Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8fe178b2c865524971da242eead5a0a0fec5b3cb218040e9e466496006f5885
+oid sha256:cb0afa22ccef3c9a0ea3428b0ce49c7b49b701311e5530f6aed60817e79bf7b8
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcee50e95784bd04fda383abb23615395a0ad72d918cfafb72b7cef0032329d
+oid sha256:81aa75d70b877656bae98d60d9c24f3b5ef7089addac00c7ceb5e35601234b5b
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b061322e6ec670b87a8f9896d884fe5261ed4165781876f01308a3b5eff45c4a
+oid sha256:90d5c80c4317aec1cdd8b32ba40e7d9a283d92dfcce7300ea3ed6edd63c76074
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891e10d00e5e712dd3d3f62daa558798b38eee3e75855dd02223a9bfb9d6ca61
+oid sha256:72d75c8ad1707fd318e0f938501ec9134a4023e423bf08958c45c5e922653226
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.52,
+  "epoch": 0.56,
   "eval_steps": 1000,
-  "global_step": 26000,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2062,6 +2062,164 @@
       "eval_samples_per_second": 86.439,
       "eval_steps_per_second": 0.692,
       "step": 26000
+    },
+    {
+      "epoch": 0.522,
+      "grad_norm": 0.16366560757160187,
+      "learning_rate": 0.0010099867916842063,
+      "loss": 3.349,
+      "step": 26100
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 0.18745005130767822,
+      "learning_rate": 0.00100337307203178,
+      "loss": 3.3381,
+      "step": 26200
+    },
+    {
+      "epoch": 0.526,
+      "grad_norm": 0.14261376857757568,
+      "learning_rate": 0.0009967592048302552,
+      "loss": 3.334,
+      "step": 26300
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.16403239965438843,
+      "learning_rate": 0.0009901454793916102,
+      "loss": 3.3253,
+      "step": 26400
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1447836309671402,
+      "learning_rate": 0.00098353218502162,
+      "loss": 3.3442,
+      "step": 26500
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 0.18312039971351624,
+      "learning_rate": 0.0009769196110072061,
+      "loss": 3.338,
+      "step": 26600
+    },
+    {
+      "epoch": 0.534,
+      "grad_norm": 0.1727229803800583,
+      "learning_rate": 0.0009703080466037767,
+      "loss": 3.3183,
+      "step": 26700
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.15190576016902924,
+      "learning_rate": 0.0009636977810225777,
+      "loss": 3.3387,
+      "step": 26800
+    },
+    {
+      "epoch": 0.538,
+      "grad_norm": 0.1397494077682495,
+      "learning_rate": 0.0009570891034180394,
+      "loss": 3.3415,
+      "step": 26900
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1609794944524765,
+      "learning_rate": 0.0009504823028751295,
+      "loss": 3.3174,
+      "step": 27000
+    },
+    {
+      "epoch": 0.54,
+      "eval_accuracy": 0.38231311154598824,
+      "eval_loss": 3.3193719387054443,
+      "eval_runtime": 11.9776,
+      "eval_samples_per_second": 83.489,
+      "eval_steps_per_second": 0.668,
+      "step": 27000
+    },
+    {
+      "epoch": 0.542,
+      "grad_norm": 0.14202991127967834,
+      "learning_rate": 0.0009438776683967071,
+      "loss": 3.334,
+      "step": 27100
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.14222672581672668,
+      "learning_rate": 0.0009372754888908796,
+      "loss": 3.329,
+      "step": 27200
+    },
+    {
+      "epoch": 0.546,
+      "grad_norm": 0.2155715525150299,
+      "learning_rate": 0.000930676053158368,
+      "loss": 3.3328,
+      "step": 27300
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 0.14550994336605072,
+      "learning_rate": 0.0009240796498798694,
+      "loss": 3.3314,
+      "step": 27400
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1446721851825714,
+      "learning_rate": 0.0009174865676034329,
+      "loss": 3.322,
+      "step": 27500
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.15072402358055115,
+      "learning_rate": 0.000910897094731836,
+      "loss": 3.3292,
+      "step": 27600
+    },
+    {
+      "epoch": 0.554,
+      "grad_norm": 0.14199484884738922,
+      "learning_rate": 0.0009043115195099688,
+      "loss": 3.3319,
+      "step": 27700
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.1559506356716156,
+      "learning_rate": 0.0008977301300122259,
+      "loss": 3.3161,
+      "step": 27800
+    },
+    {
+      "epoch": 0.558,
+      "grad_norm": 0.14755868911743164,
+      "learning_rate": 0.0008911532141299046,
+      "loss": 3.3283,
+      "step": 27900
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.17486320436000824,
+      "learning_rate": 0.000884581059558612,
+      "loss": 3.3317,
+      "step": 28000
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.38318786692759293,
+      "eval_loss": 3.3127212524414062,
+      "eval_runtime": 13.6461,
+      "eval_samples_per_second": 73.281,
+      "eval_steps_per_second": 0.586,
+      "step": 28000
     }
   ],
   "logging_steps": 100,