Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a72aea82d33a0df376039af26e4fb5cea26ea4417d8c78ed85fc757bb6a39ca
+oid sha256:4e6652d4f4cf847b56ee09f55ddc4aa71f4b641ef2a2d758460b17d2b05b1154
 size 4682414560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea46decce79789e325e0aa6d402cfa5b28b69b0c3e037f2a401da9623e1a137
+oid sha256:22c36679d5b9dae75f3ef6d4ee031e17c0bdffe90022cc65eb8474f3006a513d
 size 2498736801

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227e3caad3f787fbe810fbac3c378957e1394c039f30869d94e84d08288a0af5
+oid sha256:dc4678e09f8fcc61d92df0e65077038de31aeb262232e6a2dbf1a3ffba70ea64
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0bfa5100128a3b17f1f0f23b4edee8f727028cbe6ad3d5850d5d9861a5a8b4
+oid sha256:dd3aba3a7d5dd6e1fe4ca9aeb5413dce931776ed2a811c0c689ce3b6ea4e2b48
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006061952089513209,
+  "epoch": 0.00636504969398887,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1408,6 +1408,76 @@
       "learning_rate": 9.939410802638646e-05,
       "loss": 3.175491943359375,
       "step": 10000
+    },
+    {
+      "epoch": 0.006092261849960775,
+      "grad_norm": 2.3004519939422607,
+      "learning_rate": 9.939107705103073e-05,
+      "loss": 3.217908935546875,
+      "step": 10050
+    },
+    {
+      "epoch": 0.006122571610408341,
+      "grad_norm": 2.0357086658477783,
+      "learning_rate": 9.938804607567496e-05,
+      "loss": 3.2446975708007812,
+      "step": 10100
+    },
+    {
+      "epoch": 0.006152881370855907,
+      "grad_norm": 2.126295566558838,
+      "learning_rate": 9.938501510031923e-05,
+      "loss": 3.1879031372070314,
+      "step": 10150
+    },
+    {
+      "epoch": 0.0061831911313034735,
+      "grad_norm": 1.7915022373199463,
+      "learning_rate": 9.938198412496348e-05,
+      "loss": 3.098807373046875,
+      "step": 10200
+    },
+    {
+      "epoch": 0.00621350089175104,
+      "grad_norm": 2.8946573734283447,
+      "learning_rate": 9.937895314960774e-05,
+      "loss": 3.3009078979492186,
+      "step": 10250
+    },
+    {
+      "epoch": 0.006243810652198606,
+      "grad_norm": 2.3917036056518555,
+      "learning_rate": 9.937592217425199e-05,
+      "loss": 3.362381591796875,
+      "step": 10300
+    },
+    {
+      "epoch": 0.006274120412646172,
+      "grad_norm": 2.2558183670043945,
+      "learning_rate": 9.937289119889624e-05,
+      "loss": 3.2506768798828123,
+      "step": 10350
+    },
+    {
+      "epoch": 0.006304430173093738,
+      "grad_norm": 1.747912883758545,
+      "learning_rate": 9.93698602235405e-05,
+      "loss": 3.1590435791015623,
+      "step": 10400
+    },
+    {
+      "epoch": 0.006334739933541304,
+      "grad_norm": 2.056442975997925,
+      "learning_rate": 9.936682924818475e-05,
+      "loss": 3.1585858154296873,
+      "step": 10450
+    },
+    {
+      "epoch": 0.00636504969398887,
+      "grad_norm": 2.221165895462036,
+      "learning_rate": 9.936379827282901e-05,
+      "loss": 3.2523733520507814,
+      "step": 10500
     }
   ],
   "logging_steps": 50,
@@ -1427,7 +1497,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.755622008506368e+16,
+  "total_flos": 3.94406667566039e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null