Training in progress, step 200, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5dd95401fc3b99c31feb93554bc64e099ff8726b9ae2b76642755b56a78788
+oid sha256:a4830c7dfae77af1baf72bf90cd6854788975df823f1b1ec49037d3331f4b713
 size 4972163696

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de9da9da4489bbbed52369b08304f129f60af591f846bd1c657c6a76a786dab
+oid sha256:922d604842e24363921eaa52716294005a05f1ccdec8b6716513c45ad8592ea7
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2508c5face8bf2392945c63d45c7f260daaaf486f9e1c94da0dd42bd621a7a58
+oid sha256:fa9debffe532ffb09a3d501e8e6ea700bc44ef490a68be3084838733c4fb61d2
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0b45e6fd019f23318ffd2d46ef8cf6d2a160038f49f06fc17960b67863906f
+oid sha256:02b8d06323d7782eba280757f4398dbd280b072f40187b91d87fe4f49d7e6828
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e71e2096e47d5825ef2ce323a1cf303b37363e73043bd284a3ba35f73c6da6e
+oid sha256:6fe37d9f1cbca235c339a9316b5b88784b3b45f0c10ef4f8070517c1de6878f5
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220a99772b3d8f35e3e108e580fbc19089c4a43d7f11750324b648fbd4e2c7d7
+oid sha256:f07ce69a2abeb161a8250a6ab5003f92f86de92b90dabd232da31b8c613fe6b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4150943396226414,
+  "epoch": 1.8867924528301887,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 38.266,
       "eval_steps_per_second": 4.793,
       "step": 150
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 1.1987,
+      "step": 160
+    },
+    {
+      "epoch": 1.6037735849056602,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00019645406355025565,
+      "loss": 1.1701,
+      "step": 170
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.0001957515340994193,
+      "loss": 1.1686,
+      "step": 180
+    },
+    {
+      "epoch": 1.7924528301886793,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00019498704796656018,
+      "loss": 1.1835,
+      "step": 190
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.00019416109981763526,
+      "loss": 1.4218,
+      "step": 200
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "eval_loss": 1.8310290575027466,
+      "eval_runtime": 38.9304,
+      "eval_samples_per_second": 38.556,
+      "eval_steps_per_second": 4.829,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -163,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.484351812376986e+16,
+  "total_flos": 7.313993787611546e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null