Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dddca729ab09142c6d4a86292fcb09c8240e120212ff2dea7784702f1c454342
+oid sha256:b7da8882c4eba065851f3d33946d222f14c2f723a8e4b466de1f227567d55531
 size 579748776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ae4821caa875af2772c8c1c8a8f25674e533cf460c88cc3b72e2ecf795355b
+oid sha256:3dc6db80c72368f3c3b7f1bca017a3f8af377e6e79bfb95dfa6de9e3819b27d4
 size 1159627083

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5387f6e99d51202c7ef90fef723e457487d08949715af1e6a0aff706c078f5bd
+oid sha256:a4d8242b37901ec7cc0992b7a6173ea32c89632c26198ca917c21035a4c247c4
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6418bc04f5e424107d7c94f43f8158a47397e1e0f7c2b0b675aeed07c6fcfe3
+oid sha256:6bbac1cf1ce1610978037481a5035e6b523662562dd00a236dbb2507431643e9
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fdb738e61f6acc5e69da32f32a665c3f109e78a2b1b3b8004b382d7b5d9fa18
+oid sha256:4d78ed09f8ef41008377f42bff0e363b7ba82ecd1c922f2e831caad0254e1ac5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45,
+  "epoch": 0.6,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -341,6 +341,117 @@
       "eval_samples_per_second": 64.921,
       "eval_steps_per_second": 2.142,
       "step": 900
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 13.373994827270508,
+      "learning_rate": 6.268105304531354e-05,
+      "loss": 92.7674,
+      "step": 925
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 20.701358795166016,
+      "learning_rate": 6.061695044309973e-05,
+      "loss": 92.4968,
+      "step": 950
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 13.155655860900879,
+      "learning_rate": 5.8533715378581e-05,
+      "loss": 92.2234,
+      "step": 975
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 46.88108444213867,
+      "learning_rate": 5.643510198215082e-05,
+      "loss": 92.0125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.17633533442055147,
+      "eval_loss": 5.7336883544921875,
+      "eval_runtime": 7.3739,
+      "eval_samples_per_second": 65.773,
+      "eval_steps_per_second": 2.17,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5125,
+      "grad_norm": 482.2004699707031,
+      "learning_rate": 5.432489209699614e-05,
+      "loss": 93.2148,
+      "step": 1025
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 297.8095703125,
+      "learning_rate": 5.220688846396047e-05,
+      "loss": 95.0004,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5375,
+      "grad_norm": 332.8581848144531,
+      "learning_rate": 5.0084907868747746e-05,
+      "loss": 95.3143,
+      "step": 1075
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 9733.95703125,
+      "learning_rate": 4.796277426381657e-05,
+      "loss": 95.8613,
+      "step": 1100
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.1554284329416992,
+      "eval_loss": 6.006833553314209,
+      "eval_runtime": 7.2985,
+      "eval_samples_per_second": 66.452,
+      "eval_steps_per_second": 2.192,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 1343.75537109375,
+      "learning_rate": 4.5844311877359384e-05,
+      "loss": 96.7118,
+      "step": 1125
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 234.01663208007812,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 97.3733,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5875,
+      "grad_norm": 868.69921875,
+      "learning_rate": 4.1633657714122e-05,
+      "loss": 97.8172,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 370.631591796875,
+      "learning_rate": 3.954905382074478e-05,
+      "loss": 98.1012,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.14907376084903992,
+      "eval_loss": 6.105465888977051,
+      "eval_runtime": 7.4782,
+      "eval_samples_per_second": 64.855,
+      "eval_steps_per_second": 2.14,
+      "step": 1200
     }
   ],
   "logging_steps": 25,
@@ -360,7 +471,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.020016214376448e+17,
+  "total_flos": 8.026688285835264e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null