Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e885cac5c061624d6bc12dc0e231dbf23d716a260ebf59bb508281da295fe021
+oid sha256:6b71114f676b03c0bcb0f46c8fd50023e59488725d453b15759a44f3e2d04275
 size 499730128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d0700dd49d8512365f4fe50959ea0dbc3be2ffc5b05812fda8483189b4e5a4
+oid sha256:1069d6130a8bebfd2ceeda1d0936f626f5637e1fc5ef945629ede330c4c05e04
 size 812034507

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e06dfbf969388fb27efc692631d298abe0d1c57738a0c64598fe664b1ac46b1
+oid sha256:15bd918144b9671ae295d46e463180bdad2e73e51a7670636feb8fc58e14c426
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
+oid sha256:eb2a89a85e1c8ac7ee9b5678d857a4d99090faa37a24489f44839e0801dfe16a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 194.133,
       "eval_steps_per_second": 1.553,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.43114492297172546,
+      "learning_rate": 0.0019944130517800893,
+      "loss": 4.0238558959960935,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.26026225090026855,
+      "learning_rate": 0.001993693153591457,
+      "loss": 4.017567443847656,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.23712828755378723,
+      "learning_rate": 0.0019929297880451674,
+      "loss": 3.9972265625,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.44415482878685,
+      "learning_rate": 0.0019921229885333023,
+      "loss": 3.9874578857421876,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.27471208572387695,
+      "learning_rate": 0.001991272790347886,
+      "loss": 3.998799133300781,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.2248983383178711,
+      "learning_rate": 0.0019903792306793415,
+      "loss": 3.9638967895507813,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.36029258370399475,
+      "learning_rate": 0.001989442348614863,
+      "loss": 3.972870178222656,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.26471713185310364,
+      "learning_rate": 0.0019884621851367075,
+      "loss": 3.959658508300781,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.23001010715961456,
+      "learning_rate": 0.001987438783120401,
+      "loss": 3.9595660400390624,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.23091939091682434,
+      "learning_rate": 0.001986372187332862,
+      "loss": 3.9660198974609373,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.3069041095890411,
+      "eval_loss": 3.95263409614563,
+      "eval_runtime": 5.269,
+      "eval_samples_per_second": 189.788,
+      "eval_steps_per_second": 1.518,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.28329843282699585,
+      "learning_rate": 0.0019852624444304467,
+      "loss": 3.9279766845703126,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.4390493333339691,
+      "learning_rate": 0.0019841096029569044,
+      "loss": 3.940526123046875,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.22625097632408142,
+      "learning_rate": 0.0019829137133412556,
+      "loss": 3.9342303466796875,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.21681281924247742,
+      "learning_rate": 0.001981674827895587,
+      "loss": 3.9172735595703125,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.3054690957069397,
+      "learning_rate": 0.00198039300081276,
+      "loss": 3.920041198730469,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.24492567777633667,
+      "learning_rate": 0.0019790682881640448,
+      "loss": 3.918515319824219,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.20615942776203156,
+      "learning_rate": 0.001977700747896664,
+      "loss": 3.902435302734375,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.2998456358909607,
+      "learning_rate": 0.001976290439831259,
+      "loss": 3.9016647338867188,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.22004957497119904,
+      "learning_rate": 0.0019748374256592736,
+      "loss": 3.897244567871094,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2709659934043884,
+      "learning_rate": 0.0019733417689402543,
+      "loss": 3.892081604003906,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.31208414872798435,
+      "eval_loss": 3.8932552337646484,
+      "eval_runtime": 5.3089,
+      "eval_samples_per_second": 188.362,
+      "eval_steps_per_second": 1.507,
+      "step": 6000
     }
   ],
   "logging_steps": 100,