a499bb9160456c508f7be5abff3710269e6fdf4a
+oid sha256:66774c6e05115bebae2c4f1d957fbbf1529b4a28c6a6bf08a7cad3ceb574a9aa
 size 2479955235

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504b7bc543b9e5f039f6559d07b099507a66c15c86836ff5981e4eee51792c02
+oid sha256:e41f9a9fd18b485398505f595af3510abbf13d7745049b3d74379645d85abae1
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb268d80dcd8f32a0b291e0f300bdc2df3898cc3661ea44beb8067d70741b7b
+oid sha256:dd6ac75c94c2f7dfcfe42f00a66031ae062ed94adea9b80ebcb8b3240ad4424c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36,
+  "epoch": 0.4,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,6 +638,76 @@
       "learning_rate": 3.22347266881029e-05,
       "loss": 0.625,
       "step": 900
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 23.470478057861328,
+      "learning_rate": 3.2033762057877816e-05,
+      "loss": 0.9571,
+      "step": 910
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 31.515092849731445,
+      "learning_rate": 3.1832797427652735e-05,
+      "loss": 0.7395,
+      "step": 920
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 14.246073722839355,
+      "learning_rate": 3.1631832797427654e-05,
+      "loss": 0.6884,
+      "step": 930
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 25.352590560913086,
+      "learning_rate": 3.143086816720258e-05,
+      "loss": 0.772,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 14.441354751586914,
+      "learning_rate": 3.12299035369775e-05,
+      "loss": 0.7406,
+      "step": 950
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 29.33234405517578,
+      "learning_rate": 3.102893890675242e-05,
+      "loss": 0.7242,
+      "step": 960
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 16.018104553222656,
+      "learning_rate": 3.0827974276527335e-05,
+      "loss": 0.9183,
+      "step": 970
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 14.766180992126465,
+      "learning_rate": 3.0627009646302254e-05,
+      "loss": 0.8971,
+      "step": 980
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 10.733450889587402,
+      "learning_rate": 3.042604501607717e-05,
+      "loss": 0.5546,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 15.318602561950684,
+      "learning_rate": 3.0225080385852088e-05,
+      "loss": 0.7582,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -657,7 +727,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6191274912395264e+16,
+  "total_flos": 1.7984652389369856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null