Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0204cf51b4c0454e7406fa74c21a5e0237b72b16d8ea379e5d411dd6b4fe48
+oid sha256:615b2afd3bc142e08bf251a928f84b4e1cea9ae26762fc89ba0a4736dba7eb66
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f4ed06e1e181ea3e149a774abae5fb9a53631081196369a72dea4441008fd6
+oid sha256:8dfeca88de39ac397647f995ea8cde7b1fb6e6871fa362fb780526f82a902479
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a7a87e66fdab18edc7df0621c2a005fd54541ab1c68bc3e038e8b969d2fabe
+oid sha256:9bb1461e40c7e08171c25a0bc2bf64964397ea8cc712bb88016a59954d83db2d
 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": 78.832,
       "eval_steps_per_second": 0.631,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.14800746738910675,
+      "learning_rate": 0.0019944130517800893,
+      "loss": 3.8319,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.14713813364505768,
+      "learning_rate": 0.001993693153591457,
+      "loss": 3.8319,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.17019635438919067,
+      "learning_rate": 0.0019929297880451674,
+      "loss": 3.8095,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.15243591368198395,
+      "learning_rate": 0.0019921229885333023,
+      "loss": 3.8003,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16134986281394958,
+      "learning_rate": 0.001991272790347886,
+      "loss": 3.814,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.16883811354637146,
+      "learning_rate": 0.0019903792306793415,
+      "loss": 3.7822,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.15718473494052887,
+      "learning_rate": 0.001989442348614863,
+      "loss": 3.7902,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.14631035923957825,
+      "learning_rate": 0.0019884621851367075,
+      "loss": 3.7805,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.14771369099617004,
+      "learning_rate": 0.001987438783120401,
+      "loss": 3.7778,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1536298543214798,
+      "learning_rate": 0.001986372187332862,
+      "loss": 3.7848,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.340252446183953,
+      "eval_loss": 3.7290549278259277,
+      "eval_runtime": 11.9375,
+      "eval_samples_per_second": 83.77,
+      "eval_steps_per_second": 0.67,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.15110976994037628,
+      "learning_rate": 0.0019852624444304467,
+      "loss": 3.7502,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.15862922370433807,
+      "learning_rate": 0.0019841096029569044,
+      "loss": 3.761,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.13948658108711243,
+      "learning_rate": 0.0019829137133412556,
+      "loss": 3.7591,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.148148313164711,
+      "learning_rate": 0.001981674827895587,
+      "loss": 3.7385,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13170774281024933,
+      "learning_rate": 0.00198039300081276,
+      "loss": 3.7424,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.14352479577064514,
+      "learning_rate": 0.0019790682881640448,
+      "loss": 3.7423,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.12865835428237915,
+      "learning_rate": 0.001977700747896664,
+      "loss": 3.7263,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.15470698475837708,
+      "learning_rate": 0.001976290439831259,
+      "loss": 3.7297,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.1353532075881958,
+      "learning_rate": 0.0019748374256592736,
+      "loss": 3.7218,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.14982788264751434,
+      "learning_rate": 0.0019733417689402543,
+      "loss": 3.7164,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.34496673189823873,
+      "eval_loss": 3.6746184825897217,
+      "eval_runtime": 11.9904,
+      "eval_samples_per_second": 83.4,
+      "eval_steps_per_second": 0.667,
+      "step": 6000
     }
   ],
   "logging_steps": 100,